diff --git a/Makefile b/Makefile new file mode 100644 index 00000000..1d98b707 --- /dev/null +++ b/Makefile @@ -0,0 +1,14 @@ +BUCKET ?= zero-downtime +BUCKET_PREFIX ?= /cloudbender/distfiles +FILES ?= distfiles.txt + +.PHONY: clean update + +all: update + + +clean: + rm -f kubezero*.tgz + +update: + ./script/update_helm.sh diff --git a/charts/kubezero-metrics/Chart.yaml b/charts/kubezero-metrics/Chart.yaml index f70476fc..9b2dd2e4 100644 --- a/charts/kubezero-metrics/Chart.yaml +++ b/charts/kubezero-metrics/Chart.yaml @@ -17,7 +17,8 @@ dependencies: repository: https://zero-down-time.github.io/kubezero/ - name: kube-prometheus-stack version: 12.8.0 - repository: https://prometheus-community.github.io/helm-charts + # Switch back to upstream once all alerts are fixed eg. etcd gpcr + # repository: https://prometheus-community.github.io/helm-charts - name: prometheus-adapter version: 2.10.1 repository: https://prometheus-community.github.io/helm-charts diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/.helmignore b/charts/kubezero-metrics/charts/kube-prometheus-stack/.helmignore new file mode 100644 index 00000000..93bf1ec0 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/.helmignore @@ -0,0 +1,26 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj +# helm/charts +OWNERS +hack/ +ci/ +kube-prometheus-*.tgz diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/CONTRIBUTING.md b/charts/kubezero-metrics/charts/kube-prometheus-stack/CONTRIBUTING.md new file mode 100644 index 00000000..f6ce2a32 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/CONTRIBUTING.md @@ -0,0 +1,12 @@ +# Contributing Guidelines + +## How to contribute to this chart + +1. Fork this repository, develop and test your Chart. +1. Bump the chart version for every change. +1. Ensure PR title has the prefix `[kube-prometheus-stack]` +1. When making changes to rules or dashboards, see the README.md section on how to sync data from upstream repositories +1. Check the `hack/minikube` folder has scripts to set up minikube and components of this chart that will allow all components to be scraped. You can use this configuration when validating your changes. +1. Check for changes of RBAC rules. +1. Check for changes in CRD specs. +1. PR must pass the linter (`helm lint`) diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/Chart.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/Chart.yaml new file mode 100644 index 00000000..a410ff2b --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/Chart.yaml @@ -0,0 +1,50 @@ +annotations: + artifacthub.io/links: | + - name: Chart Source + url: https://github.com/prometheus-community/helm-charts + - name: Upstream Project + url: https://github.com/prometheus-operator/kube-prometheus + artifacthub.io/operator: "true" +apiVersion: v2 +appVersion: 0.44.0 +dependencies: +- condition: kubeStateMetrics.enabled + name: kube-state-metrics + repository: https://charts.helm.sh/stable + version: 2.9.* +- condition: nodeExporter.enabled + name: prometheus-node-exporter + repository: https://prometheus-community.github.io/helm-charts + version: 1.12.* +- condition: grafana.enabled + name: grafana + repository: https://grafana.github.io/helm-charts + version: 5.8.* +description: kube-prometheus-stack collects Kubernetes manifests, Grafana dashboards, + and Prometheus rules combined with documentation and scripts to provide easy to + operate end-to-end Kubernetes cluster monitoring with Prometheus using the Prometheus + Operator. +home: https://github.com/prometheus-operator/kube-prometheus +icon: https://raw.githubusercontent.com/prometheus/prometheus.github.io/master/assets/prometheus_logo-cb55bb5c346.png +keywords: +- operator +- prometheus +- kube-prometheus +kubeVersion: '>=1.16.0-0' +maintainers: +- name: vsliouniaev +- name: bismarck +- email: gianrubio@gmail.com + name: gianrubio +- email: github.gkarthiks@gmail.com + name: gkarthiks +- email: scott@r6by.com + name: scottrigby +- email: miroslav.hadzhiev@gmail.com + name: Xtigyro +name: kube-prometheus-stack +sources: +- https://github.com/prometheus-community/helm-charts +- https://github.com/prometheus-operator/kube-prometheus +type: application +version: 12.8.0 diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/README.md b/charts/kubezero-metrics/charts/kube-prometheus-stack/README.md new file mode 100644 index 00000000..37794b14 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/README.md @@ -0,0 +1,396 @@ +# kube-prometheus-stack + +Installs the [kube-prometheus stack](https://github.com/prometheus-operator/kube-prometheus), a collection of Kubernetes manifests, [Grafana](http://grafana.com/) dashboards, and [Prometheus rules](https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/) combined with documentation and scripts to provide easy to operate end-to-end Kubernetes cluster monitoring with [Prometheus](https://prometheus.io/) using the [Prometheus Operator](https://github.com/prometheus-operator/prometheus-operator). + +See the [kube-prometheus](https://github.com/prometheus-operator/kube-prometheus) README for details about components, dashboards, and alerts. + +_Note: This chart was formerly named `prometheus-operator` chart, now renamed to more clearly reflect that it installs the `kube-prometheus` project stack, within which Prometheus Operator is only one component._ + +## Prerequisites + +- Kubernetes 1.16+ +- Helm 3+ + +## Get Repo Info + +```console +helm repo add prometheus-community https://prometheus-community.github.io/helm-charts +helm repo add stable https://charts.helm.sh/stable +helm repo update +``` + +_See [helm repo](https://helm.sh/docs/helm/helm_repo/) for command documentation._ + +## Install Chart + +```console +# Helm +$ helm install [RELEASE_NAME] prometheus-community/kube-prometheus-stack +``` + +_See [configuration](#configuration) below._ + +_See [helm install](https://helm.sh/docs/helm/helm_install/) for command documentation._ + +## Dependencies + +By default this chart installs additional, dependent charts: + +- [stable/kube-state-metrics](https://github.com/helm/charts/tree/master/stable/kube-state-metrics) +- [prometheus-community/prometheus-node-exporter](https://github.com/prometheus-community/helm-charts/tree/main/charts/prometheus-node-exporter) +- [grafana/grafana](https://github.com/grafana/helm-charts/tree/main/charts/grafana) + +To disable dependencies during installation, see [multiple releases](#multiple-releases) below. + +_See [helm dependency](https://helm.sh/docs/helm/helm_dependency/) for command documentation._ + +## Uninstall Chart + +```console +# Helm +$ helm uninstall [RELEASE_NAME] +``` + +This removes all the Kubernetes components associated with the chart and deletes the release. + +_See [helm uninstall](https://helm.sh/docs/helm/helm_uninstall/) for command documentation._ + +CRDs created by this chart are not removed by default and should be manually cleaned up: + +```console +kubectl delete crd alertmanagerconfigs.monitoring.coreos.com +kubectl delete crd alertmanagers.monitoring.coreos.com +kubectl delete crd podmonitors.monitoring.coreos.com +kubectl delete crd probes.monitoring.coreos.com +kubectl delete crd prometheuses.monitoring.coreos.com +kubectl delete crd prometheusrules.monitoring.coreos.com +kubectl delete crd servicemonitors.monitoring.coreos.com +kubectl delete crd thanosrulers.monitoring.coreos.com +``` + +## Upgrading Chart + +```console +# Helm +$ helm upgrade [RELEASE_NAME] prometheus-community/kube-prometheus-stack +``` + +With Helm v3, CRDs created by this chart are not updated by default and should be manually updated. +Consult also the [Helm Documentation on CRDs](https://helm.sh/docs/chart_best_practices/custom_resource_definitions). + +_See [helm upgrade](https://helm.sh/docs/helm/helm_upgrade/) for command documentation._ + +### Upgrading an existing Release to a new major version + +A major chart version change (like v1.2.3 -> v2.0.0) indicates that there is an incompatible breaking change needing manual actions. + +### From 11.x to 12.x + +The chart was migrated to support only helm v3 and later. + +### From 10.x to 11.x + +Version 11 upgrades prometheus-operator from 0.42.x to 0.43.x. Starting with 0.43.x an additional `AlertmanagerConfigs` CRD is introduced. Helm does not automatically upgrade or install new CRDs on a chart upgrade, so you have to install the CRD manually before updating: + +```console +kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/release-0.43/example/prometheus-operator-crd/monitoring.coreos.com_alertmanagerconfigs.yaml +``` + +Version 11 removes the deprecated tlsProxy via ghostunnel in favor of native TLS support the prometheus-operator gained with v0.39.0. + +### From 9.x to 10.x + +Version 10 upgrades prometheus-operator from 0.38.x to 0.42.x. Starting with 0.40.x an additional `Probes` CRD is introduced. Helm does not automatically upgrade or install new CRDs on a chart upgrade, so you have to install the CRD manually before updating: + +```console +kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/release-0.42/example/prometheus-operator-crd/monitoring.coreos.com_probes.yaml +``` + +### From 8.x to 9.x + +Version 9 of the helm chart removes the existing `additionalScrapeConfigsExternal` in favour of `additionalScrapeConfigsSecret`. This change lets users specify the secret name and secret key to use for the additional scrape configuration of prometheus. This is useful for users that have prometheus-operator as a subchart and also have a template that creates the additional scrape configuration. + +### From 7.x to 8.x + +Due to new template functions being used in the rules in version 8.x.x of the chart, an upgrade to Prometheus Operator and Prometheus is necessary in order to support them. First, upgrade to the latest version of 7.x.x + +```console +helm upgrade [RELEASE_NAME] prometheus-community/kube-prometheus-stack --version 7.5.0 +``` + +Then upgrade to 8.x.x + +```console +helm upgrade [RELEASE_NAME] prometheus-community/kube-prometheus-stack --version [8.x.x] +``` + +Minimal recommended Prometheus version for this chart release is `2.12.x` + +### From 6.x to 7.x + +Due to a change in grafana subchart, version 7.x.x now requires Helm >= 2.12.0. + +### From 5.x to 6.x + +Due to a change in deployment labels of kube-state-metrics, the upgrade requires `helm upgrade --force` in order to re-create the deployment. If this is not done an error will occur indicating that the deployment cannot be modified: + +```console +invalid: spec.selector: Invalid value: v1.LabelSelector{MatchLabels:map[string]string{"app.kubernetes.io/name":"kube-state-metrics"}, MatchExpressions:[]v1.LabelSelectorRequirement(nil)}: field is immutable +``` + +If this error has already been encountered, a `helm history` command can be used to determine which release has worked, then `helm rollback` to the release, then `helm upgrade --force` to this new one + +## Configuration + +See [Customizing the Chart Before Installing](https://helm.sh/docs/intro/using_helm/#customizing-the-chart-before-installing). To see all configurable options with detailed comments: + +```console +helm show values prometheus-community/kube-prometheus-stack +``` + +You may also `helm show values` on this chart's [dependencies](#dependencies) for additional options. + +### Multiple releases + +The same chart can be used to run multiple Prometheus instances in the same cluster if required. To achieve this, it is necessary to run only one instance of prometheus-operator and a pair of alertmanager pods for an HA configuration, while all other components need to be disabled. To disable a dependency during installation, set `kubeStateMetrics.enabled`, `nodeExporter.enabled` and `grafana.enabled` to `false`. + +## Work-Arounds for Known Issues + +### Running on private GKE clusters + +When Google configure the control plane for private clusters, they automatically configure VPC peering between your Kubernetes cluster’s network and a separate Google managed project. In order to restrict what Google are able to access within your cluster, the firewall rules configured restrict access to your Kubernetes pods. This means that in order to use the webhook component with a GKE private cluster, you must configure an additional firewall rule to allow the GKE control plane access to your webhook pod. + +You can read more information on how to add firewall rules for the GKE control plane nodes in the [GKE docs](https://cloud.google.com/kubernetes-engine/docs/how-to/private-clusters#add_firewall_rules) + +Alternatively, you can disable the hooks by setting `prometheusOperator.admissionWebhooks.enabled=false`. + +## PrometheusRules Admission Webhooks + +With Prometheus Operator version 0.30+, the core Prometheus Operator pod exposes an endpoint that will integrate with the `validatingwebhookconfiguration` Kubernetes feature to prevent malformed rules from being added to the cluster. + +### How the Chart Configures the Hooks + +A validating and mutating webhook configuration requires the endpoint to which the request is sent to use TLS. It is possible to set up custom certificates to do this, but in most cases, a self-signed certificate is enough. The setup of this component requires some more complex orchestration when using helm. The steps are created to be idempotent and to allow turning the feature on and off without running into helm quirks. + +1. A pre-install hook provisions a certificate into the same namespace using a format compatible with provisioning using end-user certificates. If the certificate already exists, the hook exits. +2. The prometheus operator pod is configured to use a TLS proxy container, which will load that certificate. +3. Validating and Mutating webhook configurations are created in the cluster, with their failure mode set to Ignore. This allows rules to be created by the same chart at the same time, even though the webhook has not yet been fully set up - it does not have the correct CA field set. +4. A post-install hook reads the CA from the secret created by step 1 and patches the Validating and Mutating webhook configurations. This process will allow a custom CA provisioned by some other process to also be patched into the webhook configurations. The chosen failure policy is also patched into the webhook configurations + +### Alternatives + +It should be possible to use [jetstack/cert-manager](https://github.com/jetstack/cert-manager) if a more complete solution is required, but it has not been tested. + +### Limitations + +Because the operator can only run as a single pod, there is potential for this component failure to cause rule deployment failure. Because this risk is outweighed by the benefit of having validation, the feature is enabled by default. + +## Developing Prometheus Rules and Grafana Dashboards + +This chart Grafana Dashboards and Prometheus Rules are just a copy from [prometheus-operator/prometheus-operator](https://github.com/prometheus-operator/prometheus-operator) and other sources, synced (with alterations) by scripts in [hack](hack) folder. In order to introduce any changes you need to first [add them to the original repo](https://github.com/prometheus-operator/kube-prometheus/blob/master/docs/developing-prometheus-rules-and-grafana-dashboards.md) and then sync there by scripts. + +## Further Information + +For more in-depth documentation of configuration options meanings, please see + +- [Prometheus Operator](https://github.com/prometheus-operator/prometheus-operator) +- [Prometheus](https://prometheus.io/docs/introduction/overview/) +- [Grafana](https://github.com/grafana/helm-charts/tree/main/charts/grafana#grafana-helm-chart) + +## prometheus.io/scrape + +The prometheus operator does not support annotation-based discovery of services, using the `PodMonitor` or `ServiceMonitor` CRD in its place as they provide far more configuration options. +For information on how to use PodMonitors/ServiceMonitors, please see the documentation on the `prometheus-operator/prometheus-operator` documentation here: + +- [ServiceMonitors](https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/user-guides/getting-started.md#include-servicemonitors) +- [PodMonitors](https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/user-guides/getting-started.md#include-podmonitors) +- [Running Exporters](https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/user-guides/running-exporters.md) + +By default, Prometheus discovers PodMonitors and ServiceMonitors within its namespace, that are labeled with the same release tag as the prometheus-operator release. +Sometimes, you may need to discover custom PodMonitors/ServiceMonitors, for example used to scrape data from third-party applications. +An easy way of doing this, without compromising the default PodMonitors/ServiceMonitors discovery, is allowing Prometheus to discover all PodMonitors/ServiceMonitors within its namespace, without applying label filtering. +To do so, you can set `prometheus.prometheusSpec.podMonitorSelectorNilUsesHelmValues` and `prometheus.prometheusSpec.serviceMonitorSelectorNilUsesHelmValues` to `false`. + +## Migrating from stable/prometheus-operator chart + +## Zero downtime + +Since `kube-prometheus-stack` is fully compatible with the `stable/prometheus-operator` chart, a migration without downtime can be achieved. +However, the old name prefix needs to be kept. If you want the new name please follow the step by step guide below (with downtime). + +You can override the name to achieve this: + +```console +helm upgrade prometheus-operator prometheus-community/kube-prometheus-stack -n monitoring --reuse-values --set nameOverride=prometheus-operator +``` + +**Note**: It is recommended to run this first with `--dry-run --debug`. + +## Redeploy with new name (downtime) + +If the **prometheus-operator** values are compatible with the new **kube-prometheus-stack** chart, please follow the below steps for migration: + +> The guide presumes that chart is deployed in `monitoring` namespace and the deployments are running there. If in other namespace, please replace the `monitoring` to the deployed namespace. + +1. Patch the PersistenceVolume created/used by the prometheus-operator chart to `Retain` claim policy: + + ```console + kubectl patch pv/ -p '{"spec":{"persistentVolumeReclaimPolicy":"Retain"}}' + ``` + + **Note:** To execute the above command, the user must have a cluster wide permission. Please refer [Kubernetes RBAC](https://kubernetes.io/docs/reference/access-authn-authz/rbac/) + +2. Uninstall the **prometheus-operator** release and delete the existing PersistentVolumeClaim, and verify PV become Released. + + ```console + helm uninstall prometheus-operator -n monitoring + kubectl delete pvc/ -n monitoring + ``` + + Additionally, you have to manually remove the remaining `prometheus-operator-kubelet` service. + + ```console + kubectl delete service/prometheus-operator-kubelet -n kube-system + ``` + + You can choose to remove all your existing CRDs (ServiceMonitors, Podmonitors, etc.) if you want to. + +3. Remove current `spec.claimRef` values to change the PV's status from Released to Available. + + ```console + kubectl patch pv/ --type json -p='[{"op": "remove", "path": "/spec/claimRef"}]' -n monitoring + ``` + +**Note:** To execute the above command, the user must have a cluster wide permission. Please refer to [Kubernetes RBAC](https://kubernetes.io/docs/reference/access-authn-authz/rbac/) + +After these steps, proceed to a fresh **kube-prometheus-stack** installation and make sure the current release of **kube-prometheus-stack** matching the `volumeClaimTemplate` values in the `values.yaml`. + +The binding is done via matching a specific amount of storage requested and with certain access modes. + +For example, if you had storage specified as this with **prometheus-operator**: + +```yaml +volumeClaimTemplate: + spec: + storageClassName: gp2 + accessModes: ["ReadWriteOnce"] + resources: + requests: + storage: 50Gi +``` + +You have to specify matching `volumeClaimTemplate` with 50Gi storage and `ReadWriteOnce` access mode. + +Additionally, you should check the current AZ of your legacy installation's PV, and configure the fresh release to use the same AZ as the old one. If the pods are in a different AZ than the PV, the release will fail to bind the existing one, hence creating a new PV. + +This can be achieved either by specifying the labels through `values.yaml`, e.g. setting `prometheus.prometheusSpec.nodeSelector` to: + +```yaml +nodeSelector: + failure-domain.beta.kubernetes.io/zone: east-west-1a +``` + +or passing these values as `--set` overrides during installation. + +The new release should now re-attach your previously released PV with its content. + +## Migrating from coreos/prometheus-operator chart + +The multiple charts have been combined into a single chart that installs prometheus operator, prometheus, alertmanager, grafana as well as the multitude of exporters necessary to monitor a cluster. + +There is no simple and direct migration path between the charts as the changes are extensive and intended to make the chart easier to support. + +The capabilities of the old chart are all available in the new chart, including the ability to run multiple prometheus instances on a single cluster - you will need to disable the parts of the chart you do not wish to deploy. + +You can check out the tickets for this change [here](https://github.com/prometheus-operator/prometheus-operator/issues/592) and [here](https://github.com/helm/charts/pull/6765). + +### High-level overview of Changes + +#### Added dependencies + +The chart has added 3 [dependencies](#dependencies). + +- Node-Exporter, Kube-State-Metrics: These components are loaded as dependencies into the chart, and are relatively simple components +- Grafana: The Grafana chart is more feature-rich than this chart - it contains a sidecar that is able to load data sources and dashboards from configmaps deployed into the same cluster. For more information check out the [documentation for the chart](https://github.com/helm/charts/tree/master/stable/grafana) + +#### Kubelet Service + +Because the kubelet service has a new name in the chart, make sure to clean up the old kubelet service in the `kube-system` namespace to prevent counting container metrics twice. + +#### Persistent Volumes + +If you would like to keep the data of the current persistent volumes, it should be possible to attach existing volumes to new PVCs and PVs that are created using the conventions in the new chart. For example, in order to use an existing Azure disk for a helm release called `prometheus-migration` the following resources can be created: + +```yaml +apiVersion: v1 +kind: PersistentVolume +metadata: + name: pvc-prometheus-migration-prometheus-0 +spec: + accessModes: + - ReadWriteOnce + azureDisk: + cachingMode: None + diskName: pvc-prometheus-migration-prometheus-0 + diskURI: /subscriptions/f5125d82-2622-4c50-8d25-3f7ba3e9ac4b/resourceGroups/sample-migration-resource-group/providers/Microsoft.Compute/disks/pvc-prometheus-migration-prometheus-0 + fsType: "" + kind: Managed + readOnly: false + capacity: + storage: 1Gi + persistentVolumeReclaimPolicy: Delete + storageClassName: prometheus + volumeMode: Filesystem +``` + +```yaml +apiVersion: v1 +kind: PersistentVolumeClaim +metadata: + labels: + app: prometheus + prometheus: prometheus-migration-prometheus + name: prometheus-prometheus-migration-prometheus-db-prometheus-prometheus-migration-prometheus-0 + namespace: monitoring +spec: + accessModes: + - ReadWriteOnce + resources: + requests: + storage: 1Gi + storageClassName: prometheus + volumeMode: Filesystem + volumeName: pvc-prometheus-migration-prometheus-0 +``` + +The PVC will take ownership of the PV and when you create a release using a persistent volume claim template it will use the existing PVCs as they match the naming convention used by the chart. For other cloud providers similar approaches can be used. + +#### KubeProxy + +The metrics bind address of kube-proxy is default to `127.0.0.1:10249` that prometheus instances **cannot** access to. You should expose metrics by changing `metricsBindAddress` field value to `0.0.0.0:10249` if you want to collect them. + +Depending on the cluster, the relevant part `config.conf` will be in ConfigMap `kube-system/kube-proxy` or `kube-system/kube-proxy-config`. For example: + +```console +kubectl -n kube-system edit cm kube-proxy +``` + +```yaml +apiVersion: v1 +data: + config.conf: |- + apiVersion: kubeproxy.config.k8s.io/v1alpha1 + kind: KubeProxyConfiguration + # ... + # metricsBindAddress: 127.0.0.1:10249 + metricsBindAddress: 0.0.0.0:10249 + # ... + kubeconfig.conf: |- + # ... +kind: ConfigMap +metadata: + labels: + app: kube-proxy + name: kube-proxy + namespace: kube-system +``` diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/.helmignore b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/.helmignore new file mode 100644 index 00000000..8cade131 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/.helmignore @@ -0,0 +1,23 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.vscode +.project +.idea/ +*.tmproj +OWNERS diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/Chart.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/Chart.yaml new file mode 100644 index 00000000..2f6e0761 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/Chart.yaml @@ -0,0 +1,19 @@ +apiVersion: v1 +appVersion: 7.2.1 +description: The leading tool for querying and visualizing time series and metrics. +home: https://grafana.net +icon: https://raw.githubusercontent.com/grafana/grafana/master/public/img/logo_transparent_400x.png +kubeVersion: ^1.8.0-0 +maintainers: +- email: zanhsieh@gmail.com + name: zanhsieh +- email: rluckie@cisco.com + name: rtluckie +- email: maor.friedman@redhat.com + name: maorfr +- email: miroslav.hadzhiev@gmail.com + name: Xtigyro +name: grafana +sources: +- https://github.com/grafana/grafana +version: 5.8.16 diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/README.md b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/README.md new file mode 100644 index 00000000..2dc1822e --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/README.md @@ -0,0 +1,499 @@ +# Grafana Helm Chart + +* Installs the web dashboarding system [Grafana](http://grafana.org/) + +## Get Repo Info + +```console +helm repo add grafana https://grafana.github.io/helm-charts +helm repo update +``` + +_See [helm repo](https://helm.sh/docs/helm/helm_repo/) for command documentation._ + +## Installing the Chart + +To install the chart with the release name `my-release`: + +```console +helm install --name my-release grafana/grafana +``` + +## Uninstalling the Chart + +To uninstall/delete the my-release deployment: + +```console +helm delete my-release +``` + +The command removes all the Kubernetes components associated with the chart and deletes the release. + +## Upgrading an existing Release to a new major version + +A major chart version change (like v1.2.3 -> v2.0.0) indicates that there is an +incompatible breaking change needing manual actions. + +### To 4.0.0 (And 3.12.1) + +This version requires Helm >= 2.12.0. + +### To 5.0.0 + +You have to add --force to your helm upgrade command as the labels of the chart have changed. + +## Configuration + +| Parameter | Description | Default | +|-------------------------------------------|-----------------------------------------------|---------------------------------------------------------| +| `replicas` | Number of nodes | `1` | +| `podDisruptionBudget.minAvailable` | Pod disruption minimum available | `nil` | +| `podDisruptionBudget.maxUnavailable` | Pod disruption maximum unavailable | `nil` | +| `deploymentStrategy` | Deployment strategy | `{ "type": "RollingUpdate" }` | +| `livenessProbe` | Liveness Probe settings | `{ "httpGet": { "path": "/api/health", "port": 3000 } "initialDelaySeconds": 60, "timeoutSeconds": 30, "failureThreshold": 10 }` | +| `readinessProbe` | Readiness Probe settings | `{ "httpGet": { "path": "/api/health", "port": 3000 } }`| +| `securityContext` | Deployment securityContext | `{"runAsUser": 472, "runAsGroup": 472, "fsGroup": 472}` | +| `priorityClassName` | Name of Priority Class to assign pods | `nil` | +| `image.repository` | Image repository | `grafana/grafana` | +| `image.tag` | Image tag (`Must be >= 5.0.0`) | `7.0.3` | +| `image.sha` | Image sha (optional) | `17cbd08b9515fda889ca959e9d72ee6f3327c8f1844a3336dfd952134f38e2fe` | +| `image.pullPolicy` | Image pull policy | `IfNotPresent` | +| `image.pullSecrets` | Image pull secrets | `{}` | +| `service.type` | Kubernetes service type | `ClusterIP` | +| `service.port` | Kubernetes port where service is exposed | `80` | +| `service.portName` | Name of the port on the service | `service` | +| `service.targetPort` | Internal service is port | `3000` | +| `service.nodePort` | Kubernetes service nodePort | `nil` | +| `service.annotations` | Service annotations | `{}` | +| `service.labels` | Custom labels | `{}` | +| `service.clusterIP` | internal cluster service IP | `nil` | +| `service.loadBalancerIP` | IP address to assign to load balancer (if supported) | `nil` | +| `service.loadBalancerSourceRanges` | list of IP CIDRs allowed access to lb (if supported) | `[]` | +| `service.externalIPs` | service external IP addresses | `[]` | +| `extraExposePorts` | Additional service ports for sidecar containers| `[]` | +| `hostAliases` | adds rules to the pod's /etc/hosts | `[]` | +| `ingress.enabled` | Enables Ingress | `false` | +| `ingress.annotations` | Ingress annotations (values are templated) | `{}` | +| `ingress.labels` | Custom labels | `{}` | +| `ingress.path` | Ingress accepted path | `/` | +| `ingress.hosts` | Ingress accepted hostnames | `["chart-example.local"]` | +| `ingress.extraPaths` | Ingress extra paths to prepend to every host configuration. Useful when configuring [custom actions with AWS ALB Ingress Controller](https://kubernetes-sigs.github.io/aws-alb-ingress-controller/guide/ingress/annotation/#actions). | `[]` | +| `ingress.tls` | Ingress TLS configuration | `[]` | +| `resources` | CPU/Memory resource requests/limits | `{}` | +| `nodeSelector` | Node labels for pod assignment | `{}` | +| `tolerations` | Toleration labels for pod assignment | `[]` | +| `affinity` | Affinity settings for pod assignment | `{}` | +| `extraInitContainers` | Init containers to add to the grafana pod | `{}` | +| `extraContainers` | Sidecar containers to add to the grafana pod | `{}` | +| `extraContainerVolumes` | Volumes that can be mounted in sidecar containers | `[]` | +| `schedulerName` | Name of the k8s scheduler (other than default) | `nil` | +| `persistence.enabled` | Use persistent volume to store data | `false` | +| `persistence.type` | Type of persistence (`pvc` or `statefulset`) | `pvc` | +| `persistence.size` | Size of persistent volume claim | `10Gi` | +| `persistence.existingClaim` | Use an existing PVC to persist data | `nil` | +| `persistence.storageClassName` | Type of persistent volume claim | `nil` | +| `persistence.accessModes` | Persistence access modes | `[ReadWriteOnce]` | +| `persistence.annotations` | PersistentVolumeClaim annotations | `{}` | +| `persistence.finalizers` | PersistentVolumeClaim finalizers | `[ "kubernetes.io/pvc-protection" ]` | +| `persistence.subPath` | Mount a sub dir of the persistent volume | `nil` | +| `initChownData.enabled` | If false, don't reset data ownership at startup | true | +| `initChownData.image.repository` | init-chown-data container image repository | `busybox` | +| `initChownData.image.tag` | init-chown-data container image tag | `1.31.1` | +| `initChownData.image.sha` | init-chown-data container image sha (optional)| `""` | +| `initChownData.image.pullPolicy` | init-chown-data container image pull policy | `IfNotPresent` | +| `initChownData.resources` | init-chown-data pod resource requests & limits | `{}` | +| `schedulerName` | Alternate scheduler name | `nil` | +| `env` | Extra environment variables passed to pods | `{}` | +| `envValueFrom` | Environment variables from alternate sources. See the API docs on [EnvVarSource](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.17/#envvarsource-v1-core) for format details. | `{}` | +| `envFromSecret` | Name of a Kubernetes secret (must be manually created in the same namespace) containing values to be added to the environment. Can be templated | `""` | +| `envRenderSecret` | Sensible environment variables passed to pods and stored as secret | `{}` | +| `extraSecretMounts` | Additional grafana server secret mounts | `[]` | +| `extraVolumeMounts` | Additional grafana server volume mounts | `[]` | +| `extraConfigmapMounts` | Additional grafana server configMap volume mounts | `[]` | +| `extraEmptyDirMounts` | Additional grafana server emptyDir volume mounts | `[]` | +| `plugins` | Plugins to be loaded along with Grafana | `[]` | +| `datasources` | Configure grafana datasources (passed through tpl) | `{}` | +| `notifiers` | Configure grafana notifiers | `{}` | +| `dashboardProviders` | Configure grafana dashboard providers | `{}` | +| `dashboards` | Dashboards to import | `{}` | +| `dashboardsConfigMaps` | ConfigMaps reference that contains dashboards | `{}` | +| `grafana.ini` | Grafana's primary configuration | `{}` | +| `ldap.enabled` | Enable LDAP authentication | `false` | +| `ldap.existingSecret` | The name of an existing secret containing the `ldap.toml` file, this must have the key `ldap-toml`. | `""` | +| `ldap.config` | Grafana's LDAP configuration | `""` | +| `annotations` | Deployment annotations | `{}` | +| `labels` | Deployment labels | `{}` | +| `podAnnotations` | Pod annotations | `{}` | +| `podLabels` | Pod labels | `{}` | +| `podPortName` | Name of the grafana port on the pod | `grafana` | +| `sidecar.image.repository` | Sidecar image repository | `kiwigrid/k8s-sidecar` | +| `sidecar.image.tag` | Sidecar image tag | `1.1.0` | +| `sidecar.image.sha` | Sidecar image sha (optional) | `""` | +| `sidecar.imagePullPolicy` | Sidecar image pull policy | `IfNotPresent` | +| `sidecar.resources` | Sidecar resources | `{}` | +| `sidecar.enableUniqueFilenames` | Sets the kiwigrid/k8s-sidecar UNIQUE_FILENAMES environment variable | `false` | +| `sidecar.dashboards.enabled` | Enables the cluster wide search for dashboards and adds/updates/deletes them in grafana | `false` | +| `sidecar.dashboards.SCProvider` | Enables creation of sidecar provider | `true` | +| `sidecar.dashboards.provider.name` | Unique name of the grafana provider | `sidecarProvider` | +| `sidecar.dashboards.provider.orgid` | Id of the organisation, to which the dashboards should be added | `1` | +| `sidecar.dashboards.provider.folder` | Logical folder in which grafana groups dashboards | `""` | +| `sidecar.dashboards.provider.disableDelete` | Activate to avoid the deletion of imported dashboards | `false` | +| `sidecar.dashboards.provider.allowUiUpdates` | Allow updating provisioned dashboards from the UI | `false` | +| `sidecar.dashboards.provider.type` | Provider type | `file` | +| `sidecar.dashboards.provider.foldersFromFilesStructure` | Allow Grafana to replicate dashboard structure from filesystem. | `false` | +| `sidecar.dashboards.watchMethod` | Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. | `WATCH` | +| `sidecar.skipTlsVerify` | Set to true to skip tls verification for kube api calls | `nil` | +| `sidecar.dashboards.label` | Label that config maps with dashboards should have to be added | `grafana_dashboard` | +| `sidecar.dashboards.folder` | Folder in the pod that should hold the collected dashboards (unless `sidecar.dashboards.defaultFolderName` is set). This path will be mounted. | `/tmp/dashboards` | +| `sidecar.dashboards.folderAnnotation` | The annotation the sidecar will look for in configmaps to override the destination folder for files | `nil` | +| `sidecar.dashboards.defaultFolderName` | The default folder name, it will create a subfolder under the `sidecar.dashboards.folder` and put dashboards in there instead | `nil` | +| `sidecar.dashboards.searchNamespace` | If specified, the sidecar will search for dashboard config-maps inside this namespace. Otherwise the namespace in which the sidecar is running will be used. It's also possible to specify ALL to search in all namespaces | `nil` | +| `sidecar.datasources.enabled` | Enables the cluster wide search for datasources and adds/updates/deletes them in grafana |`false` | +| `sidecar.datasources.label` | Label that config maps with datasources should have to be added | `grafana_datasource` | +| `sidecar.datasources.searchNamespace` | If specified, the sidecar will search for datasources config-maps inside this namespace. Otherwise the namespace in which the sidecar is running will be used. It's also possible to specify ALL to search in all namespaces | `nil` | +| `sidecar.notifiers.enabled` | Enables the cluster wide search for notifiers and adds/updates/deletes them in grafana |`false` | +| `sidecar.notifiers.label` | Label that config maps with notifiers should have to be added | `grafana_notifier` | +| `sidecar.notifiers.searchNamespace` | If specified, the sidecar will search for notifiers config-maps (or secrets) inside this namespace. Otherwise the namespace in which the sidecar is running will be used. It's also possible to specify ALL to search in all namespaces | `nil` | +| `smtp.existingSecret` | The name of an existing secret containing the SMTP credentials. | `""` | +| `smtp.userKey` | The key in the existing SMTP secret containing the username. | `"user"` | +| `smtp.passwordKey` | The key in the existing SMTP secret containing the password. | `"password"` | +| `admin.existingSecret` | The name of an existing secret containing the admin credentials. | `""` | +| `admin.userKey` | The key in the existing admin secret containing the username. | `"admin-user"` | +| `admin.passwordKey` | The key in the existing admin secret containing the password. | `"admin-password"` | +| `serviceAccount.annotations` | ServiceAccount annotations | | +| `serviceAccount.create` | Create service account | `true` | +| `serviceAccount.name` | Service account name to use, when empty will be set to created account if `serviceAccount.create` is set else to `default` | `` | +| `serviceAccount.nameTest` | Service account name to use for test, when empty will be set to created account if `serviceAccount.create` is set else to `default` | `nil` | +| `rbac.create` | Create and use RBAC resources | `true` | +| `rbac.namespaced` | Creates Role and Rolebinding instead of the default ClusterRole and ClusteRoleBindings for the grafana instance | `false` | +| `rbac.useExistingRole` | Set to a rolename to use existing role - skipping role creating - but still doing serviceaccount and rolebinding to the rolename set here. | `nil` | +| `rbac.pspEnabled` | Create PodSecurityPolicy (with `rbac.create`, grant roles permissions as well) | `true` | +| `rbac.pspUseAppArmor` | Enforce AppArmor in created PodSecurityPolicy (requires `rbac.pspEnabled`) | `true` | +| `rbac.extraRoleRules` | Additional rules to add to the Role | [] | +| `rbac.extraClusterRoleRules` | Additional rules to add to the ClusterRole | [] | +| `command` | Define command to be executed by grafana container at startup | `nil` | +| `testFramework.enabled` | Whether to create test-related resources | `true` | +| `testFramework.image` | `test-framework` image repository. | `bats/bats` | +| `testFramework.tag` | `test-framework` image tag. | `v1.1.0` | +| `testFramework.imagePullPolicy` | `test-framework` image pull policy. | `IfNotPresent` | +| `testFramework.securityContext` | `test-framework` securityContext | `{}` | +| `downloadDashboards.env` | Environment variables to be passed to the `download-dashboards` container | `{}` | +| `downloadDashboards.resources` | Resources of `download-dashboards` container | `{}` | +| `downloadDashboardsImage.repository` | Curl docker image repo | `curlimages/curl` | +| `downloadDashboardsImage.tag` | Curl docker image tag | `7.73.0` | +| `downloadDashboardsImage.sha` | Curl docker image sha (optional) | `""` | +| `downloadDashboardsImage.pullPolicy` | Curl docker image pull policy | `IfNotPresent` | +| `namespaceOverride` | Override the deployment namespace | `""` (`Release.Namespace`) | +| `serviceMonitor.enabled` | Use servicemonitor from prometheus operator | `false` | +| `serviceMonitor.namespace` | Namespace this servicemonitor is installed in | | +| `serviceMonitor.interval` | How frequently Prometheus should scrape | `1m` | +| `serviceMonitor.path` | Path to scrape | `/metrics` | +| `serviceMonitor.labels` | Labels for the servicemonitor passed to Prometheus Operator | `{}` | +| `serviceMonitor.scrapeTimeout` | Timeout after which the scrape is ended | `30s` | +| `serviceMonitor.relabelings` | MetricRelabelConfigs to apply to samples before ingestion. | `[]` | +| `revisionHistoryLimit` | Number of old ReplicaSets to retain | `10` | +| `imageRenderer.enabled` | Enable the image-renderer deployment & service | `false` | +| `imageRenderer.image.repository` | image-renderer Image repository | `grafana/grafana-image-renderer` | +| `imageRenderer.image.tag` | image-renderer Image tag | `latest` | +| `imageRenderer.image.sha` | image-renderer Image sha (optional) | `""` | +| `imageRenderer.image.pullPolicy` | image-renderer ImagePullPolicy | `Always` | +| `imageRenderer.env` | extra env-vars for image-renderer | `{}` | +| `imageRenderer.securityContext` | image-renderer deployment securityContext | `{}` | +| `imageRenderer.hostAliases` | image-renderer deployment Host Aliases | `[]` | +| `imageRenderer.priorityClassName` | image-renderer deployment priority class | `''` | +| `imageRenderer.service.portName` | image-renderer service port name | `'http'` | +| `imageRenderer.service.port` | image-renderer service port used by both service and deployment | `8081` | +| `imageRenderer.podPortName` | name of the image-renderer port on the pod | `http` | +| `imageRenderer.revisionHistoryLimit` | number of image-renderer replica sets to keep | `10` | +| `imageRenderer.networkPolicy.limitIngress` | Enable a NetworkPolicy to limit inbound traffic from only the created grafana pods | `true` | +| `imageRenderer.networkPolicy.limitEgress` | Enable a NetworkPolicy to limit outbound traffic to only the created grafana pods | `false` | +| `imageRenderer.resources` | Set resource limits for image-renderer pdos | `{}` | + +### Example ingress with path + +With grafana 6.3 and above +```yaml +grafana.ini: + server: + domain: monitoring.example.com + root_url: "%(protocol)s://%(domain)s/grafana" + serve_from_sub_path: true +ingress: + enabled: true + hosts: + - "monitoring.example.com" + path: "/grafana" +``` + +### Example of extraVolumeMounts + +```yaml +- extraVolumeMounts: + - name: plugins + mountPath: /var/lib/grafana/plugins + subPath: configs/grafana/plugins + existingClaim: existing-grafana-claim + readOnly: false +``` + +## Import dashboards + +There are a few methods to import dashboards to Grafana. Below are some examples and explanations as to how to use each method: + +```yaml +dashboards: + default: + some-dashboard: + json: | + { + "annotations": + + ... + # Complete json file here + ... + + "title": "Some Dashboard", + "uid": "abcd1234", + "version": 1 + } + custom-dashboard: + # This is a path to a file inside the dashboards directory inside the chart directory + file: dashboards/custom-dashboard.json + prometheus-stats: + # Ref: https://grafana.com/dashboards/2 + gnetId: 2 + revision: 2 + datasource: Prometheus + local-dashboard: + url: https://raw.githubusercontent.com/user/repository/master/dashboards/dashboard.json +``` + +## BASE64 dashboards + +Dashboards could be stored on a server that does not return JSON directly and instead of it returns a Base64 encoded file (e.g. Gerrit) +A new parameter has been added to the url use case so if you specify a b64content value equals to true after the url entry a Base64 decoding is applied before save the file to disk. +If this entry is not set or is equals to false not decoding is applied to the file before saving it to disk. + +### Gerrit use case + +Gerrit API for download files has the following schema: where {project-name} and +{file-id} usually has '/' in their values and so they MUST be replaced by %2F so if project-name is user/repo, branch-id is master and file-id is equals to dir1/dir2/dashboard +the url value is + +## Sidecar for dashboards + +If the parameter `sidecar.dashboards.enabled` is set, a sidecar container is deployed in the grafana +pod. This container watches all configmaps (or secrets) in the cluster and filters out the ones with +a label as defined in `sidecar.dashboards.label`. The files defined in those configmaps are written +to a folder and accessed by grafana. Changes to the configmaps are monitored and the imported +dashboards are deleted/updated. + +A recommendation is to use one configmap per dashboard, as a reduction of multiple dashboards inside +one configmap is currently not properly mirrored in grafana. + +Example dashboard config: + +```yaml +apiVersion: v1 +kind: ConfigMap +metadata: + name: sample-grafana-dashboard + labels: + grafana_dashboard: "1" +data: + k8s-dashboard.json: |- + [...] +``` + +## Sidecar for datasources + +If the parameter `sidecar.datasources.enabled` is set, an init container is deployed in the grafana +pod. This container lists all secrets (or configmaps, though not recommended) in the cluster and +filters out the ones with a label as defined in `sidecar.datasources.label`. The files defined in +those secrets are written to a folder and accessed by grafana on startup. Using these yaml files, +the data sources in grafana can be imported. The secrets must be created before `helm install` so +that the datasources init container can list the secrets. + +Secrets are recommended over configmaps for this usecase because datasources usually contain private +data like usernames and passwords. Secrets are the more appropriate cluster resource to manage those. + +Example datasource config adapted from [Grafana](http://docs.grafana.org/administration/provisioning/#example-datasource-config-file): + +```yaml +apiVersion: v1 +kind: Secret +metadata: + name: sample-grafana-datasource + labels: + grafana_datasource: "1" +type: Opaque +stringData: + datasource.yaml: |- + # config file version + apiVersion: 1 + + # list of datasources that should be deleted from the database + deleteDatasources: + - name: Graphite + orgId: 1 + + # list of datasources to insert/update depending + # whats available in the database + datasources: + # name of the datasource. Required + - name: Graphite + # datasource type. Required + type: graphite + # access mode. proxy or direct (Server or Browser in the UI). Required + access: proxy + # org id. will default to orgId 1 if not specified + orgId: 1 + # url + url: http://localhost:8080 + # database password, if used + password: + # database user, if used + user: + # database name, if used + database: + # enable/disable basic auth + basicAuth: + # basic auth username + basicAuthUser: + # basic auth password + basicAuthPassword: + # enable/disable with credentials headers + withCredentials: + # mark as default datasource. Max one per org + isDefault: + # fields that will be converted to json and stored in json_data + jsonData: + graphiteVersion: "1.1" + tlsAuth: true + tlsAuthWithCACert: true + # json object of data that will be encrypted. + secureJsonData: + tlsCACert: "..." + tlsClientCert: "..." + tlsClientKey: "..." + version: 1 + # allow users to edit datasources from the UI. + editable: false + +``` + +## Sidecar for notifiers + +If the parameter `sidecar.notifiers.enabled` is set, an init container is deployed in the grafana +pod. This container lists all secrets (or configmaps, though not recommended) in the cluster and +filters out the ones with a label as defined in `sidecar.notifiers.label`. The files defined in +those secrets are written to a folder and accessed by grafana on startup. Using these yaml files, +the notification channels in grafana can be imported. The secrets must be created before +`helm install` so that the notifiers init container can list the secrets. + +Secrets are recommended over configmaps for this usecase because alert notification channels usually contain +private data like SMTP usernames and passwords. Secrets are the more appropriate cluster resource to manage those. + +Example datasource config adapted from [Grafana](https://grafana.com/docs/grafana/latest/administration/provisioning/#alert-notification-channels): + +```yaml +notifiers: + - name: notification-channel-1 + type: slack + uid: notifier1 + # either + org_id: 2 + # or + org_name: Main Org. + is_default: true + send_reminder: true + frequency: 1h + disable_resolve_message: false + # See `Supported Settings` section for settings supporter for each + # alert notification type. + settings: + recipient: 'XXX' + token: 'xoxb' + uploadImage: true + url: https://slack.com + +delete_notifiers: + - name: notification-channel-1 + uid: notifier1 + org_id: 2 + - name: notification-channel-2 + # default org_id: 1 +``` + +## How to serve Grafana with a path prefix (/grafana) + +In order to serve Grafana with a prefix (e.g., ), add the following to your values.yaml. + +```yaml +ingress: + enabled: true + annotations: + kubernetes.io/ingress.class: "nginx" + nginx.ingress.kubernetes.io/rewrite-target: /$1 + nginx.ingress.kubernetes.io/use-regex: "true" + + path: /grafana/?(.*) + hosts: + - k8s.example.dev + +grafana.ini: + server: + root_url: http://localhost:3000/grafana # this host can be localhost +``` + +## How to securely reference secrets in grafana.ini + +This example uses Grafana uses [file providers](https://grafana.com/docs/grafana/latest/administration/configuration/#file-provider) for secret values and the `extraSecretMounts` configuration flag (Additional grafana server secret mounts) to mount the secrets. + +In grafana.ini: + +```yaml +grafana.ini: + [auth.generic_oauth] + enabled = true + client_id = $__file{/etc/secrets/auth_generic_oauth/client_id} + client_secret = $__file{/etc/secrets/auth_generic_oauth/client_secret} +``` + +Existing secret, or created along with helm: + +```yaml +--- +apiVersion: v1 +kind: Secret +metadata: + name: auth-generic-oauth-secret +type: Opaque +stringData: + client_id: + client_secret: +``` + +Include in the `extraSecretMounts` configuration flag: + +```yaml +- extraSecretMounts: + - name: auth-generic-oauth-secret-mount + secretName: auth-generic-oauth-secret + defaultMode: 0440 + mountPath: /etc/secrets/auth_generic_oauth + readOnly: true +``` + +## Image Renderer Plug-In + +This chart supports enabling [remote image rendering](https://github.com/grafana/grafana-image-renderer/blob/master/docs/remote_rendering_using_docker.md) + +```yaml +imageRenderer: + enabled: true +``` + +### Image Renderer NetworkPolicy + +By default the image-renderer pods will have a network policy which only allows ingress traffic from the created grafana instance diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/ci/default-values.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/ci/default-values.yaml new file mode 100644 index 00000000..fc2ba605 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/ci/default-values.yaml @@ -0,0 +1 @@ +# Leave this file empty to ensure that CI runs builds against the default configuration in values.yaml. diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/ci/with-dashboard-json-values.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/ci/with-dashboard-json-values.yaml new file mode 100644 index 00000000..e0c4e416 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/ci/with-dashboard-json-values.yaml @@ -0,0 +1,53 @@ +dashboards: + my-provider: + my-awesome-dashboard: + # An empty but valid dashboard + json: | + { + "__inputs": [], + "__requires": [ + { + "type": "grafana", + "id": "grafana", + "name": "Grafana", + "version": "6.3.5" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "id": null, + "links": [], + "panels": [], + "schemaVersion": 19, + "style": "dark", + "tags": [], + "templating": { + "list": [] + }, + "time": { + "from": "now-6h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": ["5s"] + }, + "timezone": "", + "title": "Dummy Dashboard", + "uid": "IdcYQooWk", + "version": 1 + } + datasource: Prometheus diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/ci/with-dashboard-values.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/ci/with-dashboard-values.yaml new file mode 100644 index 00000000..7b662c5f --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/ci/with-dashboard-values.yaml @@ -0,0 +1,19 @@ +dashboards: + my-provider: + my-awesome-dashboard: + gnetId: 10000 + revision: 1 + datasource: Prometheus +dashboardProviders: + dashboardproviders.yaml: + apiVersion: 1 + providers: + - name: 'my-provider' + orgId: 1 + folder: '' + type: file + updateIntervalSeconds: 10 + disableDeletion: true + editable: true + options: + path: /var/lib/grafana/dashboards/my-provider diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/ci/with-image-renderer-values.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/ci/with-image-renderer-values.yaml new file mode 100644 index 00000000..32f30743 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/ci/with-image-renderer-values.yaml @@ -0,0 +1,19 @@ +podLabels: + customLableA: Aaaaa +imageRenderer: + enabled: true + env: + RENDERING_ARGS: --disable-gpu,--window-size=1280x758 + RENDERING_MODE: clustered + podLabels: + customLableB: Bbbbb + networkPolicy: + limitIngress: true + limitEgress: true + resources: + limits: + cpu: 1000m + memory: 1000Mi + requests: + cpu: 500m + memory: 50Mi diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/dashboards/custom-dashboard.json b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/dashboards/custom-dashboard.json new file mode 100644 index 00000000..9e26dfee --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/dashboards/custom-dashboard.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/NOTES.txt b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/NOTES.txt new file mode 100644 index 00000000..1fc8436d --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/NOTES.txt @@ -0,0 +1,54 @@ +1. Get your '{{ .Values.adminUser }}' user password by running: + + kubectl get secret --namespace {{ template "grafana.namespace" . }} {{ template "grafana.fullname" . }} -o jsonpath="{.data.admin-password}" | base64 --decode ; echo + +2. The Grafana server can be accessed via port {{ .Values.service.port }} on the following DNS name from within your cluster: + + {{ template "grafana.fullname" . }}.{{ template "grafana.namespace" . }}.svc.cluster.local +{{ if .Values.ingress.enabled }} + If you bind grafana to 80, please update values in values.yaml and reinstall: + ``` + securityContext: + runAsUser: 0 + runAsGroup: 0 + fsGroup: 0 + + command: + - "setcap" + - "'cap_net_bind_service=+ep'" + - "/usr/sbin/grafana-server &&" + - "sh" + - "/run.sh" + ``` + Details refer to https://grafana.com/docs/installation/configuration/#http-port. + Or grafana would always crash. + + From outside the cluster, the server URL(s) are: +{{- range .Values.ingress.hosts }} + http://{{ . }} +{{- end }} +{{ else }} + Get the Grafana URL to visit by running these commands in the same shell: +{{ if contains "NodePort" .Values.service.type -}} + export NODE_PORT=$(kubectl get --namespace {{ template "grafana.namespace" . }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ template "grafana.fullname" . }}) + export NODE_IP=$(kubectl get nodes --namespace {{ template "grafana.namespace" . }} -o jsonpath="{.items[0].status.addresses[0].address}") + echo http://$NODE_IP:$NODE_PORT +{{ else if contains "LoadBalancer" .Values.service.type -}} + NOTE: It may take a few minutes for the LoadBalancer IP to be available. + You can watch the status of by running 'kubectl get svc --namespace {{ template "grafana.namespace" . }} -w {{ template "grafana.fullname" . }}' + export SERVICE_IP=$(kubectl get svc --namespace {{ template "grafana.namespace" . }} {{ template "grafana.fullname" . }} -o jsonpath='{.status.loadBalancer.ingress[0].ip}') + http://$SERVICE_IP:{{ .Values.service.port -}} +{{ else if contains "ClusterIP" .Values.service.type }} + export POD_NAME=$(kubectl get pods --namespace {{ template "grafana.namespace" . }} -l "app.kubernetes.io/name={{ template "grafana.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}") + kubectl --namespace {{ template "grafana.namespace" . }} port-forward $POD_NAME 3000 +{{- end }} +{{- end }} + +3. Login with the password from step 1 and the username: {{ .Values.adminUser }} + +{{- if not .Values.persistence.enabled }} +################################################################################# +###### WARNING: Persistence is disabled!!! You will lose your data when ##### +###### the Grafana pod is terminated. ##### +################################################################################# +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/_helpers.tpl b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/_helpers.tpl new file mode 100644 index 00000000..4dd88345 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/_helpers.tpl @@ -0,0 +1,102 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "grafana.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "grafana.fullname" -}} +{{- if .Values.fullnameOverride -}} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .Chart.Name .Values.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- .Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "grafana.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create the name of the service account +*/}} +{{- define "grafana.serviceAccountName" -}} +{{- if .Values.serviceAccount.create -}} + {{ default (include "grafana.fullname" .) .Values.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{- define "grafana.serviceAccountNameTest" -}} +{{- if .Values.serviceAccount.create -}} + {{ default (print (include "grafana.fullname" .) "-test") .Values.serviceAccount.nameTest }} +{{- else -}} + {{ default "default" .Values.serviceAccount.nameTest }} +{{- end -}} +{{- end -}} + +{{/* +Allow the release namespace to be overridden for multi-namespace deployments in combined charts +*/}} +{{- define "grafana.namespace" -}} + {{- if .Values.namespaceOverride -}} + {{- .Values.namespaceOverride -}} + {{- else -}} + {{- .Release.Namespace -}} + {{- end -}} +{{- end -}} + +{{/* +Common labels +*/}} +{{- define "grafana.labels" -}} +helm.sh/chart: {{ include "grafana.chart" . }} +{{ include "grafana.selectorLabels" . }} +{{- if or .Chart.AppVersion .Values.image.tag }} +app.kubernetes.io/version: {{ .Values.image.tag | default .Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- end -}} + +{{/* +Selector labels +*/}} +{{- define "grafana.selectorLabels" -}} +app.kubernetes.io/name: {{ include "grafana.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end -}} + +{{/* +Common labels +*/}} +{{- define "grafana.imageRenderer.labels" -}} +helm.sh/chart: {{ include "grafana.chart" . }} +{{ include "grafana.imageRenderer.selectorLabels" . }} +{{- if or .Chart.AppVersion .Values.image.tag }} +app.kubernetes.io/version: {{ .Values.image.tag | default .Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- end -}} + +{{/* +Selector labels ImageRenderer +*/}} +{{- define "grafana.imageRenderer.selectorLabels" -}} +app.kubernetes.io/name: {{ include "grafana.name" . }}-image-renderer +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/_pod.tpl b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/_pod.tpl new file mode 100644 index 00000000..a9e471ca --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/_pod.tpl @@ -0,0 +1,464 @@ + +{{- define "grafana.pod" -}} +{{- if .Values.schedulerName }} +schedulerName: "{{ .Values.schedulerName }}" +{{- end }} +serviceAccountName: {{ template "grafana.serviceAccountName" . }} +{{- if .Values.securityContext }} +securityContext: +{{ toYaml .Values.securityContext | indent 2 }} +{{- end }} +{{- if .Values.hostAliases }} +hostAliases: +{{ toYaml .Values.hostAliases | indent 2 }} +{{- end }} +{{- if .Values.priorityClassName }} +priorityClassName: {{ .Values.priorityClassName }} +{{- end }} +{{- if ( or .Values.persistence.enabled .Values.dashboards .Values.sidecar.datasources.enabled .Values.sidecar.notifiers.enabled .Values.extraInitContainers) }} +initContainers: +{{- end }} +{{- if ( and .Values.persistence.enabled .Values.initChownData.enabled ) }} + - name: init-chown-data + {{- if .Values.initChownData.image.sha }} + image: "{{ .Values.initChownData.image.repository }}:{{ .Values.initChownData.image.tag }}@sha256:{{ .Values.initChownData.image.sha }}" + {{- else }} + image: "{{ .Values.initChownData.image.repository }}:{{ .Values.initChownData.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.initChownData.image.pullPolicy }} + securityContext: + runAsNonRoot: false + runAsUser: 0 + command: ["chown", "-R", "{{ .Values.securityContext.runAsUser }}:{{ .Values.securityContext.runAsGroup }}", "/var/lib/grafana"] + resources: +{{ toYaml .Values.initChownData.resources | indent 6 }} + volumeMounts: + - name: storage + mountPath: "/var/lib/grafana" +{{- if .Values.persistence.subPath }} + subPath: {{ .Values.persistence.subPath }} +{{- end }} +{{- end }} +{{- if .Values.dashboards }} + - name: download-dashboards + {{- if .Values.downloadDashboardsImage.sha }} + image: "{{ .Values.downloadDashboardsImage.repository }}:{{ .Values.downloadDashboardsImage.tag }}@sha256:{{ .Values.downloadDashboardsImage.sha }}" + {{- else }} + image: "{{ .Values.downloadDashboardsImage.repository }}:{{ .Values.downloadDashboardsImage.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.downloadDashboardsImage.pullPolicy }} + command: ["/bin/sh"] + args: [ "-c", "mkdir -p /var/lib/grafana/dashboards/default && /bin/sh /etc/grafana/download_dashboards.sh" ] + resources: +{{ toYaml .Values.downloadDashboards.resources | indent 6 }} + env: +{{- range $key, $value := .Values.downloadDashboards.env }} + - name: "{{ $key }}" + value: "{{ $value }}" +{{- end }} + volumeMounts: + - name: config + mountPath: "/etc/grafana/download_dashboards.sh" + subPath: download_dashboards.sh + - name: storage + mountPath: "/var/lib/grafana" +{{- if .Values.persistence.subPath }} + subPath: {{ .Values.persistence.subPath }} +{{- end }} + {{- range .Values.extraSecretMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + readOnly: {{ .readOnly }} + {{- end }} +{{- end }} +{{- if .Values.sidecar.datasources.enabled }} + - name: {{ template "grafana.name" . }}-sc-datasources + {{- if .Values.sidecar.image.sha }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + - name: METHOD + value: LIST + - name: LABEL + value: "{{ .Values.sidecar.datasources.label }}" + - name: FOLDER + value: "/etc/grafana/provisioning/datasources" + - name: RESOURCE + value: "both" + {{- if .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ .Values.sidecar.enableUniqueFilenames }}" + {{- end }} + {{- if .Values.sidecar.datasources.searchNamespace }} + - name: NAMESPACE + value: "{{ .Values.sidecar.datasources.searchNamespace }}" + {{- end }} + {{- if .Values.sidecar.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: "{{ .Values.sidecar.skipTlsVerify }}" + {{- end }} + resources: +{{ toYaml .Values.sidecar.resources | indent 6 }} + volumeMounts: + - name: sc-datasources-volume + mountPath: "/etc/grafana/provisioning/datasources" +{{- end}} +{{- if .Values.sidecar.notifiers.enabled }} + - name: {{ template "grafana.name" . }}-sc-notifiers + {{- if .Values.sidecar.image.sha }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + - name: METHOD + value: LIST + - name: LABEL + value: "{{ .Values.sidecar.notifiers.label }}" + - name: FOLDER + value: "/etc/grafana/provisioning/notifiers" + - name: RESOURCE + value: "both" + {{- if .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ .Values.sidecar.enableUniqueFilenames }}" + {{- end }} + {{- if .Values.sidecar.notifiers.searchNamespace }} + - name: NAMESPACE + value: "{{ .Values.sidecar.notifiers.searchNamespace }}" + {{- end }} + {{- if .Values.sidecar.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: "{{ .Values.sidecar.skipTlsVerify }}" + {{- end }} + resources: +{{ toYaml .Values.sidecar.resources | indent 6 }} + volumeMounts: + - name: sc-notifiers-volume + mountPath: "/etc/grafana/provisioning/notifiers" +{{- end}} +{{- if .Values.extraInitContainers }} +{{ toYaml .Values.extraInitContainers | indent 2 }} +{{- end }} +{{- if .Values.image.pullSecrets }} +imagePullSecrets: +{{- range .Values.image.pullSecrets }} + - name: {{ . }} +{{- end}} +{{- end }} +containers: +{{- if .Values.sidecar.dashboards.enabled }} + - name: {{ template "grafana.name" . }}-sc-dashboard + {{- if .Values.sidecar.image.sha }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + - name: METHOD + value: {{ .Values.sidecar.dashboards.watchMethod }} + - name: LABEL + value: "{{ .Values.sidecar.dashboards.label }}" + - name: FOLDER + value: "{{ .Values.sidecar.dashboards.folder }}{{- with .Values.sidecar.dashboards.defaultFolderName }}/{{ . }}{{- end }}" + - name: RESOURCE + value: "both" + {{- if .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ .Values.sidecar.enableUniqueFilenames }}" + {{- end }} + {{- if .Values.sidecar.dashboards.searchNamespace }} + - name: NAMESPACE + value: "{{ .Values.sidecar.dashboards.searchNamespace }}" + {{- end }} + {{- if .Values.sidecar.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: "{{ .Values.sidecar.skipTlsVerify }}" + {{- end }} + {{- if .Values.sidecar.dashboards.folderAnnotation }} + - name: FOLDER_ANNOTATION + value: "{{ .Values.sidecar.dashboards.folderAnnotation }}" + {{- end }} + resources: +{{ toYaml .Values.sidecar.resources | indent 6 }} + volumeMounts: + - name: sc-dashboard-volume + mountPath: {{ .Values.sidecar.dashboards.folder | quote }} +{{- end}} + - name: {{ .Chart.Name }} + {{- if .Values.image.sha }} + image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}@sha256:{{ .Values.image.sha }}" + {{- else }} + image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + {{- if .Values.command }} + command: + {{- range .Values.command }} + - {{ . }} + {{- end }} + {{- end}} + volumeMounts: + - name: config + mountPath: "/etc/grafana/grafana.ini" + subPath: grafana.ini + {{- if .Values.ldap.enabled }} + - name: ldap + mountPath: "/etc/grafana/ldap.toml" + subPath: ldap.toml + {{- end }} + {{- range .Values.extraConfigmapMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + subPath: {{ .subPath | default "" }} + readOnly: {{ .readOnly }} + {{- end }} + - name: storage + mountPath: "/var/lib/grafana" +{{- if .Values.persistence.subPath }} + subPath: {{ .Values.persistence.subPath }} +{{- end }} +{{- if .Values.dashboards }} +{{- range $provider, $dashboards := .Values.dashboards }} +{{- range $key, $value := $dashboards }} +{{- if (or (hasKey $value "json") (hasKey $value "file")) }} + - name: dashboards-{{ $provider }} + mountPath: "/var/lib/grafana/dashboards/{{ $provider }}/{{ $key }}.json" + subPath: "{{ $key }}.json" +{{- end }} +{{- end }} +{{- end }} +{{- end -}} +{{- if .Values.dashboardsConfigMaps }} +{{- range (keys .Values.dashboardsConfigMaps | sortAlpha) }} + - name: dashboards-{{ . }} + mountPath: "/var/lib/grafana/dashboards/{{ . }}" +{{- end }} +{{- end }} +{{- if .Values.datasources }} + - name: config + mountPath: "/etc/grafana/provisioning/datasources/datasources.yaml" + subPath: datasources.yaml +{{- end }} +{{- if .Values.notifiers }} + - name: config + mountPath: "/etc/grafana/provisioning/notifiers/notifiers.yaml" + subPath: notifiers.yaml +{{- end }} +{{- if .Values.dashboardProviders }} + - name: config + mountPath: "/etc/grafana/provisioning/dashboards/dashboardproviders.yaml" + subPath: dashboardproviders.yaml +{{- end }} +{{- if .Values.sidecar.dashboards.enabled }} + - name: sc-dashboard-volume + mountPath: {{ .Values.sidecar.dashboards.folder | quote }} +{{ if .Values.sidecar.dashboards.SCProvider }} + - name: sc-dashboard-provider + mountPath: "/etc/grafana/provisioning/dashboards/sc-dashboardproviders.yaml" + subPath: provider.yaml +{{- end}} +{{- end}} +{{- if .Values.sidecar.datasources.enabled }} + - name: sc-datasources-volume + mountPath: "/etc/grafana/provisioning/datasources" +{{- end}} +{{- if .Values.sidecar.notifiers.enabled }} + - name: sc-notifiers-volume + mountPath: "/etc/grafana/provisioning/notifiers" +{{- end}} + {{- range .Values.extraSecretMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + readOnly: {{ .readOnly }} + subPath: {{ .subPath | default "" }} + {{- end }} + {{- range .Values.extraVolumeMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + subPath: {{ .subPath | default "" }} + readOnly: {{ .readOnly }} + {{- end }} + {{- range .Values.extraEmptyDirMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + {{- end }} + ports: + - name: {{ .Values.service.portName }} + containerPort: {{ .Values.service.port }} + protocol: TCP + - name: {{ .Values.podPortName }} + containerPort: 3000 + protocol: TCP + env: + {{- if not .Values.env.GF_SECURITY_ADMIN_USER }} + - name: GF_SECURITY_ADMIN_USER + valueFrom: + secretKeyRef: + name: {{ .Values.admin.existingSecret | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.userKey | default "admin-user" }} + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) }} + - name: GF_SECURITY_ADMIN_PASSWORD + valueFrom: + secretKeyRef: + name: {{ .Values.admin.existingSecret | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.passwordKey | default "admin-password" }} + {{- end }} + {{- if .Values.plugins }} + - name: GF_INSTALL_PLUGINS + valueFrom: + configMapKeyRef: + name: {{ template "grafana.fullname" . }} + key: plugins + {{- end }} + {{- if .Values.smtp.existingSecret }} + - name: GF_SMTP_USER + valueFrom: + secretKeyRef: + name: {{ .Values.smtp.existingSecret }} + key: {{ .Values.smtp.userKey | default "user" }} + - name: GF_SMTP_PASSWORD + valueFrom: + secretKeyRef: + name: {{ .Values.smtp.existingSecret }} + key: {{ .Values.smtp.passwordKey | default "password" }} + {{- end }} + {{ if .Values.imageRenderer.enabled }} + - name: GF_RENDERING_SERVER_URL + value: http://{{ template "grafana.fullname" . }}-image-renderer.{{ template "grafana.namespace" . }}:{{ .Values.imageRenderer.service.port }}/render + - name: GF_RENDERING_CALLBACK_URL + value: http://{{ template "grafana.fullname" . }}.{{ template "grafana.namespace" . }}:{{ .Values.service.port }}/ + {{ end }} + {{- range $key, $value := .Values.envValueFrom }} + - name: {{ $key | quote }} + valueFrom: +{{ toYaml $value | indent 10 }} + {{- end }} +{{- range $key, $value := .Values.env }} + - name: "{{ tpl $key $ }}" + value: "{{ tpl (print $value) $ }}" +{{- end }} + {{- if .Values.envFromSecret }} + envFrom: + - secretRef: + name: {{ tpl .Values.envFromSecret . }} + {{- end }} + {{- if .Values.envRenderSecret }} + envFrom: + - secretRef: + name: {{ template "grafana.fullname" . }}-env + {{- end }} + livenessProbe: +{{ toYaml .Values.livenessProbe | indent 6 }} + readinessProbe: +{{ toYaml .Values.readinessProbe | indent 6 }} + resources: +{{ toYaml .Values.resources | indent 6 }} +{{- with .Values.extraContainers }} +{{ tpl . $ | indent 2 }} +{{- end }} +{{- with .Values.nodeSelector }} +nodeSelector: +{{ toYaml . | indent 2 }} +{{- end }} +{{- with .Values.affinity }} +affinity: +{{ toYaml . | indent 2 }} +{{- end }} +{{- with .Values.tolerations }} +tolerations: +{{ toYaml . | indent 2 }} +{{- end }} +volumes: + - name: config + configMap: + name: {{ template "grafana.fullname" . }} +{{- range .Values.extraConfigmapMounts }} + - name: {{ .name }} + configMap: + name: {{ .configMap }} +{{- end }} + {{- if .Values.dashboards }} + {{- range (keys .Values.dashboards | sortAlpha) }} + - name: dashboards-{{ . }} + configMap: + name: {{ template "grafana.fullname" $ }}-dashboards-{{ . }} + {{- end }} + {{- end }} + {{- if .Values.dashboardsConfigMaps }} + {{ $root := . }} + {{- range $provider, $name := .Values.dashboardsConfigMaps }} + - name: dashboards-{{ $provider }} + configMap: + name: {{ tpl $name $root }} + {{- end }} + {{- end }} + {{- if .Values.ldap.enabled }} + - name: ldap + secret: + {{- if .Values.ldap.existingSecret }} + secretName: {{ .Values.ldap.existingSecret }} + {{- else }} + secretName: {{ template "grafana.fullname" . }} + {{- end }} + items: + - key: ldap-toml + path: ldap.toml + {{- end }} +{{- if and .Values.persistence.enabled (eq .Values.persistence.type "pvc") }} + - name: storage + persistentVolumeClaim: + claimName: {{ .Values.persistence.existingClaim | default (include "grafana.fullname" .) }} +{{- else if and .Values.persistence.enabled (eq .Values.persistence.type "statefulset") }} +# nothing +{{- else }} + - name: storage + emptyDir: {} +{{- end -}} +{{- if .Values.sidecar.dashboards.enabled }} + - name: sc-dashboard-volume + emptyDir: {} +{{- if .Values.sidecar.dashboards.SCProvider }} + - name: sc-dashboard-provider + configMap: + name: {{ template "grafana.fullname" . }}-config-dashboards +{{- end }} +{{- end }} +{{- if .Values.sidecar.datasources.enabled }} + - name: sc-datasources-volume + emptyDir: {} +{{- end -}} +{{- if .Values.sidecar.notifiers.enabled }} + - name: sc-notifiers-volume + emptyDir: {} +{{- end -}} +{{- range .Values.extraSecretMounts }} +{{- if .secretName }} + - name: {{ .name }} + secret: + secretName: {{ .secretName }} + defaultMode: {{ .defaultMode }} +{{- else if .projected }} + - name: {{ .name }} + projected: {{- toYaml .projected | nindent 6 }} +{{- end }} +{{- end }} +{{- range .Values.extraVolumeMounts }} + - name: {{ .name }} + persistentVolumeClaim: + claimName: {{ .existingClaim }} +{{- end }} +{{- range .Values.extraEmptyDirMounts }} + - name: {{ .name }} + emptyDir: {} +{{- end -}} +{{- if .Values.extraContainerVolumes }} +{{ toYaml .Values.extraContainerVolumes | indent 2 }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/clusterrole.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/clusterrole.yaml new file mode 100644 index 00000000..f09e0656 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/clusterrole.yaml @@ -0,0 +1,25 @@ +{{- if and .Values.rbac.create (not .Values.rbac.namespaced) (not .Values.rbac.useExistingRole) }} +kind: ClusterRole +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + labels: + {{- include "grafana.labels" . | nindent 4 }} +{{- with .Values.annotations }} + annotations: +{{ toYaml . | indent 4 }} +{{- end }} + name: {{ template "grafana.fullname" . }}-clusterrole +{{- if or .Values.sidecar.dashboards.enabled (or .Values.sidecar.datasources.enabled .Values.rbac.extraClusterRoleRules) }} +rules: +{{- if or .Values.sidecar.dashboards.enabled .Values.sidecar.datasources.enabled }} +- apiGroups: [""] # "" indicates the core API group + resources: ["configmaps", "secrets"] + verbs: ["get", "watch", "list"] +{{- end}} +{{- with .Values.rbac.extraClusterRoleRules }} +{{ toYaml . | indent 0 }} +{{- end}} +{{- else }} +rules: [] +{{- end}} +{{- end}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/clusterrolebinding.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/clusterrolebinding.yaml new file mode 100644 index 00000000..4accbfac --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/clusterrolebinding.yaml @@ -0,0 +1,24 @@ +{{- if and .Values.rbac.create (not .Values.rbac.namespaced) }} +kind: ClusterRoleBinding +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: {{ template "grafana.fullname" . }}-clusterrolebinding + labels: + {{- include "grafana.labels" . | nindent 4 }} +{{- with .Values.annotations }} + annotations: +{{ toYaml . | indent 4 }} +{{- end }} +subjects: + - kind: ServiceAccount + name: {{ template "grafana.serviceAccountName" . }} + namespace: {{ template "grafana.namespace" . }} +roleRef: + kind: ClusterRole +{{- if (not .Values.rbac.useExistingRole) }} + name: {{ template "grafana.fullname" . }}-clusterrole +{{- else }} + name: {{ .Values.rbac.useExistingRole }} +{{- end }} + apiGroup: rbac.authorization.k8s.io +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/configmap-dashboard-provider.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/configmap-dashboard-provider.yaml new file mode 100644 index 00000000..8bb05670 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/configmap-dashboard-provider.yaml @@ -0,0 +1,26 @@ +{{- if .Values.sidecar.dashboards.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + labels: + {{- include "grafana.labels" . | nindent 4 }} +{{- with .Values.annotations }} + annotations: +{{ toYaml . | indent 4 }} +{{- end }} + name: {{ template "grafana.fullname" . }}-config-dashboards + namespace: {{ template "grafana.namespace" . }} +data: + provider.yaml: |- + apiVersion: 1 + providers: + - name: '{{ .Values.sidecar.dashboards.provider.name }}' + orgId: {{ .Values.sidecar.dashboards.provider.orgid }} + folder: '{{ .Values.sidecar.dashboards.provider.folder }}' + type: {{ .Values.sidecar.dashboards.provider.type }} + disableDeletion: {{ .Values.sidecar.dashboards.provider.disableDelete }} + allowUiUpdates: {{ .Values.sidecar.dashboards.provider.allowUiUpdates }} + options: + foldersFromFilesStructure: {{ .Values.sidecar.dashboards.provider.foldersFromFilesStructure }} + path: {{ .Values.sidecar.dashboards.folder }}{{- with .Values.sidecar.dashboards.defaultFolderName }}/{{ . }}{{- end }} +{{- end}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/configmap.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/configmap.yaml new file mode 100644 index 00000000..a9fdc3a8 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/configmap.yaml @@ -0,0 +1,69 @@ +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ template "grafana.fullname" . }} + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} +data: +{{- if .Values.plugins }} + plugins: {{ join "," .Values.plugins }} +{{- end }} + grafana.ini: | +{{- range $key, $value := index .Values "grafana.ini" }} + [{{ $key }}] + {{- range $elem, $elemVal := $value }} + {{ $elem }} = {{ $elemVal }} + {{- end }} +{{- end }} + +{{- if .Values.datasources }} +{{ $root := . }} + {{- range $key, $value := .Values.datasources }} + {{ $key }}: | +{{ tpl (toYaml $value | indent 4) $root }} + {{- end -}} +{{- end -}} + +{{- if .Values.notifiers }} + {{- range $key, $value := .Values.notifiers }} + {{ $key }}: | +{{ toYaml $value | indent 4 }} + {{- end -}} +{{- end -}} + +{{- if .Values.dashboardProviders }} + {{- range $key, $value := .Values.dashboardProviders }} + {{ $key }}: | +{{ toYaml $value | indent 4 }} + {{- end -}} +{{- end -}} + +{{- if .Values.dashboards }} + download_dashboards.sh: | + #!/usr/bin/env sh + set -euf + {{- if .Values.dashboardProviders }} + {{- range $key, $value := .Values.dashboardProviders }} + {{- range $value.providers }} + mkdir -p {{ .options.path }} + {{- end }} + {{- end }} + {{- end }} + + {{- range $provider, $dashboards := .Values.dashboards }} + {{- range $key, $value := $dashboards }} + {{- if (or (hasKey $value "gnetId") (hasKey $value "url")) }} + curl -skf \ + --connect-timeout 60 \ + --max-time 60 \ + {{- if not $value.b64content }} + -H "Accept: application/json" \ + -H "Content-Type: application/json;charset=UTF-8" \ + {{ end }} + {{- if $value.url -}}"{{ $value.url }}"{{- else -}}"https://grafana.com/api/dashboards/{{ $value.gnetId }}/revisions/{{- if $value.revision -}}{{ $value.revision }}{{- else -}}1{{- end -}}/download"{{- end -}}{{ if $value.datasource }} | sed '/-- .* --/! s/"datasource":.*,/"datasource": "{{ $value.datasource }}",/g'{{ end }}{{- if $value.b64content -}} | base64 -d {{- end -}} \ + > "/var/lib/grafana/dashboards/{{ $provider }}/{{ $key }}.json" + {{- end -}} + {{- end }} + {{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/dashboards-json-configmap.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/dashboards-json-configmap.yaml new file mode 100644 index 00000000..59e0be64 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/dashboards-json-configmap.yaml @@ -0,0 +1,35 @@ +{{- if .Values.dashboards }} +{{ $files := .Files }} +{{- range $provider, $dashboards := .Values.dashboards }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ template "grafana.fullname" $ }}-dashboards-{{ $provider }} + namespace: {{ template "grafana.namespace" $ }} + labels: + {{- include "grafana.labels" $ | nindent 4 }} + dashboard-provider: {{ $provider }} +{{- if $dashboards }} +data: +{{- $dashboardFound := false }} +{{- range $key, $value := $dashboards }} +{{- if (or (hasKey $value "json") (hasKey $value "file")) }} +{{- $dashboardFound = true }} +{{ print $key | indent 2 }}.json: +{{- if hasKey $value "json" }} + |- +{{ $value.json | indent 6 }} +{{- end }} +{{- if hasKey $value "file" }} +{{ toYaml ( $files.Get $value.file ) | indent 4}} +{{- end }} +{{- end }} +{{- end }} +{{- if not $dashboardFound }} + {} +{{- end }} +{{- end }} +--- +{{- end }} + +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/deployment.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/deployment.yaml new file mode 100644 index 00000000..4d77794c --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/deployment.yaml @@ -0,0 +1,48 @@ +{{ if (or (not .Values.persistence.enabled) (eq .Values.persistence.type "pvc")) }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ template "grafana.fullname" . }} + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} +{{- if .Values.labels }} +{{ toYaml .Values.labels | indent 4 }} +{{- end }} +{{- with .Values.annotations }} + annotations: +{{ toYaml . | indent 4 }} +{{- end }} +spec: + replicas: {{ .Values.replicas }} + revisionHistoryLimit: {{ .Values.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 6 }} +{{- with .Values.deploymentStrategy }} + strategy: +{{ toYaml . | trim | indent 4 }} +{{- end }} + template: + metadata: + labels: + {{- include "grafana.selectorLabels" . | nindent 8 }} +{{- with .Values.podLabels }} +{{ toYaml . | indent 8 }} +{{- end }} + annotations: + checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} + checksum/dashboards-json-config: {{ include (print $.Template.BasePath "/dashboards-json-configmap.yaml") . | sha256sum }} + checksum/sc-dashboard-provider-config: {{ include (print $.Template.BasePath "/configmap-dashboard-provider.yaml") . | sha256sum }} +{{- if or (and (not .Values.admin.existingSecret) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD)) (and .Values.ldap.enabled (not .Values.ldap.existingSecret)) }} + checksum/secret: {{ include (print $.Template.BasePath "/secret.yaml") . | sha256sum }} +{{- end }} +{{- if .Values.envRenderSecret }} + checksum/secret-env: {{ include (print $.Template.BasePath "/secret-env.yaml") . | sha256sum }} +{{- end }} +{{- with .Values.podAnnotations }} +{{ toYaml . | indent 8 }} +{{- end }} + spec: + {{- include "grafana.pod" . | nindent 6 }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/headless-service.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/headless-service.yaml new file mode 100644 index 00000000..2fa816e0 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/headless-service.yaml @@ -0,0 +1,18 @@ +{{- if and .Values.persistence.enabled (not .Values.persistence.existingClaim) (eq .Values.persistence.type "statefulset")}} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "grafana.fullname" . }}-headless + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} +{{- with .Values.annotations }} + annotations: +{{ toYaml . | indent 4 }} +{{- end }} +spec: + clusterIP: None + selector: + {{- include "grafana.selectorLabels" . | nindent 4 }} + type: ClusterIP +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/image-renderer-deployment.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/image-renderer-deployment.yaml new file mode 100644 index 00000000..1f60ffb4 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/image-renderer-deployment.yaml @@ -0,0 +1,112 @@ +{{ if .Values.imageRenderer.enabled }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ template "grafana.fullname" . }}-image-renderer + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.imageRenderer.labels" . | nindent 4 }} +{{- if .Values.imageRenderer.labels }} +{{ toYaml .Values.imageRenderer.labels | indent 4 }} +{{- end }} +{{- with .Values.imageRenderer.annotations }} + annotations: +{{ toYaml . | indent 4 }} +{{- end }} +spec: + replicas: {{ .Values.imageRenderer.replicas }} + revisionHistoryLimit: {{ .Values.imageRenderer.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "grafana.imageRenderer.selectorLabels" . | nindent 6 }} +{{- with .Values.imageRenderer.deploymentStrategy }} + strategy: +{{ toYaml . | trim | indent 4 }} +{{- end }} + template: + metadata: + labels: + {{- include "grafana.imageRenderer.selectorLabels" . | nindent 8 }} +{{- with .Values.imageRenderer.podLabels }} +{{ toYaml . | indent 8 }} +{{- end }} + annotations: + checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} +{{- with .Values.imageRenderer.podAnnotations }} +{{ toYaml . | indent 8 }} +{{- end }} + spec: + + {{- if .Values.imageRenderer.schedulerName }} + schedulerName: "{{ .Values.imageRenderer.schedulerName }}" + {{- end }} + {{- if .Values.imageRenderer.securityContext }} + securityContext: + {{ toYaml .Values.imageRenderer.securityContext | indent 2 }} + {{- end }} + {{- if .Values.imageRenderer.hostAliases }} + hostAliases: + {{ toYaml .Values.imageRenderer.hostAliases | indent 2 }} + {{- end }} + {{- if .Values.imageRenderer.priorityClassName }} + priorityClassName: {{ .Values.imageRenderer.priorityClassName }} + {{- end }} + {{- if .Values.imageRenderer.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.imageRenderer.image.pullSecrets }} + - name: {{ . }} + {{- end}} + {{- end }} + containers: + - name: {{ .Chart.Name }}-image-renderer + {{- if .Values.imageRenderer.image.sha }} + image: "{{ .Values.imageRenderer.image.repository }}:{{ .Values.imageRenderer.image.tag }}@sha256:{{ .Values.imageRenderer.image.sha }}" + {{- else }} + image: "{{ .Values.imageRenderer.image.repository }}:{{ .Values.imageRenderer.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.imageRenderer.image.pullPolicy }} + {{- if .Values.imageRenderer.command }} + command: + {{- range .Values.imageRenderer.command }} + - {{ . }} + {{- end }} + {{- end}} + ports: + - name: {{ .Values.imageRenderer.service.portName }} + containerPort: {{ .Values.imageRenderer.service.port }} + protocol: TCP + env: + - name: HTTP_PORT + value: {{ .Values.imageRenderer.service.port | quote }} + {{- range $key, $value := .Values.imageRenderer.env }} + - name: {{ $key | quote }} + value: {{ $value | quote }} + {{- end }} + securityContext: + capabilities: + drop: ['all'] + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + volumeMounts: + - mountPath: /tmp + name: image-renderer-tmpfs + {{- with .Values.imageRenderer.resources }} + resources: +{{ toYaml . | indent 12 }} + {{- end }} + {{- with .Values.imageRenderer.nodeSelector }} + nodeSelector: +{{ toYaml . | indent 8 }} + {{- end }} + {{- with .Values.imageRenderer.affinity }} + affinity: +{{ toYaml . | indent 8 }} + {{- end }} + {{- with .Values.imageRenderer.tolerations }} + tolerations: +{{ toYaml . | indent 8 }} + {{- end }} + volumes: + - name: image-renderer-tmpfs + emptyDir: {} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/image-renderer-network-policy.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/image-renderer-network-policy.yaml new file mode 100644 index 00000000..f8ca73aa --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/image-renderer-network-policy.yaml @@ -0,0 +1,76 @@ +{{- if and (.Values.imageRenderer.enabled) (.Values.imageRenderer.networkPolicy.limitIngress) }} +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ template "grafana.fullname" . }}-image-renderer-ingress + namespace: {{ template "grafana.namespace" . }} + annotations: + comment: Limit image-renderer ingress traffic from grafana +spec: + podSelector: + matchLabels: + {{- include "grafana.imageRenderer.selectorLabels" . | nindent 6 }} + {{- if .Values.imageRenderer.podLabels }} + {{ toYaml .Values.imageRenderer.podLabels | nindent 6 }} + {{- end }} + + policyTypes: + - Ingress + ingress: + - ports: + - port: {{ .Values.imageRenderer.service.port }} + protocol: TCP + from: + - namespaceSelector: + matchLabels: + name: {{ template "grafana.namespace" . }} + podSelector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 14 }} + {{- if .Values.podLabels }} + {{ toYaml .Values.podLabels | nindent 14 }} + {{- end }} +{{ end }} + +{{- if and (.Values.imageRenderer.enabled) (.Values.imageRenderer.networkPolicy.limitEgress) }} +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ template "grafana.fullname" . }}-image-renderer-egress + namespace: {{ template "grafana.namespace" . }} + annotations: + comment: Limit image-renderer egress traffic to grafana +spec: + podSelector: + matchLabels: + {{- include "grafana.imageRenderer.selectorLabels" . | nindent 6 }} + {{- if .Values.imageRenderer.podLabels }} + {{ toYaml .Values.imageRenderer.podLabels | nindent 6 }} + {{- end }} + + policyTypes: + - Egress + egress: + # allow dns resolution + - ports: + - port: 53 + protocol: UDP + - port: 53 + protocol: TCP + # talk only to grafana + - ports: + - port: {{ .Values.service.port }} + protocol: TCP + to: + - namespaceSelector: + matchLabels: + name: {{ template "grafana.namespace" . }} + podSelector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 14 }} + {{- if .Values.podLabels }} + {{ toYaml .Values.podLabels | nindent 14 }} + {{- end }} +{{ end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/image-renderer-service.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/image-renderer-service.yaml new file mode 100644 index 00000000..f5d3eb02 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/image-renderer-service.yaml @@ -0,0 +1,28 @@ +{{ if .Values.imageRenderer.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "grafana.fullname" . }}-image-renderer + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.imageRenderer.labels" . | nindent 4 }} +{{- if .Values.imageRenderer.service.labels }} +{{ toYaml .Values.imageRenderer.service.labels | indent 4 }} +{{- end }} +{{- with .Values.imageRenderer.service.annotations }} + annotations: +{{ toYaml . | indent 4 }} +{{- end }} +spec: + type: ClusterIP + {{- if .Values.imageRenderer.service.clusterIP }} + clusterIP: {{ .Values.imageRenderer.service.clusterIP }} + {{end}} + ports: + - name: {{ .Values.imageRenderer.service.portName }} + port: {{ .Values.imageRenderer.service.port }} + protocol: TCP + targetPort: {{ .Values.imageRenderer.service.targetPort }} + selector: + {{- include "grafana.imageRenderer.selectorLabels" . | nindent 4 }} +{{ end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/ingress.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/ingress.yaml new file mode 100644 index 00000000..8d35662e --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/ingress.yaml @@ -0,0 +1,55 @@ +{{- if .Values.ingress.enabled -}} +{{- $fullName := include "grafana.fullname" . -}} +{{- $servicePort := .Values.service.port -}} +{{- $ingressPath := .Values.ingress.path -}} +{{- $extraPaths := .Values.ingress.extraPaths -}} +{{- if .Capabilities.APIVersions.Has "networking.k8s.io/v1beta1" }} +apiVersion: networking.k8s.io/v1beta1 +{{ else }} +apiVersion: extensions/v1beta1 +{{ end -}} +kind: Ingress +metadata: + name: {{ $fullName }} + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} +{{- if .Values.ingress.labels }} +{{ toYaml .Values.ingress.labels | indent 4 }} +{{- end }} + {{- if .Values.ingress.annotations }} + annotations: + {{- range $key, $value := .Values.ingress.annotations }} + {{ $key }}: {{ tpl $value $ | quote }} + {{- end }} + {{- end }} +spec: +{{- if .Values.ingress.tls }} + tls: +{{ toYaml .Values.ingress.tls | indent 4 }} +{{- end }} + rules: + {{- if .Values.ingress.hosts }} + {{- range .Values.ingress.hosts }} + - host: {{ . }} + http: + paths: +{{ if $extraPaths }} +{{ toYaml $extraPaths | indent 10 }} +{{- end }} + - path: {{ $ingressPath }} + backend: + serviceName: {{ $fullName }} + servicePort: {{ $servicePort }} + {{- end }} + {{- else }} + - http: + paths: + - backend: + serviceName: {{ $fullName }} + servicePort: {{ $servicePort }} + {{- if $ingressPath }} + path: {{ $ingressPath }} + {{- end }} + {{- end -}} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/poddisruptionbudget.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/poddisruptionbudget.yaml new file mode 100644 index 00000000..61813a43 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/poddisruptionbudget.yaml @@ -0,0 +1,22 @@ +{{- if .Values.podDisruptionBudget }} +apiVersion: policy/v1beta1 +kind: PodDisruptionBudget +metadata: + name: {{ template "grafana.fullname" . }} + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} +{{- if .Values.labels }} +{{ toYaml .Values.labels | indent 4 }} +{{- end }} +spec: +{{- if .Values.podDisruptionBudget.minAvailable }} + minAvailable: {{ .Values.podDisruptionBudget.minAvailable }} +{{- end }} +{{- if .Values.podDisruptionBudget.maxUnavailable }} + maxUnavailable: {{ .Values.podDisruptionBudget.maxUnavailable }} +{{- end }} + selector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 6 }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/podsecuritypolicy.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/podsecuritypolicy.yaml new file mode 100644 index 00000000..9d50471b --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/podsecuritypolicy.yaml @@ -0,0 +1,52 @@ +{{- if .Values.rbac.pspEnabled }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ template "grafana.fullname" . }} + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + annotations: + seccomp.security.alpha.kubernetes.io/allowedProfileNames: 'docker/default,runtime/default' + seccomp.security.alpha.kubernetes.io/defaultProfileName: 'docker/default' + {{- if .Values.rbac.pspUseAppArmor }} + apparmor.security.beta.kubernetes.io/allowedProfileNames: 'runtime/default' + apparmor.security.beta.kubernetes.io/defaultProfileName: 'runtime/default' + {{- end }} +spec: + privileged: false + allowPrivilegeEscalation: false + requiredDropCapabilities: + # Default set from Docker, without DAC_OVERRIDE or CHOWN + - FOWNER + - FSETID + - KILL + - SETGID + - SETUID + - SETPCAP + - NET_BIND_SERVICE + - NET_RAW + - SYS_CHROOT + - MKNOD + - AUDIT_WRITE + - SETFCAP + volumes: + - 'configMap' + - 'emptyDir' + - 'projected' + - 'secret' + - 'downwardAPI' + - 'persistentVolumeClaim' + hostNetwork: false + hostIPC: false + hostPID: false + runAsUser: + rule: 'RunAsAny' + seLinux: + rule: 'RunAsAny' + supplementalGroups: + rule: 'RunAsAny' + fsGroup: + rule: 'RunAsAny' + readOnlyRootFilesystem: false +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/pvc.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/pvc.yaml new file mode 100644 index 00000000..4727d0aa --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/pvc.yaml @@ -0,0 +1,28 @@ +{{- if and .Values.persistence.enabled (not .Values.persistence.existingClaim) (eq .Values.persistence.type "pvc")}} +apiVersion: v1 +kind: PersistentVolumeClaim +metadata: + name: {{ template "grafana.fullname" . }} + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.persistence.annotations }} + annotations: +{{ toYaml . | indent 4 }} + {{- end }} + {{- with .Values.persistence.finalizers }} + finalizers: +{{ toYaml . | indent 4 }} + {{- end }} +spec: + accessModes: + {{- range .Values.persistence.accessModes }} + - {{ . | quote }} + {{- end }} + resources: + requests: + storage: {{ .Values.persistence.size | quote }} + {{- if .Values.persistence.storageClassName }} + storageClassName: {{ .Values.persistence.storageClassName }} + {{- end -}} +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/role.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/role.yaml new file mode 100644 index 00000000..db853559 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/role.yaml @@ -0,0 +1,32 @@ +{{- if and .Values.rbac.create (not .Values.rbac.useExistingRole) -}} +apiVersion: rbac.authorization.k8s.io/v1beta1 +kind: Role +metadata: + name: {{ template "grafana.fullname" . }} + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} +{{- with .Values.annotations }} + annotations: +{{ toYaml . | indent 4 }} +{{- end }} +{{- if or .Values.rbac.pspEnabled (and .Values.rbac.namespaced (or .Values.sidecar.dashboards.enabled (or .Values.sidecar.datasources.enabled .Values.rbac.extraRoleRules))) }} +rules: +{{- if .Values.rbac.pspEnabled }} +- apiGroups: ['extensions'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: [{{ template "grafana.fullname" . }}] +{{- end }} +{{- if and .Values.rbac.namespaced (or .Values.sidecar.dashboards.enabled .Values.sidecar.datasources.enabled) }} +- apiGroups: [""] # "" indicates the core API group + resources: ["configmaps", "secrets"] + verbs: ["get", "watch", "list"] +{{- end }} +{{- with .Values.rbac.extraRoleRules }} +{{ toYaml . | indent 0 }} +{{- end}} +{{- else }} +rules: [] +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/rolebinding.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/rolebinding.yaml new file mode 100644 index 00000000..3738e580 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/rolebinding.yaml @@ -0,0 +1,25 @@ +{{- if .Values.rbac.create -}} +apiVersion: rbac.authorization.k8s.io/v1beta1 +kind: RoleBinding +metadata: + name: {{ template "grafana.fullname" . }} + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} +{{- with .Values.annotations }} + annotations: +{{ toYaml . | indent 4 }} +{{- end }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role +{{- if (not .Values.rbac.useExistingRole) }} + name: {{ template "grafana.fullname" . }} +{{- else }} + name: {{ .Values.rbac.useExistingRole }} +{{- end }} +subjects: +- kind: ServiceAccount + name: {{ template "grafana.serviceAccountName" . }} + namespace: {{ template "grafana.namespace" . }} +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/secret-env.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/secret-env.yaml new file mode 100644 index 00000000..5c09313e --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/secret-env.yaml @@ -0,0 +1,14 @@ +{{- if .Values.envRenderSecret }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ template "grafana.fullname" . }}-env + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} +type: Opaque +data: +{{- range $key, $val := .Values.envRenderSecret }} + {{ $key }}: {{ $val | b64enc | quote }} +{{- end -}} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/secret.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/secret.yaml new file mode 100644 index 00000000..9d2f072e --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/secret.yaml @@ -0,0 +1,22 @@ +{{- if or (and (not .Values.admin.existingSecret) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD)) (and .Values.ldap.enabled (not .Values.ldap.existingSecret)) }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ template "grafana.fullname" . }} + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} +type: Opaque +data: + {{- if and (not .Values.admin.existingSecret) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) }} + admin-user: {{ .Values.adminUser | b64enc | quote }} + {{- if .Values.adminPassword }} + admin-password: {{ .Values.adminPassword | b64enc | quote }} + {{- else }} + admin-password: {{ randAlphaNum 40 | b64enc | quote }} + {{- end }} + {{- end }} + {{- if not .Values.ldap.existingSecret }} + ldap-toml: {{ .Values.ldap.config | b64enc | quote }} + {{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/service.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/service.yaml new file mode 100644 index 00000000..27645669 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/service.yaml @@ -0,0 +1,50 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ template "grafana.fullname" . }} + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} +{{- if .Values.service.labels }} +{{ toYaml .Values.service.labels | indent 4 }} +{{- end }} +{{- with .Values.service.annotations }} + annotations: +{{ toYaml . | indent 4 }} +{{- end }} +spec: +{{- if (or (eq .Values.service.type "ClusterIP") (empty .Values.service.type)) }} + type: ClusterIP + {{- if .Values.service.clusterIP }} + clusterIP: {{ .Values.service.clusterIP }} + {{end}} +{{- else if eq .Values.service.type "LoadBalancer" }} + type: {{ .Values.service.type }} + {{- if .Values.service.loadBalancerIP }} + loadBalancerIP: {{ .Values.service.loadBalancerIP }} + {{- end }} + {{- if .Values.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: +{{ toYaml .Values.service.loadBalancerSourceRanges | indent 4 }} + {{- end -}} +{{- else }} + type: {{ .Values.service.type }} +{{- end }} +{{- if .Values.service.externalIPs }} + externalIPs: +{{ toYaml .Values.service.externalIPs | indent 4 }} +{{- end }} + ports: + - name: {{ .Values.service.portName }} + port: {{ .Values.service.port }} + protocol: TCP + targetPort: {{ .Values.service.targetPort }} +{{ if (and (eq .Values.service.type "NodePort") (not (empty .Values.service.nodePort))) }} + nodePort: {{.Values.service.nodePort}} +{{ end }} + {{- if .Values.extraExposePorts }} + {{- tpl (toYaml .Values.extraExposePorts) . | indent 4 }} + {{- end }} + selector: + {{- include "grafana.selectorLabels" . | nindent 4 }} + diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/serviceaccount.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/serviceaccount.yaml new file mode 100644 index 00000000..7576eeef --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/serviceaccount.yaml @@ -0,0 +1,13 @@ +{{- if .Values.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + labels: + {{- include "grafana.labels" . | nindent 4 }} +{{- with .Values.serviceAccount.annotations }} + annotations: +{{ toYaml . | indent 4 }} +{{- end }} + name: {{ template "grafana.serviceAccountName" . }} + namespace: {{ template "grafana.namespace" . }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/servicemonitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/servicemonitor.yaml new file mode 100644 index 00000000..988956bc --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/servicemonitor.yaml @@ -0,0 +1,36 @@ +{{- if .Values.serviceMonitor.enabled }} +--- +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "grafana.fullname" . }} + {{- if .Values.serviceMonitor.namespace }} + namespace: {{ .Values.serviceMonitor.namespace }} + {{- end }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- if .Values.serviceMonitor.labels }} + {{- toYaml .Values.serviceMonitor.labels | nindent 4 }} + {{- end }} +spec: + endpoints: + - interval: {{ .Values.serviceMonitor.interval }} + {{- if .Values.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ .Values.serviceMonitor.scrapeTimeout }} + {{- end }} + honorLabels: true + port: {{ .Values.service.portName }} + path: {{ .Values.serviceMonitor.path }} + {{- if .Values.serviceMonitor.relabelings }} + relabelings: + {{- toYaml .Values.serviceMonitor.relabelings | nindent 4 }} + {{- end }} + jobLabel: "{{ .Release.Name }}" + selector: + matchLabels: + app: {{ template "grafana.name" . }} + release: "{{ .Release.Name }}" + namespaceSelector: + matchNames: + - {{ .Release.Namespace }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/statefulset.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/statefulset.yaml new file mode 100644 index 00000000..accfa560 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/statefulset.yaml @@ -0,0 +1,47 @@ +{{- if and .Values.persistence.enabled (not .Values.persistence.existingClaim) (eq .Values.persistence.type "statefulset")}} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ template "grafana.fullname" . }} + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} +{{- with .Values.annotations }} + annotations: +{{ toYaml . | indent 4 }} +{{- end }} +spec: + replicas: {{ .Values.replicas }} + selector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 6 }} + serviceName: {{ template "grafana.fullname" . }}-headless + template: + metadata: + labels: + {{- include "grafana.selectorLabels" . | nindent 8 }} +{{- with .Values.podLabels }} +{{ toYaml . | indent 8 }} +{{- end }} + annotations: + checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} + checksum/dashboards-json-config: {{ include (print $.Template.BasePath "/dashboards-json-configmap.yaml") . | sha256sum }} + checksum/sc-dashboard-provider-config: {{ include (print $.Template.BasePath "/configmap-dashboard-provider.yaml") . | sha256sum }} + {{- if or (and (not .Values.admin.existingSecret) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD)) (and .Values.ldap.enabled (not .Values.ldap.existingSecret)) }} + checksum/secret: {{ include (print $.Template.BasePath "/secret.yaml") . | sha256sum }} +{{- end }} +{{- with .Values.podAnnotations }} +{{ toYaml . | indent 8 }} +{{- end }} + spec: + {{- include "grafana.pod" . | nindent 6 }} + volumeClaimTemplates: + - metadata: + name: storage + spec: + accessModes: {{ .Values.persistence.accessModes }} + storageClassName: {{ .Values.persistence.storageClassName }} + resources: + requests: + storage: {{ .Values.persistence.size }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-configmap.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-configmap.yaml new file mode 100644 index 00000000..ff53aaf1 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-configmap.yaml @@ -0,0 +1,17 @@ +{{- if .Values.testFramework.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ template "grafana.fullname" . }}-test + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} +data: + run.sh: |- + @test "Test Health" { + url="http://{{ template "grafana.fullname" . }}/api/health" + + code=$(wget --server-response --spider --timeout 10 --tries 1 ${url} 2>&1 | awk '/^ HTTP/{print $2}') + [ "$code" == "200" ] + } +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-podsecuritypolicy.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-podsecuritypolicy.yaml new file mode 100644 index 00000000..eb5cbbcd --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-podsecuritypolicy.yaml @@ -0,0 +1,29 @@ +{{- if and .Values.testFramework.enabled .Values.rbac.pspEnabled }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ template "grafana.fullname" . }}-test + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} +spec: + allowPrivilegeEscalation: true + privileged: false + hostNetwork: false + hostIPC: false + hostPID: false + fsGroup: + rule: RunAsAny + seLinux: + rule: RunAsAny + supplementalGroups: + rule: RunAsAny + runAsUser: + rule: RunAsAny + volumes: + - configMap + - downwardAPI + - emptyDir + - projected + - secret +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-role.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-role.yaml new file mode 100644 index 00000000..6b10677a --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-role.yaml @@ -0,0 +1,14 @@ +{{- if and .Values.testFramework.enabled .Values.rbac.pspEnabled -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ template "grafana.fullname" . }}-test + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} +rules: +- apiGroups: ['policy'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: [{{ template "grafana.fullname" . }}-test] +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-rolebinding.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-rolebinding.yaml new file mode 100644 index 00000000..58fa5e78 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-rolebinding.yaml @@ -0,0 +1,17 @@ +{{- if and .Values.testFramework.enabled .Values.rbac.pspEnabled -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ template "grafana.fullname" . }}-test + namespace: {{ template "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ template "grafana.fullname" . }}-test +subjects: +- kind: ServiceAccount + name: {{ template "grafana.serviceAccountNameTest" . }} + namespace: {{ template "grafana.namespace" . }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-serviceaccount.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-serviceaccount.yaml new file mode 100644 index 00000000..5c335073 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-serviceaccount.yaml @@ -0,0 +1,9 @@ +{{- if and .Values.testFramework.enabled .Values.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + labels: + {{- include "grafana.labels" . | nindent 4 }} + name: {{ template "grafana.serviceAccountNameTest" . }} + namespace: {{ template "grafana.namespace" . }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test.yaml new file mode 100644 index 00000000..cdc86e5f --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test.yaml @@ -0,0 +1,48 @@ +{{- if .Values.testFramework.enabled }} +apiVersion: v1 +kind: Pod +metadata: + name: {{ template "grafana.fullname" . }}-test + labels: + {{- include "grafana.labels" . | nindent 4 }} + annotations: + "helm.sh/hook": test-success + namespace: {{ template "grafana.namespace" . }} +spec: + serviceAccountName: {{ template "grafana.serviceAccountNameTest" . }} + {{- if .Values.testFramework.securityContext }} + securityContext: {{ toYaml .Values.testFramework.securityContext | nindent 4 }} + {{- end }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end}} + {{- end }} + {{- with .Values.nodeSelector }} + nodeSelector: +{{ toYaml . | indent 4 }} + {{- end }} + {{- with .Values.affinity }} + affinity: +{{ toYaml . | indent 4 }} + {{- end }} + {{- with .Values.tolerations }} + tolerations: +{{ toYaml . | indent 4 }} + {{- end }} + containers: + - name: {{ .Release.Name }}-test + image: "{{ .Values.testFramework.image}}:{{ .Values.testFramework.tag }}" + imagePullPolicy: "{{ .Values.testFramework.imagePullPolicy}}" + command: ["/opt/bats/bin/bats", "-t", "/tests/run.sh"] + volumeMounts: + - mountPath: /tests + name: tests + readOnly: true + volumes: + - name: tests + configMap: + name: {{ template "grafana.fullname" . }}-test + restartPolicy: Never +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/values.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/values.yaml new file mode 100644 index 00000000..1f22b938 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/values.yaml @@ -0,0 +1,648 @@ +rbac: + create: true + ## Use an existing ClusterRole/Role (depending on rbac.namespaced false/true) + # useExistingRole: name-of-some-(cluster)role + pspEnabled: true + pspUseAppArmor: true + namespaced: false + extraRoleRules: [] + # - apiGroups: [] + # resources: [] + # verbs: [] + extraClusterRoleRules: [] + # - apiGroups: [] + # resources: [] + # verbs: [] +serviceAccount: + create: true + name: + nameTest: +# annotations: +# eks.amazonaws.com/role-arn: arn:aws:iam::123456789000:role/iam-role-name-here + +replicas: 1 + +## See `kubectl explain poddisruptionbudget.spec` for more +## ref: https://kubernetes.io/docs/tasks/run-application/configure-pdb/ +podDisruptionBudget: {} +# minAvailable: 1 +# maxUnavailable: 1 + +## See `kubectl explain deployment.spec.strategy` for more +## ref: https://kubernetes.io/docs/concepts/workloads/controllers/deployment/#strategy +deploymentStrategy: + type: RollingUpdate + +readinessProbe: + httpGet: + path: /api/health + port: 3000 + +livenessProbe: + httpGet: + path: /api/health + port: 3000 + initialDelaySeconds: 60 + timeoutSeconds: 30 + failureThreshold: 10 + +## Use an alternate scheduler, e.g. "stork". +## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/ +## +# schedulerName: "default-scheduler" + +image: + repository: grafana/grafana + tag: 7.2.1 + sha: "" + pullPolicy: IfNotPresent + + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## + # pullSecrets: + # - myRegistrKeySecretName + +testFramework: + enabled: true + image: "bats/bats" + tag: "v1.1.0" + imagePullPolicy: IfNotPresent + securityContext: {} + +securityContext: + runAsUser: 472 + runAsGroup: 472 + fsGroup: 472 + + +extraConfigmapMounts: [] + # - name: certs-configmap + # mountPath: /etc/grafana/ssl/ + # subPath: certificates.crt # (optional) + # configMap: certs-configmap + # readOnly: true + + +extraEmptyDirMounts: [] + # - name: provisioning-notifiers + # mountPath: /etc/grafana/provisioning/notifiers + + +## Assign a PriorityClassName to pods if set +# priorityClassName: + +downloadDashboardsImage: + repository: curlimages/curl + tag: 7.73.0 + sha: "" + pullPolicy: IfNotPresent + +downloadDashboards: + env: {} + resources: {} + +## Pod Annotations +# podAnnotations: {} + +## Pod Labels +# podLabels: {} + +podPortName: grafana + +## Deployment annotations +# annotations: {} + +## Expose the grafana service to be accessed from outside the cluster (LoadBalancer service). +## or access it from within the cluster (ClusterIP service). Set the service type and the port to serve it. +## ref: http://kubernetes.io/docs/user-guide/services/ +## +service: + type: ClusterIP + port: 80 + targetPort: 3000 + # targetPort: 4181 To be used with a proxy extraContainer + annotations: {} + labels: {} + portName: service + +serviceMonitor: + ## If true, a ServiceMonitor CRD is created for a prometheus operator + ## https://github.com/coreos/prometheus-operator + ## + enabled: false + path: /metrics + # namespace: monitoring (defaults to use the namespace this chart is deployed to) + labels: {} + interval: 1m + scrapeTimeout: 30s + relabelings: [] + +extraExposePorts: [] + # - name: keycloak + # port: 8080 + # targetPort: 8080 + # type: ClusterIP + +# overrides pod.spec.hostAliases in the grafana deployment's pods +hostAliases: [] + # - ip: "1.2.3.4" + # hostnames: + # - "my.host.com" + +ingress: + enabled: false + # Values can be templated + annotations: {} + # kubernetes.io/ingress.class: nginx + # kubernetes.io/tls-acme: "true" + labels: {} + path: / + hosts: + - chart-example.local + ## Extra paths to prepend to every host configuration. This is useful when working with annotation based services. + extraPaths: [] + # - path: /* + # backend: + # serviceName: ssl-redirect + # servicePort: use-annotation + tls: [] + # - secretName: chart-example-tls + # hosts: + # - chart-example.local + +resources: {} +# limits: +# cpu: 100m +# memory: 128Mi +# requests: +# cpu: 100m +# memory: 128Mi + +## Node labels for pod assignment +## ref: https://kubernetes.io/docs/user-guide/node-selection/ +# +nodeSelector: {} + +## Tolerations for pod assignment +## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ +## +tolerations: [] + +## Affinity for pod assignment +## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity +## +affinity: {} + +extraInitContainers: [] + +## Enable an Specify container in extraContainers. This is meant to allow adding an authentication proxy to a grafana pod +extraContainers: | +# - name: proxy +# image: quay.io/gambol99/keycloak-proxy:latest +# args: +# - -provider=github +# - -client-id= +# - -client-secret= +# - -github-org= +# - -email-domain=* +# - -cookie-secret= +# - -http-address=http://0.0.0.0:4181 +# - -upstream-url=http://127.0.0.1:3000 +# ports: +# - name: proxy-web +# containerPort: 4181 + +## Volumes that can be used in init containers that will not be mounted to deployment pods +extraContainerVolumes: [] +# - name: volume-from-secret +# secret: +# secretName: secret-to-mount +# - name: empty-dir-volume +# emptyDir: {} + +## Enable persistence using Persistent Volume Claims +## ref: http://kubernetes.io/docs/user-guide/persistent-volumes/ +## +persistence: + type: pvc + enabled: false + # storageClassName: default + accessModes: + - ReadWriteOnce + size: 10Gi + # annotations: {} + finalizers: + - kubernetes.io/pvc-protection + # subPath: "" + # existingClaim: + +initChownData: + ## If false, data ownership will not be reset at startup + ## This allows the prometheus-server to be run with an arbitrary user + ## + enabled: true + + ## initChownData container image + ## + image: + repository: busybox + tag: "1.31.1" + sha: "" + pullPolicy: IfNotPresent + + ## initChownData resource requests and limits + ## Ref: http://kubernetes.io/docs/user-guide/compute-resources/ + ## + resources: {} + # limits: + # cpu: 100m + # memory: 128Mi + # requests: + # cpu: 100m + # memory: 128Mi + + +# Administrator credentials when not using an existing secret (see below) +adminUser: admin +# adminPassword: strongpassword + +# Use an existing secret for the admin user. +admin: + existingSecret: "" + userKey: admin-user + passwordKey: admin-password + +## Define command to be executed at startup by grafana container +## Needed if using `vault-env` to manage secrets (ref: https://banzaicloud.com/blog/inject-secrets-into-pods-vault/) +## Default is "run.sh" as defined in grafana's Dockerfile +# command: +# - "sh" +# - "/run.sh" + +## Use an alternate scheduler, e.g. "stork". +## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/ +## +# schedulerName: + +## Extra environment variables that will be pass onto deployment pods +## +## to provide grafana with access to CloudWatch on AWS EKS: +## 1. create an iam role of type "Web identity" with provider oidc.eks.* (note the provider for later) +## 2. edit the "Trust relationships" of the role, add a line inside the StringEquals clause using the +## same oidc eks provider as noted before (same as the existing line) +## also, replace NAMESPACE and prometheus-operator-grafana with the service account namespace and name +## +## "oidc.eks.us-east-1.amazonaws.com/id/XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX:sub": "system:serviceaccount:NAMESPACE:prometheus-operator-grafana", +## +## 3. attach a policy to the role, you can use a built in policy called CloudWatchReadOnlyAccess +## 4. use the following env: (replace 123456789000 and iam-role-name-here with your aws account number and role name) +## +## env: +## AWS_ROLE_ARN: arn:aws:iam::123456789000:role/iam-role-name-here +## AWS_WEB_IDENTITY_TOKEN_FILE: /var/run/secrets/eks.amazonaws.com/serviceaccount/token +## AWS_REGION: us-east-1 +## +## 5. uncomment the EKS section in extraSecretMounts: below +## 6. uncomment the annotation section in the serviceAccount: above +## make sure to replace arn:aws:iam::123456789000:role/iam-role-name-here with your role arn + +env: {} + +## "valueFrom" environment variable references that will be added to deployment pods +## ref: https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.17/#envvarsource-v1-core +## Renders in container spec as: +## env: +## ... +## - name: +## valueFrom: +## +envValueFrom: {} + +## The name of a secret in the same kubernetes namespace which contain values to be added to the environment +## This can be useful for auth tokens, etc. Value is templated. +envFromSecret: "" + +## Sensible environment variables that will be rendered as new secret object +## This can be useful for auth tokens, etc +envRenderSecret: {} + +## Additional grafana server secret mounts +# Defines additional mounts with secrets. Secrets must be manually created in the namespace. +extraSecretMounts: [] + # - name: secret-files + # mountPath: /etc/secrets + # secretName: grafana-secret-files + # readOnly: true + # subPath: "" + # + # for AWS EKS (cloudwatch) use the following (see also instruction in env: above) + # - name: aws-iam-token + # mountPath: /var/run/secrets/eks.amazonaws.com/serviceaccount + # readOnly: true + # projected: + # defaultMode: 420 + # sources: + # - serviceAccountToken: + # audience: sts.amazonaws.com + # expirationSeconds: 86400 + # path: token + +## Additional grafana server volume mounts +# Defines additional volume mounts. +extraVolumeMounts: [] + # - name: extra-volume + # mountPath: /mnt/volume + # readOnly: true + # existingClaim: volume-claim + +## Pass the plugins you want installed as a list. +## +plugins: [] + # - digrich-bubblechart-panel + # - grafana-clock-panel + +## Configure grafana datasources +## ref: http://docs.grafana.org/administration/provisioning/#datasources +## +datasources: {} +# datasources.yaml: +# apiVersion: 1 +# datasources: +# - name: Prometheus +# type: prometheus +# url: http://prometheus-prometheus-server +# access: proxy +# isDefault: true +# - name: CloudWatch +# type: cloudwatch +# access: proxy +# uid: cloudwatch +# editable: false +# jsonData: +# authType: credentials +# defaultRegion: us-east-1 + +## Configure notifiers +## ref: http://docs.grafana.org/administration/provisioning/#alert-notification-channels +## +notifiers: {} +# notifiers.yaml: +# notifiers: +# - name: email-notifier +# type: email +# uid: email1 +# # either: +# org_id: 1 +# # or +# org_name: Main Org. +# is_default: true +# settings: +# addresses: an_email_address@example.com +# delete_notifiers: + +## Configure grafana dashboard providers +## ref: http://docs.grafana.org/administration/provisioning/#dashboards +## +## `path` must be /var/lib/grafana/dashboards/ +## +dashboardProviders: {} +# dashboardproviders.yaml: +# apiVersion: 1 +# providers: +# - name: 'default' +# orgId: 1 +# folder: '' +# type: file +# disableDeletion: false +# editable: true +# options: +# path: /var/lib/grafana/dashboards/default + +## Configure grafana dashboard to import +## NOTE: To use dashboards you must also enable/configure dashboardProviders +## ref: https://grafana.com/dashboards +## +## dashboards per provider, use provider name as key. +## +dashboards: {} + # default: + # some-dashboard: + # json: | + # $RAW_JSON + # custom-dashboard: + # file: dashboards/custom-dashboard.json + # prometheus-stats: + # gnetId: 2 + # revision: 2 + # datasource: Prometheus + # local-dashboard: + # url: https://example.com/repository/test.json + # local-dashboard-base64: + # url: https://example.com/repository/test-b64.json + # b64content: true + +## Reference to external ConfigMap per provider. Use provider name as key and ConfigMap name as value. +## A provider dashboards must be defined either by external ConfigMaps or in values.yaml, not in both. +## ConfigMap data example: +## +## data: +## example-dashboard.json: | +## RAW_JSON +## +dashboardsConfigMaps: {} +# default: "" + +## Grafana's primary configuration +## NOTE: values in map will be converted to ini format +## ref: http://docs.grafana.org/installation/configuration/ +## +grafana.ini: + paths: + data: /var/lib/grafana/data + logs: /var/log/grafana + plugins: /var/lib/grafana/plugins + provisioning: /etc/grafana/provisioning + analytics: + check_for_updates: true + log: + mode: console + grafana_net: + url: https://grafana.net +## grafana Authentication can be enabled with the following values on grafana.ini + # server: + # The full public facing url you use in browser, used for redirects and emails + # root_url: + # https://grafana.com/docs/grafana/latest/auth/github/#enable-github-in-grafana + # auth.github: + # enabled: false + # allow_sign_up: false + # scopes: user:email,read:org + # auth_url: https://github.com/login/oauth/authorize + # token_url: https://github.com/login/oauth/access_token + # api_url: https://api.github.com/user + # team_ids: + # allowed_organizations: + # client_id: + # client_secret: +## LDAP Authentication can be enabled with the following values on grafana.ini +## NOTE: Grafana will fail to start if the value for ldap.toml is invalid + # auth.ldap: + # enabled: true + # allow_sign_up: true + # config_file: /etc/grafana/ldap.toml + +## Grafana's LDAP configuration +## Templated by the template in _helpers.tpl +## NOTE: To enable the grafana.ini must be configured with auth.ldap.enabled +## ref: http://docs.grafana.org/installation/configuration/#auth-ldap +## ref: http://docs.grafana.org/installation/ldap/#configuration +ldap: + enabled: false + # `existingSecret` is a reference to an existing secret containing the ldap configuration + # for Grafana in a key `ldap-toml`. + existingSecret: "" + # `config` is the content of `ldap.toml` that will be stored in the created secret + config: "" + # config: |- + # verbose_logging = true + + # [[servers]] + # host = "my-ldap-server" + # port = 636 + # use_ssl = true + # start_tls = false + # ssl_skip_verify = false + # bind_dn = "uid=%s,ou=users,dc=myorg,dc=com" + +## Grafana's SMTP configuration +## NOTE: To enable, grafana.ini must be configured with smtp.enabled +## ref: http://docs.grafana.org/installation/configuration/#smtp +smtp: + # `existingSecret` is a reference to an existing secret containing the smtp configuration + # for Grafana. + existingSecret: "" + userKey: "user" + passwordKey: "password" + +## Sidecars that collect the configmaps with specified label and stores the included files them into the respective folders +## Requires at least Grafana 5 to work and can't be used together with parameters dashboardProviders, datasources and dashboards +sidecar: + image: + repository: kiwigrid/k8s-sidecar + tag: 1.1.0 + sha: "" + imagePullPolicy: IfNotPresent + resources: {} +# limits: +# cpu: 100m +# memory: 100Mi +# requests: +# cpu: 50m +# memory: 50Mi + # skipTlsVerify Set to true to skip tls verification for kube api calls + # skipTlsVerify: true + enableUniqueFilenames: false + dashboards: + enabled: false + SCProvider: true + # label that the configmaps with dashboards are marked with + label: grafana_dashboard + # folder in the pod that should hold the collected dashboards (unless `defaultFolderName` is set) + folder: /tmp/dashboards + # The default folder name, it will create a subfolder under the `folder` and put dashboards in there instead + defaultFolderName: null + # If specified, the sidecar will search for dashboard config-maps inside this namespace. + # Otherwise the namespace in which the sidecar is running will be used. + # It's also possible to specify ALL to search in all namespaces + searchNamespace: null + # If specified, the sidecar will look for annotation with this name to create folder and put graph here. + # You can use this parameter together with `provider.foldersFromFilesStructure`to annotate configmaps and create folder structure. + folderAnnotation: null + # provider configuration that lets grafana manage the dashboards + provider: + # name of the provider, should be unique + name: sidecarProvider + # orgid as configured in grafana + orgid: 1 + # folder in which the dashboards should be imported in grafana + folder: '' + # type of the provider + type: file + # disableDelete to activate a import-only behaviour + disableDelete: false + # allow updating provisioned dashboards from the UI + allowUiUpdates: false + # allow Grafana to replicate dashboard structure from filesystem + foldersFromFilesStructure: false + datasources: + enabled: false + # label that the configmaps with datasources are marked with + label: grafana_datasource + # If specified, the sidecar will search for datasource config-maps inside this namespace. + # Otherwise the namespace in which the sidecar is running will be used. + # It's also possible to specify ALL to search in all namespaces + searchNamespace: null + notifiers: + enabled: false + # label that the configmaps with notifiers are marked with + label: grafana_notifier + # If specified, the sidecar will search for notifier config-maps inside this namespace. + # Otherwise the namespace in which the sidecar is running will be used. + # It's also possible to specify ALL to search in all namespaces + searchNamespace: null + +## Override the deployment namespace +## +namespaceOverride: "" + +## Number of old ReplicaSets to retain +## +revisionHistoryLimit: 10 + +## Add a seperate remote image renderer deployment/service +imageRenderer: + # Enable the image-renderer deployment & service + enabled: false + replicas: 1 + image: + # image-renderer Image repository + repository: grafana/grafana-image-renderer + # image-renderer Image tag + tag: latest + # image-renderer Image sha (optional) + sha: "" + # image-renderer ImagePullPolicy + pullPolicy: Always + # extra environment variables + env: {} + # RENDERING_ARGS: --disable-gpu,--window-size=1280x758 + # RENDERING_MODE: clustered + # image-renderer deployment securityContext + securityContext: {} + # image-renderer deployment Host Aliases + hostAliases: [] + # image-renderer deployment priority class + priorityClassName: '' + service: + # image-renderer service port name + portName: 'http' + # image-renderer service port used by both service and deployment + port: 8081 + # name of the image-renderer port on the pod + podPortName: http + # number of image-renderer replica sets to keep + revisionHistoryLimit: 10 + networkPolicy: + # Enable a NetworkPolicy to limit inbound traffic to only the created grafana pods + limitIngress: true + # Enable a NetworkPolicy to limit outbound traffic to only the created grafana pods + limitEgress: false + resources: {} +# limits: +# cpu: 100m +# memory: 100Mi +# requests: +# cpu: 50m +# memory: 50Mi diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/.helmignore b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/.helmignore new file mode 100644 index 00000000..f0c13194 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/.helmignore @@ -0,0 +1,21 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/Chart.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/Chart.yaml new file mode 100644 index 00000000..663499af --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/Chart.yaml @@ -0,0 +1,15 @@ +apiVersion: v1 +appVersion: 1.9.7 +deprecated: true +description: DEPRECATED - Install kube-state-metrics to generate and expose cluster-level + metrics +home: https://github.com/kubernetes/kube-state-metrics/ +keywords: +- metric +- monitoring +- prometheus +- kubernetes +name: kube-state-metrics +sources: +- https://github.com/kubernetes/kube-state-metrics/ +version: 2.9.4 diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/README.md b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/README.md new file mode 100644 index 00000000..4e1178eb --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/README.md @@ -0,0 +1,91 @@ +# ⚠️ Repo Archive Notice + +As of Nov 13, 2020, charts in this repo will no longer be updated. +For more information, see the Helm Charts [Deprecation and Archive Notice](https://github.com/helm/charts#%EF%B8%8F-deprecation-and-archive-notice), and [Update](https://helm.sh/blog/charts-repo-deprecation/). + +# kube-state-metrics Helm Chart + +* Installs the [kube-state-metrics agent](https://github.com/kubernetes/kube-state-metrics). + +## DEPRECATION NOTICE + +This chart is deprecated and no longer supported. + +## Installing the Chart + +To install the chart with the release name `my-release`: + +```bash +$ helm install stable/kube-state-metrics +``` + +## Configuration + +| Parameter | Description | Default | +|:---------------------------------------------|:--------------------------------------------------------------------------------------|:-------------------------------------------| +| `image.repository` | The image repository to pull from | `quay.io/coreos/kube-state-metrics` | +| `image.tag` | The image tag to pull from | `v1.9.7` | +| `image.pullPolicy` | Image pull policy | `IfNotPresent` | +| `imagePullSecrets` | List of container registry secrets | `[]` | +| `replicas` | Number of replicas | `1` | +| `autosharding.enabled` | Set to `true` to automatically shard data across `replicas` pods. EXPERIMENTAL | `false` | +| `service.port` | The port of the container | `8080` | +| `service.annotations` | Annotations to be added to the service | `{}` | +| `customLabels` | Custom labels to apply to service, deployment and pods | `{}` | +| `hostNetwork` | Whether or not to use the host network | `false` | +| `prometheusScrape` | Whether or not enable prom scrape | `true` | +| `rbac.create` | If true, create & use RBAC resources | `true` | +| `serviceAccount.create` | If true, create & use serviceAccount | `true` | +| `serviceAccount.name` | If not set & create is true, use template fullname | | +| `serviceAccount.imagePullSecrets` | Specify image pull secrets field | `[]` | +| `serviceAccount.annotations` | Annotations to be added to the serviceAccount | `{}` | +| `podSecurityPolicy.enabled` | If true, create & use PodSecurityPolicy resources. Note that related RBACs are created only if `rbac.enabled` is `true`. | `false` | +| `podSecurityPolicy.annotations` | Specify pod annotations in the pod security policy | `{}` | +| `podSecurityPolicy.additionalVolumes` | Specify allowed volumes in the pod security policy (`secret` is always allowed) | `[]` | +| `securityContext.enabled` | Enable security context | `true` | +| `securityContext.fsGroup` | Group ID for the filesystem | `65534` | +| `securityContext.runAsGroup` | Group ID for the container | `65534` | +| `securityContext.runAsUser` | User ID for the container | `65534` | +| `priorityClassName` | Name of Priority Class to assign pods | `nil` | +| `nodeSelector` | Node labels for pod assignment | `{}` | +| `affinity` | Affinity settings for pod assignment | `{}` | +| `tolerations` | Tolerations for pod assignment | `[]` | +| `podAnnotations` | Annotations to be added to the pod | `{}` | +| `podDisruptionBudget` | Optional PodDisruptionBudget | `{}` | +| `resources` | kube-state-metrics resource requests and limits | `{}` | +| `collectors.certificatesigningrequests` | Enable the certificatesigningrequests collector. | `true` | +| `collectors.configmaps` | Enable the configmaps collector. | `true` | +| `collectors.cronjobs` | Enable the cronjobs collector. | `true` | +| `collectors.daemonsets` | Enable the daemonsets collector. | `true` | +| `collectors.deployments` | Enable the deployments collector. | `true` | +| `collectors.endpoints` | Enable the endpoints collector. | `true` | +| `collectors.horizontalpodautoscalers` | Enable the horizontalpodautoscalers collector. | `true` | +| `collectors.ingresses` | Enable the ingresses collector. | `true` | +| `collectors.jobs` | Enable the jobs collector. | `true` | +| `collectors.limitranges` | Enable the limitranges collector. | `true` | +| `collectors.mutatingwebhookconfigurations` | Enable the mutatingwebhookconfigurations collector. | `true` | +| `collectors.namespaces` | Enable the namespaces collector. | `true` | +| `collectors.networkpolicies` | Enable the networkpolicies collector. | `true` | +| `collectors.nodes` | Enable the nodes collector. | `true` | +| `collectors.persistentvolumeclaims` | Enable the persistentvolumeclaims collector. | `true` | +| `collectors.persistentvolumes` | Enable the persistentvolumes collector. | `true` | +| `collectors.poddisruptionbudgets` | Enable the poddisruptionbudgets collector. | `true` | +| `collectors.pods` | Enable the pods collector. | `true` | +| `collectors.replicasets` | Enable the replicasets collector. | `true` | +| `collectors.replicationcontrollers` | Enable the replicationcontrollers collector. | `true` | +| `collectors.resourcequotas` | Enable the resourcequotas collector. | `true` | +| `collectors.secrets` | Enable the secrets collector. | `true` | +| `collectors.services` | Enable the services collector. | `true` | +| `collectors.statefulsets` | Enable the statefulsets collector. | `true` | +| `collectors.storageclasses` | Enable the storageclasses collector. | `true` | +| `collectors.validatingwebhookconfigurations` | Enable the validatingwebhookconfigurations collector. | `true` | +| `collectors.verticalpodautoscalers` | Enable the verticalpodautoscalers collector. | `true` | +| `collectors.volumeattachments` | Enable the volumeattachments collector. | `true` | +| `prometheus.monitor.enabled` | Set this to `true` to create ServiceMonitor for Prometheus operator | `false` | +| `prometheus.monitor.additionalLabels` | Additional labels that can be used so ServiceMonitor will be discovered by Prometheus | `{}` | +| `prometheus.monitor.namespace` | Namespace where servicemonitor resource should be created | `the same namespace as kube-state-metrics` | +| `prometheus.monitor.honorLabels` | Honor metric labels | `false` | +| `namespaceOverride` | Override the deployment namespace | `""` (`Release.Namespace`) | +| `kubeTargetVersionOverride` | Override the k8s version of the target cluster | `""` | +| `kubeconfig.enabled` | Adds --kubeconfig arg to container at startup | `""` | +| `kubeconfig.secret` | Base64 encoded kubeconfig file | `""` | diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/NOTES.txt b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/NOTES.txt new file mode 100644 index 00000000..5a646e0c --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/NOTES.txt @@ -0,0 +1,10 @@ +kube-state-metrics is a simple service that listens to the Kubernetes API server and generates metrics about the state of the objects. +The exposed metrics can be found here: +https://github.com/kubernetes/kube-state-metrics/blob/master/docs/README.md#exposed-metrics + +The metrics are exported on the HTTP endpoint /metrics on the listening port. +In your case, {{ template "kube-state-metrics.fullname" . }}.{{ template "kube-state-metrics.namespace" . }}.svc.cluster.local:{{ .Values.service.port }}/metrics + +They are served either as plaintext or protobuf depending on the Accept header. +They are designed to be consumed either by Prometheus itself or by a scraper that is compatible with scraping a Prometheus client endpoint. + diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/_helpers.tpl b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/_helpers.tpl new file mode 100644 index 00000000..6ae0e647 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/_helpers.tpl @@ -0,0 +1,47 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "kube-state-metrics.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "kube-state-metrics.fullname" -}} +{{- if .Values.fullnameOverride -}} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .Chart.Name .Values.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- .Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Create the name of the service account to use +*/}} +{{- define "kube-state-metrics.serviceAccountName" -}} +{{- if .Values.serviceAccount.create -}} + {{ default (include "kube-state-metrics.fullname" .) .Values.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* +Allow the release namespace to be overridden for multi-namespace deployments in combined charts +*/}} +{{- define "kube-state-metrics.namespace" -}} + {{- if .Values.namespaceOverride -}} + {{- .Values.namespaceOverride -}} + {{- else -}} + {{- .Release.Namespace -}} + {{- end -}} +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/clusterrole.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/clusterrole.yaml new file mode 100644 index 00000000..a9198b82 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/clusterrole.yaml @@ -0,0 +1,180 @@ +{{- if .Values.rbac.create -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + labels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} + helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version }} + app.kubernetes.io/managed-by: {{ .Release.Service }} + app.kubernetes.io/instance: {{ .Release.Name }} + name: {{ template "kube-state-metrics.fullname" . }} +rules: +{{ if .Values.collectors.certificatesigningrequests }} +- apiGroups: ["certificates.k8s.io"] + resources: + - certificatesigningrequests + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.configmaps }} +- apiGroups: [""] + resources: + - configmaps + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.cronjobs }} +- apiGroups: ["batch"] + resources: + - cronjobs + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.daemonsets }} +- apiGroups: ["extensions", "apps"] + resources: + - daemonsets + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.deployments }} +- apiGroups: ["extensions", "apps"] + resources: + - deployments + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.endpoints }} +- apiGroups: [""] + resources: + - endpoints + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.horizontalpodautoscalers }} +- apiGroups: ["autoscaling"] + resources: + - horizontalpodautoscalers + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.ingresses }} +- apiGroups: ["extensions", "networking.k8s.io"] + resources: + - ingresses + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.jobs }} +- apiGroups: ["batch"] + resources: + - jobs + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.limitranges }} +- apiGroups: [""] + resources: + - limitranges + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.mutatingwebhookconfigurations }} +- apiGroups: ["admissionregistration.k8s.io"] + resources: + - mutatingwebhookconfigurations + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.namespaces }} +- apiGroups: [""] + resources: + - namespaces + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.networkpolicies }} +- apiGroups: ["networking.k8s.io"] + resources: + - networkpolicies + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.nodes }} +- apiGroups: [""] + resources: + - nodes + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.persistentvolumeclaims }} +- apiGroups: [""] + resources: + - persistentvolumeclaims + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.persistentvolumes }} +- apiGroups: [""] + resources: + - persistentvolumes + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.poddisruptionbudgets }} +- apiGroups: ["policy"] + resources: + - poddisruptionbudgets + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.pods }} +- apiGroups: [""] + resources: + - pods + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.replicasets }} +- apiGroups: ["extensions", "apps"] + resources: + - replicasets + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.replicationcontrollers }} +- apiGroups: [""] + resources: + - replicationcontrollers + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.resourcequotas }} +- apiGroups: [""] + resources: + - resourcequotas + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.secrets }} +- apiGroups: [""] + resources: + - secrets + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.services }} +- apiGroups: [""] + resources: + - services + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.statefulsets }} +- apiGroups: ["apps"] + resources: + - statefulsets + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.storageclasses }} +- apiGroups: ["storage.k8s.io"] + resources: + - storageclasses + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.validatingwebhookconfigurations }} +- apiGroups: ["admissionregistration.k8s.io"] + resources: + - validatingwebhookconfigurations + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.volumeattachments }} +- apiGroups: ["storage.k8s.io"] + resources: + - volumeattachments + verbs: ["list", "watch"] +{{ end -}} +{{ if .Values.collectors.verticalpodautoscalers }} +- apiGroups: ["autoscaling.k8s.io"] + resources: + - verticalpodautoscalers + verbs: ["list", "watch"] +{{ end -}} +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/clusterrolebinding.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/clusterrolebinding.yaml new file mode 100644 index 00000000..160db8bd --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/clusterrolebinding.yaml @@ -0,0 +1,19 @@ +{{- if .Values.rbac.create -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} + helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version }} + app.kubernetes.io/managed-by: {{ .Release.Service }} + app.kubernetes.io/instance: {{ .Release.Name }} + name: {{ template "kube-state-metrics.fullname" . }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "kube-state-metrics.fullname" . }} +subjects: +- kind: ServiceAccount + name: {{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/deployment.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/deployment.yaml new file mode 100644 index 00000000..8f491ec5 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/deployment.yaml @@ -0,0 +1,206 @@ +apiVersion: apps/v1 +{{- if .Values.autosharding.enabled }} +kind: StatefulSet +{{- else }} +kind: Deployment +{{- end }} +metadata: + name: {{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} + labels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} + helm.sh/chart: "{{ .Chart.Name }}-{{ .Chart.Version }}" + app.kubernetes.io/instance: "{{ .Release.Name }}" + app.kubernetes.io/managed-by: "{{ .Release.Service }}" +{{- if .Values.customLabels }} +{{ toYaml .Values.customLabels | indent 4 }} +{{- end }} +spec: + selector: + matchLabels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} + replicas: {{ .Values.replicas }} +{{- if .Values.autosharding.enabled }} + serviceName: {{ template "kube-state-metrics.fullname" . }} + volumeClaimTemplates: [] +{{- end }} + template: + metadata: + labels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} + app.kubernetes.io/instance: "{{ .Release.Name }}" +{{- if .Values.customLabels }} +{{ toYaml .Values.customLabels | indent 8 }} +{{- end }} +{{- if .Values.podAnnotations }} + annotations: +{{ toYaml .Values.podAnnotations | indent 8 }} +{{- end }} + spec: + hostNetwork: {{ .Values.hostNetwork }} + serviceAccountName: {{ template "kube-state-metrics.serviceAccountName" . }} + {{- if .Values.securityContext.enabled }} + securityContext: + fsGroup: {{ .Values.securityContext.fsGroup }} + runAsGroup: {{ .Values.securityContext.runAsGroup }} + runAsUser: {{ .Values.securityContext.runAsUser }} + {{- end }} + {{- if .Values.priorityClassName }} + priorityClassName: {{ .Values.priorityClassName }} + {{- end }} + containers: + - name: {{ .Chart.Name }} +{{- if .Values.autosharding.enabled }} + env: + - name: POD_NAME + valueFrom: + fieldRef: + fieldPath: metadata.name + - name: POD_NAMESPACE + valueFrom: + fieldRef: + fieldPath: metadata.namespace +{{- end }} + args: +{{ if .Values.collectors.certificatesigningrequests }} + - --collectors=certificatesigningrequests +{{ end }} +{{ if .Values.collectors.configmaps }} + - --collectors=configmaps +{{ end }} +{{ if .Values.collectors.cronjobs }} + - --collectors=cronjobs +{{ end }} +{{ if .Values.collectors.daemonsets }} + - --collectors=daemonsets +{{ end }} +{{ if .Values.collectors.deployments }} + - --collectors=deployments +{{ end }} +{{ if .Values.collectors.endpoints }} + - --collectors=endpoints +{{ end }} +{{ if .Values.collectors.horizontalpodautoscalers }} + - --collectors=horizontalpodautoscalers +{{ end }} +{{ if .Values.collectors.ingresses }} + - --collectors=ingresses +{{ end }} +{{ if .Values.collectors.jobs }} + - --collectors=jobs +{{ end }} +{{ if .Values.collectors.limitranges }} + - --collectors=limitranges +{{ end }} +{{ if .Values.collectors.mutatingwebhookconfigurations }} + - --collectors=mutatingwebhookconfigurations +{{ end }} +{{ if .Values.collectors.namespaces }} + - --collectors=namespaces +{{ end }} +{{ if .Values.collectors.networkpolicies }} + - --collectors=networkpolicies +{{ end }} +{{ if .Values.collectors.nodes }} + - --collectors=nodes +{{ end }} +{{ if .Values.collectors.persistentvolumeclaims }} + - --collectors=persistentvolumeclaims +{{ end }} +{{ if .Values.collectors.persistentvolumes }} + - --collectors=persistentvolumes +{{ end }} +{{ if .Values.collectors.poddisruptionbudgets }} + - --collectors=poddisruptionbudgets +{{ end }} +{{ if .Values.collectors.pods }} + - --collectors=pods +{{ end }} +{{ if .Values.collectors.replicasets }} + - --collectors=replicasets +{{ end }} +{{ if .Values.collectors.replicationcontrollers }} + - --collectors=replicationcontrollers +{{ end }} +{{ if .Values.collectors.resourcequotas }} + - --collectors=resourcequotas +{{ end }} +{{ if .Values.collectors.secrets }} + - --collectors=secrets +{{ end }} +{{ if .Values.collectors.services }} + - --collectors=services +{{ end }} +{{ if .Values.collectors.statefulsets }} + - --collectors=statefulsets +{{ end }} +{{ if .Values.collectors.storageclasses }} + - --collectors=storageclasses +{{ end }} +{{ if .Values.collectors.validatingwebhookconfigurations }} + - --collectors=validatingwebhookconfigurations +{{ end }} +{{ if .Values.collectors.verticalpodautoscalers }} + - --collectors=verticalpodautoscalers +{{ end }} +{{ if .Values.collectors.volumeattachments }} + - --collectors=volumeattachments +{{ end }} +{{ if .Values.namespace }} + - --namespace={{ .Values.namespace }} +{{ end }} +{{ if .Values.autosharding.enabled }} + - --pod=$(POD_NAME) + - --pod-namespace=$(POD_NAMESPACE) +{{ end }} +{{ if .Values.kubeconfig.enabled }} + - --kubeconfig=/opt/k8s/.kube/config +{{ end }} +{{- if .Values.kubeconfig.enabled }} + volumeMounts: + - name: kubeconfig + mountPath: /opt/k8s/.kube/ + readOnly: true +{{- end }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}" + ports: + - containerPort: 8080 + livenessProbe: + httpGet: + path: /healthz + port: 8080 + initialDelaySeconds: 5 + timeoutSeconds: 5 + readinessProbe: + httpGet: + path: / + port: 8080 + initialDelaySeconds: 5 + timeoutSeconds: 5 +{{- if .Values.resources }} + resources: +{{ toYaml .Values.resources | indent 10 }} +{{- end }} +{{- if .Values.imagePullSecrets }} + imagePullSecrets: +{{ toYaml .Values.imagePullSecrets | indent 8 }} +{{- end }} +{{- if .Values.affinity }} + affinity: +{{ toYaml .Values.affinity | indent 8 }} +{{- end }} +{{- if .Values.nodeSelector }} + nodeSelector: +{{ toYaml .Values.nodeSelector | indent 8 }} +{{- end }} +{{- if .Values.tolerations }} + tolerations: +{{ toYaml .Values.tolerations | indent 8 }} +{{- end }} +{{- if .Values.kubeconfig.enabled}} + volumes: + - name: kubeconfig + secret: + secretName: {{ template "kube-state-metrics.fullname" . }}-kubeconfig +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/kubeconfig-secret.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/kubeconfig-secret.yaml new file mode 100644 index 00000000..a7800d7a --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/kubeconfig-secret.yaml @@ -0,0 +1,15 @@ +{{- if .Values.kubeconfig.enabled -}} +apiVersion: v1 +kind: Secret +metadata: + name: {{ template "kube-state-metrics.fullname" . }}-kubeconfig + namespace: {{ template "kube-state-metrics.namespace" . }} + labels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} + helm.sh/chart: "{{ .Chart.Name }}-{{ .Chart.Version }}" + app.kubernetes.io/instance: "{{ .Release.Name }}" + app.kubernetes.io/managed-by: "{{ .Release.Service }}" +type: Opaque +data: + config: '{{ .Values.kubeconfig.secret }}' +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/pdb.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/pdb.yaml new file mode 100644 index 00000000..6adb50d7 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/pdb.yaml @@ -0,0 +1,17 @@ +{{- if .Values.podDisruptionBudget -}} +apiVersion: policy/v1beta1 +kind: PodDisruptionBudget +metadata: + name: {{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} + labels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} + helm.sh/chart: "{{ .Chart.Name }}-{{ .Chart.Version }}" + app.kubernetes.io/instance: "{{ .Release.Name }}" + app.kubernetes.io/managed-by: "{{ .Release.Service }}" +spec: + selector: + matchLabels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} +{{ toYaml .Values.podDisruptionBudget | indent 2 }} +{{- end -}} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/podsecuritypolicy.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/podsecuritypolicy.yaml new file mode 100644 index 00000000..e822ba0e --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/podsecuritypolicy.yaml @@ -0,0 +1,42 @@ +{{- if .Values.podSecurityPolicy.enabled }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ template "kube-state-metrics.fullname" . }} + labels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} + helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version }} + app.kubernetes.io/managed-by: {{ .Release.Service }} + app.kubernetes.io/instance: {{ .Release.Name }} +{{- if .Values.podSecurityPolicy.annotations }} + annotations: +{{ toYaml .Values.podSecurityPolicy.annotations | indent 4 }} +{{- end }} +spec: + privileged: false + volumes: + - 'secret' +{{- if .Values.podSecurityPolicy.additionalVolumes }} +{{ toYaml .Values.podSecurityPolicy.additionalVolumes | indent 4 }} +{{- end }} + hostNetwork: false + hostIPC: false + hostPID: false + runAsUser: + rule: 'MustRunAsNonRoot' + seLinux: + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 1 + max: 65535 + fsGroup: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 1 + max: 65535 + readOnlyRootFilesystem: false +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/psp-clusterrole.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/psp-clusterrole.yaml new file mode 100644 index 00000000..217abc95 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/psp-clusterrole.yaml @@ -0,0 +1,22 @@ +{{- if and .Values.podSecurityPolicy.enabled .Values.rbac.create -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + labels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} + helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version }} + app.kubernetes.io/managed-by: {{ .Release.Service }} + app.kubernetes.io/instance: {{ .Release.Name }} + name: psp-{{ template "kube-state-metrics.fullname" . }} +rules: +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if semverCompare "> 1.15.0-0" $kubeTargetVersion }} +- apiGroups: ['policy'] +{{- else }} +- apiGroups: ['extensions'] +{{- end }} + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: + - {{ template "kube-state-metrics.fullname" . }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/psp-clusterrolebinding.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/psp-clusterrolebinding.yaml new file mode 100644 index 00000000..feb97f22 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/psp-clusterrolebinding.yaml @@ -0,0 +1,19 @@ +{{- if and .Values.podSecurityPolicy.enabled .Values.rbac.create -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} + helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version }} + app.kubernetes.io/managed-by: {{ .Release.Service }} + app.kubernetes.io/instance: {{ .Release.Name }} + name: psp-{{ template "kube-state-metrics.fullname" . }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: psp-{{ template "kube-state-metrics.fullname" . }} +subjects: + - kind: ServiceAccount + name: {{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/service.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/service.yaml new file mode 100644 index 00000000..5dacf521 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/service.yaml @@ -0,0 +1,36 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} + labels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} + helm.sh/chart: "{{ .Chart.Name }}-{{ .Chart.Version }}" + app.kubernetes.io/instance: "{{ .Release.Name }}" + app.kubernetes.io/managed-by: "{{ .Release.Service }}" +{{- if .Values.customLabels }} +{{ toYaml .Values.customLabels | indent 4 }} +{{- end }} + annotations: + {{- if .Values.prometheusScrape }} + prometheus.io/scrape: '{{ .Values.prometheusScrape }}' + {{- end }} + {{- if .Values.service.annotations }} + {{- toYaml .Values.service.annotations | nindent 4 }} + {{- end }} +spec: + type: "{{ .Values.service.type }}" + ports: + - name: "http" + protocol: TCP + port: {{ .Values.service.port }} + {{- if .Values.service.nodePort }} + nodePort: {{ .Values.service.nodePort }} + {{- end }} + targetPort: 8080 +{{- if .Values.service.loadBalancerIP }} + loadBalancerIP: "{{ .Values.service.loadBalancerIP }}" +{{- end }} + selector: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/serviceaccount.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/serviceaccount.yaml new file mode 100644 index 00000000..2e8a1ee3 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/serviceaccount.yaml @@ -0,0 +1,18 @@ +{{- if .Values.serviceAccount.create -}} +apiVersion: v1 +kind: ServiceAccount +metadata: + labels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} + helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version }} + app.kubernetes.io/managed-by: {{ .Release.Service }} + app.kubernetes.io/instance: {{ .Release.Name }} + name: {{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} +{{- if .Values.serviceAccount.annotations }} + annotations: +{{ toYaml .Values.serviceAccount.annotations | indent 4 }} +{{- end }} +imagePullSecrets: +{{ toYaml .Values.serviceAccount.imagePullSecrets | indent 2 }} +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/servicemonitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/servicemonitor.yaml new file mode 100644 index 00000000..54cde362 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/servicemonitor.yaml @@ -0,0 +1,25 @@ +{{- if .Values.prometheus.monitor.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} + labels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} + helm.sh/chart: "{{ .Chart.Name }}-{{ .Chart.Version }}" + app.kubernetes.io/instance: "{{ .Release.Name }}" + app.kubernetes.io/managed-by: "{{ .Release.Service }}" + {{- if .Values.prometheus.monitor.additionalLabels }} +{{ toYaml .Values.prometheus.monitor.additionalLabels | indent 4 }} + {{- end }} +spec: + selector: + matchLabels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + endpoints: + - port: http + {{- if .Values.prometheus.monitor.honorLabels }} + honorLabels: true + {{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/stsdiscovery-role.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/stsdiscovery-role.yaml new file mode 100644 index 00000000..9770b049 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/stsdiscovery-role.yaml @@ -0,0 +1,29 @@ +{{- if and .Values.autosharding.enabled .Values.rbac.create -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: stsdiscovery-{{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} + labels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} + helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version }} + app.kubernetes.io/managed-by: {{ .Release.Service }} + app.kubernetes.io/instance: {{ .Release.Name }} +rules: +- apiGroups: + - "" + resources: + - pods + verbs: + - get +- apiGroups: + - apps + resourceNames: + - {{ template "kube-state-metrics.fullname" . }} + resources: + - statefulsets + verbs: + - get + - list + - watch +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/stsdiscovery-rolebinding.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/stsdiscovery-rolebinding.yaml new file mode 100644 index 00000000..6a2e5bfe --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/stsdiscovery-rolebinding.yaml @@ -0,0 +1,20 @@ +{{- if and .Values.autosharding.enabled .Values.rbac.create -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: stsdiscovery-{{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} + labels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} + helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version }} + app.kubernetes.io/managed-by: {{ .Release.Service }} + app.kubernetes.io/instance: {{ .Release.Name }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: stsdiscovery-{{ template "kube-state-metrics.fullname" . }} +subjects: + - kind: ServiceAccount + name: {{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/values.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/values.yaml new file mode 100644 index 00000000..3edd4c81 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/values.yaml @@ -0,0 +1,161 @@ +# Default values for kube-state-metrics. +prometheusScrape: true +image: + repository: quay.io/coreos/kube-state-metrics + tag: v1.9.7 + pullPolicy: IfNotPresent + +imagePullSecrets: [] +# - name: "image-pull-secret" + +# If set to true, this will deploy kube-state-metrics as a StatefulSet and the data +# will be automatically sharded across <.Values.replicas> pods using the built-in +# autodiscovery feature: https://github.com/kubernetes/kube-state-metrics#automated-sharding +# This is an experimental feature and there are no stability guarantees. +autosharding: + enabled: false + +replicas: 1 + +service: + port: 8080 + # Default to clusterIP for backward compatibility + type: ClusterIP + nodePort: 0 + loadBalancerIP: "" + annotations: {} + +customLabels: {} + +hostNetwork: false + +rbac: + # If true, create & use RBAC resources + create: true + +serviceAccount: + # Specifies whether a ServiceAccount should be created, require rbac true + create: true + # The name of the ServiceAccount to use. + # If not set and create is true, a name is generated using the fullname template + name: + # Reference to one or more secrets to be used when pulling images + # ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + imagePullSecrets: [] + # ServiceAccount annotations. + # Use case: AWS EKS IAM roles for service accounts + # ref: https://docs.aws.amazon.com/eks/latest/userguide/specify-service-account-role.html + annotations: {} + +prometheus: + monitor: + enabled: false + additionalLabels: {} + namespace: "" + honorLabels: false + +## Specify if a Pod Security Policy for kube-state-metrics must be created +## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/ +## +podSecurityPolicy: + enabled: false + annotations: {} + ## Specify pod annotations + ## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/#apparmor + ## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/#seccomp + ## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/#sysctl + ## + # seccomp.security.alpha.kubernetes.io/allowedProfileNames: '*' + # seccomp.security.alpha.kubernetes.io/defaultProfileName: 'docker/default' + # apparmor.security.beta.kubernetes.io/defaultProfileName: 'runtime/default' + + additionalVolumes: [] + +securityContext: + enabled: true + runAsGroup: 65534 + runAsUser: 65534 + fsGroup: 65534 + +## Node labels for pod assignment +## Ref: https://kubernetes.io/docs/user-guide/node-selection/ +nodeSelector: {} + +## Affinity settings for pod assignment +## Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/ +affinity: {} + +## Tolerations for pod assignment +## Ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ +tolerations: [] + +# Annotations to be added to the pod +podAnnotations: {} + +## Assign a PriorityClassName to pods if set +# priorityClassName: "" + +# Ref: https://kubernetes.io/docs/tasks/run-application/configure-pdb/ +podDisruptionBudget: {} + +# Available collectors for kube-state-metrics. By default all available +# collectors are enabled. +collectors: + certificatesigningrequests: true + configmaps: true + cronjobs: true + daemonsets: true + deployments: true + endpoints: true + horizontalpodautoscalers: true + ingresses: true + jobs: true + limitranges: true + mutatingwebhookconfigurations: true + namespaces: true + networkpolicies: true + nodes: true + persistentvolumeclaims: true + persistentvolumes: true + poddisruptionbudgets: true + pods: true + replicasets: true + replicationcontrollers: true + resourcequotas: true + secrets: true + services: true + statefulsets: true + storageclasses: true + validatingwebhookconfigurations: true + verticalpodautoscalers: false + volumeattachments: true + +# Enabling kubeconfig will pass the --kubeconfig argument to the container +kubeconfig: + enabled: false + # base64 encoded kube-config file + secret: + +# Namespace to be enabled for collecting resources. By default all namespaces are collected. +# namespace: "" + +## Override the deployment namespace +## +namespaceOverride: "" + +resources: {} + # We usually recommend not to specify default resources and to leave this as a conscious + # choice for the user. This also increases chances charts run on environments with little + # resources, such as Minikube. If you do want to specify resources, uncomment the following + # lines, adjust them as necessary, and remove the curly braces after 'resources:'. + # limits: + # cpu: 100m + # memory: 64Mi + # requests: + # cpu: 10m + # memory: 32Mi + +## Provide a k8s version to define apiGroups for podSecurityPolicy Cluster Role. +## For example: kubeTargetVersionOverride: 1.14.9 +## +kubeTargetVersionOverride: "" diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/.helmignore b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/.helmignore new file mode 100644 index 00000000..f0c13194 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/.helmignore @@ -0,0 +1,21 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/Chart.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/Chart.yaml new file mode 100644 index 00000000..65945476 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/Chart.yaml @@ -0,0 +1,16 @@ +apiVersion: v1 +appVersion: 1.0.1 +description: A Helm chart for prometheus node-exporter +home: https://github.com/prometheus/node_exporter/ +keywords: +- node-exporter +- prometheus +- exporter +maintainers: +- email: gianrubio@gmail.com + name: gianrubio +- name: vsliouniaev +name: prometheus-node-exporter +sources: +- https://github.com/prometheus/node_exporter/ +version: 1.12.0 diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/README.md b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/README.md new file mode 100644 index 00000000..babde05e --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/README.md @@ -0,0 +1,63 @@ +# Prometheus Node Exporter + +Prometheus exporter for hardware and OS metrics exposed by *NIX kernels, written in Go with pluggable metric collectors. + +This chart bootstraps a prometheus [Node Exporter](http://github.com/prometheus/node_exporter) deployment on a [Kubernetes](http://kubernetes.io) cluster using the [Helm](https://helm.sh) package manager. + +## Get Repo Info + +```console +helm repo add prometheus-community https://prometheus-community.github.io/helm-charts +helm repo update +``` + +_See [helm repo](https://helm.sh/docs/helm/helm_repo/) for command documentation._ + +## Install Chart + +```console +# Helm 3 +$ helm install [RELEASE_NAME] prometheus-community/prometheus-node-exporter + +# Helm 2 +$ helm install --name [RELEASE_NAME] prometheus-community/prometheus-node-exporter +``` + +_See [configuration](#configuration) below._ + +_See [helm install](https://helm.sh/docs/helm/helm_install/) for command documentation._ + +## Uninstall Chart + +```console +# Helm 3 +$ helm uninstall [RELEASE_NAME] + +# Helm 2 +# helm delete --purge [RELEASE_NAME] +``` + +This removes all the Kubernetes components associated with the chart and deletes the release. + +_See [helm uninstall](https://helm.sh/docs/helm/helm_uninstall/) for command documentation._ + +## Upgrading Chart + +```console +# Helm 3 or 2 +$ helm upgrade [RELEASE_NAME] [CHART] --install +``` + +_See [helm upgrade](https://helm.sh/docs/helm/helm_upgrade/) for command documentation._ + +## Configuring + +See [Customizing the Chart Before Installing](https://helm.sh/docs/intro/using_helm/#customizing-the-chart-before-installing). To see all configurable options with detailed comments, visit the chart's [values.yaml](./values.yaml), or run these configuration commands: + +```console +# Helm 2 +$ helm inspect values prometheus-community/prometheus-node-exporter + +# Helm 3 +$ helm show values prometheus-community/prometheus-node-exporter +``` diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/ci/port-values.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/ci/port-values.yaml new file mode 100644 index 00000000..dbfb4b67 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/ci/port-values.yaml @@ -0,0 +1,3 @@ +service: + targetPort: 9102 + port: 9102 diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/NOTES.txt b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/NOTES.txt new file mode 100644 index 00000000..dc272fa9 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/NOTES.txt @@ -0,0 +1,15 @@ +1. Get the application URL by running these commands: +{{- if contains "NodePort" .Values.service.type }} + export NODE_PORT=$(kubectl get --namespace {{ template "prometheus-node-exporter.namespace" . }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ template "prometheus-node-exporter.fullname" . }}) + export NODE_IP=$(kubectl get nodes --namespace {{ template "prometheus-node-exporter.namespace" . }} -o jsonpath="{.items[0].status.addresses[0].address}") + echo http://$NODE_IP:$NODE_PORT +{{- else if contains "LoadBalancer" .Values.service.type }} + NOTE: It may take a few minutes for the LoadBalancer IP to be available. + You can watch the status of by running 'kubectl get svc -w {{ template "prometheus-node-exporter.fullname" . }}' + export SERVICE_IP=$(kubectl get svc --namespace {{ template "prometheus-node-exporter.namespace" . }} {{ template "prometheus-node-exporter.fullname" . }} -o jsonpath='{.status.loadBalancer.ingress[0].ip}') + echo http://$SERVICE_IP:{{ .Values.service.port }} +{{- else if contains "ClusterIP" .Values.service.type }} + export POD_NAME=$(kubectl get pods --namespace {{ template "prometheus-node-exporter.namespace" . }} -l "app={{ template "prometheus-node-exporter.name" . }},release={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}") + echo "Visit http://127.0.0.1:9100 to use your application" + kubectl port-forward --namespace {{ template "prometheus-node-exporter.namespace" . }} $POD_NAME 9100 +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/_helpers.tpl b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/_helpers.tpl new file mode 100644 index 00000000..e8260688 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/_helpers.tpl @@ -0,0 +1,66 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "prometheus-node-exporter.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "prometheus-node-exporter.fullname" -}} +{{- if .Values.fullnameOverride -}} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .Chart.Name .Values.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- .Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* Generate basic labels */}} +{{- define "prometheus-node-exporter.labels" }} +app: {{ template "prometheus-node-exporter.name" . }} +heritage: {{.Release.Service }} +release: {{.Release.Name }} +chart: {{ template "prometheus-node-exporter.chart" . }} +{{- if .Values.podLabels}} +{{ toYaml .Values.podLabels }} +{{- end }} +{{- end }} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "prometheus-node-exporter.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}} +{{- end -}} + + +{{/* +Create the name of the service account to use +*/}} +{{- define "prometheus-node-exporter.serviceAccountName" -}} +{{- if .Values.serviceAccount.create -}} + {{ default (include "prometheus-node-exporter.fullname" .) .Values.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* +Allow the release namespace to be overridden for multi-namespace deployments in combined charts +*/}} +{{- define "prometheus-node-exporter.namespace" -}} + {{- if .Values.namespaceOverride -}} + {{- .Values.namespaceOverride -}} + {{- else -}} + {{- .Release.Namespace -}} + {{- end -}} +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/daemonset.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/daemonset.yaml new file mode 100644 index 00000000..2787daea --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/daemonset.yaml @@ -0,0 +1,159 @@ +apiVersion: apps/v1 +kind: DaemonSet +metadata: + name: {{ template "prometheus-node-exporter.fullname" . }} + namespace: {{ template "prometheus-node-exporter.namespace" . }} + labels: {{ include "prometheus-node-exporter.labels" . | indent 4 }} +spec: + selector: + matchLabels: + app: {{ template "prometheus-node-exporter.name" . }} + release: {{ .Release.Name }} + {{- if .Values.updateStrategy }} + updateStrategy: +{{ toYaml .Values.updateStrategy | indent 4 }} + {{- end }} + template: + metadata: + labels: {{ include "prometheus-node-exporter.labels" . | indent 8 }} + {{- if .Values.podAnnotations }} + annotations: + {{- toYaml .Values.podAnnotations | nindent 8 }} + {{- end }} + spec: +{{- if and .Values.rbac.create .Values.serviceAccount.create }} + serviceAccountName: {{ template "prometheus-node-exporter.serviceAccountName" . }} +{{- end }} +{{- if .Values.securityContext }} + securityContext: +{{ toYaml .Values.securityContext | indent 8 }} +{{- end }} +{{- if .Values.priorityClassName }} + priorityClassName: {{ .Values.priorityClassName }} +{{- end }} + containers: + - name: node-exporter + image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - --path.procfs=/host/proc + - --path.sysfs=/host/sys + - --path.rootfs=/host/root + - --web.listen-address=$(HOST_IP):{{ .Values.service.port }} +{{- if .Values.extraArgs }} +{{ toYaml .Values.extraArgs | indent 12 }} +{{- end }} + env: + - name: HOST_IP + {{- if .Values.service.listenOnAllInterfaces }} + value: 0.0.0.0 + {{- else }} + valueFrom: + fieldRef: + apiVersion: v1 + fieldPath: status.hostIP + {{- end }} + ports: + - name: metrics + containerPort: {{ .Values.service.targetPort }} + protocol: TCP + livenessProbe: + httpGet: + path: / + port: {{ .Values.service.port }} + readinessProbe: + httpGet: + path: / + port: {{ .Values.service.port }} + resources: +{{ toYaml .Values.resources | indent 12 }} + volumeMounts: + - name: proc + mountPath: /host/proc + readOnly: true + - name: sys + mountPath: /host/sys + readOnly: true + - name: root + mountPath: /host/root + mountPropagation: HostToContainer + readOnly: true + {{- if .Values.extraHostVolumeMounts }} + {{- range $_, $mount := .Values.extraHostVolumeMounts }} + - name: {{ $mount.name }} + mountPath: {{ $mount.mountPath }} + readOnly: {{ $mount.readOnly }} + {{- if $mount.mountPropagation }} + mountPropagation: {{ $mount.mountPropagation }} + {{- end }} + {{- end }} + {{- end }} + {{- if .Values.sidecarVolumeMount }} + {{- range $_, $mount := .Values.sidecarVolumeMount }} + - name: {{ $mount.name }} + mountPath: {{ $mount.mountPath }} + readOnly: true + {{- end }} + {{- end }} + {{- if .Values.configmaps }} + {{- range $_, $mount := .Values.configmaps }} + - name: {{ $mount.name }} + mountPath: {{ $mount.mountPath }} + {{- end }} + {{- end }} +{{- if .Values.sidecars }} +{{ toYaml .Values.sidecars | indent 8 }} + {{- if .Values.sidecarVolumeMount }} + volumeMounts: + {{- range $_, $mount := .Values.sidecarVolumeMount }} + - name: {{ $mount.name }} + mountPath: {{ $mount.mountPath }} + readOnly: {{ $mount.readOnly }} + {{- end }} + {{- end }} +{{- end }} + hostNetwork: {{ .Values.hostNetwork }} + hostPID: true +{{- if .Values.affinity }} + affinity: +{{ toYaml .Values.affinity | indent 8 }} +{{- end }} +{{- if .Values.nodeSelector }} + nodeSelector: +{{ toYaml .Values.nodeSelector | indent 8 }} +{{- end }} + {{- with .Values.tolerations }} + tolerations: +{{ toYaml . | indent 8 }} + {{- end }} + volumes: + - name: proc + hostPath: + path: /proc + - name: sys + hostPath: + path: /sys + - name: root + hostPath: + path: / + {{- if .Values.extraHostVolumeMounts }} + {{- range $_, $mount := .Values.extraHostVolumeMounts }} + - name: {{ $mount.name }} + hostPath: + path: {{ $mount.hostPath }} + {{- end }} + {{- end }} + {{- if .Values.sidecarVolumeMount }} + {{- range $_, $mount := .Values.sidecarVolumeMount }} + - name: {{ $mount.name }} + emptyDir: + medium: Memory + {{- end }} + {{- end }} + {{- if .Values.configmaps }} + {{- range $_, $mount := .Values.configmaps }} + - name: {{ $mount.name }} + configMap: + name: {{ $mount.name }} + {{- end }} + {{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/endpoints.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/endpoints.yaml new file mode 100644 index 00000000..8daaeaaf --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/endpoints.yaml @@ -0,0 +1,18 @@ +{{- if .Values.endpoints }} +apiVersion: v1 +kind: Endpoints +metadata: + name: {{ template "prometheus-node-exporter.fullname" . }} + namespace: {{ template "prometheus-node-exporter.namespace" . }} + labels: +{{ include "prometheus-node-exporter.labels" . | indent 4 }} +subsets: + - addresses: + {{- range .Values.endpoints }} + - ip: {{ . }} + {{- end }} + ports: + - name: metrics + port: 9100 + protocol: TCP +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/monitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/monitor.yaml new file mode 100644 index 00000000..4e31ba36 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/monitor.yaml @@ -0,0 +1,25 @@ +{{- if .Values.prometheus.monitor.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "prometheus-node-exporter.fullname" . }} + namespace: {{ template "prometheus-node-exporter.namespace" . }} + labels: {{ include "prometheus-node-exporter.labels" . | indent 4 }} + {{- if .Values.prometheus.monitor.additionalLabels }} +{{ toYaml .Values.prometheus.monitor.additionalLabels | indent 4 }} + {{- end }} +spec: + selector: + matchLabels: + app: {{ template "prometheus-node-exporter.name" . }} + release: {{ .Release.Name }} + endpoints: + - port: metrics + {{- if .Values.prometheus.monitor.scrapeTimeout }} + scrapeTimeout: {{ .Values.prometheus.monitor.scrapeTimeout }} + {{- end }} +{{- if .Values.prometheus.monitor.relabelings }} + relabelings: +{{ toYaml .Values.prometheus.monitor.relabelings | indent 6 }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/psp-clusterrole.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/psp-clusterrole.yaml new file mode 100644 index 00000000..cb433369 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/psp-clusterrole.yaml @@ -0,0 +1,15 @@ +{{- if .Values.rbac.create }} +{{- if .Values.rbac.pspEnabled }} +kind: ClusterRole +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: psp-{{ template "prometheus-node-exporter.fullname" . }} + labels: {{ include "prometheus-node-exporter.labels" . | indent 4 }} +rules: +- apiGroups: ['extensions'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: + - {{ template "prometheus-node-exporter.fullname" . }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/psp-clusterrolebinding.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/psp-clusterrolebinding.yaml new file mode 100644 index 00000000..d36d93ec --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/psp-clusterrolebinding.yaml @@ -0,0 +1,17 @@ +{{- if .Values.rbac.create }} +{{- if .Values.rbac.pspEnabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: psp-{{ template "prometheus-node-exporter.fullname" . }} + labels: {{ include "prometheus-node-exporter.labels" . | indent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: psp-{{ template "prometheus-node-exporter.fullname" . }} +subjects: + - kind: ServiceAccount + name: {{ template "prometheus-node-exporter.fullname" . }} + namespace: {{ template "prometheus-node-exporter.namespace" . }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/psp.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/psp.yaml new file mode 100644 index 00000000..f00506c9 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/psp.yaml @@ -0,0 +1,52 @@ +{{- if .Values.rbac.create }} +{{- if .Values.rbac.pspEnabled }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ template "prometheus-node-exporter.fullname" . }} + namespace: {{ template "prometheus-node-exporter.namespace" . }} + labels: {{ include "prometheus-node-exporter.labels" . | indent 4 }} +spec: + privileged: false + # Required to prevent escalations to root. + # allowPrivilegeEscalation: false + # This is redundant with non-root + disallow privilege escalation, + # but we can provide it for defense in depth. + #requiredDropCapabilities: + # - ALL + # Allow core volume types. + volumes: + - 'configMap' + - 'emptyDir' + - 'projected' + - 'secret' + - 'downwardAPI' + - 'persistentVolumeClaim' + - 'hostPath' + hostNetwork: true + hostIPC: false + hostPID: true + hostPorts: + - min: 0 + max: 65535 + runAsUser: + # Permits the container to run with root privileges as well. + rule: 'RunAsAny' + seLinux: + # This policy assumes the nodes are using AppArmor rather than SELinux. + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 0 + max: 65535 + fsGroup: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 0 + max: 65535 + readOnlyRootFilesystem: false +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/service.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/service.yaml new file mode 100644 index 00000000..b0a447fe --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/service.yaml @@ -0,0 +1,23 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ template "prometheus-node-exporter.fullname" . }} + namespace: {{ template "prometheus-node-exporter.namespace" . }} +{{- if .Values.service.annotations }} + annotations: +{{ toYaml .Values.service.annotations | indent 4 }} +{{- end }} + labels: {{ include "prometheus-node-exporter.labels" . | indent 4 }} +spec: + type: {{ .Values.service.type }} + ports: + - port: {{ .Values.service.port }} + {{- if ( and (eq .Values.service.type "NodePort" ) (not (empty .Values.service.nodePort)) ) }} + nodePort: {{ .Values.service.nodePort }} + {{- end }} + targetPort: {{ .Values.service.targetPort }} + protocol: TCP + name: metrics + selector: + app: {{ template "prometheus-node-exporter.name" . }} + release: {{ .Release.Name }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/serviceaccount.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/serviceaccount.yaml new file mode 100644 index 00000000..bd1c223b --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/serviceaccount.yaml @@ -0,0 +1,16 @@ +{{- if .Values.rbac.create -}} +{{- if .Values.serviceAccount.create -}} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ template "prometheus-node-exporter.serviceAccountName" . }} + namespace: {{ template "prometheus-node-exporter.namespace" . }} + labels: + app: {{ template "prometheus-node-exporter.name" . }} + chart: {{ template "prometheus-node-exporter.chart" . }} + release: "{{ .Release.Name }}" + heritage: "{{ .Release.Service }}" +imagePullSecrets: +{{ toYaml .Values.serviceAccount.imagePullSecrets | indent 2 }} +{{- end -}} +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/values.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/values.yaml new file mode 100644 index 00000000..7edd8936 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/values.yaml @@ -0,0 +1,141 @@ +# Default values for prometheus-node-exporter. +# This is a YAML-formatted file. +# Declare variables to be passed into your templates. +image: + repository: quay.io/prometheus/node-exporter + tag: v1.0.1 + pullPolicy: IfNotPresent + +service: + type: ClusterIP + port: 9100 + targetPort: 9100 + nodePort: + listenOnAllInterfaces: true + annotations: + prometheus.io/scrape: "true" + +prometheus: + monitor: + enabled: false + additionalLabels: {} + namespace: "" + + relabelings: [] + scrapeTimeout: 10s + +## Customize the updateStrategy if set +updateStrategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 1 + +resources: {} + # We usually recommend not to specify default resources and to leave this as a conscious + # choice for the user. This also increases chances charts run on environments with little + # resources, such as Minikube. If you do want to specify resources, uncomment the following + # lines, adjust them as necessary, and remove the curly braces after 'resources:'. + # limits: + # cpu: 200m + # memory: 50Mi + # requests: + # cpu: 100m + # memory: 30Mi + +serviceAccount: + # Specifies whether a ServiceAccount should be created + create: true + # The name of the ServiceAccount to use. + # If not set and create is true, a name is generated using the fullname template + name: + imagePullSecrets: [] + +securityContext: + fsGroup: 65534 + runAsGroup: 65534 + runAsNonRoot: true + runAsUser: 65534 + +rbac: + ## If true, create & use RBAC resources + ## + create: true + ## If true, create & use Pod Security Policy resources + ## https://kubernetes.io/docs/concepts/policy/pod-security-policy/ + pspEnabled: true + +# for deployments that have node_exporter deployed outside of the cluster, list +# their addresses here +endpoints: [] + +# Expose the service to the host network +hostNetwork: true + +## Assign a group of affinity scheduling rules +## +affinity: {} +# nodeAffinity: +# requiredDuringSchedulingIgnoredDuringExecution: +# nodeSelectorTerms: +# - matchFields: +# - key: metadata.name +# operator: In +# values: +# - target-host-name + +# Annotations to be added to node exporter pods +podAnnotations: {} + +# Extra labels to be added to node exporter pods +podLabels: {} + +## Assign a nodeSelector if operating a hybrid cluster +## +nodeSelector: {} +# beta.kubernetes.io/arch: amd64 +# beta.kubernetes.io/os: linux + +tolerations: + - effect: NoSchedule + operator: Exists + +## Assign a PriorityClassName to pods if set +# priorityClassName: "" + +## Additional container arguments +## +extraArgs: [] +# - --collector.diskstats.ignored-devices=^(ram|loop|fd|(h|s|v)d[a-z]|nvme\\d+n\\d+p)\\d+$ +# - --collector.textfile.directory=/run/prometheus + +## Additional mounts from the host +## +extraHostVolumeMounts: [] +# - name: +# hostPath: +# mountPath: +# readOnly: true|false +# mountPropagation: None|HostToContainer|Bidirectional + +## Additional configmaps to be mounted. +## +configmaps: [] +# - name: +# mountPath: + +## Override the deployment namespace +## +namespaceOverride: "" + +## Additional containers for export metrics to text file +## +sidecars: [] +## - name: nvidia-dcgm-exporter +## image: nvidia/dcgm-exporter:1.4.3 + +## Volume for sidecar containers +## +sidecarVolumeMount: [] +## - name: collector-textfiles +## mountPath: /run/prometheus +## readOnly: false diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-alertmanagerconfigs.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-alertmanagerconfigs.yaml new file mode 100644 index 00000000..fb1ad5f3 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-alertmanagerconfigs.yaml @@ -0,0 +1,1854 @@ +# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.44.0/example/prometheus-operator-crd/monitoring.coreos.com_alertmanagerconfigs.yaml + +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.4.1 + creationTimestamp: null + name: alertmanagerconfigs.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + kind: AlertmanagerConfig + listKind: AlertmanagerConfigList + plural: alertmanagerconfigs + singular: alertmanagerconfig + scope: Namespaced + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + description: AlertmanagerConfig defines a namespaced AlertmanagerConfig to be aggregated across multiple namespaces configuring one Alertmanager cluster. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: AlertmanagerConfigSpec is a specification of the desired behavior of the Alertmanager configuration. By definition, the Alertmanager configuration only applies to alerts for which the `namespace` label is equal to the namespace of the AlertmanagerConfig resource. + properties: + inhibitRules: + description: List of inhibition rules. The rules will only apply to alerts matching the resource’s namespace. + items: + description: InhibitRule defines an inhibition rule that allows to mute alerts when other alerts are already firing. See https://prometheus.io/docs/alerting/latest/configuration/#inhibit_rule + properties: + equal: + description: Labels that must have an equal value in the source and target alert for the inhibition to take effect. + items: + type: string + type: array + sourceMatch: + description: Matchers for which one or more alerts have to exist for the inhibition to take effect. The operator enforces that the alert matches the resource’s namespace. + items: + description: Matcher defines how to match on alert's labels. + properties: + name: + description: Label to match. + type: string + regex: + description: Whether to match on equality (false) or regular-expression (true). + type: boolean + value: + description: Label value to match. + type: string + required: + - name + - value + type: object + type: array + targetMatch: + description: Matchers that have to be fulfilled in the alerts to be muted. The operator enforces that the alert matches the resource’s namespace. + items: + description: Matcher defines how to match on alert's labels. + properties: + name: + description: Label to match. + type: string + regex: + description: Whether to match on equality (false) or regular-expression (true). + type: boolean + value: + description: Label value to match. + type: string + required: + - name + - value + type: object + type: array + type: object + type: array + receivers: + description: List of receivers. + items: + description: Receiver defines one or more notification integrations. + properties: + emailConfigs: + description: List of Email configurations. + items: + description: EmailConfig configures notifications via Email. + properties: + authIdentity: + type: string + authPassword: + description: SecretKeySelector selects a key of a Secret. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + authSecret: + description: SecretKeySelector selects a key of a Secret. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + authUsername: + description: SMTP authentication information. + type: string + from: + description: The sender address. + type: string + headers: + description: Further headers email header key/value pairs. Overrides any headers previously set by the notification implementation. + items: + description: KeyValue defines a (key, value) tuple. + properties: + key: + description: Key of the tuple. + type: string + value: + description: Value of the tuple. + type: string + required: + - key + - value + type: object + type: array + hello: + description: The hostname to identify to the SMTP server. + type: string + html: + description: The HTML body of the email notification. + type: string + requireTLS: + description: The SMTP TLS requirement. Note that Go does not support unencrypted connections to remote SMTP endpoints. + type: boolean + sendResolved: + description: Whether or not to notify about resolved alerts. + type: boolean + smarthost: + description: The SMTP host through which emails are sent. + type: string + text: + description: The text body of the email notification. + type: string + tlsConfig: + description: TLS configuration + properties: + ca: + description: Struct containing the CA cert to use for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + cert: + description: Struct containing the client cert file for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + to: + description: The email address to send notifications to. + type: string + type: object + type: array + name: + description: Name of the receiver. Must be unique across all items from the list. + type: string + opsgenieConfigs: + description: List of OpsGenie configurations. + items: + description: OpsGenieConfig configures notifications via OpsGenie. See https://prometheus.io/docs/alerting/latest/configuration/#opsgenie_config + properties: + apiKey: + description: The secret's key that contains the OpsGenie API key. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + apiURL: + description: The URL to send OpsGenie API requests to. + type: string + description: + description: Description of the incident. + type: string + details: + description: A set of arbitrary key/value pairs that provide further detail about the incident. + items: + description: KeyValue defines a (key, value) tuple. + properties: + key: + description: Key of the tuple. + type: string + value: + description: Value of the tuple. + type: string + required: + - key + - value + type: object + type: array + httpConfig: + description: HTTP client configuration. + properties: + basicAuth: + description: BasicAuth for the client. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + bearerTokenSecret: + description: The secret's key that contains the bearer token to be used by the client for authentication. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + proxyURL: + description: Optional proxy URL. + type: string + tlsConfig: + description: TLS configuration for the client. + properties: + ca: + description: Struct containing the CA cert to use for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + cert: + description: Struct containing the client cert file for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + message: + description: Alert text limited to 130 characters. + type: string + note: + description: Additional alert note. + type: string + priority: + description: Priority level of alert. Possible values are P1, P2, P3, P4, and P5. + type: string + responders: + description: List of responders responsible for notifications. + items: + description: OpsGenieConfigResponder defines a responder to an incident. One of id, name or username has to be defined. + properties: + id: + description: ID of the responder. + type: string + name: + description: Name of the responder. + type: string + type: + description: Type of responder. + type: string + username: + description: Username of the responder. + type: string + type: object + type: array + sendResolved: + description: Whether or not to notify about resolved alerts. + type: boolean + source: + description: Backlink to the sender of the notification. + type: string + tags: + description: Comma separated list of tags attached to the notifications. + type: string + type: object + type: array + pagerdutyConfigs: + description: List of PagerDuty configurations. + items: + description: PagerDutyConfig configures notifications via PagerDuty. See https://prometheus.io/docs/alerting/latest/configuration/#pagerduty_config + properties: + class: + description: The class/type of the event. + type: string + client: + description: Client identification. + type: string + clientURL: + description: Backlink to the sender of notification. + type: string + component: + description: The part or component of the affected system that is broken. + type: string + description: + description: Description of the incident. + type: string + details: + description: Arbitrary key/value pairs that provide further detail about the incident. + items: + description: KeyValue defines a (key, value) tuple. + properties: + key: + description: Key of the tuple. + type: string + value: + description: Value of the tuple. + type: string + required: + - key + - value + type: object + type: array + group: + description: A cluster or grouping of sources. + type: string + httpConfig: + description: HTTP client configuration. + properties: + basicAuth: + description: BasicAuth for the client. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + bearerTokenSecret: + description: The secret's key that contains the bearer token to be used by the client for authentication. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + proxyURL: + description: Optional proxy URL. + type: string + tlsConfig: + description: TLS configuration for the client. + properties: + ca: + description: Struct containing the CA cert to use for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + cert: + description: Struct containing the client cert file for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + routingKey: + description: The secret's key that contains the PagerDuty integration key (when using Events API v2). Either this field or `serviceKey` needs to be defined. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + sendResolved: + description: Whether or not to notify about resolved alerts. + type: boolean + serviceKey: + description: The secret's key that contains the PagerDuty service key (when using integration type "Prometheus"). Either this field or `routingKey` needs to be defined. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + severity: + description: Severity of the incident. + type: string + url: + description: The URL to send requests to. + type: string + type: object + type: array + pushoverConfigs: + description: List of Pushover configurations. + items: + description: PushoverConfig configures notifications via Pushover. See https://prometheus.io/docs/alerting/latest/configuration/#pushover_config + properties: + expire: + description: How long your notification will continue to be retried for, unless the user acknowledges the notification. + type: string + html: + description: Whether notification message is HTML or plain text. + type: boolean + httpConfig: + description: HTTP client configuration. + properties: + basicAuth: + description: BasicAuth for the client. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + bearerTokenSecret: + description: The secret's key that contains the bearer token to be used by the client for authentication. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + proxyURL: + description: Optional proxy URL. + type: string + tlsConfig: + description: TLS configuration for the client. + properties: + ca: + description: Struct containing the CA cert to use for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + cert: + description: Struct containing the client cert file for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + message: + description: Notification message. + type: string + priority: + description: Priority, see https://pushover.net/api#priority + type: string + retry: + description: How often the Pushover servers will send the same notification to the user. Must be at least 30 seconds. + type: string + sendResolved: + description: Whether or not to notify about resolved alerts. + type: boolean + sound: + description: The name of one of the sounds supported by device clients to override the user's default sound choice + type: string + title: + description: Notification title. + type: string + token: + description: Your registered application’s API token, see https://pushover.net/apps + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + url: + description: A supplementary URL shown alongside the message. + type: string + urlTitle: + description: A title for supplementary URL, otherwise just the URL is shown + type: string + userKey: + description: The recipient user’s user key. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + type: array + slackConfigs: + description: List of Slack configurations. + items: + description: SlackConfig configures notifications via Slack. See https://prometheus.io/docs/alerting/latest/configuration/#slack_config + properties: + actions: + description: A list of Slack actions that are sent with each notification. + items: + description: SlackAction configures a single Slack action that is sent with each notification. See https://api.slack.com/docs/message-attachments#action_fields and https://api.slack.com/docs/message-buttons for more information. + properties: + confirm: + description: SlackConfirmationField protect users from destructive actions or particularly distinguished decisions by asking them to confirm their button click one more time. See https://api.slack.com/docs/interactive-message-field-guide#confirmation_fields for more information. + properties: + dismissText: + type: string + okText: + type: string + text: + type: string + title: + type: string + required: + - text + type: object + name: + type: string + style: + type: string + text: + type: string + type: + type: string + url: + type: string + value: + type: string + required: + - text + - type + type: object + type: array + apiURL: + description: The secret's key that contains the Slack webhook URL. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + callbackId: + type: string + channel: + description: The channel or user to send notifications to. + type: string + color: + type: string + fallback: + type: string + fields: + description: A list of Slack fields that are sent with each notification. + items: + description: SlackField configures a single Slack field that is sent with each notification. Each field must contain a title, value, and optionally, a boolean value to indicate if the field is short enough to be displayed next to other fields designated as short. See https://api.slack.com/docs/message-attachments#fields for more information. + properties: + short: + type: boolean + title: + type: string + value: + type: string + required: + - title + - value + type: object + type: array + footer: + type: string + httpConfig: + description: HTTP client configuration. + properties: + basicAuth: + description: BasicAuth for the client. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + bearerTokenSecret: + description: The secret's key that contains the bearer token to be used by the client for authentication. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + proxyURL: + description: Optional proxy URL. + type: string + tlsConfig: + description: TLS configuration for the client. + properties: + ca: + description: Struct containing the CA cert to use for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + cert: + description: Struct containing the client cert file for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + iconEmoji: + type: string + iconURL: + type: string + imageURL: + type: string + linkNames: + type: boolean + mrkdwnIn: + items: + type: string + type: array + pretext: + type: string + sendResolved: + description: Whether or not to notify about resolved alerts. + type: boolean + shortFields: + type: boolean + text: + type: string + thumbURL: + type: string + title: + type: string + titleLink: + type: string + username: + type: string + type: object + type: array + victoropsConfigs: + description: List of VictorOps configurations. + items: + description: VictorOpsConfig configures notifications via VictorOps. See https://prometheus.io/docs/alerting/latest/configuration/#victorops_config + properties: + apiKey: + description: The API key to use when talking to the VictorOps API. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + apiUrl: + description: The VictorOps API URL. + type: string + customFields: + description: Additional custom fields for notification. + items: + description: KeyValue defines a (key, value) tuple. + properties: + key: + description: Key of the tuple. + type: string + value: + description: Value of the tuple. + type: string + required: + - key + - value + type: object + type: array + entityDisplayName: + description: Contains summary of the alerted problem. + type: string + httpConfig: + description: The HTTP client's configuration. + properties: + basicAuth: + description: BasicAuth for the client. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + bearerTokenSecret: + description: The secret's key that contains the bearer token to be used by the client for authentication. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + proxyURL: + description: Optional proxy URL. + type: string + tlsConfig: + description: TLS configuration for the client. + properties: + ca: + description: Struct containing the CA cert to use for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + cert: + description: Struct containing the client cert file for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + messageType: + description: Describes the behavior of the alert (CRITICAL, WARNING, INFO). + type: string + monitoringTool: + description: The monitoring tool the state message is from. + type: string + routingKey: + description: A key used to map the alert to a team. + type: string + sendResolved: + description: Whether or not to notify about resolved alerts. + type: boolean + stateMessage: + description: Contains long explanation of the alerted problem. + type: string + required: + - routingKey + type: object + type: array + webhookConfigs: + description: List of webhook configurations. + items: + description: WebhookConfig configures notifications via a generic receiver supporting the webhook payload. See https://prometheus.io/docs/alerting/latest/configuration/#webhook_config + properties: + httpConfig: + description: HTTP client configuration. + properties: + basicAuth: + description: BasicAuth for the client. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + bearerTokenSecret: + description: The secret's key that contains the bearer token to be used by the client for authentication. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + proxyURL: + description: Optional proxy URL. + type: string + tlsConfig: + description: TLS configuration for the client. + properties: + ca: + description: Struct containing the CA cert to use for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + cert: + description: Struct containing the client cert file for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + maxAlerts: + description: Maximum number of alerts to be sent per webhook message. + format: int32 + type: integer + sendResolved: + description: Whether or not to notify about resolved alerts. + type: boolean + url: + description: The URL to send HTTP POST requests to. `urlSecret` takes precedence over `url`. One of `urlSecret` and `url` should be defined. + type: string + urlSecret: + description: The secret's key that contains the webhook URL to send HTTP requests to. `urlSecret` takes precedence over `url`. One of `urlSecret` and `url` should be defined. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + type: array + wechatConfigs: + description: List of WeChat configurations. + items: + description: WeChatConfig configures notifications via WeChat. See https://prometheus.io/docs/alerting/latest/configuration/#wechat_config + properties: + agentID: + type: string + apiSecret: + description: The secret's key that contains the WeChat API key. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + apiURL: + description: The WeChat API URL. + type: string + corpID: + description: The corp id for authentication. + type: string + httpConfig: + description: HTTP client configuration. + properties: + basicAuth: + description: BasicAuth for the client. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + bearerTokenSecret: + description: The secret's key that contains the bearer token to be used by the client for authentication. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + proxyURL: + description: Optional proxy URL. + type: string + tlsConfig: + description: TLS configuration for the client. + properties: + ca: + description: Struct containing the CA cert to use for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + cert: + description: Struct containing the client cert file for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + message: + description: API request data as defined by the WeChat API. + type: string + messageType: + type: string + sendResolved: + description: Whether or not to notify about resolved alerts. + type: boolean + toParty: + type: string + toTag: + type: string + toUser: + type: string + type: object + type: array + required: + - name + type: object + type: array + route: + description: The Alertmanager route definition for alerts matching the resource’s namespace. It will be added to the generated Alertmanager configuration as a first-level route. + properties: + continue: + description: Boolean indicating whether an alert should continue matching subsequent sibling nodes. It will always be overridden to true for the first-level route by the Prometheus operator. + type: boolean + groupBy: + description: List of labels to group by. + items: + type: string + type: array + groupInterval: + description: How long to wait before sending an updated notification. Must match the regular expression `[0-9]+(ms|s|m|h)` (milliseconds seconds minutes hours). + type: string + groupWait: + description: How long to wait before sending the initial notification. Must match the regular expression `[0-9]+(ms|s|m|h)` (milliseconds seconds minutes hours). + type: string + matchers: + description: 'List of matchers that the alert’s labels should match. For the first level route, the operator removes any existing equality and regexp matcher on the `namespace` label and adds a `namespace: ` matcher.' + items: + description: Matcher defines how to match on alert's labels. + properties: + name: + description: Label to match. + type: string + regex: + description: Whether to match on equality (false) or regular-expression (true). + type: boolean + value: + description: Label value to match. + type: string + required: + - name + - value + type: object + type: array + receiver: + description: Name of the receiver for this route. If present, it should be listed in the `receivers` field. The field can be omitted only for nested routes otherwise it is mandatory. + type: string + repeatInterval: + description: How long to wait before repeating the last notification. Must match the regular expression `[0-9]+(ms|s|m|h)` (milliseconds seconds minutes hours). + type: string + routes: + description: Child routes. + items: + x-kubernetes-preserve-unknown-fields: true + type: array + type: object + type: object + required: + - spec + type: object + served: true + storage: true +status: + acceptedNames: + kind: "" + plural: "" + conditions: [] + storedVersions: [] diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-alertmanagers.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-alertmanagers.yaml new file mode 100644 index 00000000..86a6b980 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-alertmanagers.yaml @@ -0,0 +1,3216 @@ +# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.44.0/example/prometheus-operator-crd/monitoring.coreos.com_alertmanagers.yaml + +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.4.1 + creationTimestamp: null + name: alertmanagers.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + kind: Alertmanager + listKind: AlertmanagerList + plural: alertmanagers + singular: alertmanager + scope: Namespaced + versions: + - additionalPrinterColumns: + - description: The version of Alertmanager + jsonPath: .spec.version + name: Version + type: string + - description: The desired replicas number of Alertmanagers + jsonPath: .spec.replicas + name: Replicas + type: integer + - jsonPath: .metadata.creationTimestamp + name: Age + type: date + name: v1 + schema: + openAPIV3Schema: + description: Alertmanager describes an Alertmanager cluster. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: 'Specification of the desired behavior of the Alertmanager cluster. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#spec-and-status' + properties: + additionalPeers: + description: AdditionalPeers allows injecting a set of additional Alertmanagers to peer with to form a highly available cluster. + items: + type: string + type: array + affinity: + description: If specified, the pod's scheduling constraints. + properties: + nodeAffinity: + description: Describes node affinity scheduling rules for the pod. + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node matches the corresponding matchExpressions; the node(s) with the highest sum are the most preferred. + items: + description: An empty preferred scheduling term matches all objects with implicit weight 0 (i.e. it's a no-op). A null preferred scheduling term matches no objects (i.e. is also a no-op). + properties: + preference: + description: A node selector term, associated with the corresponding weight. + properties: + matchExpressions: + description: A list of node selector requirements by node's labels. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchFields: + description: A list of node selector requirements by node's fields. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + type: object + weight: + description: Weight associated with matching the corresponding nodeSelectorTerm, in the range 1-100. + format: int32 + type: integer + required: + - preference + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node. + properties: + nodeSelectorTerms: + description: Required. A list of node selector terms. The terms are ORed. + items: + description: A null or empty node selector term matches no objects. The requirements of them are ANDed. The TopologySelectorTerm type implements a subset of the NodeSelectorTerm. + properties: + matchExpressions: + description: A list of node selector requirements by node's labels. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchFields: + description: A list of node selector requirements by node's fields. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + type: object + type: array + required: + - nodeSelectorTerms + type: object + type: object + podAffinity: + description: Describes pod affinity scheduling rules (e.g. co-locate this pod in the same node, zone, etc. as some other pod(s)). + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. + items: + description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated with the corresponding weight. + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + namespaces: + description: namespaces specifies which namespaces the labelSelector applies to (matches against); null or empty list means "this pod's namespace" + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + weight: + description: weight associated with matching the corresponding podAffinityTerm, in the range 1-100. + format: int32 + type: integer + required: + - podAffinityTerm + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. + items: + description: Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + namespaces: + description: namespaces specifies which namespaces the labelSelector applies to (matches against); null or empty list means "this pod's namespace" + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + type: array + type: object + podAntiAffinity: + description: Describes pod anti-affinity scheduling rules (e.g. avoid putting this pod in the same node, zone, etc. as some other pod(s)). + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the anti-affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling anti-affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. + items: + description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated with the corresponding weight. + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + namespaces: + description: namespaces specifies which namespaces the labelSelector applies to (matches against); null or empty list means "this pod's namespace" + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + weight: + description: weight associated with matching the corresponding podAffinityTerm, in the range 1-100. + format: int32 + type: integer + required: + - podAffinityTerm + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the anti-affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the anti-affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. + items: + description: Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + namespaces: + description: namespaces specifies which namespaces the labelSelector applies to (matches against); null or empty list means "this pod's namespace" + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + type: array + type: object + type: object + alertmanagerConfigNamespaceSelector: + description: Namespaces to be selected for AlertmanagerConfig discovery. If nil, only check own namespace. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + alertmanagerConfigSelector: + description: AlertmanagerConfigs to be selected for to merge and configure Alertmanager with. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + baseImage: + description: 'Base image that is used to deploy pods, without tag. Deprecated: use ''image'' instead' + type: string + clusterAdvertiseAddress: + description: 'ClusterAdvertiseAddress is the explicit address to advertise in cluster. Needs to be provided for non RFC1918 [1] (public) addresses. [1] RFC1918: https://tools.ietf.org/html/rfc1918' + type: string + clusterGossipInterval: + description: Interval between gossip attempts. + type: string + clusterPeerTimeout: + description: Timeout for cluster peering. + type: string + clusterPushpullInterval: + description: Interval between pushpull attempts. + type: string + configMaps: + description: ConfigMaps is a list of ConfigMaps in the same namespace as the Alertmanager object, which shall be mounted into the Alertmanager Pods. The ConfigMaps are mounted into /etc/alertmanager/configmaps/. + items: + type: string + type: array + configSecret: + description: ConfigSecret is the name of a Kubernetes Secret in the same namespace as the Alertmanager object, which contains configuration for this Alertmanager instance. Defaults to 'alertmanager-' The secret is mounted into /etc/alertmanager/config. + type: string + containers: + description: 'Containers allows injecting additional containers. This is meant to allow adding an authentication proxy to an Alertmanager pod. Containers described here modify an operator generated container if they share the same name and modifications are done via a strategic merge patch. The current container names are: `alertmanager` and `config-reloader`. Overriding containers is entirely outside the scope of what the maintainers will support and by doing so, you accept that this behaviour may break at any time without notice.' + items: + description: A single application container that you want to run within a pod. + properties: + args: + description: 'Arguments to the entrypoint. The docker image''s CMD is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + command: + description: 'Entrypoint array. Not executed within a shell. The docker image''s ENTRYPOINT is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + env: + description: List of environment variables to set in the container. Cannot be updated. + items: + description: EnvVar represents an environment variable present in a Container. + properties: + name: + description: Name of the environment variable. Must be a C_IDENTIFIER. + type: string + value: + description: 'Variable references $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "".' + type: string + valueFrom: + description: Source for the environment variable's value. Cannot be used if value is not empty. + properties: + configMapKeyRef: + description: Selects a key of a ConfigMap. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + fieldRef: + description: 'Selects a field of the pod: supports metadata.name, metadata.namespace, metadata.labels, metadata.annotations, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + secretKeyRef: + description: Selects a key of a secret in the pod's namespace + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + required: + - name + type: object + type: array + envFrom: + description: List of sources to populate environment variables in the container. The keys defined within a source must be a C_IDENTIFIER. All invalid keys will be reported as an event when the container is starting. When a key exists in multiple sources, the value associated with the last source will take precedence. Values defined by an Env with a duplicate key will take precedence. Cannot be updated. + items: + description: EnvFromSource represents the source of a set of ConfigMaps + properties: + configMapRef: + description: The ConfigMap to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap must be defined + type: boolean + type: object + prefix: + description: An optional identifier to prepend to each key in the ConfigMap. Must be a C_IDENTIFIER. + type: string + secretRef: + description: The Secret to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret must be defined + type: boolean + type: object + type: object + type: array + image: + description: 'Docker image name. More info: https://kubernetes.io/docs/concepts/containers/images This field is optional to allow higher level config management to default or override container images in workload controllers like Deployments and StatefulSets.' + type: string + imagePullPolicy: + description: 'Image pull policy. One of Always, Never, IfNotPresent. Defaults to Always if :latest tag is specified, or IfNotPresent otherwise. Cannot be updated. More info: https://kubernetes.io/docs/concepts/containers/images#updating-images' + type: string + lifecycle: + description: Actions that the management system should take in response to container lifecycle events. Cannot be updated. + properties: + postStart: + description: 'PostStart is called immediately after a container is created. If the handler fails, the container is terminated and restarted according to its restart policy. Other management of the container blocks until the hook completes. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + preStop: + description: 'PreStop is called immediately before a container is terminated due to an API request or management event such as liveness/startup probe failure, preemption, resource contention, etc. The handler is not called if the container crashes or exits. The reason for termination is passed to the handler. The Pod''s termination grace period countdown begins before the PreStop hooked is executed. Regardless of the outcome of the handler, the container will eventually terminate within the Pod''s termination grace period. Other management of the container blocks until the hook completes or until the termination grace period is reached. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + type: object + livenessProbe: + description: 'Periodic probe of container liveness. Container will be restarted if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + name: + description: Name of the container specified as a DNS_LABEL. Each container in a pod must have a unique name (DNS_LABEL). Cannot be updated. + type: string + ports: + description: List of ports to expose from the container. Exposing a port here gives the system additional information about the network connections a container uses, but is primarily informational. Not specifying a port here DOES NOT prevent that port from being exposed. Any port which is listening on the default "0.0.0.0" address inside a container will be accessible from the network. Cannot be updated. + items: + description: ContainerPort represents a network port in a single container. + properties: + containerPort: + description: Number of port to expose on the pod's IP address. This must be a valid port number, 0 < x < 65536. + format: int32 + type: integer + hostIP: + description: What host IP to bind the external port to. + type: string + hostPort: + description: Number of port to expose on the host. If specified, this must be a valid port number, 0 < x < 65536. If HostNetwork is specified, this must match ContainerPort. Most containers do not need this. + format: int32 + type: integer + name: + description: If specified, this must be an IANA_SVC_NAME and unique within the pod. Each named port in a pod must have a unique name. Name for the port that can be referred to by services. + type: string + protocol: + default: TCP + description: Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP". + type: string + required: + - containerPort + type: object + type: array + x-kubernetes-list-map-keys: + - containerPort + - protocol + x-kubernetes-list-type: map + readinessProbe: + description: 'Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + resources: + description: 'Compute Resources required by this container. Cannot be updated. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + type: object + securityContext: + description: 'Security options the pod should run with. More info: https://kubernetes.io/docs/concepts/policy/security-context/ More info: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/' + properties: + allowPrivilegeEscalation: + description: 'AllowPrivilegeEscalation controls whether a process can gain more privileges than its parent process. This bool directly controls if the no_new_privs flag will be set on the container process. AllowPrivilegeEscalation is true always when the container is: 1) run as Privileged 2) has CAP_SYS_ADMIN' + type: boolean + capabilities: + description: The capabilities to add/drop when running containers. Defaults to the default set of capabilities granted by the container runtime. + properties: + add: + description: Added capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + drop: + description: Removed capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + type: object + privileged: + description: Run container in privileged mode. Processes in privileged containers are essentially equivalent to root on the host. Defaults to false. + type: boolean + procMount: + description: procMount denotes the type of proc mount to use for the containers. The default is DefaultProcMount which uses the container runtime defaults for readonly paths and masked paths. This requires the ProcMountType feature flag to be enabled. + type: string + readOnlyRootFilesystem: + description: Whether this container has a read-only root filesystem. Default is false. + type: boolean + runAsGroup: + description: The GID to run the entrypoint of the container process. Uses runtime default if unset. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + format: int64 + type: integer + runAsNonRoot: + description: Indicates that the container must run as a non-root user. If true, the Kubelet will validate the image at runtime to ensure that it does not run as UID 0 (root) and fail to start the container if it does. If unset or false, no such validation will be performed. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: boolean + runAsUser: + description: The UID to run the entrypoint of the container process. Defaults to user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + format: int64 + type: integer + seLinuxOptions: + description: The SELinux context to be applied to the container. If unspecified, the container runtime will allocate a random SELinux context for each container. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + properties: + level: + description: Level is SELinux level label that applies to the container. + type: string + role: + description: Role is a SELinux role label that applies to the container. + type: string + type: + description: Type is a SELinux type label that applies to the container. + type: string + user: + description: User is a SELinux user label that applies to the container. + type: string + type: object + windowsOptions: + description: The Windows specific settings applied to all containers. If unspecified, the options from the PodSecurityContext will be used. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + properties: + gmsaCredentialSpec: + description: GMSACredentialSpec is where the GMSA admission webhook (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the GMSA credential spec named by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the GMSA credential spec to use. + type: string + runAsUserName: + description: The UserName in Windows to run the entrypoint of the container process. Defaults to the user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: string + type: object + type: object + startupProbe: + description: 'StartupProbe indicates that the Pod has successfully initialized. If specified, no other probes are executed until this completes successfully. If this probe fails, the Pod will be restarted, just as if the livenessProbe failed. This can be used to provide different probe parameters at the beginning of a Pod''s lifecycle, when it might take a long time to load data or warm a cache, than during steady-state operation. This cannot be updated. This is a beta feature enabled by the StartupProbe feature flag. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + stdin: + description: Whether this container should allocate a buffer for stdin in the container runtime. If this is not set, reads from stdin in the container will always result in EOF. Default is false. + type: boolean + stdinOnce: + description: Whether the container runtime should close the stdin channel after it has been opened by a single attach. When stdin is true the stdin stream will remain open across multiple attach sessions. If stdinOnce is set to true, stdin is opened on container start, is empty until the first client attaches to stdin, and then remains open and accepts data until the client disconnects, at which time stdin is closed and remains closed until the container is restarted. If this flag is false, a container processes that reads from stdin will never receive an EOF. Default is false + type: boolean + terminationMessagePath: + description: 'Optional: Path at which the file to which the container''s termination message will be written is mounted into the container''s filesystem. Message written is intended to be brief final status, such as an assertion failure message. Will be truncated by the node if greater than 4096 bytes. The total message length across all containers will be limited to 12kb. Defaults to /dev/termination-log. Cannot be updated.' + type: string + terminationMessagePolicy: + description: Indicate how the termination message should be populated. File will use the contents of terminationMessagePath to populate the container status message on both success and failure. FallbackToLogsOnError will use the last chunk of container log output if the termination message file is empty and the container exited with an error. The log output is limited to 2048 bytes or 80 lines, whichever is smaller. Defaults to File. Cannot be updated. + type: string + tty: + description: Whether this container should allocate a TTY for itself, also requires 'stdin' to be true. Default is false. + type: boolean + volumeDevices: + description: volumeDevices is the list of block devices to be used by the container. + items: + description: volumeDevice describes a mapping of a raw block device within a container. + properties: + devicePath: + description: devicePath is the path inside of the container that the device will be mapped to. + type: string + name: + description: name must match the name of a persistentVolumeClaim in the pod + type: string + required: + - devicePath + - name + type: object + type: array + volumeMounts: + description: Pod volumes to mount into the container's filesystem. Cannot be updated. + items: + description: VolumeMount describes a mounting of a Volume within a container. + properties: + mountPath: + description: Path within the container at which the volume should be mounted. Must not contain ':'. + type: string + mountPropagation: + description: mountPropagation determines how mounts are propagated from the host to container and the other way around. When not set, MountPropagationNone is used. This field is beta in 1.10. + type: string + name: + description: This must match the Name of a Volume. + type: string + readOnly: + description: Mounted read-only if true, read-write otherwise (false or unspecified). Defaults to false. + type: boolean + subPath: + description: Path within the volume from which the container's volume should be mounted. Defaults to "" (volume's root). + type: string + subPathExpr: + description: Expanded path within the volume from which the container's volume should be mounted. Behaves similarly to SubPath but environment variable references $(VAR_NAME) are expanded using the container's environment. Defaults to "" (volume's root). SubPathExpr and SubPath are mutually exclusive. + type: string + required: + - mountPath + - name + type: object + type: array + workingDir: + description: Container's working directory. If not specified, the container runtime's default will be used, which might be configured in the container image. Cannot be updated. + type: string + required: + - name + type: object + type: array + externalUrl: + description: The external URL the Alertmanager instances will be available under. This is necessary to generate correct URLs. This is necessary if Alertmanager is not served from root of a DNS name. + type: string + forceEnableClusterMode: + description: ForceEnableClusterMode ensures Alertmanager does not deactivate the cluster mode when running with a single replica. Use case is e.g. spanning an Alertmanager cluster across Kubernetes clusters with a single replica in each. + type: boolean + image: + description: Image if specified has precedence over baseImage, tag and sha combinations. Specifying the version is still necessary to ensure the Prometheus Operator knows what version of Alertmanager is being configured. + type: string + imagePullSecrets: + description: An optional list of references to secrets in the same namespace to use for pulling prometheus and alertmanager images from registries see http://kubernetes.io/docs/user-guide/images#specifying-imagepullsecrets-on-a-pod + items: + description: LocalObjectReference contains enough information to let you locate the referenced object inside the same namespace. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + type: array + initContainers: + description: 'InitContainers allows adding initContainers to the pod definition. Those can be used to e.g. fetch secrets for injection into the Alertmanager configuration from external sources. Any errors during the execution of an initContainer will lead to a restart of the Pod. More info: https://kubernetes.io/docs/concepts/workloads/pods/init-containers/ Using initContainers for any use case other then secret fetching is entirely outside the scope of what the maintainers will support and by doing so, you accept that this behaviour may break at any time without notice.' + items: + description: A single application container that you want to run within a pod. + properties: + args: + description: 'Arguments to the entrypoint. The docker image''s CMD is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + command: + description: 'Entrypoint array. Not executed within a shell. The docker image''s ENTRYPOINT is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + env: + description: List of environment variables to set in the container. Cannot be updated. + items: + description: EnvVar represents an environment variable present in a Container. + properties: + name: + description: Name of the environment variable. Must be a C_IDENTIFIER. + type: string + value: + description: 'Variable references $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "".' + type: string + valueFrom: + description: Source for the environment variable's value. Cannot be used if value is not empty. + properties: + configMapKeyRef: + description: Selects a key of a ConfigMap. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + fieldRef: + description: 'Selects a field of the pod: supports metadata.name, metadata.namespace, metadata.labels, metadata.annotations, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + secretKeyRef: + description: Selects a key of a secret in the pod's namespace + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + required: + - name + type: object + type: array + envFrom: + description: List of sources to populate environment variables in the container. The keys defined within a source must be a C_IDENTIFIER. All invalid keys will be reported as an event when the container is starting. When a key exists in multiple sources, the value associated with the last source will take precedence. Values defined by an Env with a duplicate key will take precedence. Cannot be updated. + items: + description: EnvFromSource represents the source of a set of ConfigMaps + properties: + configMapRef: + description: The ConfigMap to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap must be defined + type: boolean + type: object + prefix: + description: An optional identifier to prepend to each key in the ConfigMap. Must be a C_IDENTIFIER. + type: string + secretRef: + description: The Secret to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret must be defined + type: boolean + type: object + type: object + type: array + image: + description: 'Docker image name. More info: https://kubernetes.io/docs/concepts/containers/images This field is optional to allow higher level config management to default or override container images in workload controllers like Deployments and StatefulSets.' + type: string + imagePullPolicy: + description: 'Image pull policy. One of Always, Never, IfNotPresent. Defaults to Always if :latest tag is specified, or IfNotPresent otherwise. Cannot be updated. More info: https://kubernetes.io/docs/concepts/containers/images#updating-images' + type: string + lifecycle: + description: Actions that the management system should take in response to container lifecycle events. Cannot be updated. + properties: + postStart: + description: 'PostStart is called immediately after a container is created. If the handler fails, the container is terminated and restarted according to its restart policy. Other management of the container blocks until the hook completes. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + preStop: + description: 'PreStop is called immediately before a container is terminated due to an API request or management event such as liveness/startup probe failure, preemption, resource contention, etc. The handler is not called if the container crashes or exits. The reason for termination is passed to the handler. The Pod''s termination grace period countdown begins before the PreStop hooked is executed. Regardless of the outcome of the handler, the container will eventually terminate within the Pod''s termination grace period. Other management of the container blocks until the hook completes or until the termination grace period is reached. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + type: object + livenessProbe: + description: 'Periodic probe of container liveness. Container will be restarted if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + name: + description: Name of the container specified as a DNS_LABEL. Each container in a pod must have a unique name (DNS_LABEL). Cannot be updated. + type: string + ports: + description: List of ports to expose from the container. Exposing a port here gives the system additional information about the network connections a container uses, but is primarily informational. Not specifying a port here DOES NOT prevent that port from being exposed. Any port which is listening on the default "0.0.0.0" address inside a container will be accessible from the network. Cannot be updated. + items: + description: ContainerPort represents a network port in a single container. + properties: + containerPort: + description: Number of port to expose on the pod's IP address. This must be a valid port number, 0 < x < 65536. + format: int32 + type: integer + hostIP: + description: What host IP to bind the external port to. + type: string + hostPort: + description: Number of port to expose on the host. If specified, this must be a valid port number, 0 < x < 65536. If HostNetwork is specified, this must match ContainerPort. Most containers do not need this. + format: int32 + type: integer + name: + description: If specified, this must be an IANA_SVC_NAME and unique within the pod. Each named port in a pod must have a unique name. Name for the port that can be referred to by services. + type: string + protocol: + default: TCP + description: Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP". + type: string + required: + - containerPort + type: object + type: array + x-kubernetes-list-map-keys: + - containerPort + - protocol + x-kubernetes-list-type: map + readinessProbe: + description: 'Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + resources: + description: 'Compute Resources required by this container. Cannot be updated. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + type: object + securityContext: + description: 'Security options the pod should run with. More info: https://kubernetes.io/docs/concepts/policy/security-context/ More info: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/' + properties: + allowPrivilegeEscalation: + description: 'AllowPrivilegeEscalation controls whether a process can gain more privileges than its parent process. This bool directly controls if the no_new_privs flag will be set on the container process. AllowPrivilegeEscalation is true always when the container is: 1) run as Privileged 2) has CAP_SYS_ADMIN' + type: boolean + capabilities: + description: The capabilities to add/drop when running containers. Defaults to the default set of capabilities granted by the container runtime. + properties: + add: + description: Added capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + drop: + description: Removed capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + type: object + privileged: + description: Run container in privileged mode. Processes in privileged containers are essentially equivalent to root on the host. Defaults to false. + type: boolean + procMount: + description: procMount denotes the type of proc mount to use for the containers. The default is DefaultProcMount which uses the container runtime defaults for readonly paths and masked paths. This requires the ProcMountType feature flag to be enabled. + type: string + readOnlyRootFilesystem: + description: Whether this container has a read-only root filesystem. Default is false. + type: boolean + runAsGroup: + description: The GID to run the entrypoint of the container process. Uses runtime default if unset. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + format: int64 + type: integer + runAsNonRoot: + description: Indicates that the container must run as a non-root user. If true, the Kubelet will validate the image at runtime to ensure that it does not run as UID 0 (root) and fail to start the container if it does. If unset or false, no such validation will be performed. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: boolean + runAsUser: + description: The UID to run the entrypoint of the container process. Defaults to user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + format: int64 + type: integer + seLinuxOptions: + description: The SELinux context to be applied to the container. If unspecified, the container runtime will allocate a random SELinux context for each container. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + properties: + level: + description: Level is SELinux level label that applies to the container. + type: string + role: + description: Role is a SELinux role label that applies to the container. + type: string + type: + description: Type is a SELinux type label that applies to the container. + type: string + user: + description: User is a SELinux user label that applies to the container. + type: string + type: object + windowsOptions: + description: The Windows specific settings applied to all containers. If unspecified, the options from the PodSecurityContext will be used. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + properties: + gmsaCredentialSpec: + description: GMSACredentialSpec is where the GMSA admission webhook (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the GMSA credential spec named by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the GMSA credential spec to use. + type: string + runAsUserName: + description: The UserName in Windows to run the entrypoint of the container process. Defaults to the user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: string + type: object + type: object + startupProbe: + description: 'StartupProbe indicates that the Pod has successfully initialized. If specified, no other probes are executed until this completes successfully. If this probe fails, the Pod will be restarted, just as if the livenessProbe failed. This can be used to provide different probe parameters at the beginning of a Pod''s lifecycle, when it might take a long time to load data or warm a cache, than during steady-state operation. This cannot be updated. This is a beta feature enabled by the StartupProbe feature flag. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + stdin: + description: Whether this container should allocate a buffer for stdin in the container runtime. If this is not set, reads from stdin in the container will always result in EOF. Default is false. + type: boolean + stdinOnce: + description: Whether the container runtime should close the stdin channel after it has been opened by a single attach. When stdin is true the stdin stream will remain open across multiple attach sessions. If stdinOnce is set to true, stdin is opened on container start, is empty until the first client attaches to stdin, and then remains open and accepts data until the client disconnects, at which time stdin is closed and remains closed until the container is restarted. If this flag is false, a container processes that reads from stdin will never receive an EOF. Default is false + type: boolean + terminationMessagePath: + description: 'Optional: Path at which the file to which the container''s termination message will be written is mounted into the container''s filesystem. Message written is intended to be brief final status, such as an assertion failure message. Will be truncated by the node if greater than 4096 bytes. The total message length across all containers will be limited to 12kb. Defaults to /dev/termination-log. Cannot be updated.' + type: string + terminationMessagePolicy: + description: Indicate how the termination message should be populated. File will use the contents of terminationMessagePath to populate the container status message on both success and failure. FallbackToLogsOnError will use the last chunk of container log output if the termination message file is empty and the container exited with an error. The log output is limited to 2048 bytes or 80 lines, whichever is smaller. Defaults to File. Cannot be updated. + type: string + tty: + description: Whether this container should allocate a TTY for itself, also requires 'stdin' to be true. Default is false. + type: boolean + volumeDevices: + description: volumeDevices is the list of block devices to be used by the container. + items: + description: volumeDevice describes a mapping of a raw block device within a container. + properties: + devicePath: + description: devicePath is the path inside of the container that the device will be mapped to. + type: string + name: + description: name must match the name of a persistentVolumeClaim in the pod + type: string + required: + - devicePath + - name + type: object + type: array + volumeMounts: + description: Pod volumes to mount into the container's filesystem. Cannot be updated. + items: + description: VolumeMount describes a mounting of a Volume within a container. + properties: + mountPath: + description: Path within the container at which the volume should be mounted. Must not contain ':'. + type: string + mountPropagation: + description: mountPropagation determines how mounts are propagated from the host to container and the other way around. When not set, MountPropagationNone is used. This field is beta in 1.10. + type: string + name: + description: This must match the Name of a Volume. + type: string + readOnly: + description: Mounted read-only if true, read-write otherwise (false or unspecified). Defaults to false. + type: boolean + subPath: + description: Path within the volume from which the container's volume should be mounted. Defaults to "" (volume's root). + type: string + subPathExpr: + description: Expanded path within the volume from which the container's volume should be mounted. Behaves similarly to SubPath but environment variable references $(VAR_NAME) are expanded using the container's environment. Defaults to "" (volume's root). SubPathExpr and SubPath are mutually exclusive. + type: string + required: + - mountPath + - name + type: object + type: array + workingDir: + description: Container's working directory. If not specified, the container runtime's default will be used, which might be configured in the container image. Cannot be updated. + type: string + required: + - name + type: object + type: array + listenLocal: + description: ListenLocal makes the Alertmanager server listen on loopback, so that it does not bind against the Pod IP. Note this is only for the Alertmanager UI, not the gossip communication. + type: boolean + logFormat: + description: Log format for Alertmanager to be configured with. + type: string + logLevel: + description: Log level for Alertmanager to be configured with. + type: string + nodeSelector: + additionalProperties: + type: string + description: Define which Nodes the Pods are scheduled on. + type: object + paused: + description: If set to true all actions on the underlying managed objects are not goint to be performed, except for delete actions. + type: boolean + podMetadata: + description: PodMetadata configures Labels and Annotations which are propagated to the alertmanager pods. + properties: + annotations: + additionalProperties: + type: string + description: 'Annotations is an unstructured key value map stored with a resource that may be set by external tools to store and retrieve arbitrary metadata. They are not queryable and should be preserved when modifying objects. More info: http://kubernetes.io/docs/user-guide/annotations' + type: object + labels: + additionalProperties: + type: string + description: 'Map of string keys and values that can be used to organize and categorize (scope and select) objects. May match selectors of replication controllers and services. More info: http://kubernetes.io/docs/user-guide/labels' + type: object + name: + description: 'Name must be unique within a namespace. Is required when creating resources, although some resources may allow a client to request the generation of an appropriate name automatically. Name is primarily intended for creation idempotence and configuration definition. Cannot be updated. More info: http://kubernetes.io/docs/user-guide/identifiers#names' + type: string + type: object + portName: + description: Port name used for the pods and governing service. This defaults to web + type: string + priorityClassName: + description: Priority class assigned to the Pods + type: string + replicas: + description: Size is the expected size of the alertmanager cluster. The controller will eventually make the size of the running cluster equal to the expected size. + format: int32 + type: integer + resources: + description: Define resources requests and limits for single Pods. + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + type: object + retention: + description: Time duration Alertmanager shall retain data for. Default is '120h', and must match the regular expression `[0-9]+(ms|s|m|h)` (milliseconds seconds minutes hours). + type: string + routePrefix: + description: The route prefix Alertmanager registers HTTP handlers for. This is useful, if using ExternalURL and a proxy is rewriting HTTP routes of a request, and the actual ExternalURL is still true, but the server serves requests under a different route prefix. For example for use with `kubectl proxy`. + type: string + secrets: + description: Secrets is a list of Secrets in the same namespace as the Alertmanager object, which shall be mounted into the Alertmanager Pods. The Secrets are mounted into /etc/alertmanager/secrets/. + items: + type: string + type: array + securityContext: + description: SecurityContext holds pod-level security attributes and common container settings. This defaults to the default PodSecurityContext. + properties: + fsGroup: + description: "A special supplemental group that applies to all containers in a pod. Some volume types allow the Kubelet to change the ownership of that volume to be owned by the pod: \n 1. The owning GID will be the FSGroup 2. The setgid bit is set (new files created in the volume will be owned by FSGroup) 3. The permission bits are OR'd with rw-rw---- \n If unset, the Kubelet will not modify the ownership and permissions of any volume." + format: int64 + type: integer + fsGroupChangePolicy: + description: 'fsGroupChangePolicy defines behavior of changing ownership and permission of the volume before being exposed inside Pod. This field will only apply to volume types which support fsGroup based ownership(and permissions). It will have no effect on ephemeral volume types such as: secret, configmaps and emptydir. Valid values are "OnRootMismatch" and "Always". If not specified defaults to "Always".' + type: string + runAsGroup: + description: The GID to run the entrypoint of the container process. Uses runtime default if unset. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. + format: int64 + type: integer + runAsNonRoot: + description: Indicates that the container must run as a non-root user. If true, the Kubelet will validate the image at runtime to ensure that it does not run as UID 0 (root) and fail to start the container if it does. If unset or false, no such validation will be performed. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: boolean + runAsUser: + description: The UID to run the entrypoint of the container process. Defaults to user specified in image metadata if unspecified. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. + format: int64 + type: integer + seLinuxOptions: + description: The SELinux context to be applied to all containers. If unspecified, the container runtime will allocate a random SELinux context for each container. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. + properties: + level: + description: Level is SELinux level label that applies to the container. + type: string + role: + description: Role is a SELinux role label that applies to the container. + type: string + type: + description: Type is a SELinux type label that applies to the container. + type: string + user: + description: User is a SELinux user label that applies to the container. + type: string + type: object + supplementalGroups: + description: A list of groups applied to the first process run in each container, in addition to the container's primary GID. If unspecified, no groups will be added to any container. + items: + format: int64 + type: integer + type: array + sysctls: + description: Sysctls hold a list of namespaced sysctls used for the pod. Pods with unsupported sysctls (by the container runtime) might fail to launch. + items: + description: Sysctl defines a kernel parameter to be set + properties: + name: + description: Name of a property to set + type: string + value: + description: Value of a property to set + type: string + required: + - name + - value + type: object + type: array + windowsOptions: + description: The Windows specific settings applied to all containers. If unspecified, the options within a container's SecurityContext will be used. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + properties: + gmsaCredentialSpec: + description: GMSACredentialSpec is where the GMSA admission webhook (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the GMSA credential spec named by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the GMSA credential spec to use. + type: string + runAsUserName: + description: The UserName in Windows to run the entrypoint of the container process. Defaults to the user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: string + type: object + type: object + serviceAccountName: + description: ServiceAccountName is the name of the ServiceAccount to use to run the Prometheus Pods. + type: string + sha: + description: 'SHA of Alertmanager container image to be deployed. Defaults to the value of `version`. Similar to a tag, but the SHA explicitly deploys an immutable container image. Version and Tag are ignored if SHA is set. Deprecated: use ''image'' instead. The image digest can be specified as part of the image URL.' + type: string + storage: + description: Storage is the definition of how storage will be used by the Alertmanager instances. + properties: + disableMountSubPath: + description: 'Deprecated: subPath usage will be disabled by default in a future release, this option will become unnecessary. DisableMountSubPath allows to remove any subPath usage in volume mounts.' + type: boolean + emptyDir: + description: 'EmptyDirVolumeSource to be used by the Prometheus StatefulSets. If specified, used in place of any volumeClaimTemplate. More info: https://kubernetes.io/docs/concepts/storage/volumes/#emptydir' + properties: + medium: + description: 'What type of storage medium should back this directory. The default is "" which means to use the node''s default medium. Must be an empty string (default) or Memory. More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + type: string + sizeLimit: + anyOf: + - type: integer + - type: string + description: 'Total amount of local storage required for this EmptyDir volume. The size limit is also applicable for memory medium. The maximum usage on memory medium EmptyDir would be the minimum value between the SizeLimit specified here and the sum of memory limits of all containers in a pod. The default is nil which means that the limit is undefined. More info: http://kubernetes.io/docs/user-guide/volumes#emptydir' + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + volumeClaimTemplate: + description: A PVC spec to be used by the Prometheus StatefulSets. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + description: EmbeddedMetadata contains metadata relevant to an EmbeddedResource. + properties: + annotations: + additionalProperties: + type: string + description: 'Annotations is an unstructured key value map stored with a resource that may be set by external tools to store and retrieve arbitrary metadata. They are not queryable and should be preserved when modifying objects. More info: http://kubernetes.io/docs/user-guide/annotations' + type: object + labels: + additionalProperties: + type: string + description: 'Map of string keys and values that can be used to organize and categorize (scope and select) objects. May match selectors of replication controllers and services. More info: http://kubernetes.io/docs/user-guide/labels' + type: object + name: + description: 'Name must be unique within a namespace. Is required when creating resources, although some resources may allow a client to request the generation of an appropriate name automatically. Name is primarily intended for creation idempotence and configuration definition. Cannot be updated. More info: http://kubernetes.io/docs/user-guide/identifiers#names' + type: string + type: object + spec: + description: 'Spec defines the desired characteristics of a volume requested by a pod author. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + properties: + accessModes: + description: 'AccessModes contains the desired access modes the volume should have. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#access-modes-1' + items: + type: string + type: array + dataSource: + description: 'This field can be used to specify either: * An existing VolumeSnapshot object (snapshot.storage.k8s.io/VolumeSnapshot - Beta) * An existing PVC (PersistentVolumeClaim) * An existing custom resource/object that implements data population (Alpha) In order to use VolumeSnapshot object types, the appropriate feature gate must be enabled (VolumeSnapshotDataSource or AnyVolumeDataSource) If the provisioner or an external controller can support the specified data source, it will create a new volume based on the contents of the specified data source. If the specified data source is not supported, the volume will not be created and the failure will be reported as an event. In the future, we plan to support more data source types and the behavior of the provisioner may change.' + properties: + apiGroup: + description: APIGroup is the group for the resource being referenced. If APIGroup is not specified, the specified Kind must be in the core API group. For any other third-party types, APIGroup is required. + type: string + kind: + description: Kind is the type of resource being referenced + type: string + name: + description: Name is the name of resource being referenced + type: string + required: + - kind + - name + type: object + resources: + description: 'Resources represents the minimum resources the volume should have. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#resources' + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + type: object + selector: + description: A label query over volumes to consider for binding. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + storageClassName: + description: 'Name of the StorageClass required by the claim. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#class-1' + type: string + volumeMode: + description: volumeMode defines what type of volume is required by the claim. Value of Filesystem is implied when not included in claim spec. + type: string + volumeName: + description: VolumeName is the binding reference to the PersistentVolume backing this claim. + type: string + type: object + status: + description: 'Status represents the current information/status of a persistent volume claim. Read-only. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + properties: + accessModes: + description: 'AccessModes contains the actual access modes the volume backing the PVC has. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#access-modes-1' + items: + type: string + type: array + capacity: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: Represents the actual resources of the underlying volume. + type: object + conditions: + description: Current Condition of persistent volume claim. If underlying persistent volume is being resized then the Condition will be set to 'ResizeStarted'. + items: + description: PersistentVolumeClaimCondition contails details about state of pvc + properties: + lastProbeTime: + description: Last time we probed the condition. + format: date-time + type: string + lastTransitionTime: + description: Last time the condition transitioned from one status to another. + format: date-time + type: string + message: + description: Human-readable message indicating details about last transition. + type: string + reason: + description: Unique, this should be a short, machine understandable string that gives the reason for condition's last transition. If it reports "ResizeStarted" that means the underlying persistent volume is being resized. + type: string + status: + type: string + type: + description: PersistentVolumeClaimConditionType is a valid value of PersistentVolumeClaimCondition.Type + type: string + required: + - status + - type + type: object + type: array + phase: + description: Phase represents the current phase of PersistentVolumeClaim. + type: string + type: object + type: object + type: object + tag: + description: 'Tag of Alertmanager container image to be deployed. Defaults to the value of `version`. Version is ignored if Tag is set. Deprecated: use ''image'' instead. The image tag can be specified as part of the image URL.' + type: string + tolerations: + description: If specified, the pod's tolerations. + items: + description: The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . + properties: + effect: + description: Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. + type: string + key: + description: Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. + type: string + operator: + description: Operator represents a key's relationship to the value. Valid operators are Exists and Equal. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. + type: string + tolerationSeconds: + description: TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. + format: int64 + type: integer + value: + description: Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. + type: string + type: object + type: array + topologySpreadConstraints: + description: If specified, the pod's topology spread constraints. + items: + description: TopologySpreadConstraint specifies how to spread matching pods among the given topology. + properties: + labelSelector: + description: LabelSelector is used to find matching pods. Pods that match this label selector are counted to determine the number of pods in their corresponding topology domain. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + maxSkew: + description: 'MaxSkew describes the degree to which pods may be unevenly distributed. It''s the maximum permitted difference between the number of matching pods in any two topology domains of a given topology type. For example, in a 3-zone cluster, MaxSkew is set to 1, and pods with the same labelSelector spread as 1/1/0: | zone1 | zone2 | zone3 | | P | P | | - if MaxSkew is 1, incoming pod can only be scheduled to zone3 to become 1/1/1; scheduling it onto zone1(zone2) would make the ActualSkew(2-0) on zone1(zone2) violate MaxSkew(1). - if MaxSkew is 2, incoming pod can be scheduled onto any zone. It''s a required field. Default value is 1 and 0 is not allowed.' + format: int32 + type: integer + topologyKey: + description: TopologyKey is the key of node labels. Nodes that have a label with this key and identical values are considered to be in the same topology. We consider each as a "bucket", and try to put balanced number of pods into each bucket. It's a required field. + type: string + whenUnsatisfiable: + description: 'WhenUnsatisfiable indicates how to deal with a pod if it doesn''t satisfy the spread constraint. - DoNotSchedule (default) tells the scheduler not to schedule it - ScheduleAnyway tells the scheduler to still schedule it It''s considered as "Unsatisfiable" if and only if placing incoming pod on any topology violates "MaxSkew". For example, in a 3-zone cluster, MaxSkew is set to 1, and pods with the same labelSelector spread as 3/1/1: | zone1 | zone2 | zone3 | | P P P | P | P | If WhenUnsatisfiable is set to DoNotSchedule, incoming pod can only be scheduled to zone2(zone3) to become 3/2/1(3/1/2) as ActualSkew(2-1) on zone2(zone3) satisfies MaxSkew(1). In other words, the cluster can still be imbalanced, but scheduler won''t make it *more* imbalanced. It''s a required field.' + type: string + required: + - maxSkew + - topologyKey + - whenUnsatisfiable + type: object + type: array + version: + description: Version the cluster should be on. + type: string + volumeMounts: + description: VolumeMounts allows configuration of additional VolumeMounts on the output StatefulSet definition. VolumeMounts specified will be appended to other VolumeMounts in the alertmanager container, that are generated as a result of StorageSpec objects. + items: + description: VolumeMount describes a mounting of a Volume within a container. + properties: + mountPath: + description: Path within the container at which the volume should be mounted. Must not contain ':'. + type: string + mountPropagation: + description: mountPropagation determines how mounts are propagated from the host to container and the other way around. When not set, MountPropagationNone is used. This field is beta in 1.10. + type: string + name: + description: This must match the Name of a Volume. + type: string + readOnly: + description: Mounted read-only if true, read-write otherwise (false or unspecified). Defaults to false. + type: boolean + subPath: + description: Path within the volume from which the container's volume should be mounted. Defaults to "" (volume's root). + type: string + subPathExpr: + description: Expanded path within the volume from which the container's volume should be mounted. Behaves similarly to SubPath but environment variable references $(VAR_NAME) are expanded using the container's environment. Defaults to "" (volume's root). SubPathExpr and SubPath are mutually exclusive. + type: string + required: + - mountPath + - name + type: object + type: array + volumes: + description: Volumes allows configuration of additional volumes on the output StatefulSet definition. Volumes specified will be appended to other volumes that are generated as a result of StorageSpec objects. + items: + description: Volume represents a named volume in a pod that may be accessed by any container in the pod. + properties: + awsElasticBlockStore: + description: 'AWSElasticBlockStore represents an AWS Disk resource that is attached to a kubelet''s host machine and then exposed to the pod. More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + properties: + fsType: + description: 'Filesystem type of the volume that you want to mount. Tip: Ensure that the filesystem type is supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + partition: + description: 'The partition in the volume that you want to mount. If omitted, the default is to mount by volume name. Examples: For volume /dev/sda1, you specify the partition as "1". Similarly, the volume partition for /dev/sda is "0" (or you can leave the property empty).' + format: int32 + type: integer + readOnly: + description: 'Specify "true" to force and set the ReadOnly property in VolumeMounts to "true". If omitted, the default is "false". More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + type: boolean + volumeID: + description: 'Unique ID of the persistent disk resource in AWS (Amazon EBS volume). More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + type: string + required: + - volumeID + type: object + azureDisk: + description: AzureDisk represents an Azure Data Disk mount on the host and bind mount to the pod. + properties: + cachingMode: + description: 'Host Caching mode: None, Read Only, Read Write.' + type: string + diskName: + description: The Name of the data disk in the blob storage + type: string + diskURI: + description: The URI the data disk in the blob storage + type: string + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + kind: + description: 'Expected values Shared: multiple blob disks per storage account Dedicated: single blob disk per storage account Managed: azure managed data disk (only in managed availability set). defaults to shared' + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + required: + - diskName + - diskURI + type: object + azureFile: + description: AzureFile represents an Azure File Service mount on the host and bind mount to the pod. + properties: + readOnly: + description: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + secretName: + description: the name of secret that contains Azure Storage Account Name and Key + type: string + shareName: + description: Share Name + type: string + required: + - secretName + - shareName + type: object + cephfs: + description: CephFS represents a Ceph FS mount on the host that shares a pod's lifetime + properties: + monitors: + description: 'Required: Monitors is a collection of Ceph monitors More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + items: + type: string + type: array + path: + description: 'Optional: Used as the mounted root, rather than the full Ceph tree, default is /' + type: string + readOnly: + description: 'Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: boolean + secretFile: + description: 'Optional: SecretFile is the path to key ring for User, default is /etc/ceph/user.secret More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: string + secretRef: + description: 'Optional: SecretRef is reference to the authentication secret for User, default is empty. More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + user: + description: 'Optional: User is the rados user name, default is admin More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: string + required: + - monitors + type: object + cinder: + description: 'Cinder represents a cinder volume attached and mounted on kubelets host machine. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + properties: + fsType: + description: 'Filesystem type to mount. Must be a filesystem type supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: string + readOnly: + description: 'Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: boolean + secretRef: + description: 'Optional: points to a secret object containing parameters used to connect to OpenStack.' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + volumeID: + description: 'volume id used to identify the volume in cinder. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: string + required: + - volumeID + type: object + configMap: + description: ConfigMap represents a configMap that should populate this volume + properties: + defaultMode: + description: 'Optional: mode bits to use on created files by default. Must be a value between 0 and 0777. Defaults to 0644. Directories within the path are not affected by this setting. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + items: + description: If unspecified, each key-value pair in the Data field of the referenced ConfigMap will be projected into the volume as a file whose name is the key and content is the value. If specified, the listed keys will be projected into the specified paths, and unlisted keys will not be present. If a key is specified which is not present in the ConfigMap, the volume setup will error unless it is marked optional. Paths must be relative and may not contain the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file to map the key to. May not be an absolute path. May not contain the path element '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its keys must be defined + type: boolean + type: object + csi: + description: CSI (Container Storage Interface) represents storage that is handled by an external CSI driver (Alpha feature). + properties: + driver: + description: Driver is the name of the CSI driver that handles this volume. Consult with your admin for the correct name as registered in the cluster. + type: string + fsType: + description: Filesystem type to mount. Ex. "ext4", "xfs", "ntfs". If not provided, the empty value is passed to the associated CSI driver which will determine the default filesystem to apply. + type: string + nodePublishSecretRef: + description: NodePublishSecretRef is a reference to the secret object containing sensitive information to pass to the CSI driver to complete the CSI NodePublishVolume and NodeUnpublishVolume calls. This field is optional, and may be empty if no secret is required. If the secret object contains more than one secret, all secret references are passed. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + readOnly: + description: Specifies a read-only configuration for the volume. Defaults to false (read/write). + type: boolean + volumeAttributes: + additionalProperties: + type: string + description: VolumeAttributes stores driver-specific properties that are passed to the CSI driver. Consult your driver's documentation for supported values. + type: object + required: + - driver + type: object + downwardAPI: + description: DownwardAPI represents downward API about the pod that should populate this volume + properties: + defaultMode: + description: 'Optional: mode bits to use on created files by default. Must be a value between 0 and 0777. Defaults to 0644. Directories within the path are not affected by this setting. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + items: + description: Items is a list of downward API volume file + items: + description: DownwardAPIVolumeFile represents information to create the file containing the pod field + properties: + fieldRef: + description: 'Required: Selects a field of the pod: only annotations, labels, name and namespace are supported.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: 'Required: Path is the relative path name of the file to be created. Must not be absolute or contain the ''..'' path. Must be utf-8 encoded. The first item of the relative path must not start with ''..''' + type: string + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, requests.cpu and requests.memory) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + required: + - path + type: object + type: array + type: object + emptyDir: + description: 'EmptyDir represents a temporary directory that shares a pod''s lifetime. More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + properties: + medium: + description: 'What type of storage medium should back this directory. The default is "" which means to use the node''s default medium. Must be an empty string (default) or Memory. More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + type: string + sizeLimit: + anyOf: + - type: integer + - type: string + description: 'Total amount of local storage required for this EmptyDir volume. The size limit is also applicable for memory medium. The maximum usage on memory medium EmptyDir would be the minimum value between the SizeLimit specified here and the sum of memory limits of all containers in a pod. The default is nil which means that the limit is undefined. More info: http://kubernetes.io/docs/user-guide/volumes#emptydir' + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + fc: + description: FC represents a Fibre Channel resource that is attached to a kubelet's host machine and then exposed to the pod. + properties: + fsType: + description: 'Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + lun: + description: 'Optional: FC target lun number' + format: int32 + type: integer + readOnly: + description: 'Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts.' + type: boolean + targetWWNs: + description: 'Optional: FC target worldwide names (WWNs)' + items: + type: string + type: array + wwids: + description: 'Optional: FC volume world wide identifiers (wwids) Either wwids or combination of targetWWNs and lun must be set, but not both simultaneously.' + items: + type: string + type: array + type: object + flexVolume: + description: FlexVolume represents a generic volume resource that is provisioned/attached using an exec based plugin. + properties: + driver: + description: Driver is the name of the driver to use for this volume. + type: string + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". The default filesystem depends on FlexVolume script. + type: string + options: + additionalProperties: + type: string + description: 'Optional: Extra command options if any.' + type: object + readOnly: + description: 'Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts.' + type: boolean + secretRef: + description: 'Optional: SecretRef is reference to the secret object containing sensitive information to pass to the plugin scripts. This may be empty if no secret object is specified. If the secret object contains more than one secret, all secrets are passed to the plugin scripts.' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + required: + - driver + type: object + flocker: + description: Flocker represents a Flocker volume attached to a kubelet's host machine. This depends on the Flocker control service being running + properties: + datasetName: + description: Name of the dataset stored as metadata -> name on the dataset for Flocker should be considered as deprecated + type: string + datasetUUID: + description: UUID of the dataset. This is unique identifier of a Flocker dataset + type: string + type: object + gcePersistentDisk: + description: 'GCEPersistentDisk represents a GCE Disk resource that is attached to a kubelet''s host machine and then exposed to the pod. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + properties: + fsType: + description: 'Filesystem type of the volume that you want to mount. Tip: Ensure that the filesystem type is supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + partition: + description: 'The partition in the volume that you want to mount. If omitted, the default is to mount by volume name. Examples: For volume /dev/sda1, you specify the partition as "1". Similarly, the volume partition for /dev/sda is "0" (or you can leave the property empty). More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + format: int32 + type: integer + pdName: + description: 'Unique name of the PD resource in GCE. Used to identify the disk in GCE. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + type: string + readOnly: + description: 'ReadOnly here will force the ReadOnly setting in VolumeMounts. Defaults to false. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + type: boolean + required: + - pdName + type: object + gitRepo: + description: 'GitRepo represents a git repository at a particular revision. DEPRECATED: GitRepo is deprecated. To provision a container with a git repo, mount an EmptyDir into an InitContainer that clones the repo using git, then mount the EmptyDir into the Pod''s container.' + properties: + directory: + description: Target directory name. Must not contain or start with '..'. If '.' is supplied, the volume directory will be the git repository. Otherwise, if specified, the volume will contain the git repository in the subdirectory with the given name. + type: string + repository: + description: Repository URL + type: string + revision: + description: Commit hash for the specified revision. + type: string + required: + - repository + type: object + glusterfs: + description: 'Glusterfs represents a Glusterfs mount on the host that shares a pod''s lifetime. More info: https://examples.k8s.io/volumes/glusterfs/README.md' + properties: + endpoints: + description: 'EndpointsName is the endpoint name that details Glusterfs topology. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: string + path: + description: 'Path is the Glusterfs volume path. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: string + readOnly: + description: 'ReadOnly here will force the Glusterfs volume to be mounted with read-only permissions. Defaults to false. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: boolean + required: + - endpoints + - path + type: object + hostPath: + description: 'HostPath represents a pre-existing file or directory on the host machine that is directly exposed to the container. This is generally used for system agents or other privileged things that are allowed to see the host machine. Most containers will NOT need this. More info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath --- TODO(jonesdl) We need to restrict who can use host directory mounts and who can/can not mount host directories as read/write.' + properties: + path: + description: 'Path of the directory on the host. If the path is a symlink, it will follow the link to the real path. More info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath' + type: string + type: + description: 'Type for HostPath Volume Defaults to "" More info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath' + type: string + required: + - path + type: object + iscsi: + description: 'ISCSI represents an ISCSI Disk resource that is attached to a kubelet''s host machine and then exposed to the pod. More info: https://examples.k8s.io/volumes/iscsi/README.md' + properties: + chapAuthDiscovery: + description: whether support iSCSI Discovery CHAP authentication + type: boolean + chapAuthSession: + description: whether support iSCSI Session CHAP authentication + type: boolean + fsType: + description: 'Filesystem type of the volume that you want to mount. Tip: Ensure that the filesystem type is supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://kubernetes.io/docs/concepts/storage/volumes#iscsi TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + initiatorName: + description: Custom iSCSI Initiator Name. If initiatorName is specified with iscsiInterface simultaneously, new iSCSI interface : will be created for the connection. + type: string + iqn: + description: Target iSCSI Qualified Name. + type: string + iscsiInterface: + description: iSCSI Interface Name that uses an iSCSI transport. Defaults to 'default' (tcp). + type: string + lun: + description: iSCSI Target Lun number. + format: int32 + type: integer + portals: + description: iSCSI Target Portal List. The portal is either an IP or ip_addr:port if the port is other than default (typically TCP ports 860 and 3260). + items: + type: string + type: array + readOnly: + description: ReadOnly here will force the ReadOnly setting in VolumeMounts. Defaults to false. + type: boolean + secretRef: + description: CHAP Secret for iSCSI target and initiator authentication + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + targetPortal: + description: iSCSI Target Portal. The Portal is either an IP or ip_addr:port if the port is other than default (typically TCP ports 860 and 3260). + type: string + required: + - iqn + - lun + - targetPortal + type: object + name: + description: 'Volume''s name. Must be a DNS_LABEL and unique within the pod. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + nfs: + description: 'NFS represents an NFS mount on the host that shares a pod''s lifetime More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + properties: + path: + description: 'Path that is exported by the NFS server. More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: string + readOnly: + description: 'ReadOnly here will force the NFS export to be mounted with read-only permissions. Defaults to false. More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: boolean + server: + description: 'Server is the hostname or IP address of the NFS server. More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: string + required: + - path + - server + type: object + persistentVolumeClaim: + description: 'PersistentVolumeClaimVolumeSource represents a reference to a PersistentVolumeClaim in the same namespace. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + properties: + claimName: + description: 'ClaimName is the name of a PersistentVolumeClaim in the same namespace as the pod using this volume. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + type: string + readOnly: + description: Will force the ReadOnly setting in VolumeMounts. Default false. + type: boolean + required: + - claimName + type: object + photonPersistentDisk: + description: PhotonPersistentDisk represents a PhotonController persistent disk attached and mounted on kubelets host machine + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + pdID: + description: ID that identifies Photon Controller persistent disk + type: string + required: + - pdID + type: object + portworxVolume: + description: PortworxVolume represents a portworx volume attached and mounted on kubelets host machine + properties: + fsType: + description: FSType represents the filesystem type to mount Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs". Implicitly inferred to be "ext4" if unspecified. + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + volumeID: + description: VolumeID uniquely identifies a Portworx volume + type: string + required: + - volumeID + type: object + projected: + description: Items for all in one resources secrets, configmaps, and downward API + properties: + defaultMode: + description: Mode bits to use on created files by default. Must be a value between 0 and 0777. Directories within the path are not affected by this setting. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set. + format: int32 + type: integer + sources: + description: list of volume projections + items: + description: Projection that may be projected along with other supported volume types + properties: + configMap: + description: information about the configMap data to project + properties: + items: + description: If unspecified, each key-value pair in the Data field of the referenced ConfigMap will be projected into the volume as a file whose name is the key and content is the value. If specified, the listed keys will be projected into the specified paths, and unlisted keys will not be present. If a key is specified which is not present in the ConfigMap, the volume setup will error unless it is marked optional. Paths must be relative and may not contain the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file to map the key to. May not be an absolute path. May not contain the path element '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its keys must be defined + type: boolean + type: object + downwardAPI: + description: information about the downwardAPI data to project + properties: + items: + description: Items is a list of DownwardAPIVolume file + items: + description: DownwardAPIVolumeFile represents information to create the file containing the pod field + properties: + fieldRef: + description: 'Required: Selects a field of the pod: only annotations, labels, name and namespace are supported.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: 'Required: Path is the relative path name of the file to be created. Must not be absolute or contain the ''..'' path. Must be utf-8 encoded. The first item of the relative path must not start with ''..''' + type: string + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, requests.cpu and requests.memory) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + required: + - path + type: object + type: array + type: object + secret: + description: information about the secret data to project + properties: + items: + description: If unspecified, each key-value pair in the Data field of the referenced Secret will be projected into the volume as a file whose name is the key and content is the value. If specified, the listed keys will be projected into the specified paths, and unlisted keys will not be present. If a key is specified which is not present in the Secret, the volume setup will error unless it is marked optional. Paths must be relative and may not contain the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file to map the key to. May not be an absolute path. May not contain the path element '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + type: object + serviceAccountToken: + description: information about the serviceAccountToken data to project + properties: + audience: + description: Audience is the intended audience of the token. A recipient of a token must identify itself with an identifier specified in the audience of the token, and otherwise should reject the token. The audience defaults to the identifier of the apiserver. + type: string + expirationSeconds: + description: ExpirationSeconds is the requested duration of validity of the service account token. As the token approaches expiration, the kubelet volume plugin will proactively rotate the service account token. The kubelet will start trying to rotate the token if the token is older than 80 percent of its time to live or if the token is older than 24 hours.Defaults to 1 hour and must be at least 10 minutes. + format: int64 + type: integer + path: + description: Path is the path relative to the mount point of the file to project the token into. + type: string + required: + - path + type: object + type: object + type: array + required: + - sources + type: object + quobyte: + description: Quobyte represents a Quobyte mount on the host that shares a pod's lifetime + properties: + group: + description: Group to map volume access to Default is no group + type: string + readOnly: + description: ReadOnly here will force the Quobyte volume to be mounted with read-only permissions. Defaults to false. + type: boolean + registry: + description: Registry represents a single or multiple Quobyte Registry services specified as a string as host:port pair (multiple entries are separated with commas) which acts as the central registry for volumes + type: string + tenant: + description: Tenant owning the given Quobyte volume in the Backend Used with dynamically provisioned Quobyte volumes, value is set by the plugin + type: string + user: + description: User to map volume access to Defaults to serivceaccount user + type: string + volume: + description: Volume is a string that references an already created Quobyte volume by name. + type: string + required: + - registry + - volume + type: object + rbd: + description: 'RBD represents a Rados Block Device mount on the host that shares a pod''s lifetime. More info: https://examples.k8s.io/volumes/rbd/README.md' + properties: + fsType: + description: 'Filesystem type of the volume that you want to mount. Tip: Ensure that the filesystem type is supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://kubernetes.io/docs/concepts/storage/volumes#rbd TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + image: + description: 'The rados image name. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + keyring: + description: 'Keyring is the path to key ring for RBDUser. Default is /etc/ceph/keyring. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + monitors: + description: 'A collection of Ceph monitors. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + items: + type: string + type: array + pool: + description: 'The rados pool name. Default is rbd. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + readOnly: + description: 'ReadOnly here will force the ReadOnly setting in VolumeMounts. Defaults to false. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: boolean + secretRef: + description: 'SecretRef is name of the authentication secret for RBDUser. If provided overrides keyring. Default is nil. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + user: + description: 'The rados user name. Default is admin. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + required: + - image + - monitors + type: object + scaleIO: + description: ScaleIO represents a ScaleIO persistent volume attached and mounted on Kubernetes nodes. + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Default is "xfs". + type: string + gateway: + description: The host address of the ScaleIO API Gateway. + type: string + protectionDomain: + description: The name of the ScaleIO Protection Domain for the configured storage. + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + secretRef: + description: SecretRef references to the secret for ScaleIO user and other sensitive information. If this is not provided, Login operation will fail. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + sslEnabled: + description: Flag to enable/disable SSL communication with Gateway, default false + type: boolean + storageMode: + description: Indicates whether the storage for a volume should be ThickProvisioned or ThinProvisioned. Default is ThinProvisioned. + type: string + storagePool: + description: The ScaleIO Storage Pool associated with the protection domain. + type: string + system: + description: The name of the storage system as configured in ScaleIO. + type: string + volumeName: + description: The name of a volume already created in the ScaleIO system that is associated with this volume source. + type: string + required: + - gateway + - secretRef + - system + type: object + secret: + description: 'Secret represents a secret that should populate this volume. More info: https://kubernetes.io/docs/concepts/storage/volumes#secret' + properties: + defaultMode: + description: 'Optional: mode bits to use on created files by default. Must be a value between 0 and 0777. Defaults to 0644. Directories within the path are not affected by this setting. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + items: + description: If unspecified, each key-value pair in the Data field of the referenced Secret will be projected into the volume as a file whose name is the key and content is the value. If specified, the listed keys will be projected into the specified paths, and unlisted keys will not be present. If a key is specified which is not present in the Secret, the volume setup will error unless it is marked optional. Paths must be relative and may not contain the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file to map the key to. May not be an absolute path. May not contain the path element '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + optional: + description: Specify whether the Secret or its keys must be defined + type: boolean + secretName: + description: 'Name of the secret in the pod''s namespace to use. More info: https://kubernetes.io/docs/concepts/storage/volumes#secret' + type: string + type: object + storageos: + description: StorageOS represents a StorageOS volume attached and mounted on Kubernetes nodes. + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + secretRef: + description: SecretRef specifies the secret to use for obtaining the StorageOS API credentials. If not specified, default values will be attempted. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + volumeName: + description: VolumeName is the human-readable name of the StorageOS volume. Volume names are only unique within a namespace. + type: string + volumeNamespace: + description: VolumeNamespace specifies the scope of the volume within StorageOS. If no namespace is specified then the Pod's namespace will be used. This allows the Kubernetes name scoping to be mirrored within StorageOS for tighter integration. Set VolumeName to any name to override the default behaviour. Set to "default" if you are not using namespaces within StorageOS. Namespaces that do not pre-exist within StorageOS will be created. + type: string + type: object + vsphereVolume: + description: VsphereVolume represents a vSphere volume attached and mounted on kubelets host machine + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + storagePolicyID: + description: Storage Policy Based Management (SPBM) profile ID associated with the StoragePolicyName. + type: string + storagePolicyName: + description: Storage Policy Based Management (SPBM) profile name. + type: string + volumePath: + description: Path that identifies vSphere volume vmdk + type: string + required: + - volumePath + type: object + required: + - name + type: object + type: array + type: object + status: + description: 'Most recent observed status of the Alertmanager cluster. Read-only. Not included when requesting from the apiserver, only from the Prometheus Operator API itself. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#spec-and-status' + properties: + availableReplicas: + description: Total number of available pods (ready for at least minReadySeconds) targeted by this Alertmanager cluster. + format: int32 + type: integer + paused: + description: Represents whether any actions on the underlying managed objects are being performed. Only delete actions will be performed. + type: boolean + replicas: + description: Total number of non-terminated pods targeted by this Alertmanager cluster (their labels match the selector). + format: int32 + type: integer + unavailableReplicas: + description: Total number of unavailable pods targeted by this Alertmanager cluster. + format: int32 + type: integer + updatedReplicas: + description: Total number of non-terminated pods targeted by this Alertmanager cluster that have the desired version spec. + format: int32 + type: integer + required: + - availableReplicas + - paused + - replicas + - unavailableReplicas + - updatedReplicas + type: object + required: + - spec + type: object + served: true + storage: true + subresources: {} +status: + acceptedNames: + kind: "" + plural: "" + conditions: [] + storedVersions: [] diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-podmonitors.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-podmonitors.yaml new file mode 100644 index 00000000..630465b8 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-podmonitors.yaml @@ -0,0 +1,356 @@ +# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.44.0/example/prometheus-operator-crd/monitoring.coreos.com_podmonitors.yaml + +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.4.1 + creationTimestamp: null + name: podmonitors.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + kind: PodMonitor + listKind: PodMonitorList + plural: podmonitors + singular: podmonitor + scope: Namespaced + versions: + - name: v1 + schema: + openAPIV3Schema: + description: PodMonitor defines monitoring for a set of pods. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Specification of desired Pod selection for target discovery by Prometheus. + properties: + jobLabel: + description: The label to use to retrieve the job name from. + type: string + namespaceSelector: + description: Selector to select which namespaces the Endpoints objects are discovered from. + properties: + any: + description: Boolean describing whether all namespaces are selected in contrast to a list restricting them. + type: boolean + matchNames: + description: List of namespace names. + items: + type: string + type: array + type: object + podMetricsEndpoints: + description: A list of endpoints allowed as part of this PodMonitor. + items: + description: PodMetricsEndpoint defines a scrapeable endpoint of a Kubernetes Pod serving Prometheus metrics. + properties: + basicAuth: + description: 'BasicAuth allow an endpoint to authenticate over basic authentication. More info: https://prometheus.io/docs/operating/configuration/#endpoint' + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + bearerTokenSecret: + description: Secret to mount to read bearer token for scraping targets. The secret needs to be in the same namespace as the pod monitor and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + honorLabels: + description: HonorLabels chooses the metric's labels on collisions with target labels. + type: boolean + honorTimestamps: + description: HonorTimestamps controls whether Prometheus respects the timestamps present in scraped data. + type: boolean + interval: + description: Interval at which metrics should be scraped + type: string + metricRelabelings: + description: MetricRelabelConfigs to apply to samples before ingestion. + items: + description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines ``-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + description: Action to perform based on regex matching. Default is 'replace' + type: string + modulus: + description: Modulus to take of the hash of the source label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions. + items: + type: string + type: array + targetLabel: + description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available. + type: string + type: object + type: array + params: + additionalProperties: + items: + type: string + type: array + description: Optional HTTP URL parameters + type: object + path: + description: HTTP path to scrape for metrics. + type: string + port: + description: Name of the pod port this endpoint refers to. Mutually exclusive with targetPort. + type: string + proxyUrl: + description: ProxyURL eg http://proxyserver:2195 Directs scrapes to proxy through this endpoint. + type: string + relabelings: + description: 'RelabelConfigs to apply to samples before ingestion. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config' + items: + description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines ``-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + description: Action to perform based on regex matching. Default is 'replace' + type: string + modulus: + description: Modulus to take of the hash of the source label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions. + items: + type: string + type: array + targetLabel: + description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available. + type: string + type: object + type: array + scheme: + description: HTTP scheme to use for scraping. + type: string + scrapeTimeout: + description: Timeout after which the scrape is ended + type: string + targetPort: + anyOf: + - type: integer + - type: string + description: 'Deprecated: Use ''port'' instead.' + x-kubernetes-int-or-string: true + tlsConfig: + description: TLS configuration to use when scraping the endpoint. + properties: + ca: + description: Struct containing the CA cert to use for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + cert: + description: Struct containing the client cert file for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + type: array + podTargetLabels: + description: PodTargetLabels transfers labels on the Kubernetes Pod onto the target. + items: + type: string + type: array + sampleLimit: + description: SampleLimit defines per-scrape limit on number of scraped samples that will be accepted. + format: int64 + type: integer + selector: + description: Selector to select Pod objects. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + targetLimit: + description: TargetLimit defines a limit on the number of scraped targets that will be accepted. + format: int64 + type: integer + required: + - podMetricsEndpoints + - selector + type: object + required: + - spec + type: object + served: true + storage: true +status: + acceptedNames: + kind: "" + plural: "" + conditions: [] + storedVersions: [] diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-probes.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-probes.yaml new file mode 100644 index 00000000..41a1b6ff --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-probes.yaml @@ -0,0 +1,169 @@ +# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.44.0/example/prometheus-operator-crd/monitoring.coreos.com_probes.yaml + +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.4.1 + creationTimestamp: null + name: probes.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + kind: Probe + listKind: ProbeList + plural: probes + singular: probe + scope: Namespaced + versions: + - name: v1 + schema: + openAPIV3Schema: + description: Probe defines monitoring for a set of static targets or ingresses. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Specification of desired Ingress selection for target discovery by Prometheus. + properties: + interval: + description: Interval at which targets are probed using the configured prober. If not specified Prometheus' global scrape interval is used. + type: string + jobName: + description: The job name assigned to scraped metrics by default. + type: string + module: + description: 'The module to use for probing specifying how to probe the target. Example module configuring in the blackbox exporter: https://github.com/prometheus/blackbox_exporter/blob/master/example.yml' + type: string + prober: + description: Specification for the prober to use for probing targets. The prober.URL parameter is required. Targets cannot be probed if left empty. + properties: + path: + description: Path to collect metrics from. Defaults to `/probe`. + type: string + scheme: + description: HTTP scheme to use for scraping. Defaults to `http`. + type: string + url: + description: Mandatory URL of the prober. + type: string + required: + - url + type: object + scrapeTimeout: + description: Timeout for scraping metrics from the Prometheus exporter. + type: string + targets: + description: Targets defines a set of static and/or dynamically discovered targets to be probed using the prober. + properties: + ingress: + description: Ingress defines the set of dynamically discovered ingress objects which hosts are considered for probing. + properties: + namespaceSelector: + description: Select Ingress objects by namespace. + properties: + any: + description: Boolean describing whether all namespaces are selected in contrast to a list restricting them. + type: boolean + matchNames: + description: List of namespace names. + items: + type: string + type: array + type: object + relabelingConfigs: + description: 'RelabelConfigs to apply to samples before ingestion. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config' + items: + description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines ``-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + description: Action to perform based on regex matching. Default is 'replace' + type: string + modulus: + description: Modulus to take of the hash of the source label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions. + items: + type: string + type: array + targetLabel: + description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available. + type: string + type: object + type: array + selector: + description: Select Ingress objects by labels. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + type: object + staticConfig: + description: 'StaticConfig defines static targets which are considers for probing. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#static_config.' + properties: + labels: + additionalProperties: + type: string + description: Labels assigned to all metrics scraped from the targets. + type: object + static: + description: Targets is a list of URLs to probe using the configured prober. + items: + type: string + type: array + type: object + type: object + type: object + required: + - spec + type: object + served: true + storage: true +status: + acceptedNames: + kind: "" + plural: "" + conditions: [] + storedVersions: [] diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-prometheuses.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-prometheuses.yaml new file mode 100644 index 00000000..fd43ebca --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-prometheuses.yaml @@ -0,0 +1,4422 @@ +# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.44.0/example/prometheus-operator-crd/monitoring.coreos.com_prometheuses.yaml + +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.4.1 + creationTimestamp: null + name: prometheuses.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + kind: Prometheus + listKind: PrometheusList + plural: prometheuses + singular: prometheus + scope: Namespaced + versions: + - additionalPrinterColumns: + - description: The version of Prometheus + jsonPath: .spec.version + name: Version + type: string + - description: The desired replicas number of Prometheuses + jsonPath: .spec.replicas + name: Replicas + type: integer + - jsonPath: .metadata.creationTimestamp + name: Age + type: date + name: v1 + schema: + openAPIV3Schema: + description: Prometheus defines a Prometheus deployment. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: 'Specification of the desired behavior of the Prometheus cluster. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#spec-and-status' + properties: + additionalAlertManagerConfigs: + description: 'AdditionalAlertManagerConfigs allows specifying a key of a Secret containing additional Prometheus AlertManager configurations. AlertManager configurations specified are appended to the configurations generated by the Prometheus Operator. Job configurations specified must have the form as specified in the official Prometheus documentation: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#alertmanager_config. As AlertManager configs are appended, the user is responsible to make sure it is valid. Note that using this feature may expose the possibility to break upgrades of Prometheus. It is advised to review Prometheus release notes to ensure that no incompatible AlertManager configs are going to break Prometheus after the upgrade.' + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + additionalAlertRelabelConfigs: + description: 'AdditionalAlertRelabelConfigs allows specifying a key of a Secret containing additional Prometheus alert relabel configurations. Alert relabel configurations specified are appended to the configurations generated by the Prometheus Operator. Alert relabel configurations specified must have the form as specified in the official Prometheus documentation: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#alert_relabel_configs. As alert relabel configs are appended, the user is responsible to make sure it is valid. Note that using this feature may expose the possibility to break upgrades of Prometheus. It is advised to review Prometheus release notes to ensure that no incompatible alert relabel configs are going to break Prometheus after the upgrade.' + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + additionalScrapeConfigs: + description: 'AdditionalScrapeConfigs allows specifying a key of a Secret containing additional Prometheus scrape configurations. Scrape configurations specified are appended to the configurations generated by the Prometheus Operator. Job configurations specified must have the form as specified in the official Prometheus documentation: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#scrape_config. As scrape configs are appended, the user is responsible to make sure it is valid. Note that using this feature may expose the possibility to break upgrades of Prometheus. It is advised to review Prometheus release notes to ensure that no incompatible scrape configs are going to break Prometheus after the upgrade.' + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + affinity: + description: If specified, the pod's scheduling constraints. + properties: + nodeAffinity: + description: Describes node affinity scheduling rules for the pod. + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node matches the corresponding matchExpressions; the node(s) with the highest sum are the most preferred. + items: + description: An empty preferred scheduling term matches all objects with implicit weight 0 (i.e. it's a no-op). A null preferred scheduling term matches no objects (i.e. is also a no-op). + properties: + preference: + description: A node selector term, associated with the corresponding weight. + properties: + matchExpressions: + description: A list of node selector requirements by node's labels. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchFields: + description: A list of node selector requirements by node's fields. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + type: object + weight: + description: Weight associated with matching the corresponding nodeSelectorTerm, in the range 1-100. + format: int32 + type: integer + required: + - preference + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node. + properties: + nodeSelectorTerms: + description: Required. A list of node selector terms. The terms are ORed. + items: + description: A null or empty node selector term matches no objects. The requirements of them are ANDed. The TopologySelectorTerm type implements a subset of the NodeSelectorTerm. + properties: + matchExpressions: + description: A list of node selector requirements by node's labels. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchFields: + description: A list of node selector requirements by node's fields. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + type: object + type: array + required: + - nodeSelectorTerms + type: object + type: object + podAffinity: + description: Describes pod affinity scheduling rules (e.g. co-locate this pod in the same node, zone, etc. as some other pod(s)). + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. + items: + description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated with the corresponding weight. + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + namespaces: + description: namespaces specifies which namespaces the labelSelector applies to (matches against); null or empty list means "this pod's namespace" + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + weight: + description: weight associated with matching the corresponding podAffinityTerm, in the range 1-100. + format: int32 + type: integer + required: + - podAffinityTerm + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. + items: + description: Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + namespaces: + description: namespaces specifies which namespaces the labelSelector applies to (matches against); null or empty list means "this pod's namespace" + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + type: array + type: object + podAntiAffinity: + description: Describes pod anti-affinity scheduling rules (e.g. avoid putting this pod in the same node, zone, etc. as some other pod(s)). + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the anti-affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling anti-affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. + items: + description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated with the corresponding weight. + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + namespaces: + description: namespaces specifies which namespaces the labelSelector applies to (matches against); null or empty list means "this pod's namespace" + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + weight: + description: weight associated with matching the corresponding podAffinityTerm, in the range 1-100. + format: int32 + type: integer + required: + - podAffinityTerm + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the anti-affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the anti-affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. + items: + description: Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + namespaces: + description: namespaces specifies which namespaces the labelSelector applies to (matches against); null or empty list means "this pod's namespace" + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + type: array + type: object + type: object + alerting: + description: Define details regarding alerting. + properties: + alertmanagers: + description: AlertmanagerEndpoints Prometheus should fire alerts against. + items: + description: AlertmanagerEndpoints defines a selection of a single Endpoints object containing alertmanager IPs to fire alerts against. + properties: + apiVersion: + description: Version of the Alertmanager API that Prometheus uses to send alerts. It can be "v1" or "v2". + type: string + bearerTokenFile: + description: BearerTokenFile to read from filesystem to use when authenticating to Alertmanager. + type: string + name: + description: Name of Endpoints object in Namespace. + type: string + namespace: + description: Namespace of Endpoints object. + type: string + pathPrefix: + description: Prefix for the HTTP path alerts are pushed to. + type: string + port: + anyOf: + - type: integer + - type: string + description: Port the Alertmanager API is exposed on. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use when firing alerts. + type: string + timeout: + description: Timeout is a per-target Alertmanager timeout when pushing alerts. + type: string + tlsConfig: + description: TLS Config to use for alertmanager connection. + properties: + ca: + description: Struct containing the CA cert to use for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + caFile: + description: Path to the CA cert in the Prometheus container to use for the targets. + type: string + cert: + description: Struct containing the client cert file for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + certFile: + description: Path to the client cert file in the Prometheus container for the targets. + type: string + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keyFile: + description: Path to the client key file in the Prometheus container for the targets. + type: string + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + required: + - name + - namespace + - port + type: object + type: array + required: + - alertmanagers + type: object + allowOverlappingBlocks: + description: AllowOverlappingBlocks enables vertical compaction and vertical query merge in Prometheus. This is still experimental in Prometheus so it may change in any upcoming release. + type: boolean + apiserverConfig: + description: APIServerConfig allows specifying a host and auth methods to access apiserver. If left empty, Prometheus is assumed to run inside of the cluster and will discover API servers automatically and use the pod's CA certificate and bearer token file at /var/run/secrets/kubernetes.io/serviceaccount/. + properties: + basicAuth: + description: BasicAuth allow an endpoint to authenticate over basic authentication + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + bearerToken: + description: Bearer token for accessing apiserver. + type: string + bearerTokenFile: + description: File to read bearer token for accessing apiserver. + type: string + host: + description: Host of apiserver. A valid string consisting of a hostname or IP followed by an optional port number + type: string + tlsConfig: + description: TLS Config to use for accessing apiserver. + properties: + ca: + description: Struct containing the CA cert to use for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + caFile: + description: Path to the CA cert in the Prometheus container to use for the targets. + type: string + cert: + description: Struct containing the client cert file for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + certFile: + description: Path to the client cert file in the Prometheus container for the targets. + type: string + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keyFile: + description: Path to the client key file in the Prometheus container for the targets. + type: string + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + required: + - host + type: object + arbitraryFSAccessThroughSMs: + description: ArbitraryFSAccessThroughSMs configures whether configuration based on a service monitor can access arbitrary files on the file system of the Prometheus container e.g. bearer token files. + properties: + deny: + type: boolean + type: object + baseImage: + description: 'Base image to use for a Prometheus deployment. Deprecated: use ''image'' instead' + type: string + configMaps: + description: ConfigMaps is a list of ConfigMaps in the same namespace as the Prometheus object, which shall be mounted into the Prometheus Pods. The ConfigMaps are mounted into /etc/prometheus/configmaps/. + items: + type: string + type: array + containers: + description: 'Containers allows injecting additional containers or modifying operator generated containers. This can be used to allow adding an authentication proxy to a Prometheus pod or to change the behavior of an operator generated container. Containers described here modify an operator generated container if they share the same name and modifications are done via a strategic merge patch. The current container names are: `prometheus`, `config-reloader`, and `thanos-sidecar`. Overriding containers is entirely outside the scope of what the maintainers will support and by doing so, you accept that this behaviour may break at any time without notice.' + items: + description: A single application container that you want to run within a pod. + properties: + args: + description: 'Arguments to the entrypoint. The docker image''s CMD is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + command: + description: 'Entrypoint array. Not executed within a shell. The docker image''s ENTRYPOINT is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + env: + description: List of environment variables to set in the container. Cannot be updated. + items: + description: EnvVar represents an environment variable present in a Container. + properties: + name: + description: Name of the environment variable. Must be a C_IDENTIFIER. + type: string + value: + description: 'Variable references $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "".' + type: string + valueFrom: + description: Source for the environment variable's value. Cannot be used if value is not empty. + properties: + configMapKeyRef: + description: Selects a key of a ConfigMap. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + fieldRef: + description: 'Selects a field of the pod: supports metadata.name, metadata.namespace, metadata.labels, metadata.annotations, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + secretKeyRef: + description: Selects a key of a secret in the pod's namespace + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + required: + - name + type: object + type: array + envFrom: + description: List of sources to populate environment variables in the container. The keys defined within a source must be a C_IDENTIFIER. All invalid keys will be reported as an event when the container is starting. When a key exists in multiple sources, the value associated with the last source will take precedence. Values defined by an Env with a duplicate key will take precedence. Cannot be updated. + items: + description: EnvFromSource represents the source of a set of ConfigMaps + properties: + configMapRef: + description: The ConfigMap to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap must be defined + type: boolean + type: object + prefix: + description: An optional identifier to prepend to each key in the ConfigMap. Must be a C_IDENTIFIER. + type: string + secretRef: + description: The Secret to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret must be defined + type: boolean + type: object + type: object + type: array + image: + description: 'Docker image name. More info: https://kubernetes.io/docs/concepts/containers/images This field is optional to allow higher level config management to default or override container images in workload controllers like Deployments and StatefulSets.' + type: string + imagePullPolicy: + description: 'Image pull policy. One of Always, Never, IfNotPresent. Defaults to Always if :latest tag is specified, or IfNotPresent otherwise. Cannot be updated. More info: https://kubernetes.io/docs/concepts/containers/images#updating-images' + type: string + lifecycle: + description: Actions that the management system should take in response to container lifecycle events. Cannot be updated. + properties: + postStart: + description: 'PostStart is called immediately after a container is created. If the handler fails, the container is terminated and restarted according to its restart policy. Other management of the container blocks until the hook completes. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + preStop: + description: 'PreStop is called immediately before a container is terminated due to an API request or management event such as liveness/startup probe failure, preemption, resource contention, etc. The handler is not called if the container crashes or exits. The reason for termination is passed to the handler. The Pod''s termination grace period countdown begins before the PreStop hooked is executed. Regardless of the outcome of the handler, the container will eventually terminate within the Pod''s termination grace period. Other management of the container blocks until the hook completes or until the termination grace period is reached. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + type: object + livenessProbe: + description: 'Periodic probe of container liveness. Container will be restarted if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + name: + description: Name of the container specified as a DNS_LABEL. Each container in a pod must have a unique name (DNS_LABEL). Cannot be updated. + type: string + ports: + description: List of ports to expose from the container. Exposing a port here gives the system additional information about the network connections a container uses, but is primarily informational. Not specifying a port here DOES NOT prevent that port from being exposed. Any port which is listening on the default "0.0.0.0" address inside a container will be accessible from the network. Cannot be updated. + items: + description: ContainerPort represents a network port in a single container. + properties: + containerPort: + description: Number of port to expose on the pod's IP address. This must be a valid port number, 0 < x < 65536. + format: int32 + type: integer + hostIP: + description: What host IP to bind the external port to. + type: string + hostPort: + description: Number of port to expose on the host. If specified, this must be a valid port number, 0 < x < 65536. If HostNetwork is specified, this must match ContainerPort. Most containers do not need this. + format: int32 + type: integer + name: + description: If specified, this must be an IANA_SVC_NAME and unique within the pod. Each named port in a pod must have a unique name. Name for the port that can be referred to by services. + type: string + protocol: + default: TCP + description: Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP". + type: string + required: + - containerPort + type: object + type: array + x-kubernetes-list-map-keys: + - containerPort + - protocol + x-kubernetes-list-type: map + readinessProbe: + description: 'Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + resources: + description: 'Compute Resources required by this container. Cannot be updated. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + type: object + securityContext: + description: 'Security options the pod should run with. More info: https://kubernetes.io/docs/concepts/policy/security-context/ More info: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/' + properties: + allowPrivilegeEscalation: + description: 'AllowPrivilegeEscalation controls whether a process can gain more privileges than its parent process. This bool directly controls if the no_new_privs flag will be set on the container process. AllowPrivilegeEscalation is true always when the container is: 1) run as Privileged 2) has CAP_SYS_ADMIN' + type: boolean + capabilities: + description: The capabilities to add/drop when running containers. Defaults to the default set of capabilities granted by the container runtime. + properties: + add: + description: Added capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + drop: + description: Removed capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + type: object + privileged: + description: Run container in privileged mode. Processes in privileged containers are essentially equivalent to root on the host. Defaults to false. + type: boolean + procMount: + description: procMount denotes the type of proc mount to use for the containers. The default is DefaultProcMount which uses the container runtime defaults for readonly paths and masked paths. This requires the ProcMountType feature flag to be enabled. + type: string + readOnlyRootFilesystem: + description: Whether this container has a read-only root filesystem. Default is false. + type: boolean + runAsGroup: + description: The GID to run the entrypoint of the container process. Uses runtime default if unset. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + format: int64 + type: integer + runAsNonRoot: + description: Indicates that the container must run as a non-root user. If true, the Kubelet will validate the image at runtime to ensure that it does not run as UID 0 (root) and fail to start the container if it does. If unset or false, no such validation will be performed. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: boolean + runAsUser: + description: The UID to run the entrypoint of the container process. Defaults to user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + format: int64 + type: integer + seLinuxOptions: + description: The SELinux context to be applied to the container. If unspecified, the container runtime will allocate a random SELinux context for each container. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + properties: + level: + description: Level is SELinux level label that applies to the container. + type: string + role: + description: Role is a SELinux role label that applies to the container. + type: string + type: + description: Type is a SELinux type label that applies to the container. + type: string + user: + description: User is a SELinux user label that applies to the container. + type: string + type: object + windowsOptions: + description: The Windows specific settings applied to all containers. If unspecified, the options from the PodSecurityContext will be used. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + properties: + gmsaCredentialSpec: + description: GMSACredentialSpec is where the GMSA admission webhook (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the GMSA credential spec named by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the GMSA credential spec to use. + type: string + runAsUserName: + description: The UserName in Windows to run the entrypoint of the container process. Defaults to the user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: string + type: object + type: object + startupProbe: + description: 'StartupProbe indicates that the Pod has successfully initialized. If specified, no other probes are executed until this completes successfully. If this probe fails, the Pod will be restarted, just as if the livenessProbe failed. This can be used to provide different probe parameters at the beginning of a Pod''s lifecycle, when it might take a long time to load data or warm a cache, than during steady-state operation. This cannot be updated. This is a beta feature enabled by the StartupProbe feature flag. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + stdin: + description: Whether this container should allocate a buffer for stdin in the container runtime. If this is not set, reads from stdin in the container will always result in EOF. Default is false. + type: boolean + stdinOnce: + description: Whether the container runtime should close the stdin channel after it has been opened by a single attach. When stdin is true the stdin stream will remain open across multiple attach sessions. If stdinOnce is set to true, stdin is opened on container start, is empty until the first client attaches to stdin, and then remains open and accepts data until the client disconnects, at which time stdin is closed and remains closed until the container is restarted. If this flag is false, a container processes that reads from stdin will never receive an EOF. Default is false + type: boolean + terminationMessagePath: + description: 'Optional: Path at which the file to which the container''s termination message will be written is mounted into the container''s filesystem. Message written is intended to be brief final status, such as an assertion failure message. Will be truncated by the node if greater than 4096 bytes. The total message length across all containers will be limited to 12kb. Defaults to /dev/termination-log. Cannot be updated.' + type: string + terminationMessagePolicy: + description: Indicate how the termination message should be populated. File will use the contents of terminationMessagePath to populate the container status message on both success and failure. FallbackToLogsOnError will use the last chunk of container log output if the termination message file is empty and the container exited with an error. The log output is limited to 2048 bytes or 80 lines, whichever is smaller. Defaults to File. Cannot be updated. + type: string + tty: + description: Whether this container should allocate a TTY for itself, also requires 'stdin' to be true. Default is false. + type: boolean + volumeDevices: + description: volumeDevices is the list of block devices to be used by the container. + items: + description: volumeDevice describes a mapping of a raw block device within a container. + properties: + devicePath: + description: devicePath is the path inside of the container that the device will be mapped to. + type: string + name: + description: name must match the name of a persistentVolumeClaim in the pod + type: string + required: + - devicePath + - name + type: object + type: array + volumeMounts: + description: Pod volumes to mount into the container's filesystem. Cannot be updated. + items: + description: VolumeMount describes a mounting of a Volume within a container. + properties: + mountPath: + description: Path within the container at which the volume should be mounted. Must not contain ':'. + type: string + mountPropagation: + description: mountPropagation determines how mounts are propagated from the host to container and the other way around. When not set, MountPropagationNone is used. This field is beta in 1.10. + type: string + name: + description: This must match the Name of a Volume. + type: string + readOnly: + description: Mounted read-only if true, read-write otherwise (false or unspecified). Defaults to false. + type: boolean + subPath: + description: Path within the volume from which the container's volume should be mounted. Defaults to "" (volume's root). + type: string + subPathExpr: + description: Expanded path within the volume from which the container's volume should be mounted. Behaves similarly to SubPath but environment variable references $(VAR_NAME) are expanded using the container's environment. Defaults to "" (volume's root). SubPathExpr and SubPath are mutually exclusive. + type: string + required: + - mountPath + - name + type: object + type: array + workingDir: + description: Container's working directory. If not specified, the container runtime's default will be used, which might be configured in the container image. Cannot be updated. + type: string + required: + - name + type: object + type: array + disableCompaction: + description: Disable prometheus compaction. + type: boolean + enableAdminAPI: + description: 'Enable access to prometheus web admin API. Defaults to the value of `false`. WARNING: Enabling the admin APIs enables mutating endpoints, to delete data, shutdown Prometheus, and more. Enabling this should be done with care and the user is advised to add additional authentication authorization via a proxy to ensure only clients authorized to perform these actions can do so. For more information see https://prometheus.io/docs/prometheus/latest/querying/api/#tsdb-admin-apis' + type: boolean + enforcedNamespaceLabel: + description: EnforcedNamespaceLabel enforces adding a namespace label of origin for each alert and metric that is user created. The label value will always be the namespace of the object that is being created. + type: string + enforcedSampleLimit: + description: EnforcedSampleLimit defines global limit on number of scraped samples that will be accepted. This overrides any SampleLimit set per ServiceMonitor or/and PodMonitor. It is meant to be used by admins to enforce the SampleLimit to keep overall number of samples/series under the desired limit. Note that if SampleLimit is lower that value will be taken instead. + format: int64 + type: integer + enforcedTargetLimit: + description: EnforcedTargetLimit defines a global limit on the number of scraped targets. This overrides any TargetLimit set per ServiceMonitor or/and PodMonitor. It is meant to be used by admins to enforce the TargetLimit to keep overall number of targets under the desired limit. Note that if TargetLimit is higher that value will be taken instead. + format: int64 + type: integer + evaluationInterval: + description: Interval between consecutive evaluations. + type: string + externalLabels: + additionalProperties: + type: string + description: The labels to add to any time series or alerts when communicating with external systems (federation, remote storage, Alertmanager). + type: object + externalUrl: + description: The external URL the Prometheus instances will be available under. This is necessary to generate correct URLs. This is necessary if Prometheus is not served from root of a DNS name. + type: string + ignoreNamespaceSelectors: + description: IgnoreNamespaceSelectors if set to true will ignore NamespaceSelector settings from the podmonitor and servicemonitor configs, and they will only discover endpoints within their current namespace. Defaults to false. + type: boolean + image: + description: Image if specified has precedence over baseImage, tag and sha combinations. Specifying the version is still necessary to ensure the Prometheus Operator knows what version of Prometheus is being configured. + type: string + imagePullSecrets: + description: An optional list of references to secrets in the same namespace to use for pulling prometheus and alertmanager images from registries see http://kubernetes.io/docs/user-guide/images#specifying-imagepullsecrets-on-a-pod + items: + description: LocalObjectReference contains enough information to let you locate the referenced object inside the same namespace. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + type: array + initContainers: + description: 'InitContainers allows adding initContainers to the pod definition. Those can be used to e.g. fetch secrets for injection into the Prometheus configuration from external sources. Any errors during the execution of an initContainer will lead to a restart of the Pod. More info: https://kubernetes.io/docs/concepts/workloads/pods/init-containers/ Using initContainers for any use case other then secret fetching is entirely outside the scope of what the maintainers will support and by doing so, you accept that this behaviour may break at any time without notice.' + items: + description: A single application container that you want to run within a pod. + properties: + args: + description: 'Arguments to the entrypoint. The docker image''s CMD is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + command: + description: 'Entrypoint array. Not executed within a shell. The docker image''s ENTRYPOINT is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + env: + description: List of environment variables to set in the container. Cannot be updated. + items: + description: EnvVar represents an environment variable present in a Container. + properties: + name: + description: Name of the environment variable. Must be a C_IDENTIFIER. + type: string + value: + description: 'Variable references $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "".' + type: string + valueFrom: + description: Source for the environment variable's value. Cannot be used if value is not empty. + properties: + configMapKeyRef: + description: Selects a key of a ConfigMap. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + fieldRef: + description: 'Selects a field of the pod: supports metadata.name, metadata.namespace, metadata.labels, metadata.annotations, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + secretKeyRef: + description: Selects a key of a secret in the pod's namespace + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + required: + - name + type: object + type: array + envFrom: + description: List of sources to populate environment variables in the container. The keys defined within a source must be a C_IDENTIFIER. All invalid keys will be reported as an event when the container is starting. When a key exists in multiple sources, the value associated with the last source will take precedence. Values defined by an Env with a duplicate key will take precedence. Cannot be updated. + items: + description: EnvFromSource represents the source of a set of ConfigMaps + properties: + configMapRef: + description: The ConfigMap to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap must be defined + type: boolean + type: object + prefix: + description: An optional identifier to prepend to each key in the ConfigMap. Must be a C_IDENTIFIER. + type: string + secretRef: + description: The Secret to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret must be defined + type: boolean + type: object + type: object + type: array + image: + description: 'Docker image name. More info: https://kubernetes.io/docs/concepts/containers/images This field is optional to allow higher level config management to default or override container images in workload controllers like Deployments and StatefulSets.' + type: string + imagePullPolicy: + description: 'Image pull policy. One of Always, Never, IfNotPresent. Defaults to Always if :latest tag is specified, or IfNotPresent otherwise. Cannot be updated. More info: https://kubernetes.io/docs/concepts/containers/images#updating-images' + type: string + lifecycle: + description: Actions that the management system should take in response to container lifecycle events. Cannot be updated. + properties: + postStart: + description: 'PostStart is called immediately after a container is created. If the handler fails, the container is terminated and restarted according to its restart policy. Other management of the container blocks until the hook completes. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + preStop: + description: 'PreStop is called immediately before a container is terminated due to an API request or management event such as liveness/startup probe failure, preemption, resource contention, etc. The handler is not called if the container crashes or exits. The reason for termination is passed to the handler. The Pod''s termination grace period countdown begins before the PreStop hooked is executed. Regardless of the outcome of the handler, the container will eventually terminate within the Pod''s termination grace period. Other management of the container blocks until the hook completes or until the termination grace period is reached. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + type: object + livenessProbe: + description: 'Periodic probe of container liveness. Container will be restarted if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + name: + description: Name of the container specified as a DNS_LABEL. Each container in a pod must have a unique name (DNS_LABEL). Cannot be updated. + type: string + ports: + description: List of ports to expose from the container. Exposing a port here gives the system additional information about the network connections a container uses, but is primarily informational. Not specifying a port here DOES NOT prevent that port from being exposed. Any port which is listening on the default "0.0.0.0" address inside a container will be accessible from the network. Cannot be updated. + items: + description: ContainerPort represents a network port in a single container. + properties: + containerPort: + description: Number of port to expose on the pod's IP address. This must be a valid port number, 0 < x < 65536. + format: int32 + type: integer + hostIP: + description: What host IP to bind the external port to. + type: string + hostPort: + description: Number of port to expose on the host. If specified, this must be a valid port number, 0 < x < 65536. If HostNetwork is specified, this must match ContainerPort. Most containers do not need this. + format: int32 + type: integer + name: + description: If specified, this must be an IANA_SVC_NAME and unique within the pod. Each named port in a pod must have a unique name. Name for the port that can be referred to by services. + type: string + protocol: + default: TCP + description: Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP". + type: string + required: + - containerPort + type: object + type: array + x-kubernetes-list-map-keys: + - containerPort + - protocol + x-kubernetes-list-type: map + readinessProbe: + description: 'Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + resources: + description: 'Compute Resources required by this container. Cannot be updated. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + type: object + securityContext: + description: 'Security options the pod should run with. More info: https://kubernetes.io/docs/concepts/policy/security-context/ More info: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/' + properties: + allowPrivilegeEscalation: + description: 'AllowPrivilegeEscalation controls whether a process can gain more privileges than its parent process. This bool directly controls if the no_new_privs flag will be set on the container process. AllowPrivilegeEscalation is true always when the container is: 1) run as Privileged 2) has CAP_SYS_ADMIN' + type: boolean + capabilities: + description: The capabilities to add/drop when running containers. Defaults to the default set of capabilities granted by the container runtime. + properties: + add: + description: Added capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + drop: + description: Removed capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + type: object + privileged: + description: Run container in privileged mode. Processes in privileged containers are essentially equivalent to root on the host. Defaults to false. + type: boolean + procMount: + description: procMount denotes the type of proc mount to use for the containers. The default is DefaultProcMount which uses the container runtime defaults for readonly paths and masked paths. This requires the ProcMountType feature flag to be enabled. + type: string + readOnlyRootFilesystem: + description: Whether this container has a read-only root filesystem. Default is false. + type: boolean + runAsGroup: + description: The GID to run the entrypoint of the container process. Uses runtime default if unset. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + format: int64 + type: integer + runAsNonRoot: + description: Indicates that the container must run as a non-root user. If true, the Kubelet will validate the image at runtime to ensure that it does not run as UID 0 (root) and fail to start the container if it does. If unset or false, no such validation will be performed. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: boolean + runAsUser: + description: The UID to run the entrypoint of the container process. Defaults to user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + format: int64 + type: integer + seLinuxOptions: + description: The SELinux context to be applied to the container. If unspecified, the container runtime will allocate a random SELinux context for each container. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + properties: + level: + description: Level is SELinux level label that applies to the container. + type: string + role: + description: Role is a SELinux role label that applies to the container. + type: string + type: + description: Type is a SELinux type label that applies to the container. + type: string + user: + description: User is a SELinux user label that applies to the container. + type: string + type: object + windowsOptions: + description: The Windows specific settings applied to all containers. If unspecified, the options from the PodSecurityContext will be used. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + properties: + gmsaCredentialSpec: + description: GMSACredentialSpec is where the GMSA admission webhook (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the GMSA credential spec named by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the GMSA credential spec to use. + type: string + runAsUserName: + description: The UserName in Windows to run the entrypoint of the container process. Defaults to the user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: string + type: object + type: object + startupProbe: + description: 'StartupProbe indicates that the Pod has successfully initialized. If specified, no other probes are executed until this completes successfully. If this probe fails, the Pod will be restarted, just as if the livenessProbe failed. This can be used to provide different probe parameters at the beginning of a Pod''s lifecycle, when it might take a long time to load data or warm a cache, than during steady-state operation. This cannot be updated. This is a beta feature enabled by the StartupProbe feature flag. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + stdin: + description: Whether this container should allocate a buffer for stdin in the container runtime. If this is not set, reads from stdin in the container will always result in EOF. Default is false. + type: boolean + stdinOnce: + description: Whether the container runtime should close the stdin channel after it has been opened by a single attach. When stdin is true the stdin stream will remain open across multiple attach sessions. If stdinOnce is set to true, stdin is opened on container start, is empty until the first client attaches to stdin, and then remains open and accepts data until the client disconnects, at which time stdin is closed and remains closed until the container is restarted. If this flag is false, a container processes that reads from stdin will never receive an EOF. Default is false + type: boolean + terminationMessagePath: + description: 'Optional: Path at which the file to which the container''s termination message will be written is mounted into the container''s filesystem. Message written is intended to be brief final status, such as an assertion failure message. Will be truncated by the node if greater than 4096 bytes. The total message length across all containers will be limited to 12kb. Defaults to /dev/termination-log. Cannot be updated.' + type: string + terminationMessagePolicy: + description: Indicate how the termination message should be populated. File will use the contents of terminationMessagePath to populate the container status message on both success and failure. FallbackToLogsOnError will use the last chunk of container log output if the termination message file is empty and the container exited with an error. The log output is limited to 2048 bytes or 80 lines, whichever is smaller. Defaults to File. Cannot be updated. + type: string + tty: + description: Whether this container should allocate a TTY for itself, also requires 'stdin' to be true. Default is false. + type: boolean + volumeDevices: + description: volumeDevices is the list of block devices to be used by the container. + items: + description: volumeDevice describes a mapping of a raw block device within a container. + properties: + devicePath: + description: devicePath is the path inside of the container that the device will be mapped to. + type: string + name: + description: name must match the name of a persistentVolumeClaim in the pod + type: string + required: + - devicePath + - name + type: object + type: array + volumeMounts: + description: Pod volumes to mount into the container's filesystem. Cannot be updated. + items: + description: VolumeMount describes a mounting of a Volume within a container. + properties: + mountPath: + description: Path within the container at which the volume should be mounted. Must not contain ':'. + type: string + mountPropagation: + description: mountPropagation determines how mounts are propagated from the host to container and the other way around. When not set, MountPropagationNone is used. This field is beta in 1.10. + type: string + name: + description: This must match the Name of a Volume. + type: string + readOnly: + description: Mounted read-only if true, read-write otherwise (false or unspecified). Defaults to false. + type: boolean + subPath: + description: Path within the volume from which the container's volume should be mounted. Defaults to "" (volume's root). + type: string + subPathExpr: + description: Expanded path within the volume from which the container's volume should be mounted. Behaves similarly to SubPath but environment variable references $(VAR_NAME) are expanded using the container's environment. Defaults to "" (volume's root). SubPathExpr and SubPath are mutually exclusive. + type: string + required: + - mountPath + - name + type: object + type: array + workingDir: + description: Container's working directory. If not specified, the container runtime's default will be used, which might be configured in the container image. Cannot be updated. + type: string + required: + - name + type: object + type: array + listenLocal: + description: ListenLocal makes the Prometheus server listen on loopback, so that it does not bind against the Pod IP. + type: boolean + logFormat: + description: Log format for Prometheus to be configured with. + type: string + logLevel: + description: Log level for Prometheus to be configured with. + type: string + nodeSelector: + additionalProperties: + type: string + description: Define which Nodes the Pods are scheduled on. + type: object + overrideHonorLabels: + description: OverrideHonorLabels if set to true overrides all user configured honor_labels. If HonorLabels is set in ServiceMonitor or PodMonitor to true, this overrides honor_labels to false. + type: boolean + overrideHonorTimestamps: + description: OverrideHonorTimestamps allows to globally enforce honoring timestamps in all scrape configs. + type: boolean + paused: + description: When a Prometheus deployment is paused, no actions except for deletion will be performed on the underlying objects. + type: boolean + podMetadata: + description: PodMetadata configures Labels and Annotations which are propagated to the prometheus pods. + properties: + annotations: + additionalProperties: + type: string + description: 'Annotations is an unstructured key value map stored with a resource that may be set by external tools to store and retrieve arbitrary metadata. They are not queryable and should be preserved when modifying objects. More info: http://kubernetes.io/docs/user-guide/annotations' + type: object + labels: + additionalProperties: + type: string + description: 'Map of string keys and values that can be used to organize and categorize (scope and select) objects. May match selectors of replication controllers and services. More info: http://kubernetes.io/docs/user-guide/labels' + type: object + name: + description: 'Name must be unique within a namespace. Is required when creating resources, although some resources may allow a client to request the generation of an appropriate name automatically. Name is primarily intended for creation idempotence and configuration definition. Cannot be updated. More info: http://kubernetes.io/docs/user-guide/identifiers#names' + type: string + type: object + podMonitorNamespaceSelector: + description: Namespaces to be selected for PodMonitor discovery. If nil, only check own namespace. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + podMonitorSelector: + description: '*Experimental* PodMonitors to be selected for target discovery. *Deprecated:* if neither this nor serviceMonitorSelector are specified, configuration is unmanaged.' + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + portName: + description: Port name used for the pods and governing service. This defaults to web + type: string + priorityClassName: + description: Priority class assigned to the Pods + type: string + probeNamespaceSelector: + description: '*Experimental* Namespaces to be selected for Probe discovery. If nil, only check own namespace.' + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + probeSelector: + description: '*Experimental* Probes to be selected for target discovery.' + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + prometheusExternalLabelName: + description: Name of Prometheus external label used to denote Prometheus instance name. Defaults to the value of `prometheus`. External label will _not_ be added when value is set to empty string (`""`). + type: string + prometheusRulesExcludedFromEnforce: + description: PrometheusRulesExcludedFromEnforce - list of prometheus rules to be excluded from enforcing of adding namespace labels. Works only if enforcedNamespaceLabel set to true. Make sure both ruleNamespace and ruleName are set for each pair + items: + description: PrometheusRuleExcludeConfig enables users to configure excluded PrometheusRule names and their namespaces to be ignored while enforcing namespace label for alerts and metrics. + properties: + ruleName: + description: RuleNamespace - name of excluded rule + type: string + ruleNamespace: + description: RuleNamespace - namespace of excluded rule + type: string + required: + - ruleName + - ruleNamespace + type: object + type: array + query: + description: QuerySpec defines the query command line flags when starting Prometheus. + properties: + lookbackDelta: + description: The delta difference allowed for retrieving metrics during expression evaluations. + type: string + maxConcurrency: + description: Number of concurrent queries that can be run at once. + format: int32 + type: integer + maxSamples: + description: Maximum number of samples a single query can load into memory. Note that queries will fail if they would load more samples than this into memory, so this also limits the number of samples a query can return. + format: int32 + type: integer + timeout: + description: Maximum time a query may take before being aborted. + type: string + type: object + queryLogFile: + description: QueryLogFile specifies the file to which PromQL queries are logged. Note that this location must be writable, and can be persisted using an attached volume. Alternatively, the location can be set to a stdout location such as `/dev/stdout` to log querie information to the default Prometheus log stream. This is only available in versions of Prometheus >= 2.16.0. For more details, see the Prometheus docs (https://prometheus.io/docs/guides/query-log/) + type: string + remoteRead: + description: If specified, the remote_read spec. This is an experimental feature, it may change in any upcoming release in a breaking way. + items: + description: RemoteReadSpec defines the remote_read configuration for prometheus. + properties: + basicAuth: + description: BasicAuth for the URL. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + bearerToken: + description: bearer token for remote read. + type: string + bearerTokenFile: + description: File to read bearer token for remote read. + type: string + name: + description: The name of the remote read queue, must be unique if specified. The name is used in metrics and logging in order to differentiate read configurations. Only valid in Prometheus versions 2.15.0 and newer. + type: string + proxyUrl: + description: Optional ProxyURL + type: string + readRecent: + description: Whether reads should be made for queries for time ranges that the local storage should have complete data for. + type: boolean + remoteTimeout: + description: Timeout for requests to the remote read endpoint. + type: string + requiredMatchers: + additionalProperties: + type: string + description: An optional list of equality matchers which have to be present in a selector to query the remote read endpoint. + type: object + tlsConfig: + description: TLS Config to use for remote read. + properties: + ca: + description: Struct containing the CA cert to use for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + caFile: + description: Path to the CA cert in the Prometheus container to use for the targets. + type: string + cert: + description: Struct containing the client cert file for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + certFile: + description: Path to the client cert file in the Prometheus container for the targets. + type: string + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keyFile: + description: Path to the client key file in the Prometheus container for the targets. + type: string + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + url: + description: The URL of the endpoint to send samples to. + type: string + required: + - url + type: object + type: array + remoteWrite: + description: If specified, the remote_write spec. This is an experimental feature, it may change in any upcoming release in a breaking way. + items: + description: RemoteWriteSpec defines the remote_write configuration for prometheus. + properties: + basicAuth: + description: BasicAuth for the URL. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + bearerToken: + description: File to read bearer token for remote write. + type: string + bearerTokenFile: + description: File to read bearer token for remote write. + type: string + name: + description: The name of the remote write queue, must be unique if specified. The name is used in metrics and logging in order to differentiate queues. Only valid in Prometheus versions 2.15.0 and newer. + type: string + proxyUrl: + description: Optional ProxyURL + type: string + queueConfig: + description: QueueConfig allows tuning of the remote write queue parameters. + properties: + batchSendDeadline: + description: BatchSendDeadline is the maximum time a sample will wait in buffer. + type: string + capacity: + description: Capacity is the number of samples to buffer per shard before we start dropping them. + type: integer + maxBackoff: + description: MaxBackoff is the maximum retry delay. + type: string + maxRetries: + description: MaxRetries is the maximum number of times to retry a batch on recoverable errors. + type: integer + maxSamplesPerSend: + description: MaxSamplesPerSend is the maximum number of samples per send. + type: integer + maxShards: + description: MaxShards is the maximum number of shards, i.e. amount of concurrency. + type: integer + minBackoff: + description: MinBackoff is the initial retry delay. Gets doubled for every retry. + type: string + minShards: + description: MinShards is the minimum number of shards, i.e. amount of concurrency. + type: integer + type: object + remoteTimeout: + description: Timeout for requests to the remote write endpoint. + type: string + tlsConfig: + description: TLS Config to use for remote write. + properties: + ca: + description: Struct containing the CA cert to use for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + caFile: + description: Path to the CA cert in the Prometheus container to use for the targets. + type: string + cert: + description: Struct containing the client cert file for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + certFile: + description: Path to the client cert file in the Prometheus container for the targets. + type: string + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keyFile: + description: Path to the client key file in the Prometheus container for the targets. + type: string + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + url: + description: The URL of the endpoint to send samples to. + type: string + writeRelabelConfigs: + description: The list of remote write relabel configurations. + items: + description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines ``-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + description: Action to perform based on regex matching. Default is 'replace' + type: string + modulus: + description: Modulus to take of the hash of the source label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions. + items: + type: string + type: array + targetLabel: + description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available. + type: string + type: object + type: array + required: + - url + type: object + type: array + replicaExternalLabelName: + description: Name of Prometheus external label used to denote replica name. Defaults to the value of `prometheus_replica`. External label will _not_ be added when value is set to empty string (`""`). + type: string + replicas: + description: Number of replicas of each shard to deploy for a Prometheus deployment. Number of replicas multiplied by shards is the total number of Pods created. + format: int32 + type: integer + resources: + description: Define resources requests and limits for single Pods. + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + type: object + retention: + description: Time duration Prometheus shall retain data for. Default is '24h', and must match the regular expression `[0-9]+(ms|s|m|h|d|w|y)` (milliseconds seconds minutes hours days weeks years). + type: string + retentionSize: + description: Maximum amount of disk space used by blocks. + type: string + routePrefix: + description: The route prefix Prometheus registers HTTP handlers for. This is useful, if using ExternalURL and a proxy is rewriting HTTP routes of a request, and the actual ExternalURL is still true, but the server serves requests under a different route prefix. For example for use with `kubectl proxy`. + type: string + ruleNamespaceSelector: + description: Namespaces to be selected for PrometheusRules discovery. If unspecified, only the same namespace as the Prometheus object is in is used. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + ruleSelector: + description: A selector to select which PrometheusRules to mount for loading alerting/recording rules from. Until (excluding) Prometheus Operator v0.24.0 Prometheus Operator will migrate any legacy rule ConfigMaps to PrometheusRule custom resources selected by RuleSelector. Make sure it does not match any config maps that you do not want to be migrated. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + rules: + description: /--rules.*/ command-line arguments. + properties: + alert: + description: /--rules.alert.*/ command-line arguments + properties: + forGracePeriod: + description: Minimum duration between alert and restored 'for' state. This is maintained only for alerts with configured 'for' time greater than grace period. + type: string + forOutageTolerance: + description: Max time to tolerate prometheus outage for restoring 'for' state of alert. + type: string + resendDelay: + description: Minimum amount of time to wait before resending an alert to Alertmanager. + type: string + type: object + type: object + scrapeInterval: + description: Interval between consecutive scrapes. + type: string + scrapeTimeout: + description: Number of seconds to wait for target to respond before erroring. + type: string + secrets: + description: Secrets is a list of Secrets in the same namespace as the Prometheus object, which shall be mounted into the Prometheus Pods. The Secrets are mounted into /etc/prometheus/secrets/. + items: + type: string + type: array + securityContext: + description: SecurityContext holds pod-level security attributes and common container settings. This defaults to the default PodSecurityContext. + properties: + fsGroup: + description: "A special supplemental group that applies to all containers in a pod. Some volume types allow the Kubelet to change the ownership of that volume to be owned by the pod: \n 1. The owning GID will be the FSGroup 2. The setgid bit is set (new files created in the volume will be owned by FSGroup) 3. The permission bits are OR'd with rw-rw---- \n If unset, the Kubelet will not modify the ownership and permissions of any volume." + format: int64 + type: integer + fsGroupChangePolicy: + description: 'fsGroupChangePolicy defines behavior of changing ownership and permission of the volume before being exposed inside Pod. This field will only apply to volume types which support fsGroup based ownership(and permissions). It will have no effect on ephemeral volume types such as: secret, configmaps and emptydir. Valid values are "OnRootMismatch" and "Always". If not specified defaults to "Always".' + type: string + runAsGroup: + description: The GID to run the entrypoint of the container process. Uses runtime default if unset. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. + format: int64 + type: integer + runAsNonRoot: + description: Indicates that the container must run as a non-root user. If true, the Kubelet will validate the image at runtime to ensure that it does not run as UID 0 (root) and fail to start the container if it does. If unset or false, no such validation will be performed. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: boolean + runAsUser: + description: The UID to run the entrypoint of the container process. Defaults to user specified in image metadata if unspecified. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. + format: int64 + type: integer + seLinuxOptions: + description: The SELinux context to be applied to all containers. If unspecified, the container runtime will allocate a random SELinux context for each container. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. + properties: + level: + description: Level is SELinux level label that applies to the container. + type: string + role: + description: Role is a SELinux role label that applies to the container. + type: string + type: + description: Type is a SELinux type label that applies to the container. + type: string + user: + description: User is a SELinux user label that applies to the container. + type: string + type: object + supplementalGroups: + description: A list of groups applied to the first process run in each container, in addition to the container's primary GID. If unspecified, no groups will be added to any container. + items: + format: int64 + type: integer + type: array + sysctls: + description: Sysctls hold a list of namespaced sysctls used for the pod. Pods with unsupported sysctls (by the container runtime) might fail to launch. + items: + description: Sysctl defines a kernel parameter to be set + properties: + name: + description: Name of a property to set + type: string + value: + description: Value of a property to set + type: string + required: + - name + - value + type: object + type: array + windowsOptions: + description: The Windows specific settings applied to all containers. If unspecified, the options within a container's SecurityContext will be used. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + properties: + gmsaCredentialSpec: + description: GMSACredentialSpec is where the GMSA admission webhook (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the GMSA credential spec named by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the GMSA credential spec to use. + type: string + runAsUserName: + description: The UserName in Windows to run the entrypoint of the container process. Defaults to the user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: string + type: object + type: object + serviceAccountName: + description: ServiceAccountName is the name of the ServiceAccount to use to run the Prometheus Pods. + type: string + serviceMonitorNamespaceSelector: + description: Namespaces to be selected for ServiceMonitor discovery. If nil, only check own namespace. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + serviceMonitorSelector: + description: ServiceMonitors to be selected for target discovery. *Deprecated:* if neither this nor podMonitorSelector are specified, configuration is unmanaged. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + sha: + description: 'SHA of Prometheus container image to be deployed. Defaults to the value of `version`. Similar to a tag, but the SHA explicitly deploys an immutable container image. Version and Tag are ignored if SHA is set. Deprecated: use ''image'' instead. The image digest can be specified as part of the image URL.' + type: string + shards: + description: 'EXPERIMENTAL: Number of shards to distribute targets onto. Number of replicas multiplied by shards is the total number of Pods created. Note that scaling down shards will not reshard data onto remaining instances, it must be manually moved. Increasing shards will not reshard data either but it will continue to be available from the same instances. To query globally use Thanos sidecar and Thanos querier or remote write data to a central location. Sharding is done on the content of the `__address__` target meta-label.' + format: int32 + type: integer + storage: + description: Storage spec to specify how storage shall be used. + properties: + disableMountSubPath: + description: 'Deprecated: subPath usage will be disabled by default in a future release, this option will become unnecessary. DisableMountSubPath allows to remove any subPath usage in volume mounts.' + type: boolean + emptyDir: + description: 'EmptyDirVolumeSource to be used by the Prometheus StatefulSets. If specified, used in place of any volumeClaimTemplate. More info: https://kubernetes.io/docs/concepts/storage/volumes/#emptydir' + properties: + medium: + description: 'What type of storage medium should back this directory. The default is "" which means to use the node''s default medium. Must be an empty string (default) or Memory. More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + type: string + sizeLimit: + anyOf: + - type: integer + - type: string + description: 'Total amount of local storage required for this EmptyDir volume. The size limit is also applicable for memory medium. The maximum usage on memory medium EmptyDir would be the minimum value between the SizeLimit specified here and the sum of memory limits of all containers in a pod. The default is nil which means that the limit is undefined. More info: http://kubernetes.io/docs/user-guide/volumes#emptydir' + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + volumeClaimTemplate: + description: A PVC spec to be used by the Prometheus StatefulSets. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + description: EmbeddedMetadata contains metadata relevant to an EmbeddedResource. + properties: + annotations: + additionalProperties: + type: string + description: 'Annotations is an unstructured key value map stored with a resource that may be set by external tools to store and retrieve arbitrary metadata. They are not queryable and should be preserved when modifying objects. More info: http://kubernetes.io/docs/user-guide/annotations' + type: object + labels: + additionalProperties: + type: string + description: 'Map of string keys and values that can be used to organize and categorize (scope and select) objects. May match selectors of replication controllers and services. More info: http://kubernetes.io/docs/user-guide/labels' + type: object + name: + description: 'Name must be unique within a namespace. Is required when creating resources, although some resources may allow a client to request the generation of an appropriate name automatically. Name is primarily intended for creation idempotence and configuration definition. Cannot be updated. More info: http://kubernetes.io/docs/user-guide/identifiers#names' + type: string + type: object + spec: + description: 'Spec defines the desired characteristics of a volume requested by a pod author. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + properties: + accessModes: + description: 'AccessModes contains the desired access modes the volume should have. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#access-modes-1' + items: + type: string + type: array + dataSource: + description: 'This field can be used to specify either: * An existing VolumeSnapshot object (snapshot.storage.k8s.io/VolumeSnapshot - Beta) * An existing PVC (PersistentVolumeClaim) * An existing custom resource/object that implements data population (Alpha) In order to use VolumeSnapshot object types, the appropriate feature gate must be enabled (VolumeSnapshotDataSource or AnyVolumeDataSource) If the provisioner or an external controller can support the specified data source, it will create a new volume based on the contents of the specified data source. If the specified data source is not supported, the volume will not be created and the failure will be reported as an event. In the future, we plan to support more data source types and the behavior of the provisioner may change.' + properties: + apiGroup: + description: APIGroup is the group for the resource being referenced. If APIGroup is not specified, the specified Kind must be in the core API group. For any other third-party types, APIGroup is required. + type: string + kind: + description: Kind is the type of resource being referenced + type: string + name: + description: Name is the name of resource being referenced + type: string + required: + - kind + - name + type: object + resources: + description: 'Resources represents the minimum resources the volume should have. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#resources' + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + type: object + selector: + description: A label query over volumes to consider for binding. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + storageClassName: + description: 'Name of the StorageClass required by the claim. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#class-1' + type: string + volumeMode: + description: volumeMode defines what type of volume is required by the claim. Value of Filesystem is implied when not included in claim spec. + type: string + volumeName: + description: VolumeName is the binding reference to the PersistentVolume backing this claim. + type: string + type: object + status: + description: 'Status represents the current information/status of a persistent volume claim. Read-only. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + properties: + accessModes: + description: 'AccessModes contains the actual access modes the volume backing the PVC has. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#access-modes-1' + items: + type: string + type: array + capacity: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: Represents the actual resources of the underlying volume. + type: object + conditions: + description: Current Condition of persistent volume claim. If underlying persistent volume is being resized then the Condition will be set to 'ResizeStarted'. + items: + description: PersistentVolumeClaimCondition contails details about state of pvc + properties: + lastProbeTime: + description: Last time we probed the condition. + format: date-time + type: string + lastTransitionTime: + description: Last time the condition transitioned from one status to another. + format: date-time + type: string + message: + description: Human-readable message indicating details about last transition. + type: string + reason: + description: Unique, this should be a short, machine understandable string that gives the reason for condition's last transition. If it reports "ResizeStarted" that means the underlying persistent volume is being resized. + type: string + status: + type: string + type: + description: PersistentVolumeClaimConditionType is a valid value of PersistentVolumeClaimCondition.Type + type: string + required: + - status + - type + type: object + type: array + phase: + description: Phase represents the current phase of PersistentVolumeClaim. + type: string + type: object + type: object + type: object + tag: + description: 'Tag of Prometheus container image to be deployed. Defaults to the value of `version`. Version is ignored if Tag is set. Deprecated: use ''image'' instead. The image tag can be specified as part of the image URL.' + type: string + thanos: + description: "Thanos configuration allows configuring various aspects of a Prometheus server in a Thanos environment. \n This section is experimental, it may change significantly without deprecation notice in any release. \n This is experimental and may change significantly without backward compatibility in any release." + properties: + baseImage: + description: 'Thanos base image if other than default. Deprecated: use ''image'' instead' + type: string + grpcServerTlsConfig: + description: 'GRPCServerTLSConfig configures the gRPC server from which Thanos Querier reads recorded rule data. Note: Currently only the CAFile, CertFile, and KeyFile fields are supported. Maps to the ''--grpc-server-tls-*'' CLI args.' + properties: + ca: + description: Struct containing the CA cert to use for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + caFile: + description: Path to the CA cert in the Prometheus container to use for the targets. + type: string + cert: + description: Struct containing the client cert file for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + certFile: + description: Path to the client cert file in the Prometheus container for the targets. + type: string + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keyFile: + description: Path to the client key file in the Prometheus container for the targets. + type: string + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + image: + description: Image if specified has precedence over baseImage, tag and sha combinations. Specifying the version is still necessary to ensure the Prometheus Operator knows what version of Thanos is being configured. + type: string + listenLocal: + description: ListenLocal makes the Thanos sidecar listen on loopback, so that it does not bind against the Pod IP. + type: boolean + logFormat: + description: LogFormat for Thanos sidecar to be configured with. + type: string + logLevel: + description: LogLevel for Thanos sidecar to be configured with. + type: string + minTime: + description: MinTime for Thanos sidecar to be configured with. Option can be a constant time in RFC3339 format or time duration relative to current time, such as -1d or 2h45m. Valid duration units are ms, s, m, h, d, w, y. + type: string + objectStorageConfig: + description: ObjectStorageConfig configures object storage in Thanos. Alternative to ObjectStorageConfigFile, and lower order priority. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + objectStorageConfigFile: + description: ObjectStorageConfigFile specifies the path of the object storage configuration file. When used alongside with ObjectStorageConfig, ObjectStorageConfigFile takes precedence. + type: string + resources: + description: Resources defines the resource requirements for the Thanos sidecar. If not provided, no requests/limits will be set + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + type: object + sha: + description: 'SHA of Thanos container image to be deployed. Defaults to the value of `version`. Similar to a tag, but the SHA explicitly deploys an immutable container image. Version and Tag are ignored if SHA is set. Deprecated: use ''image'' instead. The image digest can be specified as part of the image URL.' + type: string + tag: + description: 'Tag of Thanos sidecar container image to be deployed. Defaults to the value of `version`. Version is ignored if Tag is set. Deprecated: use ''image'' instead. The image tag can be specified as part of the image URL.' + type: string + tracingConfig: + description: TracingConfig configures tracing in Thanos. This is an experimental feature, it may change in any upcoming release in a breaking way. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + version: + description: Version describes the version of Thanos to use. + type: string + type: object + tolerations: + description: If specified, the pod's tolerations. + items: + description: The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . + properties: + effect: + description: Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. + type: string + key: + description: Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. + type: string + operator: + description: Operator represents a key's relationship to the value. Valid operators are Exists and Equal. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. + type: string + tolerationSeconds: + description: TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. + format: int64 + type: integer + value: + description: Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. + type: string + type: object + type: array + topologySpreadConstraints: + description: If specified, the pod's topology spread constraints. + items: + description: TopologySpreadConstraint specifies how to spread matching pods among the given topology. + properties: + labelSelector: + description: LabelSelector is used to find matching pods. Pods that match this label selector are counted to determine the number of pods in their corresponding topology domain. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + maxSkew: + description: 'MaxSkew describes the degree to which pods may be unevenly distributed. It''s the maximum permitted difference between the number of matching pods in any two topology domains of a given topology type. For example, in a 3-zone cluster, MaxSkew is set to 1, and pods with the same labelSelector spread as 1/1/0: | zone1 | zone2 | zone3 | | P | P | | - if MaxSkew is 1, incoming pod can only be scheduled to zone3 to become 1/1/1; scheduling it onto zone1(zone2) would make the ActualSkew(2-0) on zone1(zone2) violate MaxSkew(1). - if MaxSkew is 2, incoming pod can be scheduled onto any zone. It''s a required field. Default value is 1 and 0 is not allowed.' + format: int32 + type: integer + topologyKey: + description: TopologyKey is the key of node labels. Nodes that have a label with this key and identical values are considered to be in the same topology. We consider each as a "bucket", and try to put balanced number of pods into each bucket. It's a required field. + type: string + whenUnsatisfiable: + description: 'WhenUnsatisfiable indicates how to deal with a pod if it doesn''t satisfy the spread constraint. - DoNotSchedule (default) tells the scheduler not to schedule it - ScheduleAnyway tells the scheduler to still schedule it It''s considered as "Unsatisfiable" if and only if placing incoming pod on any topology violates "MaxSkew". For example, in a 3-zone cluster, MaxSkew is set to 1, and pods with the same labelSelector spread as 3/1/1: | zone1 | zone2 | zone3 | | P P P | P | P | If WhenUnsatisfiable is set to DoNotSchedule, incoming pod can only be scheduled to zone2(zone3) to become 3/2/1(3/1/2) as ActualSkew(2-1) on zone2(zone3) satisfies MaxSkew(1). In other words, the cluster can still be imbalanced, but scheduler won''t make it *more* imbalanced. It''s a required field.' + type: string + required: + - maxSkew + - topologyKey + - whenUnsatisfiable + type: object + type: array + version: + description: Version of Prometheus to be deployed. + type: string + volumeMounts: + description: VolumeMounts allows configuration of additional VolumeMounts on the output StatefulSet definition. VolumeMounts specified will be appended to other VolumeMounts in the prometheus container, that are generated as a result of StorageSpec objects. + items: + description: VolumeMount describes a mounting of a Volume within a container. + properties: + mountPath: + description: Path within the container at which the volume should be mounted. Must not contain ':'. + type: string + mountPropagation: + description: mountPropagation determines how mounts are propagated from the host to container and the other way around. When not set, MountPropagationNone is used. This field is beta in 1.10. + type: string + name: + description: This must match the Name of a Volume. + type: string + readOnly: + description: Mounted read-only if true, read-write otherwise (false or unspecified). Defaults to false. + type: boolean + subPath: + description: Path within the volume from which the container's volume should be mounted. Defaults to "" (volume's root). + type: string + subPathExpr: + description: Expanded path within the volume from which the container's volume should be mounted. Behaves similarly to SubPath but environment variable references $(VAR_NAME) are expanded using the container's environment. Defaults to "" (volume's root). SubPathExpr and SubPath are mutually exclusive. + type: string + required: + - mountPath + - name + type: object + type: array + volumes: + description: Volumes allows configuration of additional volumes on the output StatefulSet definition. Volumes specified will be appended to other volumes that are generated as a result of StorageSpec objects. + items: + description: Volume represents a named volume in a pod that may be accessed by any container in the pod. + properties: + awsElasticBlockStore: + description: 'AWSElasticBlockStore represents an AWS Disk resource that is attached to a kubelet''s host machine and then exposed to the pod. More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + properties: + fsType: + description: 'Filesystem type of the volume that you want to mount. Tip: Ensure that the filesystem type is supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + partition: + description: 'The partition in the volume that you want to mount. If omitted, the default is to mount by volume name. Examples: For volume /dev/sda1, you specify the partition as "1". Similarly, the volume partition for /dev/sda is "0" (or you can leave the property empty).' + format: int32 + type: integer + readOnly: + description: 'Specify "true" to force and set the ReadOnly property in VolumeMounts to "true". If omitted, the default is "false". More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + type: boolean + volumeID: + description: 'Unique ID of the persistent disk resource in AWS (Amazon EBS volume). More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + type: string + required: + - volumeID + type: object + azureDisk: + description: AzureDisk represents an Azure Data Disk mount on the host and bind mount to the pod. + properties: + cachingMode: + description: 'Host Caching mode: None, Read Only, Read Write.' + type: string + diskName: + description: The Name of the data disk in the blob storage + type: string + diskURI: + description: The URI the data disk in the blob storage + type: string + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + kind: + description: 'Expected values Shared: multiple blob disks per storage account Dedicated: single blob disk per storage account Managed: azure managed data disk (only in managed availability set). defaults to shared' + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + required: + - diskName + - diskURI + type: object + azureFile: + description: AzureFile represents an Azure File Service mount on the host and bind mount to the pod. + properties: + readOnly: + description: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + secretName: + description: the name of secret that contains Azure Storage Account Name and Key + type: string + shareName: + description: Share Name + type: string + required: + - secretName + - shareName + type: object + cephfs: + description: CephFS represents a Ceph FS mount on the host that shares a pod's lifetime + properties: + monitors: + description: 'Required: Monitors is a collection of Ceph monitors More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + items: + type: string + type: array + path: + description: 'Optional: Used as the mounted root, rather than the full Ceph tree, default is /' + type: string + readOnly: + description: 'Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: boolean + secretFile: + description: 'Optional: SecretFile is the path to key ring for User, default is /etc/ceph/user.secret More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: string + secretRef: + description: 'Optional: SecretRef is reference to the authentication secret for User, default is empty. More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + user: + description: 'Optional: User is the rados user name, default is admin More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: string + required: + - monitors + type: object + cinder: + description: 'Cinder represents a cinder volume attached and mounted on kubelets host machine. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + properties: + fsType: + description: 'Filesystem type to mount. Must be a filesystem type supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: string + readOnly: + description: 'Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: boolean + secretRef: + description: 'Optional: points to a secret object containing parameters used to connect to OpenStack.' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + volumeID: + description: 'volume id used to identify the volume in cinder. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: string + required: + - volumeID + type: object + configMap: + description: ConfigMap represents a configMap that should populate this volume + properties: + defaultMode: + description: 'Optional: mode bits to use on created files by default. Must be a value between 0 and 0777. Defaults to 0644. Directories within the path are not affected by this setting. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + items: + description: If unspecified, each key-value pair in the Data field of the referenced ConfigMap will be projected into the volume as a file whose name is the key and content is the value. If specified, the listed keys will be projected into the specified paths, and unlisted keys will not be present. If a key is specified which is not present in the ConfigMap, the volume setup will error unless it is marked optional. Paths must be relative and may not contain the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file to map the key to. May not be an absolute path. May not contain the path element '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its keys must be defined + type: boolean + type: object + csi: + description: CSI (Container Storage Interface) represents storage that is handled by an external CSI driver (Alpha feature). + properties: + driver: + description: Driver is the name of the CSI driver that handles this volume. Consult with your admin for the correct name as registered in the cluster. + type: string + fsType: + description: Filesystem type to mount. Ex. "ext4", "xfs", "ntfs". If not provided, the empty value is passed to the associated CSI driver which will determine the default filesystem to apply. + type: string + nodePublishSecretRef: + description: NodePublishSecretRef is a reference to the secret object containing sensitive information to pass to the CSI driver to complete the CSI NodePublishVolume and NodeUnpublishVolume calls. This field is optional, and may be empty if no secret is required. If the secret object contains more than one secret, all secret references are passed. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + readOnly: + description: Specifies a read-only configuration for the volume. Defaults to false (read/write). + type: boolean + volumeAttributes: + additionalProperties: + type: string + description: VolumeAttributes stores driver-specific properties that are passed to the CSI driver. Consult your driver's documentation for supported values. + type: object + required: + - driver + type: object + downwardAPI: + description: DownwardAPI represents downward API about the pod that should populate this volume + properties: + defaultMode: + description: 'Optional: mode bits to use on created files by default. Must be a value between 0 and 0777. Defaults to 0644. Directories within the path are not affected by this setting. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + items: + description: Items is a list of downward API volume file + items: + description: DownwardAPIVolumeFile represents information to create the file containing the pod field + properties: + fieldRef: + description: 'Required: Selects a field of the pod: only annotations, labels, name and namespace are supported.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: 'Required: Path is the relative path name of the file to be created. Must not be absolute or contain the ''..'' path. Must be utf-8 encoded. The first item of the relative path must not start with ''..''' + type: string + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, requests.cpu and requests.memory) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + required: + - path + type: object + type: array + type: object + emptyDir: + description: 'EmptyDir represents a temporary directory that shares a pod''s lifetime. More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + properties: + medium: + description: 'What type of storage medium should back this directory. The default is "" which means to use the node''s default medium. Must be an empty string (default) or Memory. More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + type: string + sizeLimit: + anyOf: + - type: integer + - type: string + description: 'Total amount of local storage required for this EmptyDir volume. The size limit is also applicable for memory medium. The maximum usage on memory medium EmptyDir would be the minimum value between the SizeLimit specified here and the sum of memory limits of all containers in a pod. The default is nil which means that the limit is undefined. More info: http://kubernetes.io/docs/user-guide/volumes#emptydir' + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + fc: + description: FC represents a Fibre Channel resource that is attached to a kubelet's host machine and then exposed to the pod. + properties: + fsType: + description: 'Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + lun: + description: 'Optional: FC target lun number' + format: int32 + type: integer + readOnly: + description: 'Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts.' + type: boolean + targetWWNs: + description: 'Optional: FC target worldwide names (WWNs)' + items: + type: string + type: array + wwids: + description: 'Optional: FC volume world wide identifiers (wwids) Either wwids or combination of targetWWNs and lun must be set, but not both simultaneously.' + items: + type: string + type: array + type: object + flexVolume: + description: FlexVolume represents a generic volume resource that is provisioned/attached using an exec based plugin. + properties: + driver: + description: Driver is the name of the driver to use for this volume. + type: string + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". The default filesystem depends on FlexVolume script. + type: string + options: + additionalProperties: + type: string + description: 'Optional: Extra command options if any.' + type: object + readOnly: + description: 'Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts.' + type: boolean + secretRef: + description: 'Optional: SecretRef is reference to the secret object containing sensitive information to pass to the plugin scripts. This may be empty if no secret object is specified. If the secret object contains more than one secret, all secrets are passed to the plugin scripts.' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + required: + - driver + type: object + flocker: + description: Flocker represents a Flocker volume attached to a kubelet's host machine. This depends on the Flocker control service being running + properties: + datasetName: + description: Name of the dataset stored as metadata -> name on the dataset for Flocker should be considered as deprecated + type: string + datasetUUID: + description: UUID of the dataset. This is unique identifier of a Flocker dataset + type: string + type: object + gcePersistentDisk: + description: 'GCEPersistentDisk represents a GCE Disk resource that is attached to a kubelet''s host machine and then exposed to the pod. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + properties: + fsType: + description: 'Filesystem type of the volume that you want to mount. Tip: Ensure that the filesystem type is supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + partition: + description: 'The partition in the volume that you want to mount. If omitted, the default is to mount by volume name. Examples: For volume /dev/sda1, you specify the partition as "1". Similarly, the volume partition for /dev/sda is "0" (or you can leave the property empty). More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + format: int32 + type: integer + pdName: + description: 'Unique name of the PD resource in GCE. Used to identify the disk in GCE. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + type: string + readOnly: + description: 'ReadOnly here will force the ReadOnly setting in VolumeMounts. Defaults to false. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + type: boolean + required: + - pdName + type: object + gitRepo: + description: 'GitRepo represents a git repository at a particular revision. DEPRECATED: GitRepo is deprecated. To provision a container with a git repo, mount an EmptyDir into an InitContainer that clones the repo using git, then mount the EmptyDir into the Pod''s container.' + properties: + directory: + description: Target directory name. Must not contain or start with '..'. If '.' is supplied, the volume directory will be the git repository. Otherwise, if specified, the volume will contain the git repository in the subdirectory with the given name. + type: string + repository: + description: Repository URL + type: string + revision: + description: Commit hash for the specified revision. + type: string + required: + - repository + type: object + glusterfs: + description: 'Glusterfs represents a Glusterfs mount on the host that shares a pod''s lifetime. More info: https://examples.k8s.io/volumes/glusterfs/README.md' + properties: + endpoints: + description: 'EndpointsName is the endpoint name that details Glusterfs topology. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: string + path: + description: 'Path is the Glusterfs volume path. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: string + readOnly: + description: 'ReadOnly here will force the Glusterfs volume to be mounted with read-only permissions. Defaults to false. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: boolean + required: + - endpoints + - path + type: object + hostPath: + description: 'HostPath represents a pre-existing file or directory on the host machine that is directly exposed to the container. This is generally used for system agents or other privileged things that are allowed to see the host machine. Most containers will NOT need this. More info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath --- TODO(jonesdl) We need to restrict who can use host directory mounts and who can/can not mount host directories as read/write.' + properties: + path: + description: 'Path of the directory on the host. If the path is a symlink, it will follow the link to the real path. More info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath' + type: string + type: + description: 'Type for HostPath Volume Defaults to "" More info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath' + type: string + required: + - path + type: object + iscsi: + description: 'ISCSI represents an ISCSI Disk resource that is attached to a kubelet''s host machine and then exposed to the pod. More info: https://examples.k8s.io/volumes/iscsi/README.md' + properties: + chapAuthDiscovery: + description: whether support iSCSI Discovery CHAP authentication + type: boolean + chapAuthSession: + description: whether support iSCSI Session CHAP authentication + type: boolean + fsType: + description: 'Filesystem type of the volume that you want to mount. Tip: Ensure that the filesystem type is supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://kubernetes.io/docs/concepts/storage/volumes#iscsi TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + initiatorName: + description: Custom iSCSI Initiator Name. If initiatorName is specified with iscsiInterface simultaneously, new iSCSI interface : will be created for the connection. + type: string + iqn: + description: Target iSCSI Qualified Name. + type: string + iscsiInterface: + description: iSCSI Interface Name that uses an iSCSI transport. Defaults to 'default' (tcp). + type: string + lun: + description: iSCSI Target Lun number. + format: int32 + type: integer + portals: + description: iSCSI Target Portal List. The portal is either an IP or ip_addr:port if the port is other than default (typically TCP ports 860 and 3260). + items: + type: string + type: array + readOnly: + description: ReadOnly here will force the ReadOnly setting in VolumeMounts. Defaults to false. + type: boolean + secretRef: + description: CHAP Secret for iSCSI target and initiator authentication + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + targetPortal: + description: iSCSI Target Portal. The Portal is either an IP or ip_addr:port if the port is other than default (typically TCP ports 860 and 3260). + type: string + required: + - iqn + - lun + - targetPortal + type: object + name: + description: 'Volume''s name. Must be a DNS_LABEL and unique within the pod. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + nfs: + description: 'NFS represents an NFS mount on the host that shares a pod''s lifetime More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + properties: + path: + description: 'Path that is exported by the NFS server. More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: string + readOnly: + description: 'ReadOnly here will force the NFS export to be mounted with read-only permissions. Defaults to false. More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: boolean + server: + description: 'Server is the hostname or IP address of the NFS server. More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: string + required: + - path + - server + type: object + persistentVolumeClaim: + description: 'PersistentVolumeClaimVolumeSource represents a reference to a PersistentVolumeClaim in the same namespace. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + properties: + claimName: + description: 'ClaimName is the name of a PersistentVolumeClaim in the same namespace as the pod using this volume. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + type: string + readOnly: + description: Will force the ReadOnly setting in VolumeMounts. Default false. + type: boolean + required: + - claimName + type: object + photonPersistentDisk: + description: PhotonPersistentDisk represents a PhotonController persistent disk attached and mounted on kubelets host machine + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + pdID: + description: ID that identifies Photon Controller persistent disk + type: string + required: + - pdID + type: object + portworxVolume: + description: PortworxVolume represents a portworx volume attached and mounted on kubelets host machine + properties: + fsType: + description: FSType represents the filesystem type to mount Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs". Implicitly inferred to be "ext4" if unspecified. + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + volumeID: + description: VolumeID uniquely identifies a Portworx volume + type: string + required: + - volumeID + type: object + projected: + description: Items for all in one resources secrets, configmaps, and downward API + properties: + defaultMode: + description: Mode bits to use on created files by default. Must be a value between 0 and 0777. Directories within the path are not affected by this setting. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set. + format: int32 + type: integer + sources: + description: list of volume projections + items: + description: Projection that may be projected along with other supported volume types + properties: + configMap: + description: information about the configMap data to project + properties: + items: + description: If unspecified, each key-value pair in the Data field of the referenced ConfigMap will be projected into the volume as a file whose name is the key and content is the value. If specified, the listed keys will be projected into the specified paths, and unlisted keys will not be present. If a key is specified which is not present in the ConfigMap, the volume setup will error unless it is marked optional. Paths must be relative and may not contain the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file to map the key to. May not be an absolute path. May not contain the path element '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its keys must be defined + type: boolean + type: object + downwardAPI: + description: information about the downwardAPI data to project + properties: + items: + description: Items is a list of DownwardAPIVolume file + items: + description: DownwardAPIVolumeFile represents information to create the file containing the pod field + properties: + fieldRef: + description: 'Required: Selects a field of the pod: only annotations, labels, name and namespace are supported.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: 'Required: Path is the relative path name of the file to be created. Must not be absolute or contain the ''..'' path. Must be utf-8 encoded. The first item of the relative path must not start with ''..''' + type: string + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, requests.cpu and requests.memory) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + required: + - path + type: object + type: array + type: object + secret: + description: information about the secret data to project + properties: + items: + description: If unspecified, each key-value pair in the Data field of the referenced Secret will be projected into the volume as a file whose name is the key and content is the value. If specified, the listed keys will be projected into the specified paths, and unlisted keys will not be present. If a key is specified which is not present in the Secret, the volume setup will error unless it is marked optional. Paths must be relative and may not contain the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file to map the key to. May not be an absolute path. May not contain the path element '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + type: object + serviceAccountToken: + description: information about the serviceAccountToken data to project + properties: + audience: + description: Audience is the intended audience of the token. A recipient of a token must identify itself with an identifier specified in the audience of the token, and otherwise should reject the token. The audience defaults to the identifier of the apiserver. + type: string + expirationSeconds: + description: ExpirationSeconds is the requested duration of validity of the service account token. As the token approaches expiration, the kubelet volume plugin will proactively rotate the service account token. The kubelet will start trying to rotate the token if the token is older than 80 percent of its time to live or if the token is older than 24 hours.Defaults to 1 hour and must be at least 10 minutes. + format: int64 + type: integer + path: + description: Path is the path relative to the mount point of the file to project the token into. + type: string + required: + - path + type: object + type: object + type: array + required: + - sources + type: object + quobyte: + description: Quobyte represents a Quobyte mount on the host that shares a pod's lifetime + properties: + group: + description: Group to map volume access to Default is no group + type: string + readOnly: + description: ReadOnly here will force the Quobyte volume to be mounted with read-only permissions. Defaults to false. + type: boolean + registry: + description: Registry represents a single or multiple Quobyte Registry services specified as a string as host:port pair (multiple entries are separated with commas) which acts as the central registry for volumes + type: string + tenant: + description: Tenant owning the given Quobyte volume in the Backend Used with dynamically provisioned Quobyte volumes, value is set by the plugin + type: string + user: + description: User to map volume access to Defaults to serivceaccount user + type: string + volume: + description: Volume is a string that references an already created Quobyte volume by name. + type: string + required: + - registry + - volume + type: object + rbd: + description: 'RBD represents a Rados Block Device mount on the host that shares a pod''s lifetime. More info: https://examples.k8s.io/volumes/rbd/README.md' + properties: + fsType: + description: 'Filesystem type of the volume that you want to mount. Tip: Ensure that the filesystem type is supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://kubernetes.io/docs/concepts/storage/volumes#rbd TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + image: + description: 'The rados image name. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + keyring: + description: 'Keyring is the path to key ring for RBDUser. Default is /etc/ceph/keyring. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + monitors: + description: 'A collection of Ceph monitors. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + items: + type: string + type: array + pool: + description: 'The rados pool name. Default is rbd. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + readOnly: + description: 'ReadOnly here will force the ReadOnly setting in VolumeMounts. Defaults to false. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: boolean + secretRef: + description: 'SecretRef is name of the authentication secret for RBDUser. If provided overrides keyring. Default is nil. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + user: + description: 'The rados user name. Default is admin. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + required: + - image + - monitors + type: object + scaleIO: + description: ScaleIO represents a ScaleIO persistent volume attached and mounted on Kubernetes nodes. + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Default is "xfs". + type: string + gateway: + description: The host address of the ScaleIO API Gateway. + type: string + protectionDomain: + description: The name of the ScaleIO Protection Domain for the configured storage. + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + secretRef: + description: SecretRef references to the secret for ScaleIO user and other sensitive information. If this is not provided, Login operation will fail. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + sslEnabled: + description: Flag to enable/disable SSL communication with Gateway, default false + type: boolean + storageMode: + description: Indicates whether the storage for a volume should be ThickProvisioned or ThinProvisioned. Default is ThinProvisioned. + type: string + storagePool: + description: The ScaleIO Storage Pool associated with the protection domain. + type: string + system: + description: The name of the storage system as configured in ScaleIO. + type: string + volumeName: + description: The name of a volume already created in the ScaleIO system that is associated with this volume source. + type: string + required: + - gateway + - secretRef + - system + type: object + secret: + description: 'Secret represents a secret that should populate this volume. More info: https://kubernetes.io/docs/concepts/storage/volumes#secret' + properties: + defaultMode: + description: 'Optional: mode bits to use on created files by default. Must be a value between 0 and 0777. Defaults to 0644. Directories within the path are not affected by this setting. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + items: + description: If unspecified, each key-value pair in the Data field of the referenced Secret will be projected into the volume as a file whose name is the key and content is the value. If specified, the listed keys will be projected into the specified paths, and unlisted keys will not be present. If a key is specified which is not present in the Secret, the volume setup will error unless it is marked optional. Paths must be relative and may not contain the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file to map the key to. May not be an absolute path. May not contain the path element '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + optional: + description: Specify whether the Secret or its keys must be defined + type: boolean + secretName: + description: 'Name of the secret in the pod''s namespace to use. More info: https://kubernetes.io/docs/concepts/storage/volumes#secret' + type: string + type: object + storageos: + description: StorageOS represents a StorageOS volume attached and mounted on Kubernetes nodes. + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + secretRef: + description: SecretRef specifies the secret to use for obtaining the StorageOS API credentials. If not specified, default values will be attempted. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + volumeName: + description: VolumeName is the human-readable name of the StorageOS volume. Volume names are only unique within a namespace. + type: string + volumeNamespace: + description: VolumeNamespace specifies the scope of the volume within StorageOS. If no namespace is specified then the Pod's namespace will be used. This allows the Kubernetes name scoping to be mirrored within StorageOS for tighter integration. Set VolumeName to any name to override the default behaviour. Set to "default" if you are not using namespaces within StorageOS. Namespaces that do not pre-exist within StorageOS will be created. + type: string + type: object + vsphereVolume: + description: VsphereVolume represents a vSphere volume attached and mounted on kubelets host machine + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + storagePolicyID: + description: Storage Policy Based Management (SPBM) profile ID associated with the StoragePolicyName. + type: string + storagePolicyName: + description: Storage Policy Based Management (SPBM) profile name. + type: string + volumePath: + description: Path that identifies vSphere volume vmdk + type: string + required: + - volumePath + type: object + required: + - name + type: object + type: array + walCompression: + description: Enable compression of the write-ahead log using Snappy. This flag is only available in versions of Prometheus >= 2.11.0. + type: boolean + web: + description: WebSpec defines the web command line flags when starting Prometheus. + properties: + pageTitle: + description: The prometheus web page title + type: string + type: object + type: object + status: + description: 'Most recent observed status of the Prometheus cluster. Read-only. Not included when requesting from the apiserver, only from the Prometheus Operator API itself. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#spec-and-status' + properties: + availableReplicas: + description: Total number of available pods (ready for at least minReadySeconds) targeted by this Prometheus deployment. + format: int32 + type: integer + paused: + description: Represents whether any actions on the underlying managed objects are being performed. Only delete actions will be performed. + type: boolean + replicas: + description: Total number of non-terminated pods targeted by this Prometheus deployment (their labels match the selector). + format: int32 + type: integer + unavailableReplicas: + description: Total number of unavailable pods targeted by this Prometheus deployment. + format: int32 + type: integer + updatedReplicas: + description: Total number of non-terminated pods targeted by this Prometheus deployment that have the desired version spec. + format: int32 + type: integer + required: + - availableReplicas + - paused + - replicas + - unavailableReplicas + - updatedReplicas + type: object + required: + - spec + type: object + served: true + storage: true + subresources: {} +status: + acceptedNames: + kind: "" + plural: "" + conditions: [] + storedVersions: [] diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-prometheusrules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-prometheusrules.yaml new file mode 100644 index 00000000..02759cd7 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-prometheusrules.yaml @@ -0,0 +1,90 @@ +# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.44.0/example/prometheus-operator-crd/monitoring.coreos.com_prometheusrules.yaml + +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.4.1 + creationTimestamp: null + name: prometheusrules.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + kind: PrometheusRule + listKind: PrometheusRuleList + plural: prometheusrules + singular: prometheusrule + scope: Namespaced + versions: + - name: v1 + schema: + openAPIV3Schema: + description: PrometheusRule defines recording and alerting rules for a Prometheus instance + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Specification of desired alerting rule definitions for Prometheus. + properties: + groups: + description: Content of Prometheus rule file + items: + description: 'RuleGroup is a list of sequentially evaluated recording and alerting rules. Note: PartialResponseStrategy is only used by ThanosRuler and will be ignored by Prometheus instances. Valid values for this field are ''warn'' or ''abort''. More info: https://github.com/thanos-io/thanos/blob/master/docs/components/rule.md#partial-response' + properties: + interval: + type: string + name: + type: string + partial_response_strategy: + type: string + rules: + items: + description: Rule describes an alerting or recording rule. + properties: + alert: + type: string + annotations: + additionalProperties: + type: string + type: object + expr: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + for: + type: string + labels: + additionalProperties: + type: string + type: object + record: + type: string + required: + - expr + type: object + type: array + required: + - name + - rules + type: object + type: array + type: object + required: + - spec + type: object + served: true + storage: true +status: + acceptedNames: + kind: "" + plural: "" + conditions: [] + storedVersions: [] diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-servicemonitors.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-servicemonitors.yaml new file mode 100644 index 00000000..f5d989d7 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-servicemonitors.yaml @@ -0,0 +1,373 @@ +# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.44.0/example/prometheus-operator-crd/monitoring.coreos.com_servicemonitors.yaml + +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.4.1 + creationTimestamp: null + name: servicemonitors.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + kind: ServiceMonitor + listKind: ServiceMonitorList + plural: servicemonitors + singular: servicemonitor + scope: Namespaced + versions: + - name: v1 + schema: + openAPIV3Schema: + description: ServiceMonitor defines monitoring for a set of services. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Specification of desired Service selection for target discovery by Prometheus. + properties: + endpoints: + description: A list of endpoints allowed as part of this ServiceMonitor. + items: + description: Endpoint defines a scrapeable endpoint serving Prometheus metrics. + properties: + basicAuth: + description: 'BasicAuth allow an endpoint to authenticate over basic authentication More info: https://prometheus.io/docs/operating/configuration/#endpoints' + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + bearerTokenFile: + description: File to read bearer token for scraping targets. + type: string + bearerTokenSecret: + description: Secret to mount to read bearer token for scraping targets. The secret needs to be in the same namespace as the service monitor and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + honorLabels: + description: HonorLabels chooses the metric's labels on collisions with target labels. + type: boolean + honorTimestamps: + description: HonorTimestamps controls whether Prometheus respects the timestamps present in scraped data. + type: boolean + interval: + description: Interval at which metrics should be scraped + type: string + metricRelabelings: + description: MetricRelabelConfigs to apply to samples before ingestion. + items: + description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines ``-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + description: Action to perform based on regex matching. Default is 'replace' + type: string + modulus: + description: Modulus to take of the hash of the source label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions. + items: + type: string + type: array + targetLabel: + description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available. + type: string + type: object + type: array + params: + additionalProperties: + items: + type: string + type: array + description: Optional HTTP URL parameters + type: object + path: + description: HTTP path to scrape for metrics. + type: string + port: + description: Name of the service port this endpoint refers to. Mutually exclusive with targetPort. + type: string + proxyUrl: + description: ProxyURL eg http://proxyserver:2195 Directs scrapes to proxy through this endpoint. + type: string + relabelings: + description: 'RelabelConfigs to apply to samples before scraping. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config' + items: + description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines ``-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + description: Action to perform based on regex matching. Default is 'replace' + type: string + modulus: + description: Modulus to take of the hash of the source label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions. + items: + type: string + type: array + targetLabel: + description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available. + type: string + type: object + type: array + scheme: + description: HTTP scheme to use for scraping. + type: string + scrapeTimeout: + description: Timeout after which the scrape is ended + type: string + targetPort: + anyOf: + - type: integer + - type: string + description: Name or number of the target port of the Pod behind the Service, the port must be specified with container port property. Mutually exclusive with port. + x-kubernetes-int-or-string: true + tlsConfig: + description: TLS configuration to use when scraping the endpoint + properties: + ca: + description: Struct containing the CA cert to use for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + caFile: + description: Path to the CA cert in the Prometheus container to use for the targets. + type: string + cert: + description: Struct containing the client cert file for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + certFile: + description: Path to the client cert file in the Prometheus container for the targets. + type: string + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keyFile: + description: Path to the client key file in the Prometheus container for the targets. + type: string + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + type: array + jobLabel: + description: The label to use to retrieve the job name from. + type: string + namespaceSelector: + description: Selector to select which namespaces the Endpoints objects are discovered from. + properties: + any: + description: Boolean describing whether all namespaces are selected in contrast to a list restricting them. + type: boolean + matchNames: + description: List of namespace names. + items: + type: string + type: array + type: object + podTargetLabels: + description: PodTargetLabels transfers labels on the Kubernetes Pod onto the target. + items: + type: string + type: array + sampleLimit: + description: SampleLimit defines per-scrape limit on number of scraped samples that will be accepted. + format: int64 + type: integer + selector: + description: Selector to select Endpoints objects. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + targetLabels: + description: TargetLabels transfers labels on the Kubernetes Service onto the target. + items: + type: string + type: array + targetLimit: + description: TargetLimit defines a limit on the number of scraped targets that will be accepted. + format: int64 + type: integer + required: + - endpoints + - selector + type: object + required: + - spec + type: object + served: true + storage: true +status: + acceptedNames: + kind: "" + plural: "" + conditions: [] + storedVersions: [] diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-thanosrulers.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-thanosrulers.yaml new file mode 100644 index 00000000..f647e724 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-thanosrulers.yaml @@ -0,0 +1,3340 @@ +# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.44.0/example/prometheus-operator-crd/monitoring.coreos.com_thanosrulers.yaml + +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.4.1 + creationTimestamp: null + name: thanosrulers.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + kind: ThanosRuler + listKind: ThanosRulerList + plural: thanosrulers + singular: thanosruler + scope: Namespaced + versions: + - name: v1 + schema: + openAPIV3Schema: + description: ThanosRuler defines a ThanosRuler deployment. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: 'Specification of the desired behavior of the ThanosRuler cluster. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#spec-and-status' + properties: + affinity: + description: If specified, the pod's scheduling constraints. + properties: + nodeAffinity: + description: Describes node affinity scheduling rules for the pod. + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node matches the corresponding matchExpressions; the node(s) with the highest sum are the most preferred. + items: + description: An empty preferred scheduling term matches all objects with implicit weight 0 (i.e. it's a no-op). A null preferred scheduling term matches no objects (i.e. is also a no-op). + properties: + preference: + description: A node selector term, associated with the corresponding weight. + properties: + matchExpressions: + description: A list of node selector requirements by node's labels. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchFields: + description: A list of node selector requirements by node's fields. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + type: object + weight: + description: Weight associated with matching the corresponding nodeSelectorTerm, in the range 1-100. + format: int32 + type: integer + required: + - preference + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node. + properties: + nodeSelectorTerms: + description: Required. A list of node selector terms. The terms are ORed. + items: + description: A null or empty node selector term matches no objects. The requirements of them are ANDed. The TopologySelectorTerm type implements a subset of the NodeSelectorTerm. + properties: + matchExpressions: + description: A list of node selector requirements by node's labels. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchFields: + description: A list of node selector requirements by node's fields. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + type: object + type: array + required: + - nodeSelectorTerms + type: object + type: object + podAffinity: + description: Describes pod affinity scheduling rules (e.g. co-locate this pod in the same node, zone, etc. as some other pod(s)). + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. + items: + description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated with the corresponding weight. + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + namespaces: + description: namespaces specifies which namespaces the labelSelector applies to (matches against); null or empty list means "this pod's namespace" + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + weight: + description: weight associated with matching the corresponding podAffinityTerm, in the range 1-100. + format: int32 + type: integer + required: + - podAffinityTerm + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. + items: + description: Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + namespaces: + description: namespaces specifies which namespaces the labelSelector applies to (matches against); null or empty list means "this pod's namespace" + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + type: array + type: object + podAntiAffinity: + description: Describes pod anti-affinity scheduling rules (e.g. avoid putting this pod in the same node, zone, etc. as some other pod(s)). + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the anti-affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling anti-affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. + items: + description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated with the corresponding weight. + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + namespaces: + description: namespaces specifies which namespaces the labelSelector applies to (matches against); null or empty list means "this pod's namespace" + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + weight: + description: weight associated with matching the corresponding podAffinityTerm, in the range 1-100. + format: int32 + type: integer + required: + - podAffinityTerm + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the anti-affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the anti-affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. + items: + description: Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + namespaces: + description: namespaces specifies which namespaces the labelSelector applies to (matches against); null or empty list means "this pod's namespace" + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + type: array + type: object + type: object + alertDropLabels: + description: AlertDropLabels configure the label names which should be dropped in ThanosRuler alerts. If `labels` field is not provided, `thanos_ruler_replica` will be dropped in alerts by default. + items: + type: string + type: array + alertQueryUrl: + description: The external Query URL the Thanos Ruler will set in the 'Source' field of all alerts. Maps to the '--alert.query-url' CLI arg. + type: string + alertmanagersConfig: + description: Define configuration for connecting to alertmanager. Only available with thanos v0.10.0 and higher. Maps to the `alertmanagers.config` arg. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + alertmanagersUrl: + description: 'Define URLs to send alerts to Alertmanager. For Thanos v0.10.0 and higher, AlertManagersConfig should be used instead. Note: this field will be ignored if AlertManagersConfig is specified. Maps to the `alertmanagers.url` arg.' + items: + type: string + type: array + containers: + description: 'Containers allows injecting additional containers or modifying operator generated containers. This can be used to allow adding an authentication proxy to a ThanosRuler pod or to change the behavior of an operator generated container. Containers described here modify an operator generated container if they share the same name and modifications are done via a strategic merge patch. The current container names are: `thanos-ruler` and `config-reloader`. Overriding containers is entirely outside the scope of what the maintainers will support and by doing so, you accept that this behaviour may break at any time without notice.' + items: + description: A single application container that you want to run within a pod. + properties: + args: + description: 'Arguments to the entrypoint. The docker image''s CMD is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + command: + description: 'Entrypoint array. Not executed within a shell. The docker image''s ENTRYPOINT is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + env: + description: List of environment variables to set in the container. Cannot be updated. + items: + description: EnvVar represents an environment variable present in a Container. + properties: + name: + description: Name of the environment variable. Must be a C_IDENTIFIER. + type: string + value: + description: 'Variable references $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "".' + type: string + valueFrom: + description: Source for the environment variable's value. Cannot be used if value is not empty. + properties: + configMapKeyRef: + description: Selects a key of a ConfigMap. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + fieldRef: + description: 'Selects a field of the pod: supports metadata.name, metadata.namespace, metadata.labels, metadata.annotations, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + secretKeyRef: + description: Selects a key of a secret in the pod's namespace + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + required: + - name + type: object + type: array + envFrom: + description: List of sources to populate environment variables in the container. The keys defined within a source must be a C_IDENTIFIER. All invalid keys will be reported as an event when the container is starting. When a key exists in multiple sources, the value associated with the last source will take precedence. Values defined by an Env with a duplicate key will take precedence. Cannot be updated. + items: + description: EnvFromSource represents the source of a set of ConfigMaps + properties: + configMapRef: + description: The ConfigMap to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap must be defined + type: boolean + type: object + prefix: + description: An optional identifier to prepend to each key in the ConfigMap. Must be a C_IDENTIFIER. + type: string + secretRef: + description: The Secret to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret must be defined + type: boolean + type: object + type: object + type: array + image: + description: 'Docker image name. More info: https://kubernetes.io/docs/concepts/containers/images This field is optional to allow higher level config management to default or override container images in workload controllers like Deployments and StatefulSets.' + type: string + imagePullPolicy: + description: 'Image pull policy. One of Always, Never, IfNotPresent. Defaults to Always if :latest tag is specified, or IfNotPresent otherwise. Cannot be updated. More info: https://kubernetes.io/docs/concepts/containers/images#updating-images' + type: string + lifecycle: + description: Actions that the management system should take in response to container lifecycle events. Cannot be updated. + properties: + postStart: + description: 'PostStart is called immediately after a container is created. If the handler fails, the container is terminated and restarted according to its restart policy. Other management of the container blocks until the hook completes. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + preStop: + description: 'PreStop is called immediately before a container is terminated due to an API request or management event such as liveness/startup probe failure, preemption, resource contention, etc. The handler is not called if the container crashes or exits. The reason for termination is passed to the handler. The Pod''s termination grace period countdown begins before the PreStop hooked is executed. Regardless of the outcome of the handler, the container will eventually terminate within the Pod''s termination grace period. Other management of the container blocks until the hook completes or until the termination grace period is reached. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + type: object + livenessProbe: + description: 'Periodic probe of container liveness. Container will be restarted if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + name: + description: Name of the container specified as a DNS_LABEL. Each container in a pod must have a unique name (DNS_LABEL). Cannot be updated. + type: string + ports: + description: List of ports to expose from the container. Exposing a port here gives the system additional information about the network connections a container uses, but is primarily informational. Not specifying a port here DOES NOT prevent that port from being exposed. Any port which is listening on the default "0.0.0.0" address inside a container will be accessible from the network. Cannot be updated. + items: + description: ContainerPort represents a network port in a single container. + properties: + containerPort: + description: Number of port to expose on the pod's IP address. This must be a valid port number, 0 < x < 65536. + format: int32 + type: integer + hostIP: + description: What host IP to bind the external port to. + type: string + hostPort: + description: Number of port to expose on the host. If specified, this must be a valid port number, 0 < x < 65536. If HostNetwork is specified, this must match ContainerPort. Most containers do not need this. + format: int32 + type: integer + name: + description: If specified, this must be an IANA_SVC_NAME and unique within the pod. Each named port in a pod must have a unique name. Name for the port that can be referred to by services. + type: string + protocol: + default: TCP + description: Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP". + type: string + required: + - containerPort + type: object + type: array + x-kubernetes-list-map-keys: + - containerPort + - protocol + x-kubernetes-list-type: map + readinessProbe: + description: 'Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + resources: + description: 'Compute Resources required by this container. Cannot be updated. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + type: object + securityContext: + description: 'Security options the pod should run with. More info: https://kubernetes.io/docs/concepts/policy/security-context/ More info: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/' + properties: + allowPrivilegeEscalation: + description: 'AllowPrivilegeEscalation controls whether a process can gain more privileges than its parent process. This bool directly controls if the no_new_privs flag will be set on the container process. AllowPrivilegeEscalation is true always when the container is: 1) run as Privileged 2) has CAP_SYS_ADMIN' + type: boolean + capabilities: + description: The capabilities to add/drop when running containers. Defaults to the default set of capabilities granted by the container runtime. + properties: + add: + description: Added capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + drop: + description: Removed capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + type: object + privileged: + description: Run container in privileged mode. Processes in privileged containers are essentially equivalent to root on the host. Defaults to false. + type: boolean + procMount: + description: procMount denotes the type of proc mount to use for the containers. The default is DefaultProcMount which uses the container runtime defaults for readonly paths and masked paths. This requires the ProcMountType feature flag to be enabled. + type: string + readOnlyRootFilesystem: + description: Whether this container has a read-only root filesystem. Default is false. + type: boolean + runAsGroup: + description: The GID to run the entrypoint of the container process. Uses runtime default if unset. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + format: int64 + type: integer + runAsNonRoot: + description: Indicates that the container must run as a non-root user. If true, the Kubelet will validate the image at runtime to ensure that it does not run as UID 0 (root) and fail to start the container if it does. If unset or false, no such validation will be performed. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: boolean + runAsUser: + description: The UID to run the entrypoint of the container process. Defaults to user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + format: int64 + type: integer + seLinuxOptions: + description: The SELinux context to be applied to the container. If unspecified, the container runtime will allocate a random SELinux context for each container. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + properties: + level: + description: Level is SELinux level label that applies to the container. + type: string + role: + description: Role is a SELinux role label that applies to the container. + type: string + type: + description: Type is a SELinux type label that applies to the container. + type: string + user: + description: User is a SELinux user label that applies to the container. + type: string + type: object + windowsOptions: + description: The Windows specific settings applied to all containers. If unspecified, the options from the PodSecurityContext will be used. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + properties: + gmsaCredentialSpec: + description: GMSACredentialSpec is where the GMSA admission webhook (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the GMSA credential spec named by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the GMSA credential spec to use. + type: string + runAsUserName: + description: The UserName in Windows to run the entrypoint of the container process. Defaults to the user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: string + type: object + type: object + startupProbe: + description: 'StartupProbe indicates that the Pod has successfully initialized. If specified, no other probes are executed until this completes successfully. If this probe fails, the Pod will be restarted, just as if the livenessProbe failed. This can be used to provide different probe parameters at the beginning of a Pod''s lifecycle, when it might take a long time to load data or warm a cache, than during steady-state operation. This cannot be updated. This is a beta feature enabled by the StartupProbe feature flag. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + stdin: + description: Whether this container should allocate a buffer for stdin in the container runtime. If this is not set, reads from stdin in the container will always result in EOF. Default is false. + type: boolean + stdinOnce: + description: Whether the container runtime should close the stdin channel after it has been opened by a single attach. When stdin is true the stdin stream will remain open across multiple attach sessions. If stdinOnce is set to true, stdin is opened on container start, is empty until the first client attaches to stdin, and then remains open and accepts data until the client disconnects, at which time stdin is closed and remains closed until the container is restarted. If this flag is false, a container processes that reads from stdin will never receive an EOF. Default is false + type: boolean + terminationMessagePath: + description: 'Optional: Path at which the file to which the container''s termination message will be written is mounted into the container''s filesystem. Message written is intended to be brief final status, such as an assertion failure message. Will be truncated by the node if greater than 4096 bytes. The total message length across all containers will be limited to 12kb. Defaults to /dev/termination-log. Cannot be updated.' + type: string + terminationMessagePolicy: + description: Indicate how the termination message should be populated. File will use the contents of terminationMessagePath to populate the container status message on both success and failure. FallbackToLogsOnError will use the last chunk of container log output if the termination message file is empty and the container exited with an error. The log output is limited to 2048 bytes or 80 lines, whichever is smaller. Defaults to File. Cannot be updated. + type: string + tty: + description: Whether this container should allocate a TTY for itself, also requires 'stdin' to be true. Default is false. + type: boolean + volumeDevices: + description: volumeDevices is the list of block devices to be used by the container. + items: + description: volumeDevice describes a mapping of a raw block device within a container. + properties: + devicePath: + description: devicePath is the path inside of the container that the device will be mapped to. + type: string + name: + description: name must match the name of a persistentVolumeClaim in the pod + type: string + required: + - devicePath + - name + type: object + type: array + volumeMounts: + description: Pod volumes to mount into the container's filesystem. Cannot be updated. + items: + description: VolumeMount describes a mounting of a Volume within a container. + properties: + mountPath: + description: Path within the container at which the volume should be mounted. Must not contain ':'. + type: string + mountPropagation: + description: mountPropagation determines how mounts are propagated from the host to container and the other way around. When not set, MountPropagationNone is used. This field is beta in 1.10. + type: string + name: + description: This must match the Name of a Volume. + type: string + readOnly: + description: Mounted read-only if true, read-write otherwise (false or unspecified). Defaults to false. + type: boolean + subPath: + description: Path within the volume from which the container's volume should be mounted. Defaults to "" (volume's root). + type: string + subPathExpr: + description: Expanded path within the volume from which the container's volume should be mounted. Behaves similarly to SubPath but environment variable references $(VAR_NAME) are expanded using the container's environment. Defaults to "" (volume's root). SubPathExpr and SubPath are mutually exclusive. + type: string + required: + - mountPath + - name + type: object + type: array + workingDir: + description: Container's working directory. If not specified, the container runtime's default will be used, which might be configured in the container image. Cannot be updated. + type: string + required: + - name + type: object + type: array + enforcedNamespaceLabel: + description: EnforcedNamespaceLabel enforces adding a namespace label of origin for each alert and metric that is user created. The label value will always be the namespace of the object that is being created. + type: string + evaluationInterval: + description: Interval between consecutive evaluations. + type: string + externalPrefix: + description: The external URL the Thanos Ruler instances will be available under. This is necessary to generate correct URLs. This is necessary if Thanos Ruler is not served from root of a DNS name. + type: string + grpcServerTlsConfig: + description: 'GRPCServerTLSConfig configures the gRPC server from which Thanos Querier reads recorded rule data. Note: Currently only the CAFile, CertFile, and KeyFile fields are supported. Maps to the ''--grpc-server-tls-*'' CLI args.' + properties: + ca: + description: Struct containing the CA cert to use for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + caFile: + description: Path to the CA cert in the Prometheus container to use for the targets. + type: string + cert: + description: Struct containing the client cert file for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + certFile: + description: Path to the client cert file in the Prometheus container for the targets. + type: string + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keyFile: + description: Path to the client key file in the Prometheus container for the targets. + type: string + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + image: + description: Thanos container image URL. + type: string + imagePullSecrets: + description: An optional list of references to secrets in the same namespace to use for pulling thanos images from registries see http://kubernetes.io/docs/user-guide/images#specifying-imagepullsecrets-on-a-pod + items: + description: LocalObjectReference contains enough information to let you locate the referenced object inside the same namespace. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + type: array + initContainers: + description: 'InitContainers allows adding initContainers to the pod definition. Those can be used to e.g. fetch secrets for injection into the ThanosRuler configuration from external sources. Any errors during the execution of an initContainer will lead to a restart of the Pod. More info: https://kubernetes.io/docs/concepts/workloads/pods/init-containers/ Using initContainers for any use case other then secret fetching is entirely outside the scope of what the maintainers will support and by doing so, you accept that this behaviour may break at any time without notice.' + items: + description: A single application container that you want to run within a pod. + properties: + args: + description: 'Arguments to the entrypoint. The docker image''s CMD is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + command: + description: 'Entrypoint array. Not executed within a shell. The docker image''s ENTRYPOINT is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + env: + description: List of environment variables to set in the container. Cannot be updated. + items: + description: EnvVar represents an environment variable present in a Container. + properties: + name: + description: Name of the environment variable. Must be a C_IDENTIFIER. + type: string + value: + description: 'Variable references $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "".' + type: string + valueFrom: + description: Source for the environment variable's value. Cannot be used if value is not empty. + properties: + configMapKeyRef: + description: Selects a key of a ConfigMap. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + fieldRef: + description: 'Selects a field of the pod: supports metadata.name, metadata.namespace, metadata.labels, metadata.annotations, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + secretKeyRef: + description: Selects a key of a secret in the pod's namespace + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + required: + - name + type: object + type: array + envFrom: + description: List of sources to populate environment variables in the container. The keys defined within a source must be a C_IDENTIFIER. All invalid keys will be reported as an event when the container is starting. When a key exists in multiple sources, the value associated with the last source will take precedence. Values defined by an Env with a duplicate key will take precedence. Cannot be updated. + items: + description: EnvFromSource represents the source of a set of ConfigMaps + properties: + configMapRef: + description: The ConfigMap to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap must be defined + type: boolean + type: object + prefix: + description: An optional identifier to prepend to each key in the ConfigMap. Must be a C_IDENTIFIER. + type: string + secretRef: + description: The Secret to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret must be defined + type: boolean + type: object + type: object + type: array + image: + description: 'Docker image name. More info: https://kubernetes.io/docs/concepts/containers/images This field is optional to allow higher level config management to default or override container images in workload controllers like Deployments and StatefulSets.' + type: string + imagePullPolicy: + description: 'Image pull policy. One of Always, Never, IfNotPresent. Defaults to Always if :latest tag is specified, or IfNotPresent otherwise. Cannot be updated. More info: https://kubernetes.io/docs/concepts/containers/images#updating-images' + type: string + lifecycle: + description: Actions that the management system should take in response to container lifecycle events. Cannot be updated. + properties: + postStart: + description: 'PostStart is called immediately after a container is created. If the handler fails, the container is terminated and restarted according to its restart policy. Other management of the container blocks until the hook completes. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + preStop: + description: 'PreStop is called immediately before a container is terminated due to an API request or management event such as liveness/startup probe failure, preemption, resource contention, etc. The handler is not called if the container crashes or exits. The reason for termination is passed to the handler. The Pod''s termination grace period countdown begins before the PreStop hooked is executed. Regardless of the outcome of the handler, the container will eventually terminate within the Pod''s termination grace period. Other management of the container blocks until the hook completes or until the termination grace period is reached. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + type: object + livenessProbe: + description: 'Periodic probe of container liveness. Container will be restarted if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + name: + description: Name of the container specified as a DNS_LABEL. Each container in a pod must have a unique name (DNS_LABEL). Cannot be updated. + type: string + ports: + description: List of ports to expose from the container. Exposing a port here gives the system additional information about the network connections a container uses, but is primarily informational. Not specifying a port here DOES NOT prevent that port from being exposed. Any port which is listening on the default "0.0.0.0" address inside a container will be accessible from the network. Cannot be updated. + items: + description: ContainerPort represents a network port in a single container. + properties: + containerPort: + description: Number of port to expose on the pod's IP address. This must be a valid port number, 0 < x < 65536. + format: int32 + type: integer + hostIP: + description: What host IP to bind the external port to. + type: string + hostPort: + description: Number of port to expose on the host. If specified, this must be a valid port number, 0 < x < 65536. If HostNetwork is specified, this must match ContainerPort. Most containers do not need this. + format: int32 + type: integer + name: + description: If specified, this must be an IANA_SVC_NAME and unique within the pod. Each named port in a pod must have a unique name. Name for the port that can be referred to by services. + type: string + protocol: + default: TCP + description: Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP". + type: string + required: + - containerPort + type: object + type: array + x-kubernetes-list-map-keys: + - containerPort + - protocol + x-kubernetes-list-type: map + readinessProbe: + description: 'Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + resources: + description: 'Compute Resources required by this container. Cannot be updated. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + type: object + securityContext: + description: 'Security options the pod should run with. More info: https://kubernetes.io/docs/concepts/policy/security-context/ More info: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/' + properties: + allowPrivilegeEscalation: + description: 'AllowPrivilegeEscalation controls whether a process can gain more privileges than its parent process. This bool directly controls if the no_new_privs flag will be set on the container process. AllowPrivilegeEscalation is true always when the container is: 1) run as Privileged 2) has CAP_SYS_ADMIN' + type: boolean + capabilities: + description: The capabilities to add/drop when running containers. Defaults to the default set of capabilities granted by the container runtime. + properties: + add: + description: Added capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + drop: + description: Removed capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + type: object + privileged: + description: Run container in privileged mode. Processes in privileged containers are essentially equivalent to root on the host. Defaults to false. + type: boolean + procMount: + description: procMount denotes the type of proc mount to use for the containers. The default is DefaultProcMount which uses the container runtime defaults for readonly paths and masked paths. This requires the ProcMountType feature flag to be enabled. + type: string + readOnlyRootFilesystem: + description: Whether this container has a read-only root filesystem. Default is false. + type: boolean + runAsGroup: + description: The GID to run the entrypoint of the container process. Uses runtime default if unset. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + format: int64 + type: integer + runAsNonRoot: + description: Indicates that the container must run as a non-root user. If true, the Kubelet will validate the image at runtime to ensure that it does not run as UID 0 (root) and fail to start the container if it does. If unset or false, no such validation will be performed. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: boolean + runAsUser: + description: The UID to run the entrypoint of the container process. Defaults to user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + format: int64 + type: integer + seLinuxOptions: + description: The SELinux context to be applied to the container. If unspecified, the container runtime will allocate a random SELinux context for each container. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + properties: + level: + description: Level is SELinux level label that applies to the container. + type: string + role: + description: Role is a SELinux role label that applies to the container. + type: string + type: + description: Type is a SELinux type label that applies to the container. + type: string + user: + description: User is a SELinux user label that applies to the container. + type: string + type: object + windowsOptions: + description: The Windows specific settings applied to all containers. If unspecified, the options from the PodSecurityContext will be used. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + properties: + gmsaCredentialSpec: + description: GMSACredentialSpec is where the GMSA admission webhook (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the GMSA credential spec named by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the GMSA credential spec to use. + type: string + runAsUserName: + description: The UserName in Windows to run the entrypoint of the container process. Defaults to the user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: string + type: object + type: object + startupProbe: + description: 'StartupProbe indicates that the Pod has successfully initialized. If specified, no other probes are executed until this completes successfully. If this probe fails, the Pod will be restarted, just as if the livenessProbe failed. This can be used to provide different probe parameters at the beginning of a Pod''s lifecycle, when it might take a long time to load data or warm a cache, than during steady-state operation. This cannot be updated. This is a beta feature enabled by the StartupProbe feature flag. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: One and only one of the following should be specified. Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: 'TCPSocket specifies an action involving a TCP port. TCP hooks not yet supported TODO: implement a realistic TCP lifecycle hook' + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + stdin: + description: Whether this container should allocate a buffer for stdin in the container runtime. If this is not set, reads from stdin in the container will always result in EOF. Default is false. + type: boolean + stdinOnce: + description: Whether the container runtime should close the stdin channel after it has been opened by a single attach. When stdin is true the stdin stream will remain open across multiple attach sessions. If stdinOnce is set to true, stdin is opened on container start, is empty until the first client attaches to stdin, and then remains open and accepts data until the client disconnects, at which time stdin is closed and remains closed until the container is restarted. If this flag is false, a container processes that reads from stdin will never receive an EOF. Default is false + type: boolean + terminationMessagePath: + description: 'Optional: Path at which the file to which the container''s termination message will be written is mounted into the container''s filesystem. Message written is intended to be brief final status, such as an assertion failure message. Will be truncated by the node if greater than 4096 bytes. The total message length across all containers will be limited to 12kb. Defaults to /dev/termination-log. Cannot be updated.' + type: string + terminationMessagePolicy: + description: Indicate how the termination message should be populated. File will use the contents of terminationMessagePath to populate the container status message on both success and failure. FallbackToLogsOnError will use the last chunk of container log output if the termination message file is empty and the container exited with an error. The log output is limited to 2048 bytes or 80 lines, whichever is smaller. Defaults to File. Cannot be updated. + type: string + tty: + description: Whether this container should allocate a TTY for itself, also requires 'stdin' to be true. Default is false. + type: boolean + volumeDevices: + description: volumeDevices is the list of block devices to be used by the container. + items: + description: volumeDevice describes a mapping of a raw block device within a container. + properties: + devicePath: + description: devicePath is the path inside of the container that the device will be mapped to. + type: string + name: + description: name must match the name of a persistentVolumeClaim in the pod + type: string + required: + - devicePath + - name + type: object + type: array + volumeMounts: + description: Pod volumes to mount into the container's filesystem. Cannot be updated. + items: + description: VolumeMount describes a mounting of a Volume within a container. + properties: + mountPath: + description: Path within the container at which the volume should be mounted. Must not contain ':'. + type: string + mountPropagation: + description: mountPropagation determines how mounts are propagated from the host to container and the other way around. When not set, MountPropagationNone is used. This field is beta in 1.10. + type: string + name: + description: This must match the Name of a Volume. + type: string + readOnly: + description: Mounted read-only if true, read-write otherwise (false or unspecified). Defaults to false. + type: boolean + subPath: + description: Path within the volume from which the container's volume should be mounted. Defaults to "" (volume's root). + type: string + subPathExpr: + description: Expanded path within the volume from which the container's volume should be mounted. Behaves similarly to SubPath but environment variable references $(VAR_NAME) are expanded using the container's environment. Defaults to "" (volume's root). SubPathExpr and SubPath are mutually exclusive. + type: string + required: + - mountPath + - name + type: object + type: array + workingDir: + description: Container's working directory. If not specified, the container runtime's default will be used, which might be configured in the container image. Cannot be updated. + type: string + required: + - name + type: object + type: array + labels: + additionalProperties: + type: string + description: Labels configure the external label pairs to ThanosRuler. If not provided, default replica label `thanos_ruler_replica` will be added as a label and be dropped in alerts. + type: object + listenLocal: + description: ListenLocal makes the Thanos ruler listen on loopback, so that it does not bind against the Pod IP. + type: boolean + logFormat: + description: Log format for ThanosRuler to be configured with. + type: string + logLevel: + description: Log level for ThanosRuler to be configured with. + type: string + nodeSelector: + additionalProperties: + type: string + description: Define which Nodes the Pods are scheduled on. + type: object + objectStorageConfig: + description: ObjectStorageConfig configures object storage in Thanos. Alternative to ObjectStorageConfigFile, and lower order priority. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + objectStorageConfigFile: + description: ObjectStorageConfigFile specifies the path of the object storage configuration file. When used alongside with ObjectStorageConfig, ObjectStorageConfigFile takes precedence. + type: string + paused: + description: When a ThanosRuler deployment is paused, no actions except for deletion will be performed on the underlying objects. + type: boolean + podMetadata: + description: PodMetadata contains Labels and Annotations gets propagated to the thanos ruler pods. + properties: + annotations: + additionalProperties: + type: string + description: 'Annotations is an unstructured key value map stored with a resource that may be set by external tools to store and retrieve arbitrary metadata. They are not queryable and should be preserved when modifying objects. More info: http://kubernetes.io/docs/user-guide/annotations' + type: object + labels: + additionalProperties: + type: string + description: 'Map of string keys and values that can be used to organize and categorize (scope and select) objects. May match selectors of replication controllers and services. More info: http://kubernetes.io/docs/user-guide/labels' + type: object + name: + description: 'Name must be unique within a namespace. Is required when creating resources, although some resources may allow a client to request the generation of an appropriate name automatically. Name is primarily intended for creation idempotence and configuration definition. Cannot be updated. More info: http://kubernetes.io/docs/user-guide/identifiers#names' + type: string + type: object + portName: + description: Port name used for the pods and governing service. This defaults to web + type: string + priorityClassName: + description: Priority class assigned to the Pods + type: string + prometheusRulesExcludedFromEnforce: + description: PrometheusRulesExcludedFromEnforce - list of Prometheus rules to be excluded from enforcing of adding namespace labels. Works only if enforcedNamespaceLabel set to true. Make sure both ruleNamespace and ruleName are set for each pair + items: + description: PrometheusRuleExcludeConfig enables users to configure excluded PrometheusRule names and their namespaces to be ignored while enforcing namespace label for alerts and metrics. + properties: + ruleName: + description: RuleNamespace - name of excluded rule + type: string + ruleNamespace: + description: RuleNamespace - namespace of excluded rule + type: string + required: + - ruleName + - ruleNamespace + type: object + type: array + queryConfig: + description: Define configuration for connecting to thanos query instances. If this is defined, the QueryEndpoints field will be ignored. Maps to the `query.config` CLI argument. Only available with thanos v0.11.0 and higher. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + queryEndpoints: + description: QueryEndpoints defines Thanos querier endpoints from which to query metrics. Maps to the --query flag of thanos ruler. + items: + type: string + type: array + replicas: + description: Number of thanos ruler instances to deploy. + format: int32 + type: integer + resources: + description: Resources defines the resource requirements for single Pods. If not provided, no requests/limits will be set + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + type: object + retention: + description: Time duration ThanosRuler shall retain data for. Default is '24h', and must match the regular expression `[0-9]+(ms|s|m|h|d|w|y)` (milliseconds seconds minutes hours days weeks years). + type: string + routePrefix: + description: The route prefix ThanosRuler registers HTTP handlers for. This allows thanos UI to be served on a sub-path. + type: string + ruleNamespaceSelector: + description: Namespaces to be selected for Rules discovery. If unspecified, only the same namespace as the ThanosRuler object is in is used. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + ruleSelector: + description: A label selector to select which PrometheusRules to mount for alerting and recording. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + securityContext: + description: SecurityContext holds pod-level security attributes and common container settings. This defaults to the default PodSecurityContext. + properties: + fsGroup: + description: "A special supplemental group that applies to all containers in a pod. Some volume types allow the Kubelet to change the ownership of that volume to be owned by the pod: \n 1. The owning GID will be the FSGroup 2. The setgid bit is set (new files created in the volume will be owned by FSGroup) 3. The permission bits are OR'd with rw-rw---- \n If unset, the Kubelet will not modify the ownership and permissions of any volume." + format: int64 + type: integer + fsGroupChangePolicy: + description: 'fsGroupChangePolicy defines behavior of changing ownership and permission of the volume before being exposed inside Pod. This field will only apply to volume types which support fsGroup based ownership(and permissions). It will have no effect on ephemeral volume types such as: secret, configmaps and emptydir. Valid values are "OnRootMismatch" and "Always". If not specified defaults to "Always".' + type: string + runAsGroup: + description: The GID to run the entrypoint of the container process. Uses runtime default if unset. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. + format: int64 + type: integer + runAsNonRoot: + description: Indicates that the container must run as a non-root user. If true, the Kubelet will validate the image at runtime to ensure that it does not run as UID 0 (root) and fail to start the container if it does. If unset or false, no such validation will be performed. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: boolean + runAsUser: + description: The UID to run the entrypoint of the container process. Defaults to user specified in image metadata if unspecified. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. + format: int64 + type: integer + seLinuxOptions: + description: The SELinux context to be applied to all containers. If unspecified, the container runtime will allocate a random SELinux context for each container. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. + properties: + level: + description: Level is SELinux level label that applies to the container. + type: string + role: + description: Role is a SELinux role label that applies to the container. + type: string + type: + description: Type is a SELinux type label that applies to the container. + type: string + user: + description: User is a SELinux user label that applies to the container. + type: string + type: object + supplementalGroups: + description: A list of groups applied to the first process run in each container, in addition to the container's primary GID. If unspecified, no groups will be added to any container. + items: + format: int64 + type: integer + type: array + sysctls: + description: Sysctls hold a list of namespaced sysctls used for the pod. Pods with unsupported sysctls (by the container runtime) might fail to launch. + items: + description: Sysctl defines a kernel parameter to be set + properties: + name: + description: Name of a property to set + type: string + value: + description: Value of a property to set + type: string + required: + - name + - value + type: object + type: array + windowsOptions: + description: The Windows specific settings applied to all containers. If unspecified, the options within a container's SecurityContext will be used. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + properties: + gmsaCredentialSpec: + description: GMSACredentialSpec is where the GMSA admission webhook (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the GMSA credential spec named by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the GMSA credential spec to use. + type: string + runAsUserName: + description: The UserName in Windows to run the entrypoint of the container process. Defaults to the user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: string + type: object + type: object + serviceAccountName: + description: ServiceAccountName is the name of the ServiceAccount to use to run the Thanos Ruler Pods. + type: string + storage: + description: Storage spec to specify how storage shall be used. + properties: + disableMountSubPath: + description: 'Deprecated: subPath usage will be disabled by default in a future release, this option will become unnecessary. DisableMountSubPath allows to remove any subPath usage in volume mounts.' + type: boolean + emptyDir: + description: 'EmptyDirVolumeSource to be used by the Prometheus StatefulSets. If specified, used in place of any volumeClaimTemplate. More info: https://kubernetes.io/docs/concepts/storage/volumes/#emptydir' + properties: + medium: + description: 'What type of storage medium should back this directory. The default is "" which means to use the node''s default medium. Must be an empty string (default) or Memory. More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + type: string + sizeLimit: + anyOf: + - type: integer + - type: string + description: 'Total amount of local storage required for this EmptyDir volume. The size limit is also applicable for memory medium. The maximum usage on memory medium EmptyDir would be the minimum value between the SizeLimit specified here and the sum of memory limits of all containers in a pod. The default is nil which means that the limit is undefined. More info: http://kubernetes.io/docs/user-guide/volumes#emptydir' + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + volumeClaimTemplate: + description: A PVC spec to be used by the Prometheus StatefulSets. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + description: EmbeddedMetadata contains metadata relevant to an EmbeddedResource. + properties: + annotations: + additionalProperties: + type: string + description: 'Annotations is an unstructured key value map stored with a resource that may be set by external tools to store and retrieve arbitrary metadata. They are not queryable and should be preserved when modifying objects. More info: http://kubernetes.io/docs/user-guide/annotations' + type: object + labels: + additionalProperties: + type: string + description: 'Map of string keys and values that can be used to organize and categorize (scope and select) objects. May match selectors of replication controllers and services. More info: http://kubernetes.io/docs/user-guide/labels' + type: object + name: + description: 'Name must be unique within a namespace. Is required when creating resources, although some resources may allow a client to request the generation of an appropriate name automatically. Name is primarily intended for creation idempotence and configuration definition. Cannot be updated. More info: http://kubernetes.io/docs/user-guide/identifiers#names' + type: string + type: object + spec: + description: 'Spec defines the desired characteristics of a volume requested by a pod author. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + properties: + accessModes: + description: 'AccessModes contains the desired access modes the volume should have. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#access-modes-1' + items: + type: string + type: array + dataSource: + description: 'This field can be used to specify either: * An existing VolumeSnapshot object (snapshot.storage.k8s.io/VolumeSnapshot - Beta) * An existing PVC (PersistentVolumeClaim) * An existing custom resource/object that implements data population (Alpha) In order to use VolumeSnapshot object types, the appropriate feature gate must be enabled (VolumeSnapshotDataSource or AnyVolumeDataSource) If the provisioner or an external controller can support the specified data source, it will create a new volume based on the contents of the specified data source. If the specified data source is not supported, the volume will not be created and the failure will be reported as an event. In the future, we plan to support more data source types and the behavior of the provisioner may change.' + properties: + apiGroup: + description: APIGroup is the group for the resource being referenced. If APIGroup is not specified, the specified Kind must be in the core API group. For any other third-party types, APIGroup is required. + type: string + kind: + description: Kind is the type of resource being referenced + type: string + name: + description: Name is the name of resource being referenced + type: string + required: + - kind + - name + type: object + resources: + description: 'Resources represents the minimum resources the volume should have. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#resources' + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' + type: object + type: object + selector: + description: A label query over volumes to consider for binding. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + storageClassName: + description: 'Name of the StorageClass required by the claim. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#class-1' + type: string + volumeMode: + description: volumeMode defines what type of volume is required by the claim. Value of Filesystem is implied when not included in claim spec. + type: string + volumeName: + description: VolumeName is the binding reference to the PersistentVolume backing this claim. + type: string + type: object + status: + description: 'Status represents the current information/status of a persistent volume claim. Read-only. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + properties: + accessModes: + description: 'AccessModes contains the actual access modes the volume backing the PVC has. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#access-modes-1' + items: + type: string + type: array + capacity: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: Represents the actual resources of the underlying volume. + type: object + conditions: + description: Current Condition of persistent volume claim. If underlying persistent volume is being resized then the Condition will be set to 'ResizeStarted'. + items: + description: PersistentVolumeClaimCondition contails details about state of pvc + properties: + lastProbeTime: + description: Last time we probed the condition. + format: date-time + type: string + lastTransitionTime: + description: Last time the condition transitioned from one status to another. + format: date-time + type: string + message: + description: Human-readable message indicating details about last transition. + type: string + reason: + description: Unique, this should be a short, machine understandable string that gives the reason for condition's last transition. If it reports "ResizeStarted" that means the underlying persistent volume is being resized. + type: string + status: + type: string + type: + description: PersistentVolumeClaimConditionType is a valid value of PersistentVolumeClaimCondition.Type + type: string + required: + - status + - type + type: object + type: array + phase: + description: Phase represents the current phase of PersistentVolumeClaim. + type: string + type: object + type: object + type: object + tolerations: + description: If specified, the pod's tolerations. + items: + description: The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . + properties: + effect: + description: Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. + type: string + key: + description: Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. + type: string + operator: + description: Operator represents a key's relationship to the value. Valid operators are Exists and Equal. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. + type: string + tolerationSeconds: + description: TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. + format: int64 + type: integer + value: + description: Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. + type: string + type: object + type: array + topologySpreadConstraints: + description: If specified, the pod's topology spread constraints. + items: + description: TopologySpreadConstraint specifies how to spread matching pods among the given topology. + properties: + labelSelector: + description: LabelSelector is used to find matching pods. Pods that match this label selector are counted to determine the number of pods in their corresponding topology domain. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + maxSkew: + description: 'MaxSkew describes the degree to which pods may be unevenly distributed. It''s the maximum permitted difference between the number of matching pods in any two topology domains of a given topology type. For example, in a 3-zone cluster, MaxSkew is set to 1, and pods with the same labelSelector spread as 1/1/0: | zone1 | zone2 | zone3 | | P | P | | - if MaxSkew is 1, incoming pod can only be scheduled to zone3 to become 1/1/1; scheduling it onto zone1(zone2) would make the ActualSkew(2-0) on zone1(zone2) violate MaxSkew(1). - if MaxSkew is 2, incoming pod can be scheduled onto any zone. It''s a required field. Default value is 1 and 0 is not allowed.' + format: int32 + type: integer + topologyKey: + description: TopologyKey is the key of node labels. Nodes that have a label with this key and identical values are considered to be in the same topology. We consider each as a "bucket", and try to put balanced number of pods into each bucket. It's a required field. + type: string + whenUnsatisfiable: + description: 'WhenUnsatisfiable indicates how to deal with a pod if it doesn''t satisfy the spread constraint. - DoNotSchedule (default) tells the scheduler not to schedule it - ScheduleAnyway tells the scheduler to still schedule it It''s considered as "Unsatisfiable" if and only if placing incoming pod on any topology violates "MaxSkew". For example, in a 3-zone cluster, MaxSkew is set to 1, and pods with the same labelSelector spread as 3/1/1: | zone1 | zone2 | zone3 | | P P P | P | P | If WhenUnsatisfiable is set to DoNotSchedule, incoming pod can only be scheduled to zone2(zone3) to become 3/2/1(3/1/2) as ActualSkew(2-1) on zone2(zone3) satisfies MaxSkew(1). In other words, the cluster can still be imbalanced, but scheduler won''t make it *more* imbalanced. It''s a required field.' + type: string + required: + - maxSkew + - topologyKey + - whenUnsatisfiable + type: object + type: array + tracingConfig: + description: TracingConfig configures tracing in Thanos. This is an experimental feature, it may change in any upcoming release in a breaking way. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + volumes: + description: Volumes allows configuration of additional volumes on the output StatefulSet definition. Volumes specified will be appended to other volumes that are generated as a result of StorageSpec objects. + items: + description: Volume represents a named volume in a pod that may be accessed by any container in the pod. + properties: + awsElasticBlockStore: + description: 'AWSElasticBlockStore represents an AWS Disk resource that is attached to a kubelet''s host machine and then exposed to the pod. More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + properties: + fsType: + description: 'Filesystem type of the volume that you want to mount. Tip: Ensure that the filesystem type is supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + partition: + description: 'The partition in the volume that you want to mount. If omitted, the default is to mount by volume name. Examples: For volume /dev/sda1, you specify the partition as "1". Similarly, the volume partition for /dev/sda is "0" (or you can leave the property empty).' + format: int32 + type: integer + readOnly: + description: 'Specify "true" to force and set the ReadOnly property in VolumeMounts to "true". If omitted, the default is "false". More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + type: boolean + volumeID: + description: 'Unique ID of the persistent disk resource in AWS (Amazon EBS volume). More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + type: string + required: + - volumeID + type: object + azureDisk: + description: AzureDisk represents an Azure Data Disk mount on the host and bind mount to the pod. + properties: + cachingMode: + description: 'Host Caching mode: None, Read Only, Read Write.' + type: string + diskName: + description: The Name of the data disk in the blob storage + type: string + diskURI: + description: The URI the data disk in the blob storage + type: string + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + kind: + description: 'Expected values Shared: multiple blob disks per storage account Dedicated: single blob disk per storage account Managed: azure managed data disk (only in managed availability set). defaults to shared' + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + required: + - diskName + - diskURI + type: object + azureFile: + description: AzureFile represents an Azure File Service mount on the host and bind mount to the pod. + properties: + readOnly: + description: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + secretName: + description: the name of secret that contains Azure Storage Account Name and Key + type: string + shareName: + description: Share Name + type: string + required: + - secretName + - shareName + type: object + cephfs: + description: CephFS represents a Ceph FS mount on the host that shares a pod's lifetime + properties: + monitors: + description: 'Required: Monitors is a collection of Ceph monitors More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + items: + type: string + type: array + path: + description: 'Optional: Used as the mounted root, rather than the full Ceph tree, default is /' + type: string + readOnly: + description: 'Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: boolean + secretFile: + description: 'Optional: SecretFile is the path to key ring for User, default is /etc/ceph/user.secret More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: string + secretRef: + description: 'Optional: SecretRef is reference to the authentication secret for User, default is empty. More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + user: + description: 'Optional: User is the rados user name, default is admin More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: string + required: + - monitors + type: object + cinder: + description: 'Cinder represents a cinder volume attached and mounted on kubelets host machine. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + properties: + fsType: + description: 'Filesystem type to mount. Must be a filesystem type supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: string + readOnly: + description: 'Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: boolean + secretRef: + description: 'Optional: points to a secret object containing parameters used to connect to OpenStack.' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + volumeID: + description: 'volume id used to identify the volume in cinder. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: string + required: + - volumeID + type: object + configMap: + description: ConfigMap represents a configMap that should populate this volume + properties: + defaultMode: + description: 'Optional: mode bits to use on created files by default. Must be a value between 0 and 0777. Defaults to 0644. Directories within the path are not affected by this setting. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + items: + description: If unspecified, each key-value pair in the Data field of the referenced ConfigMap will be projected into the volume as a file whose name is the key and content is the value. If specified, the listed keys will be projected into the specified paths, and unlisted keys will not be present. If a key is specified which is not present in the ConfigMap, the volume setup will error unless it is marked optional. Paths must be relative and may not contain the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file to map the key to. May not be an absolute path. May not contain the path element '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its keys must be defined + type: boolean + type: object + csi: + description: CSI (Container Storage Interface) represents storage that is handled by an external CSI driver (Alpha feature). + properties: + driver: + description: Driver is the name of the CSI driver that handles this volume. Consult with your admin for the correct name as registered in the cluster. + type: string + fsType: + description: Filesystem type to mount. Ex. "ext4", "xfs", "ntfs". If not provided, the empty value is passed to the associated CSI driver which will determine the default filesystem to apply. + type: string + nodePublishSecretRef: + description: NodePublishSecretRef is a reference to the secret object containing sensitive information to pass to the CSI driver to complete the CSI NodePublishVolume and NodeUnpublishVolume calls. This field is optional, and may be empty if no secret is required. If the secret object contains more than one secret, all secret references are passed. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + readOnly: + description: Specifies a read-only configuration for the volume. Defaults to false (read/write). + type: boolean + volumeAttributes: + additionalProperties: + type: string + description: VolumeAttributes stores driver-specific properties that are passed to the CSI driver. Consult your driver's documentation for supported values. + type: object + required: + - driver + type: object + downwardAPI: + description: DownwardAPI represents downward API about the pod that should populate this volume + properties: + defaultMode: + description: 'Optional: mode bits to use on created files by default. Must be a value between 0 and 0777. Defaults to 0644. Directories within the path are not affected by this setting. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + items: + description: Items is a list of downward API volume file + items: + description: DownwardAPIVolumeFile represents information to create the file containing the pod field + properties: + fieldRef: + description: 'Required: Selects a field of the pod: only annotations, labels, name and namespace are supported.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: 'Required: Path is the relative path name of the file to be created. Must not be absolute or contain the ''..'' path. Must be utf-8 encoded. The first item of the relative path must not start with ''..''' + type: string + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, requests.cpu and requests.memory) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + required: + - path + type: object + type: array + type: object + emptyDir: + description: 'EmptyDir represents a temporary directory that shares a pod''s lifetime. More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + properties: + medium: + description: 'What type of storage medium should back this directory. The default is "" which means to use the node''s default medium. Must be an empty string (default) or Memory. More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + type: string + sizeLimit: + anyOf: + - type: integer + - type: string + description: 'Total amount of local storage required for this EmptyDir volume. The size limit is also applicable for memory medium. The maximum usage on memory medium EmptyDir would be the minimum value between the SizeLimit specified here and the sum of memory limits of all containers in a pod. The default is nil which means that the limit is undefined. More info: http://kubernetes.io/docs/user-guide/volumes#emptydir' + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + fc: + description: FC represents a Fibre Channel resource that is attached to a kubelet's host machine and then exposed to the pod. + properties: + fsType: + description: 'Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + lun: + description: 'Optional: FC target lun number' + format: int32 + type: integer + readOnly: + description: 'Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts.' + type: boolean + targetWWNs: + description: 'Optional: FC target worldwide names (WWNs)' + items: + type: string + type: array + wwids: + description: 'Optional: FC volume world wide identifiers (wwids) Either wwids or combination of targetWWNs and lun must be set, but not both simultaneously.' + items: + type: string + type: array + type: object + flexVolume: + description: FlexVolume represents a generic volume resource that is provisioned/attached using an exec based plugin. + properties: + driver: + description: Driver is the name of the driver to use for this volume. + type: string + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". The default filesystem depends on FlexVolume script. + type: string + options: + additionalProperties: + type: string + description: 'Optional: Extra command options if any.' + type: object + readOnly: + description: 'Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts.' + type: boolean + secretRef: + description: 'Optional: SecretRef is reference to the secret object containing sensitive information to pass to the plugin scripts. This may be empty if no secret object is specified. If the secret object contains more than one secret, all secrets are passed to the plugin scripts.' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + required: + - driver + type: object + flocker: + description: Flocker represents a Flocker volume attached to a kubelet's host machine. This depends on the Flocker control service being running + properties: + datasetName: + description: Name of the dataset stored as metadata -> name on the dataset for Flocker should be considered as deprecated + type: string + datasetUUID: + description: UUID of the dataset. This is unique identifier of a Flocker dataset + type: string + type: object + gcePersistentDisk: + description: 'GCEPersistentDisk represents a GCE Disk resource that is attached to a kubelet''s host machine and then exposed to the pod. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + properties: + fsType: + description: 'Filesystem type of the volume that you want to mount. Tip: Ensure that the filesystem type is supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + partition: + description: 'The partition in the volume that you want to mount. If omitted, the default is to mount by volume name. Examples: For volume /dev/sda1, you specify the partition as "1". Similarly, the volume partition for /dev/sda is "0" (or you can leave the property empty). More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + format: int32 + type: integer + pdName: + description: 'Unique name of the PD resource in GCE. Used to identify the disk in GCE. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + type: string + readOnly: + description: 'ReadOnly here will force the ReadOnly setting in VolumeMounts. Defaults to false. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + type: boolean + required: + - pdName + type: object + gitRepo: + description: 'GitRepo represents a git repository at a particular revision. DEPRECATED: GitRepo is deprecated. To provision a container with a git repo, mount an EmptyDir into an InitContainer that clones the repo using git, then mount the EmptyDir into the Pod''s container.' + properties: + directory: + description: Target directory name. Must not contain or start with '..'. If '.' is supplied, the volume directory will be the git repository. Otherwise, if specified, the volume will contain the git repository in the subdirectory with the given name. + type: string + repository: + description: Repository URL + type: string + revision: + description: Commit hash for the specified revision. + type: string + required: + - repository + type: object + glusterfs: + description: 'Glusterfs represents a Glusterfs mount on the host that shares a pod''s lifetime. More info: https://examples.k8s.io/volumes/glusterfs/README.md' + properties: + endpoints: + description: 'EndpointsName is the endpoint name that details Glusterfs topology. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: string + path: + description: 'Path is the Glusterfs volume path. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: string + readOnly: + description: 'ReadOnly here will force the Glusterfs volume to be mounted with read-only permissions. Defaults to false. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: boolean + required: + - endpoints + - path + type: object + hostPath: + description: 'HostPath represents a pre-existing file or directory on the host machine that is directly exposed to the container. This is generally used for system agents or other privileged things that are allowed to see the host machine. Most containers will NOT need this. More info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath --- TODO(jonesdl) We need to restrict who can use host directory mounts and who can/can not mount host directories as read/write.' + properties: + path: + description: 'Path of the directory on the host. If the path is a symlink, it will follow the link to the real path. More info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath' + type: string + type: + description: 'Type for HostPath Volume Defaults to "" More info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath' + type: string + required: + - path + type: object + iscsi: + description: 'ISCSI represents an ISCSI Disk resource that is attached to a kubelet''s host machine and then exposed to the pod. More info: https://examples.k8s.io/volumes/iscsi/README.md' + properties: + chapAuthDiscovery: + description: whether support iSCSI Discovery CHAP authentication + type: boolean + chapAuthSession: + description: whether support iSCSI Session CHAP authentication + type: boolean + fsType: + description: 'Filesystem type of the volume that you want to mount. Tip: Ensure that the filesystem type is supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://kubernetes.io/docs/concepts/storage/volumes#iscsi TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + initiatorName: + description: Custom iSCSI Initiator Name. If initiatorName is specified with iscsiInterface simultaneously, new iSCSI interface : will be created for the connection. + type: string + iqn: + description: Target iSCSI Qualified Name. + type: string + iscsiInterface: + description: iSCSI Interface Name that uses an iSCSI transport. Defaults to 'default' (tcp). + type: string + lun: + description: iSCSI Target Lun number. + format: int32 + type: integer + portals: + description: iSCSI Target Portal List. The portal is either an IP or ip_addr:port if the port is other than default (typically TCP ports 860 and 3260). + items: + type: string + type: array + readOnly: + description: ReadOnly here will force the ReadOnly setting in VolumeMounts. Defaults to false. + type: boolean + secretRef: + description: CHAP Secret for iSCSI target and initiator authentication + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + targetPortal: + description: iSCSI Target Portal. The Portal is either an IP or ip_addr:port if the port is other than default (typically TCP ports 860 and 3260). + type: string + required: + - iqn + - lun + - targetPortal + type: object + name: + description: 'Volume''s name. Must be a DNS_LABEL and unique within the pod. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + nfs: + description: 'NFS represents an NFS mount on the host that shares a pod''s lifetime More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + properties: + path: + description: 'Path that is exported by the NFS server. More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: string + readOnly: + description: 'ReadOnly here will force the NFS export to be mounted with read-only permissions. Defaults to false. More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: boolean + server: + description: 'Server is the hostname or IP address of the NFS server. More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: string + required: + - path + - server + type: object + persistentVolumeClaim: + description: 'PersistentVolumeClaimVolumeSource represents a reference to a PersistentVolumeClaim in the same namespace. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + properties: + claimName: + description: 'ClaimName is the name of a PersistentVolumeClaim in the same namespace as the pod using this volume. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + type: string + readOnly: + description: Will force the ReadOnly setting in VolumeMounts. Default false. + type: boolean + required: + - claimName + type: object + photonPersistentDisk: + description: PhotonPersistentDisk represents a PhotonController persistent disk attached and mounted on kubelets host machine + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + pdID: + description: ID that identifies Photon Controller persistent disk + type: string + required: + - pdID + type: object + portworxVolume: + description: PortworxVolume represents a portworx volume attached and mounted on kubelets host machine + properties: + fsType: + description: FSType represents the filesystem type to mount Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs". Implicitly inferred to be "ext4" if unspecified. + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + volumeID: + description: VolumeID uniquely identifies a Portworx volume + type: string + required: + - volumeID + type: object + projected: + description: Items for all in one resources secrets, configmaps, and downward API + properties: + defaultMode: + description: Mode bits to use on created files by default. Must be a value between 0 and 0777. Directories within the path are not affected by this setting. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set. + format: int32 + type: integer + sources: + description: list of volume projections + items: + description: Projection that may be projected along with other supported volume types + properties: + configMap: + description: information about the configMap data to project + properties: + items: + description: If unspecified, each key-value pair in the Data field of the referenced ConfigMap will be projected into the volume as a file whose name is the key and content is the value. If specified, the listed keys will be projected into the specified paths, and unlisted keys will not be present. If a key is specified which is not present in the ConfigMap, the volume setup will error unless it is marked optional. Paths must be relative and may not contain the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file to map the key to. May not be an absolute path. May not contain the path element '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its keys must be defined + type: boolean + type: object + downwardAPI: + description: information about the downwardAPI data to project + properties: + items: + description: Items is a list of DownwardAPIVolume file + items: + description: DownwardAPIVolumeFile represents information to create the file containing the pod field + properties: + fieldRef: + description: 'Required: Selects a field of the pod: only annotations, labels, name and namespace are supported.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: 'Required: Path is the relative path name of the file to be created. Must not be absolute or contain the ''..'' path. Must be utf-8 encoded. The first item of the relative path must not start with ''..''' + type: string + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, requests.cpu and requests.memory) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + required: + - path + type: object + type: array + type: object + secret: + description: information about the secret data to project + properties: + items: + description: If unspecified, each key-value pair in the Data field of the referenced Secret will be projected into the volume as a file whose name is the key and content is the value. If specified, the listed keys will be projected into the specified paths, and unlisted keys will not be present. If a key is specified which is not present in the Secret, the volume setup will error unless it is marked optional. Paths must be relative and may not contain the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file to map the key to. May not be an absolute path. May not contain the path element '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + type: object + serviceAccountToken: + description: information about the serviceAccountToken data to project + properties: + audience: + description: Audience is the intended audience of the token. A recipient of a token must identify itself with an identifier specified in the audience of the token, and otherwise should reject the token. The audience defaults to the identifier of the apiserver. + type: string + expirationSeconds: + description: ExpirationSeconds is the requested duration of validity of the service account token. As the token approaches expiration, the kubelet volume plugin will proactively rotate the service account token. The kubelet will start trying to rotate the token if the token is older than 80 percent of its time to live or if the token is older than 24 hours.Defaults to 1 hour and must be at least 10 minutes. + format: int64 + type: integer + path: + description: Path is the path relative to the mount point of the file to project the token into. + type: string + required: + - path + type: object + type: object + type: array + required: + - sources + type: object + quobyte: + description: Quobyte represents a Quobyte mount on the host that shares a pod's lifetime + properties: + group: + description: Group to map volume access to Default is no group + type: string + readOnly: + description: ReadOnly here will force the Quobyte volume to be mounted with read-only permissions. Defaults to false. + type: boolean + registry: + description: Registry represents a single or multiple Quobyte Registry services specified as a string as host:port pair (multiple entries are separated with commas) which acts as the central registry for volumes + type: string + tenant: + description: Tenant owning the given Quobyte volume in the Backend Used with dynamically provisioned Quobyte volumes, value is set by the plugin + type: string + user: + description: User to map volume access to Defaults to serivceaccount user + type: string + volume: + description: Volume is a string that references an already created Quobyte volume by name. + type: string + required: + - registry + - volume + type: object + rbd: + description: 'RBD represents a Rados Block Device mount on the host that shares a pod''s lifetime. More info: https://examples.k8s.io/volumes/rbd/README.md' + properties: + fsType: + description: 'Filesystem type of the volume that you want to mount. Tip: Ensure that the filesystem type is supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://kubernetes.io/docs/concepts/storage/volumes#rbd TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + image: + description: 'The rados image name. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + keyring: + description: 'Keyring is the path to key ring for RBDUser. Default is /etc/ceph/keyring. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + monitors: + description: 'A collection of Ceph monitors. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + items: + type: string + type: array + pool: + description: 'The rados pool name. Default is rbd. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + readOnly: + description: 'ReadOnly here will force the ReadOnly setting in VolumeMounts. Defaults to false. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: boolean + secretRef: + description: 'SecretRef is name of the authentication secret for RBDUser. If provided overrides keyring. Default is nil. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + user: + description: 'The rados user name. Default is admin. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + required: + - image + - monitors + type: object + scaleIO: + description: ScaleIO represents a ScaleIO persistent volume attached and mounted on Kubernetes nodes. + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Default is "xfs". + type: string + gateway: + description: The host address of the ScaleIO API Gateway. + type: string + protectionDomain: + description: The name of the ScaleIO Protection Domain for the configured storage. + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + secretRef: + description: SecretRef references to the secret for ScaleIO user and other sensitive information. If this is not provided, Login operation will fail. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + sslEnabled: + description: Flag to enable/disable SSL communication with Gateway, default false + type: boolean + storageMode: + description: Indicates whether the storage for a volume should be ThickProvisioned or ThinProvisioned. Default is ThinProvisioned. + type: string + storagePool: + description: The ScaleIO Storage Pool associated with the protection domain. + type: string + system: + description: The name of the storage system as configured in ScaleIO. + type: string + volumeName: + description: The name of a volume already created in the ScaleIO system that is associated with this volume source. + type: string + required: + - gateway + - secretRef + - system + type: object + secret: + description: 'Secret represents a secret that should populate this volume. More info: https://kubernetes.io/docs/concepts/storage/volumes#secret' + properties: + defaultMode: + description: 'Optional: mode bits to use on created files by default. Must be a value between 0 and 0777. Defaults to 0644. Directories within the path are not affected by this setting. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + items: + description: If unspecified, each key-value pair in the Data field of the referenced Secret will be projected into the volume as a file whose name is the key and content is the value. If specified, the listed keys will be projected into the specified paths, and unlisted keys will not be present. If a key is specified which is not present in the Secret, the volume setup will error unless it is marked optional. Paths must be relative and may not contain the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits to use on this file, must be a value between 0 and 0777. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file to map the key to. May not be an absolute path. May not contain the path element '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + optional: + description: Specify whether the Secret or its keys must be defined + type: boolean + secretName: + description: 'Name of the secret in the pod''s namespace to use. More info: https://kubernetes.io/docs/concepts/storage/volumes#secret' + type: string + type: object + storageos: + description: StorageOS represents a StorageOS volume attached and mounted on Kubernetes nodes. + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + secretRef: + description: SecretRef specifies the secret to use for obtaining the StorageOS API credentials. If not specified, default values will be attempted. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + volumeName: + description: VolumeName is the human-readable name of the StorageOS volume. Volume names are only unique within a namespace. + type: string + volumeNamespace: + description: VolumeNamespace specifies the scope of the volume within StorageOS. If no namespace is specified then the Pod's namespace will be used. This allows the Kubernetes name scoping to be mirrored within StorageOS for tighter integration. Set VolumeName to any name to override the default behaviour. Set to "default" if you are not using namespaces within StorageOS. Namespaces that do not pre-exist within StorageOS will be created. + type: string + type: object + vsphereVolume: + description: VsphereVolume represents a vSphere volume attached and mounted on kubelets host machine + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + storagePolicyID: + description: Storage Policy Based Management (SPBM) profile ID associated with the StoragePolicyName. + type: string + storagePolicyName: + description: Storage Policy Based Management (SPBM) profile name. + type: string + volumePath: + description: Path that identifies vSphere volume vmdk + type: string + required: + - volumePath + type: object + required: + - name + type: object + type: array + type: object + status: + description: 'Most recent observed status of the ThanosRuler cluster. Read-only. Not included when requesting from the apiserver, only from the ThanosRuler Operator API itself. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#spec-and-status' + properties: + availableReplicas: + description: Total number of available pods (ready for at least minReadySeconds) targeted by this ThanosRuler deployment. + format: int32 + type: integer + paused: + description: Represents whether any actions on the underlying managed objects are being performed. Only delete actions will be performed. + type: boolean + replicas: + description: Total number of non-terminated pods targeted by this ThanosRuler deployment (their labels match the selector). + format: int32 + type: integer + unavailableReplicas: + description: Total number of unavailable pods targeted by this ThanosRuler deployment. + format: int32 + type: integer + updatedReplicas: + description: Total number of non-terminated pods targeted by this ThanosRuler deployment that have the desired version spec. + format: int32 + type: integer + required: + - availableReplicas + - paused + - replicas + - unavailableReplicas + - updatedReplicas + type: object + required: + - spec + type: object + served: true + storage: true +status: + acceptedNames: + kind: "" + plural: "" + conditions: [] + storedVersions: [] diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/NOTES.txt b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/NOTES.txt new file mode 100644 index 00000000..371f3ae3 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/NOTES.txt @@ -0,0 +1,4 @@ +{{ $.Chart.Name }} has been installed. Check its status by running: + kubectl --namespace {{ template "kube-prometheus-stack.namespace" . }} get pods -l "release={{ $.Release.Name }}" + +Visit https://github.com/prometheus-operator/kube-prometheus for instructions on how to create & configure Alertmanager and Prometheus instances using the Operator. diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/_helpers.tpl b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/_helpers.tpl new file mode 100644 index 00000000..8a3d1b76 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/_helpers.tpl @@ -0,0 +1,93 @@ +{{/* vim: set filetype=mustache: */}} +{{/* Expand the name of the chart. This is suffixed with -alertmanager, which means subtract 13 from longest 63 available */}} +{{- define "kube-prometheus-stack.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 50 | trimSuffix "-" -}} +{{- end }} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +The components in this chart create additional resources that expand the longest created name strings. +The longest name that gets created adds and extra 37 characters, so truncation should be 63-35=26. +*/}} +{{- define "kube-prometheus-stack.fullname" -}} +{{- if .Values.fullnameOverride -}} +{{- .Values.fullnameOverride | trunc 26 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .Chart.Name .Values.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- .Release.Name | trunc 26 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 26 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* Fullname suffixed with operator */}} +{{- define "kube-prometheus-stack.operator.fullname" -}} +{{- printf "%s-operator" (include "kube-prometheus-stack.fullname" .) -}} +{{- end }} + +{{/* Fullname suffixed with prometheus */}} +{{- define "kube-prometheus-stack.prometheus.fullname" -}} +{{- printf "%s-prometheus" (include "kube-prometheus-stack.fullname" .) -}} +{{- end }} + +{{/* Fullname suffixed with alertmanager */}} +{{- define "kube-prometheus-stack.alertmanager.fullname" -}} +{{- printf "%s-alertmanager" (include "kube-prometheus-stack.fullname" .) -}} +{{- end }} + +{{/* Create chart name and version as used by the chart label. */}} +{{- define "kube-prometheus-stack.chartref" -}} +{{- replace "+" "_" .Chart.Version | printf "%s-%s" .Chart.Name -}} +{{- end }} + +{{/* Generate basic labels */}} +{{- define "kube-prometheus-stack.labels" }} +chart: {{ template "kube-prometheus-stack.chartref" . }} +release: {{ $.Release.Name | quote }} +heritage: {{ $.Release.Service | quote }} +{{- if .Values.commonLabels}} +{{ toYaml .Values.commonLabels }} +{{- end }} +{{- end }} + +{{/* Create the name of kube-prometheus-stack service account to use */}} +{{- define "kube-prometheus-stack.operator.serviceAccountName" -}} +{{- if .Values.prometheusOperator.serviceAccount.create -}} + {{ default (include "kube-prometheus-stack.operator.fullname" .) .Values.prometheusOperator.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.prometheusOperator.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* Create the name of prometheus service account to use */}} +{{- define "kube-prometheus-stack.prometheus.serviceAccountName" -}} +{{- if .Values.prometheus.serviceAccount.create -}} + {{ default (include "kube-prometheus-stack.prometheus.fullname" .) .Values.prometheus.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.prometheus.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* Create the name of alertmanager service account to use */}} +{{- define "kube-prometheus-stack.alertmanager.serviceAccountName" -}} +{{- if .Values.alertmanager.serviceAccount.create -}} + {{ default (include "kube-prometheus-stack.alertmanager.fullname" .) .Values.alertmanager.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.alertmanager.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* +Allow the release namespace to be overridden for multi-namespace deployments in combined charts +*/}} +{{- define "kube-prometheus-stack.namespace" -}} + {{- if .Values.namespaceOverride -}} + {{- .Values.namespaceOverride -}} + {{- else -}} + {{- .Release.Namespace -}} + {{- end -}} +{{- end -}} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/alertmanager.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/alertmanager.yaml new file mode 100644 index 00000000..78d0f7c5 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/alertmanager.yaml @@ -0,0 +1,137 @@ +{{- if .Values.alertmanager.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: Alertmanager +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-alertmanager + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-alertmanager +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: +{{- if .Values.alertmanager.alertmanagerSpec.image }} + image: {{ .Values.alertmanager.alertmanagerSpec.image.repository }}:{{ .Values.alertmanager.alertmanagerSpec.image.tag }} + version: {{ .Values.alertmanager.alertmanagerSpec.image.tag }} + {{- if .Values.alertmanager.alertmanagerSpec.image.sha }} + sha: {{ .Values.alertmanager.alertmanagerSpec.image.sha }} + {{- end }} +{{- end }} + replicas: {{ .Values.alertmanager.alertmanagerSpec.replicas }} + listenLocal: {{ .Values.alertmanager.alertmanagerSpec.listenLocal }} + serviceAccountName: {{ template "kube-prometheus-stack.alertmanager.serviceAccountName" . }} +{{- if .Values.alertmanager.alertmanagerSpec.externalUrl }} + externalUrl: "{{ .Values.alertmanager.alertmanagerSpec.externalUrl }}" +{{- else if and .Values.alertmanager.ingress.enabled .Values.alertmanager.ingress.hosts }} + externalUrl: "http://{{ tpl (index .Values.alertmanager.ingress.hosts 0) . }}{{ .Values.alertmanager.alertmanagerSpec.routePrefix }}" +{{- else }} + externalUrl: http://{{ template "kube-prometheus-stack.fullname" . }}-alertmanager.{{ template "kube-prometheus-stack.namespace" . }}:{{ .Values.alertmanager.service.port }} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.nodeSelector }} + nodeSelector: +{{ toYaml .Values.alertmanager.alertmanagerSpec.nodeSelector | indent 4 }} +{{- end }} + paused: {{ .Values.alertmanager.alertmanagerSpec.paused }} + logFormat: {{ .Values.alertmanager.alertmanagerSpec.logFormat | quote }} + logLevel: {{ .Values.alertmanager.alertmanagerSpec.logLevel | quote }} + retention: {{ .Values.alertmanager.alertmanagerSpec.retention | quote }} +{{- if .Values.alertmanager.alertmanagerSpec.secrets }} + secrets: +{{ toYaml .Values.alertmanager.alertmanagerSpec.secrets | indent 4 }} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.configSecret }} + configSecret: {{ .Values.alertmanager.alertmanagerSpec.configSecret }} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.configMaps }} + configMaps: +{{ toYaml .Values.alertmanager.alertmanagerSpec.configMaps | indent 4 }} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.alertmanagerConfigSelector }} + alertmanagerConfigSelector: +{{ toYaml .Values.alertmanager.alertmanagerSpec.alertmanagerConfigSelector | indent 4}} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.alertmanagerConfigNamespaceSelector }} + alertmanagerConfigNamespaceSelector: +{{ toYaml .Values.alertmanager.alertmanagerSpec.alertmanagerConfigNamespaceSelector | indent 4}} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.resources }} + resources: +{{ toYaml .Values.alertmanager.alertmanagerSpec.resources | indent 4 }} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.routePrefix }} + routePrefix: "{{ .Values.alertmanager.alertmanagerSpec.routePrefix }}" +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.securityContext }} + securityContext: +{{ toYaml .Values.alertmanager.alertmanagerSpec.securityContext | indent 4 }} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.storage }} + storage: +{{ toYaml .Values.alertmanager.alertmanagerSpec.storage | indent 4 }} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.podMetadata }} + podMetadata: +{{ toYaml .Values.alertmanager.alertmanagerSpec.podMetadata | indent 4 }} +{{- end }} +{{- if or .Values.alertmanager.alertmanagerSpec.podAntiAffinity .Values.alertmanager.alertmanagerSpec.affinity }} + affinity: +{{- if .Values.alertmanager.alertmanagerSpec.affinity }} +{{ toYaml .Values.alertmanager.alertmanagerSpec.affinity | indent 4 }} +{{- end }} +{{- if eq .Values.alertmanager.alertmanagerSpec.podAntiAffinity "hard" }} + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - topologyKey: {{ .Values.alertmanager.alertmanagerSpec.podAntiAffinityTopologyKey }} + labelSelector: + matchLabels: + app: alertmanager + alertmanager: {{ template "kube-prometheus-stack.fullname" . }}-alertmanager +{{- else if eq .Values.alertmanager.alertmanagerSpec.podAntiAffinity "soft" }} + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + topologyKey: {{ .Values.alertmanager.alertmanagerSpec.podAntiAffinityTopologyKey }} + labelSelector: + matchLabels: + app: alertmanager + alertmanager: {{ template "kube-prometheus-stack.fullname" . }}-alertmanager +{{- end }} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.tolerations }} + tolerations: +{{ toYaml .Values.alertmanager.alertmanagerSpec.tolerations | indent 4 }} +{{- end }} +{{- if .Values.global.imagePullSecrets }} + imagePullSecrets: +{{ toYaml .Values.global.imagePullSecrets | indent 4 }} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.containers }} + containers: +{{ toYaml .Values.alertmanager.alertmanagerSpec.containers | indent 4 }} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.initContainers }} + initContainers: +{{ toYaml .Values.alertmanager.alertmanagerSpec.initContainers | indent 4 }} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.priorityClassName }} + priorityClassName: {{.Values.alertmanager.alertmanagerSpec.priorityClassName }} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.additionalPeers }} + additionalPeers: +{{ toYaml .Values.alertmanager.alertmanagerSpec.additionalPeers | indent 4 }} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.volumes }} + volumes: +{{ toYaml .Values.alertmanager.alertmanagerSpec.volumes | indent 4 }} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.volumeMounts }} + volumeMounts: +{{ toYaml .Values.alertmanager.alertmanagerSpec.volumeMounts | indent 4 }} +{{- end }} + portName: {{ .Values.alertmanager.alertmanagerSpec.portName }} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.clusterAdvertiseAddress }} + clusterAdvertiseAddress: {{ .Values.alertmanager.alertmanagerSpec.clusterAdvertiseAddress }} +{{- end }} +{{- if .Values.alertmanager.alertmanagerSpec.forceEnableClusterMode }} + forceEnableClusterMode: {{ .Values.alertmanager.alertmanagerSpec.forceEnableClusterMode }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/ingress.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/ingress.yaml new file mode 100644 index 00000000..a87ce892 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/ingress.yaml @@ -0,0 +1,58 @@ +{{- if and .Values.alertmanager.enabled .Values.alertmanager.ingress.enabled }} +{{- $serviceName := printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "alertmanager" }} +{{- $servicePort := .Values.alertmanager.service.port -}} +{{- $routePrefix := list .Values.alertmanager.alertmanagerSpec.routePrefix }} +{{- $paths := .Values.alertmanager.ingress.paths | default $routePrefix -}} +{{- if .Capabilities.APIVersions.Has "networking.k8s.io/v1beta1" }} +apiVersion: networking.k8s.io/v1beta1 +{{ else }} +apiVersion: extensions/v1beta1 +{{ end -}} +kind: Ingress +metadata: + name: {{ $serviceName }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} +{{- if .Values.alertmanager.ingress.annotations }} + annotations: +{{ toYaml .Values.alertmanager.ingress.annotations | indent 4 }} +{{- end }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-alertmanager +{{- if .Values.alertmanager.ingress.labels }} +{{ toYaml .Values.alertmanager.ingress.labels | indent 4 }} +{{- end }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + {{- if or (.Capabilities.APIVersions.Has "networking.k8s.io/v1/IngressClass") (.Capabilities.APIVersions.Has "networking.k8s.io/v1beta1/IngressClass") }} + {{- if .Values.alertmanager.ingress.ingressClassName }} + ingressClassName: {{ .Values.alertmanager.ingress.ingressClassName }} + {{- end }} + {{- end }} + rules: + {{- if .Values.alertmanager.ingress.hosts }} + {{- range $host := .Values.alertmanager.ingress.hosts }} + - host: {{ tpl $host $ }} + http: + paths: + {{- range $p := $paths }} + - path: {{ tpl $p $ }} + backend: + serviceName: {{ $serviceName }} + servicePort: {{ $servicePort }} + {{- end -}} + {{- end -}} + {{- else }} + - http: + paths: + {{- range $p := $paths }} + - path: {{ tpl $p $ }} + backend: + serviceName: {{ $serviceName }} + servicePort: {{ $servicePort }} + {{- end -}} + {{- end -}} + {{- if .Values.alertmanager.ingress.tls }} + tls: +{{ toYaml .Values.alertmanager.ingress.tls | indent 4 }} + {{- end -}} +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/ingressperreplica.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/ingressperreplica.yaml new file mode 100644 index 00000000..6aef97d3 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/ingressperreplica.yaml @@ -0,0 +1,58 @@ +{{- if and .Values.alertmanager.enabled .Values.alertmanager.servicePerReplica.enabled .Values.alertmanager.ingressPerReplica.enabled }} +{{- $count := .Values.alertmanager.alertmanagerSpec.replicas | int -}} +{{- $servicePort := .Values.alertmanager.service.port -}} +{{- $ingressValues := .Values.alertmanager.ingressPerReplica -}} +apiVersion: v1 +kind: List +metadata: + name: {{ include "kube-prometheus-stack.fullname" $ }}-alertmanager-ingressperreplica + namespace: {{ template "kube-prometheus-stack.namespace" . }} +items: +{{ range $i, $e := until $count }} + - kind: Ingress + {{- if $.Capabilities.APIVersions.Has "networking.k8s.io/v1beta1" }} + apiVersion: networking.k8s.io/v1beta1 + {{ else }} + apiVersion: extensions/v1beta1 + {{ end -}} + metadata: + name: {{ include "kube-prometheus-stack.fullname" $ }}-alertmanager-{{ $i }} + namespace: {{ template "kube-prometheus-stack.namespace" $ }} + labels: + app: {{ include "kube-prometheus-stack.name" $ }}-alertmanager +{{ include "kube-prometheus-stack.labels" $ | indent 8 }} + {{- if $ingressValues.labels }} +{{ toYaml $ingressValues.labels | indent 8 }} + {{- end }} + {{- if $ingressValues.annotations }} + annotations: +{{ toYaml $ingressValues.annotations | indent 8 }} + {{- end }} + spec: + {{- if or ($.Capabilities.APIVersions.Has "networking.k8s.io/v1/IngressClass") ($.Capabilities.APIVersions.Has "networking.k8s.io/v1beta1/IngressClass") }} + {{- if $ingressValues.ingressClassName }} + ingressClassName: {{ $ingressValues.ingressClassName }} + {{- end }} + {{- end }} + rules: + - host: {{ $ingressValues.hostPrefix }}-{{ $i }}.{{ $ingressValues.hostDomain }} + http: + paths: + {{- range $p := $ingressValues.paths }} + - path: {{ tpl $p $ }} + backend: + serviceName: {{ include "kube-prometheus-stack.fullname" $ }}-alertmanager-{{ $i }} + servicePort: {{ $servicePort }} + {{- end -}} + {{- if or $ingressValues.tlsSecretName $ingressValues.tlsSecretPerReplica.enabled }} + tls: + - hosts: + - {{ $ingressValues.hostPrefix }}-{{ $i }}.{{ $ingressValues.hostDomain }} + {{- if $ingressValues.tlsSecretPerReplica.enabled }} + secretName: {{ $ingressValues.tlsSecretPerReplica.prefix }}-{{ $i }} + {{- else }} + secretName: {{ $ingressValues.tlsSecretName }} + {{- end }} + {{- end }} +{{- end -}} +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/podDisruptionBudget.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/podDisruptionBudget.yaml new file mode 100644 index 00000000..1dbe809c --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/podDisruptionBudget.yaml @@ -0,0 +1,21 @@ +{{- if and .Values.alertmanager.enabled .Values.alertmanager.podDisruptionBudget.enabled }} +apiVersion: policy/v1beta1 +kind: PodDisruptionBudget +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-alertmanager + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-alertmanager +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + {{- if .Values.alertmanager.podDisruptionBudget.minAvailable }} + minAvailable: {{ .Values.alertmanager.podDisruptionBudget.minAvailable }} + {{- end }} + {{- if .Values.alertmanager.podDisruptionBudget.maxUnavailable }} + maxUnavailable: {{ .Values.alertmanager.podDisruptionBudget.maxUnavailable }} + {{- end }} + selector: + matchLabels: + app: alertmanager + alertmanager: {{ template "kube-prometheus-stack.fullname" . }}-alertmanager +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/psp-role.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/psp-role.yaml new file mode 100644 index 00000000..d64d1f81 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/psp-role.yaml @@ -0,0 +1,21 @@ +{{- if and .Values.alertmanager.enabled .Values.global.rbac.create .Values.global.rbac.pspEnabled }} +kind: Role +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-alertmanager + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-alertmanager +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +rules: +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if semverCompare "> 1.15.0-0" $kubeTargetVersion }} +- apiGroups: ['policy'] +{{- else }} +- apiGroups: ['extensions'] +{{- end }} + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: + - {{ template "kube-prometheus-stack.fullname" . }}-alertmanager +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/psp-rolebinding.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/psp-rolebinding.yaml new file mode 100644 index 00000000..9248cc8d --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/psp-rolebinding.yaml @@ -0,0 +1,18 @@ +{{- if and .Values.alertmanager.enabled .Values.global.rbac.create .Values.global.rbac.pspEnabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-alertmanager + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-alertmanager +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ template "kube-prometheus-stack.fullname" . }}-alertmanager +subjects: + - kind: ServiceAccount + name: {{ template "kube-prometheus-stack.alertmanager.serviceAccountName" . }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/psp.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/psp.yaml new file mode 100644 index 00000000..6fa44500 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/psp.yaml @@ -0,0 +1,52 @@ +{{- if and .Values.alertmanager.enabled .Values.global.rbac.create .Values.global.rbac.pspEnabled }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-alertmanager + labels: + app: {{ template "kube-prometheus-stack.name" . }}-alertmanager +{{- if .Values.global.rbac.pspAnnotations }} + annotations: +{{ toYaml .Values.global.rbac.pspAnnotations | indent 4 }} +{{- end }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + privileged: false + # Required to prevent escalations to root. + # allowPrivilegeEscalation: false + # This is redundant with non-root + disallow privilege escalation, + # but we can provide it for defense in depth. + #requiredDropCapabilities: + # - ALL + # Allow core volume types. + volumes: + - 'configMap' + - 'emptyDir' + - 'projected' + - 'secret' + - 'downwardAPI' + - 'persistentVolumeClaim' + hostNetwork: false + hostIPC: false + hostPID: false + runAsUser: + # Permits the container to run with root privileges as well. + rule: 'RunAsAny' + seLinux: + # This policy assumes the nodes are using AppArmor rather than SELinux. + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 0 + max: 65535 + fsGroup: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 0 + max: 65535 + readOnlyRootFilesystem: false +{{- end }} + diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/secret.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/secret.yaml new file mode 100644 index 00000000..43c4e20b --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/secret.yaml @@ -0,0 +1,23 @@ +{{- if and (.Values.alertmanager.enabled) (not .Values.alertmanager.alertmanagerSpec.useExistingSecret) }} +apiVersion: v1 +kind: Secret +metadata: + name: alertmanager-{{ template "kube-prometheus-stack.fullname" . }}-alertmanager + namespace: {{ template "kube-prometheus-stack.namespace" . }} +{{- if .Values.alertmanager.secret.annotations }} + annotations: +{{ toYaml .Values.alertmanager.secret.annotations | indent 4 }} +{{- end }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-alertmanager +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +data: +{{- if .Values.alertmanager.tplConfig }} + alertmanager.yaml: {{ tpl (toYaml .Values.alertmanager.config) . | b64enc | quote }} +{{- else }} + alertmanager.yaml: {{ toYaml .Values.alertmanager.config | b64enc | quote }} +{{- end}} +{{- range $key, $val := .Values.alertmanager.templateFiles }} + {{ $key }}: {{ $val | b64enc | quote }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/service.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/service.yaml new file mode 100644 index 00000000..bbcc60f2 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/service.yaml @@ -0,0 +1,50 @@ +{{- if .Values.alertmanager.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-alertmanager + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-alertmanager + self-monitor: {{ .Values.alertmanager.serviceMonitor.selfMonitor | quote }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.alertmanager.service.labels }} +{{ toYaml .Values.alertmanager.service.labels | indent 4 }} +{{- end }} +{{- if .Values.alertmanager.service.annotations }} + annotations: +{{ toYaml .Values.alertmanager.service.annotations | indent 4 }} +{{- end }} +spec: +{{- if .Values.alertmanager.service.clusterIP }} + clusterIP: {{ .Values.alertmanager.service.clusterIP }} +{{- end }} +{{- if .Values.alertmanager.service.externalIPs }} + externalIPs: +{{ toYaml .Values.alertmanager.service.externalIPs | indent 4 }} +{{- end }} +{{- if .Values.alertmanager.service.loadBalancerIP }} + loadBalancerIP: {{ .Values.alertmanager.service.loadBalancerIP }} +{{- end }} +{{- if .Values.alertmanager.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: + {{- range $cidr := .Values.alertmanager.service.loadBalancerSourceRanges }} + - {{ $cidr }} + {{- end }} +{{- end }} + ports: + - name: {{ .Values.alertmanager.alertmanagerSpec.portName }} + {{- if eq .Values.alertmanager.service.type "NodePort" }} + nodePort: {{ .Values.alertmanager.service.nodePort }} + {{- end }} + port: {{ .Values.alertmanager.service.port }} + targetPort: {{ .Values.alertmanager.service.targetPort }} + protocol: TCP +{{- if .Values.alertmanager.service.additionalPorts }} +{{ toYaml .Values.alertmanager.service.additionalPorts | indent 2 }} +{{- end }} + selector: + app: alertmanager + alertmanager: {{ template "kube-prometheus-stack.fullname" . }}-alertmanager + type: "{{ .Values.alertmanager.service.type }}" +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/serviceaccount.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/serviceaccount.yaml new file mode 100644 index 00000000..c5e6e922 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/serviceaccount.yaml @@ -0,0 +1,16 @@ +{{- if and .Values.alertmanager.enabled .Values.alertmanager.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ template "kube-prometheus-stack.alertmanager.serviceAccountName" . }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-alertmanager +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.alertmanager.serviceAccount.annotations }} + annotations: +{{ toYaml .Values.alertmanager.serviceAccount.annotations | indent 4 }} +{{- end }} +imagePullSecrets: +{{ toYaml .Values.global.imagePullSecrets | indent 2 }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/servicemonitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/servicemonitor.yaml new file mode 100644 index 00000000..a699accb --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/servicemonitor.yaml @@ -0,0 +1,42 @@ +{{- if and .Values.alertmanager.enabled .Values.alertmanager.serviceMonitor.selfMonitor }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-alertmanager + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-alertmanager +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + selector: + matchLabels: + app: {{ template "kube-prometheus-stack.name" . }}-alertmanager + release: {{ $.Release.Name | quote }} + self-monitor: "true" + namespaceSelector: + matchNames: + - {{ printf "%s" (include "kube-prometheus-stack.namespace" .) | quote }} + endpoints: + - port: {{ .Values.alertmanager.alertmanagerSpec.portName }} + {{- if .Values.alertmanager.serviceMonitor.interval }} + interval: {{ .Values.alertmanager.serviceMonitor.interval }} + {{- end }} + {{- if .Values.alertmanager.serviceMonitor.scheme }} + scheme: {{ .Values.alertmanager.serviceMonitor.scheme }} + {{- end }} + {{- if .Values.alertmanager.serviceMonitor.bearerTokenFile }} + bearerTokenFile: {{ .Values.alertmanager.serviceMonitor.bearerTokenFile }} + {{- end }} + {{- if .Values.alertmanager.serviceMonitor.tlsConfig }} + tlsConfig: {{ toYaml .Values.alertmanager.serviceMonitor.tlsConfig | nindent 6 }} + {{- end }} + path: "{{ trimSuffix "/" .Values.alertmanager.alertmanagerSpec.routePrefix }}/metrics" +{{- if .Values.alertmanager.serviceMonitor.metricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.alertmanager.serviceMonitor.metricRelabelings | indent 6) . }} +{{- end }} +{{- if .Values.alertmanager.serviceMonitor.relabelings }} + relabelings: +{{ toYaml .Values.alertmanager.serviceMonitor.relabelings | indent 6 }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/serviceperreplica.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/serviceperreplica.yaml new file mode 100644 index 00000000..0f12ae87 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/serviceperreplica.yaml @@ -0,0 +1,46 @@ +{{- if and .Values.alertmanager.enabled .Values.alertmanager.servicePerReplica.enabled }} +{{- $count := .Values.alertmanager.alertmanagerSpec.replicas | int -}} +{{- $serviceValues := .Values.alertmanager.servicePerReplica -}} +apiVersion: v1 +kind: List +metadata: + name: {{ include "kube-prometheus-stack.fullname" $ }}-alertmanager-serviceperreplica + namespace: {{ template "kube-prometheus-stack.namespace" . }} +items: +{{- range $i, $e := until $count }} + - apiVersion: v1 + kind: Service + metadata: + name: {{ include "kube-prometheus-stack.fullname" $ }}-alertmanager-{{ $i }} + namespace: {{ template "kube-prometheus-stack.namespace" $ }} + labels: + app: {{ include "kube-prometheus-stack.name" $ }}-alertmanager +{{ include "kube-prometheus-stack.labels" $ | indent 8 }} + {{- if $serviceValues.annotations }} + annotations: +{{ toYaml $serviceValues.annotations | indent 8 }} + {{- end }} + spec: + {{- if $serviceValues.clusterIP }} + clusterIP: {{ $serviceValues.clusterIP }} + {{- end }} + {{- if $serviceValues.loadBalancerSourceRanges }} + loadBalancerSourceRanges: + {{- range $cidr := $serviceValues.loadBalancerSourceRanges }} + - {{ $cidr }} + {{- end }} + {{- end }} + ports: + - name: {{ $.Values.alertmanager.alertmanagerSpec.portName }} + {{- if eq $serviceValues.type "NodePort" }} + nodePort: {{ $serviceValues.nodePort }} + {{- end }} + port: {{ $serviceValues.port }} + targetPort: {{ $serviceValues.targetPort }} + selector: + app: alertmanager + alertmanager: {{ template "kube-prometheus-stack.fullname" $ }}-alertmanager + statefulset.kubernetes.io/pod-name: alertmanager-{{ include "kube-prometheus-stack.fullname" $ }}-alertmanager-{{ $i }} + type: "{{ $serviceValues.type }}" +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/core-dns/service.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/core-dns/service.yaml new file mode 100644 index 00000000..f77db419 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/core-dns/service.yaml @@ -0,0 +1,24 @@ +{{- if .Values.coreDns.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-coredns + labels: + app: {{ template "kube-prometheus-stack.name" . }}-coredns + jobLabel: coredns +{{ include "kube-prometheus-stack.labels" . | indent 4 }} + namespace: kube-system +spec: + clusterIP: None + ports: + - name: http-metrics + port: {{ .Values.coreDns.service.port }} + protocol: TCP + targetPort: {{ .Values.coreDns.service.targetPort }} + selector: + {{- if .Values.coreDns.service.selector }} +{{ toYaml .Values.coreDns.service.selector | indent 4 }} + {{- else}} + k8s-app: kube-dns + {{- end}} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/core-dns/servicemonitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/core-dns/servicemonitor.yaml new file mode 100644 index 00000000..c398db61 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/core-dns/servicemonitor.yaml @@ -0,0 +1,33 @@ +{{- if .Values.coreDns.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-coredns + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-coredns +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + jobLabel: jobLabel + selector: + matchLabels: + app: {{ template "kube-prometheus-stack.name" . }}-coredns + release: {{ $.Release.Name | quote }} + namespaceSelector: + matchNames: + - "kube-system" + endpoints: + - port: http-metrics + {{- if .Values.coreDns.serviceMonitor.interval}} + interval: {{ .Values.coreDns.serviceMonitor.interval }} + {{- end }} + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token +{{- if .Values.coreDns.serviceMonitor.metricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.coreDns.serviceMonitor.metricRelabelings | indent 4) . }} +{{- end }} +{{- if .Values.coreDns.serviceMonitor.relabelings }} + relabelings: +{{ toYaml .Values.coreDns.serviceMonitor.relabelings | indent 4 }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-api-server/servicemonitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-api-server/servicemonitor.yaml new file mode 100644 index 00000000..4c0290e7 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-api-server/servicemonitor.yaml @@ -0,0 +1,36 @@ +{{- if .Values.kubeApiServer.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-apiserver + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-apiserver +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + endpoints: + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + {{- if .Values.kubeApiServer.serviceMonitor.interval }} + interval: {{ .Values.kubeApiServer.serviceMonitor.interval }} + {{- end }} + port: https + scheme: https +{{- if .Values.kubeApiServer.serviceMonitor.metricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.kubeApiServer.serviceMonitor.metricRelabelings | indent 6) . }} +{{- end }} +{{- if .Values.kubeApiServer.relabelings }} + relabelings: +{{ toYaml .Values.kubeApiServer.relabelings | indent 6 }} +{{- end }} + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + serverName: {{ .Values.kubeApiServer.tlsConfig.serverName }} + insecureSkipVerify: {{ .Values.kubeApiServer.tlsConfig.insecureSkipVerify }} + jobLabel: {{ .Values.kubeApiServer.serviceMonitor.jobLabel }} + namespaceSelector: + matchNames: + - default + selector: +{{ toYaml .Values.kubeApiServer.serviceMonitor.selector | indent 4 }} +{{- end}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-controller-manager/endpoints.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-controller-manager/endpoints.yaml new file mode 100644 index 00000000..41319302 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-controller-manager/endpoints.yaml @@ -0,0 +1,20 @@ +{{- if and .Values.kubeControllerManager.enabled .Values.kubeControllerManager.endpoints }} +apiVersion: v1 +kind: Endpoints +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-kube-controller-manager + labels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-controller-manager + k8s-app: kube-controller-manager +{{ include "kube-prometheus-stack.labels" . | indent 4 }} + namespace: kube-system +subsets: + - addresses: + {{- range .Values.kubeControllerManager.endpoints }} + - ip: {{ . }} + {{- end }} + ports: + - name: http-metrics + port: {{ .Values.kubeControllerManager.service.port }} + protocol: TCP +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-controller-manager/service.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-controller-manager/service.yaml new file mode 100644 index 00000000..8b5556a8 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-controller-manager/service.yaml @@ -0,0 +1,27 @@ +{{- if .Values.kubeControllerManager.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-kube-controller-manager + labels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-controller-manager + jobLabel: kube-controller-manager +{{ include "kube-prometheus-stack.labels" . | indent 4 }} + namespace: kube-system +spec: + clusterIP: None + ports: + - name: http-metrics + port: {{ .Values.kubeControllerManager.service.port }} + protocol: TCP + targetPort: {{ .Values.kubeControllerManager.service.targetPort }} +{{- if .Values.kubeControllerManager.endpoints }}{{- else }} + selector: + {{- if .Values.kubeControllerManager.service.selector }} +{{ toYaml .Values.kubeControllerManager.service.selector | indent 4 }} + {{- else}} + component: kube-controller-manager + {{- end}} +{{- end }} + type: ClusterIP +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-controller-manager/servicemonitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-controller-manager/servicemonitor.yaml new file mode 100644 index 00000000..2f30a0cc --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-controller-manager/servicemonitor.yaml @@ -0,0 +1,44 @@ +{{- if .Values.kubeControllerManager.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-kube-controller-manager + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-controller-manager +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + jobLabel: jobLabel + selector: + matchLabels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-controller-manager + release: {{ $.Release.Name | quote }} + namespaceSelector: + matchNames: + - "kube-system" + endpoints: + - port: http-metrics + {{- if .Values.kubeControllerManager.serviceMonitor.interval }} + interval: {{ .Values.kubeControllerManager.serviceMonitor.interval }} + {{- end }} + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + {{- if .Values.kubeControllerManager.serviceMonitor.https }} + scheme: https + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + {{- if .Values.kubeControllerManager.serviceMonitor.insecureSkipVerify }} + insecureSkipVerify: {{ .Values.kubeControllerManager.serviceMonitor.insecureSkipVerify }} + {{- end }} + {{- if .Values.kubeControllerManager.serviceMonitor.serverName }} + serverName: {{ .Values.kubeControllerManager.serviceMonitor.serverName }} + {{- end }} + {{- end }} +{{- if .Values.kubeControllerManager.serviceMonitor.metricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.kubeControllerManager.serviceMonitor.metricRelabelings | indent 4) . }} +{{- end }} +{{- if .Values.kubeControllerManager.serviceMonitor.relabelings }} + relabelings: +{{ toYaml .Values.kubeControllerManager.serviceMonitor.relabelings | indent 4 }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-dns/service.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-dns/service.yaml new file mode 100644 index 00000000..c7bf142d --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-dns/service.yaml @@ -0,0 +1,28 @@ +{{- if .Values.kubeDns.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-kube-dns + labels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-dns + jobLabel: kube-dns +{{ include "kube-prometheus-stack.labels" . | indent 4 }} + namespace: kube-system +spec: + clusterIP: None + ports: + - name: http-metrics-dnsmasq + port: {{ .Values.kubeDns.service.dnsmasq.port }} + protocol: TCP + targetPort: {{ .Values.kubeDns.service.dnsmasq.targetPort }} + - name: http-metrics-skydns + port: {{ .Values.kubeDns.service.skydns.port }} + protocol: TCP + targetPort: {{ .Values.kubeDns.service.skydns.targetPort }} + selector: + {{- if .Values.kubeDns.service.selector }} +{{ toYaml .Values.kubeDns.service.selector | indent 4 }} + {{- else}} + k8s-app: kube-dns + {{- end}} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-dns/servicemonitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-dns/servicemonitor.yaml new file mode 100644 index 00000000..3c1a0617 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-dns/servicemonitor.yaml @@ -0,0 +1,46 @@ +{{- if .Values.kubeDns.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-kube-dns + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-dns +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + jobLabel: jobLabel + selector: + matchLabels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-dns + release: {{ $.Release.Name | quote }} + namespaceSelector: + matchNames: + - "kube-system" + endpoints: + - port: http-metrics-dnsmasq + {{- if .Values.kubeDns.serviceMonitor.interval }} + interval: {{ .Values.kubeDns.serviceMonitor.interval }} + {{- end }} + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token +{{- if .Values.kubeDns.serviceMonitor.dnsmasqMetricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.kubeDns.serviceMonitor.dnsmasqMetricRelabelings | indent 4) . }} +{{- end }} +{{- if .Values.kubeDns.serviceMonitor.dnsmasqRelabelings }} + relabelings: +{{ toYaml .Values.kubeDns.serviceMonitor.dnsmasqRelabelings | indent 4 }} +{{- end }} + - port: http-metrics-skydns + {{- if .Values.kubeDns.serviceMonitor.interval }} + interval: {{ .Values.kubeDns.serviceMonitor.interval }} + {{- end }} + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token +{{- if .Values.kubeDns.serviceMonitor.metricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.kubeDns.serviceMonitor.metricRelabelings | indent 4) . }} +{{- end }} +{{- if .Values.kubeDns.serviceMonitor.relabelings }} + relabelings: +{{ toYaml .Values.kubeDns.serviceMonitor.relabelings | indent 4 }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-etcd/endpoints.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-etcd/endpoints.yaml new file mode 100644 index 00000000..8f07a5cc --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-etcd/endpoints.yaml @@ -0,0 +1,20 @@ +{{- if and .Values.kubeEtcd.enabled .Values.kubeEtcd.endpoints }} +apiVersion: v1 +kind: Endpoints +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-kube-etcd + labels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-etcd + k8s-app: etcd-server +{{ include "kube-prometheus-stack.labels" . | indent 4 }} + namespace: kube-system +subsets: + - addresses: + {{- range .Values.kubeEtcd.endpoints }} + - ip: {{ . }} + {{- end }} + ports: + - name: http-metrics + port: {{ .Values.kubeEtcd.service.port }} + protocol: TCP +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-etcd/service.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-etcd/service.yaml new file mode 100644 index 00000000..957e8bbc --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-etcd/service.yaml @@ -0,0 +1,27 @@ +{{- if .Values.kubeEtcd.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-kube-etcd + labels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-etcd + jobLabel: kube-etcd +{{ include "kube-prometheus-stack.labels" . | indent 4 }} + namespace: kube-system +spec: + clusterIP: None + ports: + - name: http-metrics + port: {{ .Values.kubeEtcd.service.port }} + protocol: TCP + targetPort: {{ .Values.kubeEtcd.service.targetPort }} +{{- if .Values.kubeEtcd.endpoints }}{{- else }} + selector: + {{- if .Values.kubeEtcd.service.selector }} +{{ toYaml .Values.kubeEtcd.service.selector | indent 4 }} + {{- else}} + component: etcd + {{- end}} +{{- end }} + type: ClusterIP +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-etcd/servicemonitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-etcd/servicemonitor.yaml new file mode 100644 index 00000000..17a447ad --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-etcd/servicemonitor.yaml @@ -0,0 +1,50 @@ +{{- if .Values.kubeEtcd.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-kube-etcd + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-etcd +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + jobLabel: jobLabel + selector: + matchLabels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-etcd + release: {{ $.Release.Name | quote }} + namespaceSelector: + matchNames: + - "kube-system" + endpoints: + - port: http-metrics + {{- if .Values.kubeEtcd.serviceMonitor.interval }} + interval: {{ .Values.kubeEtcd.serviceMonitor.interval }} + {{- end }} + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + {{- if eq .Values.kubeEtcd.serviceMonitor.scheme "https" }} + scheme: https + tlsConfig: + {{- if .Values.kubeEtcd.serviceMonitor.serverName }} + serverName: {{ .Values.kubeEtcd.serviceMonitor.serverName }} + {{- end }} + {{- if .Values.kubeEtcd.serviceMonitor.caFile }} + caFile: {{ .Values.kubeEtcd.serviceMonitor.caFile }} + {{- end }} + {{- if .Values.kubeEtcd.serviceMonitor.certFile }} + certFile: {{ .Values.kubeEtcd.serviceMonitor.certFile }} + {{- end }} + {{- if .Values.kubeEtcd.serviceMonitor.keyFile }} + keyFile: {{ .Values.kubeEtcd.serviceMonitor.keyFile }} + {{- end}} + insecureSkipVerify: {{ .Values.kubeEtcd.serviceMonitor.insecureSkipVerify }} + {{- end }} +{{- if .Values.kubeEtcd.serviceMonitor.metricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.kubeEtcd.serviceMonitor.metricRelabelings | indent 4) . }} +{{- end }} +{{- if .Values.kubeEtcd.serviceMonitor.relabelings }} + relabelings: +{{ toYaml .Values.kubeEtcd.serviceMonitor.relabelings | indent 4 }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-proxy/endpoints.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-proxy/endpoints.yaml new file mode 100644 index 00000000..2cb756d1 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-proxy/endpoints.yaml @@ -0,0 +1,20 @@ +{{- if and .Values.kubeProxy.enabled .Values.kubeProxy.endpoints }} +apiVersion: v1 +kind: Endpoints +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-kube-proxy + labels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-proxy + k8s-app: kube-proxy +{{ include "kube-prometheus-stack.labels" . | indent 4 }} + namespace: kube-system +subsets: + - addresses: + {{- range .Values.kubeProxy.endpoints }} + - ip: {{ . }} + {{- end }} + ports: + - name: http-metrics + port: {{ .Values.kubeProxy.service.port }} + protocol: TCP +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-proxy/service.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-proxy/service.yaml new file mode 100644 index 00000000..abe42060 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-proxy/service.yaml @@ -0,0 +1,27 @@ +{{- if .Values.kubeProxy.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-kube-proxy + labels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-proxy + jobLabel: kube-proxy +{{ include "kube-prometheus-stack.labels" . | indent 4 }} + namespace: kube-system +spec: + clusterIP: None + ports: + - name: http-metrics + port: {{ .Values.kubeProxy.service.port }} + protocol: TCP + targetPort: {{ .Values.kubeProxy.service.targetPort }} +{{- if .Values.kubeProxy.endpoints }}{{- else }} + selector: + {{- if .Values.kubeProxy.service.selector }} +{{ toYaml .Values.kubeProxy.service.selector | indent 4 }} + {{- else}} + k8s-app: kube-proxy + {{- end}} +{{- end }} + type: ClusterIP +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-proxy/servicemonitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-proxy/servicemonitor.yaml new file mode 100644 index 00000000..0ac44182 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-proxy/servicemonitor.yaml @@ -0,0 +1,38 @@ +{{- if .Values.kubeProxy.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-kube-proxy + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-proxy +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + jobLabel: jobLabel + selector: + matchLabels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-proxy + release: {{ $.Release.Name | quote }} + namespaceSelector: + matchNames: + - "kube-system" + endpoints: + - port: http-metrics + {{- if .Values.kubeProxy.serviceMonitor.interval }} + interval: {{ .Values.kubeProxy.serviceMonitor.interval }} + {{- end }} + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + {{- if .Values.kubeProxy.serviceMonitor.https }} + scheme: https + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + {{- end}} +{{- if .Values.kubeProxy.serviceMonitor.metricRelabelings }} + metricRelabelings: +{{ toYaml .Values.kubeProxy.serviceMonitor.metricRelabelings | indent 4 }} +{{- end }} +{{- if .Values.kubeProxy.serviceMonitor.relabelings }} + relabelings: +{{ toYaml .Values.kubeProxy.serviceMonitor.relabelings | indent 4 }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-scheduler/endpoints.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-scheduler/endpoints.yaml new file mode 100644 index 00000000..f4ad60fd --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-scheduler/endpoints.yaml @@ -0,0 +1,20 @@ +{{- if and .Values.kubeScheduler.enabled .Values.kubeScheduler.endpoints }} +apiVersion: v1 +kind: Endpoints +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-kube-scheduler + labels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-scheduler + k8s-app: kube-scheduler +{{ include "kube-prometheus-stack.labels" . | indent 4 }} + namespace: kube-system +subsets: + - addresses: + {{- range .Values.kubeScheduler.endpoints }} + - ip: {{ . }} + {{- end }} + ports: + - name: http-metrics + port: {{ .Values.kubeScheduler.service.port }} + protocol: TCP +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-scheduler/service.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-scheduler/service.yaml new file mode 100644 index 00000000..15559d45 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-scheduler/service.yaml @@ -0,0 +1,27 @@ +{{- if .Values.kubeScheduler.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-kube-scheduler + labels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-scheduler + jobLabel: kube-scheduler +{{ include "kube-prometheus-stack.labels" . | indent 4 }} + namespace: kube-system +spec: + clusterIP: None + ports: + - name: http-metrics + port: {{ .Values.kubeScheduler.service.port}} + protocol: TCP + targetPort: {{ .Values.kubeScheduler.service.targetPort}} +{{- if .Values.kubeScheduler.endpoints }}{{- else }} + selector: + {{- if .Values.kubeScheduler.service.selector }} +{{ toYaml .Values.kubeScheduler.service.selector | indent 4 }} + {{- else}} + component: kube-scheduler + {{- end}} +{{- end }} + type: ClusterIP +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-scheduler/servicemonitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-scheduler/servicemonitor.yaml new file mode 100644 index 00000000..b565ec2b --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-scheduler/servicemonitor.yaml @@ -0,0 +1,44 @@ +{{- if .Values.kubeScheduler.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-kube-scheduler + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-scheduler +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + jobLabel: jobLabel + selector: + matchLabels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-scheduler + release: {{ $.Release.Name | quote }} + namespaceSelector: + matchNames: + - "kube-system" + endpoints: + - port: http-metrics + {{- if .Values.kubeScheduler.serviceMonitor.interval }} + interval: {{ .Values.kubeScheduler.serviceMonitor.interval }} + {{- end }} + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + {{- if .Values.kubeScheduler.serviceMonitor.https }} + scheme: https + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + {{- if .Values.kubeScheduler.serviceMonitor.insecureSkipVerify }} + insecureSkipVerify: {{ .Values.kubeScheduler.serviceMonitor.insecureSkipVerify }} + {{- end}} + {{- if .Values.kubeScheduler.serviceMonitor.serverName }} + serverName: {{ .Values.kubeScheduler.serviceMonitor.serverName }} + {{- end}} + {{- end}} +{{- if .Values.kubeScheduler.serviceMonitor.metricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.kubeScheduler.serviceMonitor.metricRelabelings | indent 4) . }} +{{- end }} +{{- if .Values.kubeScheduler.serviceMonitor.relabelings }} + relabelings: +{{ toYaml .Values.kubeScheduler.serviceMonitor.relabelings | indent 4 }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-state-metrics/serviceMonitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-state-metrics/serviceMonitor.yaml new file mode 100644 index 00000000..f09de5d2 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-state-metrics/serviceMonitor.yaml @@ -0,0 +1,30 @@ +{{- if .Values.kubeStateMetrics.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-kube-state-metrics + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-kube-state-metrics +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + jobLabel: app.kubernetes.io/name + endpoints: + - port: http + {{- if .Values.kubeStateMetrics.serviceMonitor.interval }} + interval: {{ .Values.kubeStateMetrics.serviceMonitor.interval }} + {{- end }} + honorLabels: true +{{- if .Values.kubeStateMetrics.serviceMonitor.metricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.kubeStateMetrics.serviceMonitor.metricRelabelings | indent 4) . }} +{{- end }} +{{- if .Values.kubeStateMetrics.serviceMonitor.relabelings }} + relabelings: +{{ toYaml .Values.kubeStateMetrics.serviceMonitor.relabelings | indent 4 }} +{{- end }} + selector: + matchLabels: + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: "{{ $.Release.Name }}" +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kubelet/servicemonitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kubelet/servicemonitor.yaml new file mode 100644 index 00000000..36459327 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kubelet/servicemonitor.yaml @@ -0,0 +1,151 @@ +{{- if .Values.kubelet.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-kubelet + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-kubelet +{{- include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + endpoints: + {{- if .Values.kubelet.serviceMonitor.https }} + - port: https-metrics + scheme: https + {{- if .Values.kubelet.serviceMonitor.interval }} + interval: {{ .Values.kubelet.serviceMonitor.interval }} + {{- end }} + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + insecureSkipVerify: true + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + honorLabels: true +{{- if .Values.kubelet.serviceMonitor.metricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.kubelet.serviceMonitor.metricRelabelings | indent 4) . }} +{{- end }} +{{- if .Values.kubelet.serviceMonitor.relabelings }} + relabelings: +{{ toYaml .Values.kubelet.serviceMonitor.relabelings | indent 4 }} +{{- end }} +{{- if .Values.kubelet.serviceMonitor.cAdvisor }} + - port: https-metrics + scheme: https + path: /metrics/cadvisor + {{- if .Values.kubelet.serviceMonitor.interval }} + interval: {{ .Values.kubelet.serviceMonitor.interval }} + {{- end }} + {{- if .Values.kubelet.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ .Values.kubelet.serviceMonitor.scrapeTimeout }} + {{- end }} + honorLabels: true + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + insecureSkipVerify: true + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token +{{- if .Values.kubelet.serviceMonitor.cAdvisorMetricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.kubelet.serviceMonitor.cAdvisorMetricRelabelings | indent 4) . }} +{{- end }} +{{- if .Values.kubelet.serviceMonitor.cAdvisorRelabelings }} + relabelings: +{{ toYaml .Values.kubelet.serviceMonitor.cAdvisorRelabelings | indent 4 }} +{{- end }} +{{- end }} +{{- if .Values.kubelet.serviceMonitor.probes }} + - port: https-metrics + scheme: https + path: /metrics/probes + {{- if .Values.kubelet.serviceMonitor.interval }} + interval: {{ .Values.kubelet.serviceMonitor.interval }} + {{- end }} + honorLabels: true + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + insecureSkipVerify: true + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token +{{- if .Values.kubelet.serviceMonitor.probesMetricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.kubelet.serviceMonitor.probesMetricRelabelings | indent 4) . }} +{{- end }} +{{- if .Values.kubelet.serviceMonitor.probesRelabelings }} + relabelings: +{{ toYaml .Values.kubelet.serviceMonitor.probesRelabelings | indent 4 }} +{{- end }} +{{- end }} +{{- if .Values.kubelet.serviceMonitor.resource }} + - port: https-metrics + scheme: https + path: {{ .Values.kubelet.serviceMonitor.resourcePath }} + {{- if .Values.kubelet.serviceMonitor.interval }} + interval: {{ .Values.kubelet.serviceMonitor.interval }} + {{- end }} + honorLabels: true + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + insecureSkipVerify: true + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token +{{- if .Values.kubelet.serviceMonitor.resourceMetricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.kubelet.serviceMonitor.resourceMetricRelabelings | indent 4) . }} +{{- end }} +{{- if .Values.kubelet.serviceMonitor.resourceRelabelings }} + relabelings: +{{ toYaml .Values.kubelet.serviceMonitor.resourceRelabelings | indent 4 }} +{{- end }} +{{- end }} + {{- else }} + - port: http-metrics + {{- if .Values.kubelet.serviceMonitor.interval }} + interval: {{ .Values.kubelet.serviceMonitor.interval }} + {{- end }} + honorLabels: true +{{- if .Values.kubelet.serviceMonitor.metricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.kubelet.serviceMonitor.metricRelabelings | indent 4) . }} +{{- end }} +{{- if .Values.kubelet.serviceMonitor.relabelings }} + relabelings: +{{ toYaml .Values.kubelet.serviceMonitor.relabelings | indent 4 }} +{{- end }} +{{- if .Values.kubelet.serviceMonitor.cAdvisor }} + - port: http-metrics + path: /metrics/cadvisor + {{- if .Values.kubelet.serviceMonitor.interval }} + interval: {{ .Values.kubelet.serviceMonitor.interval }} + {{- end }} + honorLabels: true +{{- if .Values.kubelet.serviceMonitor.cAdvisorMetricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.kubelet.serviceMonitor.cAdvisorMetricRelabelings | indent 4) . }} +{{- end }} +{{- if .Values.kubelet.serviceMonitor.cAdvisorRelabelings }} + relabelings: +{{ toYaml .Values.kubelet.serviceMonitor.cAdvisorRelabelings | indent 4 }} +{{- end }} +{{- if .Values.kubelet.serviceMonitor.resource }} + - port: http-metrics + path: {{ .Values.kubelet.serviceMonitor.resourcePath }} + {{- if .Values.kubelet.serviceMonitor.interval }} + interval: {{ .Values.kubelet.serviceMonitor.interval }} + {{- end }} + honorLabels: true +{{- if .Values.kubelet.serviceMonitor.resourceMetricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.kubelet.serviceMonitor.resourceMetricRelabelings | indent 4) . }} +{{- end }} +{{- if .Values.kubelet.serviceMonitor.resourceRelabelings }} + relabelings: +{{ toYaml .Values.kubelet.serviceMonitor.resourceRelabelings | indent 4 }} +{{- end }} +{{- end }} +{{- end }} + {{- end }} + jobLabel: k8s-app + namespaceSelector: + matchNames: + - {{ .Values.kubelet.namespace }} + selector: + matchLabels: + k8s-app: kubelet +{{- end}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/node-exporter/servicemonitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/node-exporter/servicemonitor.yaml new file mode 100644 index 00000000..5ca5f1b7 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/node-exporter/servicemonitor.yaml @@ -0,0 +1,32 @@ +{{- if .Values.nodeExporter.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-node-exporter + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-node-exporter +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + jobLabel: {{ .Values.nodeExporter.jobLabel }} + selector: + matchLabels: + app: prometheus-node-exporter + release: {{ $.Release.Name }} + endpoints: + - port: metrics + {{- if .Values.nodeExporter.serviceMonitor.interval }} + interval: {{ .Values.nodeExporter.serviceMonitor.interval }} + {{- end }} + {{- if .Values.nodeExporter.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ .Values.nodeExporter.serviceMonitor.scrapeTimeout }} + {{- end }} +{{- if .Values.nodeExporter.serviceMonitor.metricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.nodeExporter.serviceMonitor.metricRelabelings | indent 4) . }} +{{- end }} +{{- if .Values.nodeExporter.serviceMonitor.relabelings }} + relabelings: +{{ toYaml .Values.nodeExporter.serviceMonitor.relabelings | indent 4 }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/configmap-dashboards.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/configmap-dashboards.yaml new file mode 100644 index 00000000..fdd64ce6 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/configmap-dashboards.yaml @@ -0,0 +1,24 @@ +{{- if and .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +{{- $files := .Files.Glob "dashboards/*.json" }} +{{- if $files }} +apiVersion: v1 +kind: ConfigMapList +items: +{{- range $path, $fileContents := $files }} +{{- $dashboardName := regexReplaceAll "(^.*/)(.*)\\.json$" $path "${2}" }} +- apiVersion: v1 + kind: ConfigMap + metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) $dashboardName | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" $ }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 6 }} + data: + {{ $dashboardName }}.json: {{ $.Files.Get $path | toJson }} +{{- end }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/configmaps-datasources.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/configmaps-datasources.yaml new file mode 100644 index 00000000..de904ddb --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/configmaps-datasources.yaml @@ -0,0 +1,42 @@ +{{- if and .Values.grafana.enabled .Values.grafana.sidecar.datasources.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-grafana-datasource + namespace: {{ template "kube-prometheus-stack.namespace" . }} +{{- if .Values.grafana.sidecar.datasources.annotations }} + annotations: +{{ toYaml .Values.grafana.sidecar.datasources.annotations | indent 4 }} +{{- end }} + labels: + {{ $.Values.grafana.sidecar.datasources.label }}: "1" + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + datasource.yaml: |- + apiVersion: 1 + datasources: +{{- if .Values.grafana.sidecar.datasources.defaultDatasourceEnabled }} + - name: Prometheus + type: prometheus + url: http://{{ template "kube-prometheus-stack.fullname" . }}-prometheus:{{ .Values.prometheus.service.port }}/{{ trimPrefix "/" .Values.prometheus.prometheusSpec.routePrefix }} + access: proxy + isDefault: true + jsonData: + timeInterval: {{ .Values.prometheus.prometheusSpec.scrapeInterval | default "30s" }} +{{- if .Values.grafana.sidecar.datasources.createPrometheusReplicasDatasources }} +{{- range until (int .Values.prometheus.prometheusSpec.replicas) }} + - name: Prometheus-{{ . }} + type: prometheus + url: http://prometheus-{{ template "kube-prometheus-stack.fullname" $ }}-prometheus-{{ . }}.prometheus-operated:9090/{{ trimPrefix "/" $.Values.prometheus.prometheusSpec.routePrefix }} + access: proxy + isDefault: false + jsonData: + timeInterval: {{ .Values.prometheus.prometheusSpec.scrapeInterval | default "30s" }} +{{- end }} +{{- end }} +{{- end }} +{{- if .Values.grafana.additionalDataSources }} +{{ tpl (toYaml .Values.grafana.additionalDataSources | indent 4) . }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/apiserver.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/apiserver.yaml new file mode 100644 index 00000000..1fa3a193 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/apiserver.yaml @@ -0,0 +1,1747 @@ +{{- /* +Generated from 'apiserver' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled .Values.kubeApiServer.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "apiserver" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + apiserver.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "content": "The SLO (service level objective) and other metrics displayed on this dashboard are for informational purposes only.", + "datasource": null, + "description": "The SLO (service level objective) and other metrics displayed on this dashboard are for informational purposes only.", + "gridPos": { + "h": 2, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "mode": "markdown", + "span": 12, + "title": "Notice", + "type": "text" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "decimals": 3, + "description": "How many percent of requests (both read and write) in 30 days have been answered successfully and fast enough?", + "format": "percentunit", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 3, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 4, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "apiserver_request:availability30d{verb=\"all\", cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Availability (30d) > 99.000%", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "decimals": 3, + "description": "How much error budget is left looking at our 0.990% availability guarantees?", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 8, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "100 * (apiserver_request:availability30d{verb=\"all\", cluster=\"$cluster\"} - 0.990000)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "errorbudget", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "ErrorBudget (30d) > 99.000%", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "decimals": 3, + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "decimals": 3, + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "decimals": 3, + "description": "How many percent of read requests (LIST,GET) in 30 days have been answered successfully and fast enough?", + "format": "percentunit", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 5, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "apiserver_request:availability30d{verb=\"read\", cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Read Availability (30d)", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "How many read requests (LIST,GET) per second do the apiservers get by code?", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/2../i", + "color": "#56A64B" + }, + { + "alias": "/3../i", + "color": "#F2CC0C" + }, + { + "alias": "/4../i", + "color": "#3274D9" + }, + { + "alias": "/5../i", + "color": "#E02F44" + } + ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (code) (code_resource:apiserver_request_total:rate5m{verb=\"read\", cluster=\"$cluster\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}} code {{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Read SLI - Requests", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "How many percent of read requests (LIST,GET) per second are returned with errors (5xx)?", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"read\",code=~\"5..\", cluster=\"$cluster\"}) / sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"read\", cluster=\"$cluster\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}} resource {{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Read SLI - Errors", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "How many seconds is the 99th percentile for reading (LIST|GET) a given resource?", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{verb=\"read\", cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}} resource {{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Read SLI - Duration", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "decimals": 3, + "description": "How many percent of write requests (POST|PUT|PATCH|DELETE) in 30 days have been answered successfully and fast enough?", + "format": "percentunit", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 9, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "apiserver_request:availability30d{verb=\"write\", cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Write Availability (30d)", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "How many write requests (POST|PUT|PATCH|DELETE) per second do the apiservers get by code?", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/2../i", + "color": "#56A64B" + }, + { + "alias": "/3../i", + "color": "#F2CC0C" + }, + { + "alias": "/4../i", + "color": "#3274D9" + }, + { + "alias": "/5../i", + "color": "#E02F44" + } + ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (code) (code_resource:apiserver_request_total:rate5m{verb=\"write\", cluster=\"$cluster\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}} code {{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Write SLI - Requests", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "How many percent of write requests (POST|PUT|PATCH|DELETE) per second are returned with errors (5xx)?", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 11, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"write\",code=~\"5..\", cluster=\"$cluster\"}) / sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"write\", cluster=\"$cluster\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}} resource {{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Write SLI - Errors", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "How many seconds is the 99th percentile for writing (POST|PUT|PATCH|DELETE) a given resource?", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 12, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{verb=\"write\", cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}} resource {{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Write SLI - Duration", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(workqueue_adds_total{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance, name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}name{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Work Queue Add Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 14, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(workqueue_depth{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance, name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}name{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Work Queue Depth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 15, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance, name, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}name{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Work Queue Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 16, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "process_resident_memory_bytes{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 17, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(process_cpu_seconds_total{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 18, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "go_goroutines{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Goroutines", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(apiserver_request_total, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(apiserver_request_total{job=\"apiserver\", cluster=\"$cluster\"}, instance)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / API server", + "uid": "09ec8aa1e996d6ffcd6817bbaff4db1b", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/cluster-total.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/cluster-total.yaml new file mode 100644 index 00000000..93bf909d --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/cluster-total.yaml @@ -0,0 +1,1882 @@ +{{- /* +Generated from 'cluster-total' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "cluster-total" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + cluster-total.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 1 + }, + "id": 3, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Received", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 1 + }, + "id": 4, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Transmitted", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "columns": [ + { + "text": "Time", + "value": "Time" + }, + { + "text": "Value #A", + "value": "Value #A" + }, + { + "text": "Value #B", + "value": "Value #B" + }, + { + "text": "Value #C", + "value": "Value #C" + }, + { + "text": "Value #D", + "value": "Value #D" + }, + { + "text": "Value #E", + "value": "Value #E" + }, + { + "text": "Value #F", + "value": "Value #F" + }, + { + "text": "Value #G", + "value": "Value #G" + }, + { + "text": "Value #H", + "value": "Value #H" + }, + { + "text": "namespace", + "value": "namespace" + } + ], + "datasource": "$datasource", + "fill": 1, + "fontSize": "90%", + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 5, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null as zero", + "renderer": "flot", + "scroll": true, + "showHeader": true, + "sort": { + "col": 0, + "desc": false + }, + "spaceLength": 10, + "span": 24, + "styles": [ + { + "alias": "Time", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Time", + "thresholds": [ + + ], + "type": "hidden", + "unit": "short" + }, + { + "alias": "Current Bandwidth Received", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Bandwidth Transmitted", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Average Bandwidth Received", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Average Bandwidth Transmitted", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #H", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Namespace", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down", + "linkUrl": "d/8b7a8b326d7a6f1f04244066368c67af/kubernetes-networking-namespace-pods?orgId=1&refresh=30s&var-namespace=$__cell", + "pattern": "namespace", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "H", + "step": 10 + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Status", + "type": "table" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 6, + "panels": [ + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 11 + }, + "id": 7, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Rate of Bytes Received", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 11 + }, + "id": 8, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Rate of Bytes Transmitted", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Average Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 11 + }, + "id": 9, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth History", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 12 + }, + "id": 10, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 21 + }, + "id": 11, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 30 + }, + "id": 12, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 31 + }, + "id": 13, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 40 + }, + "id": 14, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Packets", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 31 + }, + "id": 15, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 50 + }, + "id": 16, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 59 + }, + "id": 17, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 59 + }, + "id": 18, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + { + "targetBlank": true, + "title": "What is TCP Retransmit?", + "url": "https://accedian.com/enterprises/blog/network-packet-loss-retransmissions-and-duplicate-acknowledgements/" + } + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(rate(node_netstat_Tcp_RetransSegs{cluster=\"$cluster\"}[$interval:$resolution]) / rate(node_netstat_Tcp_OutSegs{cluster=\"$cluster\"}[$interval:$resolution])) by (instance))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of TCP Retransmits out of all sent segments", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 59 + }, + "id": 19, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + { + "targetBlank": true, + "title": "Why monitor SYN retransmits?", + "url": "https://github.com/prometheus/node_exporter/issues/1023#issuecomment-408128365" + } + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(rate(node_netstat_TcpExt_TCPSynRetrans{cluster=\"$cluster\"}[$interval:$resolution]) / rate(node_netstat_Tcp_RetransSegs{cluster=\"$cluster\"}[$interval:$resolution])) by (instance))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of TCP SYN Retransmits out of all retransmits", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Errors", + "titleSize": "h6", + "type": "row" + } + ], + "refresh": "10s", + "rows": [ + + ], + "schemaVersion": 18, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "resolution", + "options": [ + { + "selected": false, + "text": "30s", + "value": "30s" + }, + { + "selected": true, + "text": "5m", + "value": "5m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + } + ], + "query": "30s,5m,1h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Networking / Cluster", + "uid": "ff635a025bcfea7bc3dd4f508990a3e9", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/controller-manager.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/controller-manager.yaml new file mode 100644 index 00000000..76d561ae --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/controller-manager.yaml @@ -0,0 +1,1151 @@ +{{- /* +Generated from 'controller-manager' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled .Values.kubeControllerManager.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "controller-manager" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + controller-manager.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 2, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(up{job=\"kube-controller-manager\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Up", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "min" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(workqueue_adds_total{job=\"kube-controller-manager\", instance=~\"$instance\"}[5m])) by (instance, name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}name{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Work Queue Add Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(workqueue_depth{job=\"kube-controller-manager\", instance=~\"$instance\"}[5m])) by (instance, name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}name{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Work Queue Depth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 5, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{job=\"kube-controller-manager\", instance=~\"$instance\"}[5m])) by (instance, name, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}name{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Work Queue Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"2..\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "2xx", + "refId": "A" + }, + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"3..\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "3xx", + "refId": "B" + }, + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"4..\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "4xx", + "refId": "C" + }, + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"5..\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "5xx", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Kube API Request Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 8, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"POST\"}[5m])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}verb{{`}}`}} {{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Post Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}verb{{`}}`}} {{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Get Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "process_resident_memory_bytes{job=\"kube-controller-manager\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(process_cpu_seconds_total{job=\"kube-controller-manager\",instance=~\"$instance\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 11, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "go_goroutines{job=\"kube-controller-manager\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Goroutines", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(process_cpu_seconds_total{job=\"kube-controller-manager\"}, instance)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Controller Manager", + "uid": "72e0e05bef5099e5f049b05fdc429ed4", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/etcd.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/etcd.yaml new file mode 100644 index 00000000..0595cb47 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/etcd.yaml @@ -0,0 +1,1116 @@ +{{- /* +Generated from 'etcd' from https://raw.githubusercontent.com/etcd-io/etcd/master/Documentation/op-guide/grafana.json +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled .Values.kubeEtcd.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "etcd" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + etcd.json: |- + { + "annotations": { + "list": [] + }, + "description": "etcd sample Grafana dashboard with Prometheus", + "editable": true, + "gnetId": null, + "hideControls": false, + "links": [], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "editable": true, + "height": "250px", + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "$datasource", + "editable": true, + "error": false, + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "id": 28, + "interval": null, + "isNew": true, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "targets": [ + { + "expr": "sum(etcd_server_has_leader{job=\"$cluster\"})", + "intervalFactor": 2, + "legendFormat": "", + "metric": "etcd_server_has_leader", + "refId": "A", + "step": 20 + } + ], + "thresholds": "", + "title": "Up", + "type": "singlestat", + "valueFontSize": "200%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fill": 0, + "id": 23, + "isNew": true, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 5, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(grpc_server_started_total{job=\"$cluster\",grpc_type=\"unary\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "RPC Rate", + "metric": "grpc_server_started_total", + "refId": "A", + "step": 2 + }, + { + "expr": "sum(rate(grpc_server_handled_total{job=\"$cluster\",grpc_type=\"unary\",grpc_code!=\"OK\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "RPC Failed Rate", + "metric": "grpc_server_handled_total", + "refId": "B", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "RPC Rate", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fill": 0, + "id": 41, + "isNew": true, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(grpc_server_started_total{job=\"$cluster\",grpc_service=\"etcdserverpb.Watch\",grpc_type=\"bidi_stream\"}) - sum(grpc_server_handled_total{job=\"$cluster\",grpc_service=\"etcdserverpb.Watch\",grpc_type=\"bidi_stream\"})", + "intervalFactor": 2, + "legendFormat": "Watch Streams", + "metric": "grpc_server_handled_total", + "refId": "A", + "step": 4 + }, + { + "expr": "sum(grpc_server_started_total{job=\"$cluster\",grpc_service=\"etcdserverpb.Lease\",grpc_type=\"bidi_stream\"}) - sum(grpc_server_handled_total{job=\"$cluster\",grpc_service=\"etcdserverpb.Lease\",grpc_type=\"bidi_stream\"})", + "intervalFactor": 2, + "legendFormat": "Lease Streams", + "metric": "grpc_server_handled_total", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Active Streams", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "showTitle": false, + "title": "Row" + }, + { + "collapse": false, + "editable": true, + "height": "250px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "decimals": null, + "editable": true, + "error": false, + "fill": 0, + "grid": {}, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "etcd_mvcc_db_total_size_in_bytes{job=\"$cluster\"}", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} DB Size", + "metric": "", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "DB Size", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fill": 0, + "grid": {}, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 1, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 4, + "stack": false, + "steppedLine": true, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=\"$cluster\"}[5m])) by (instance, le))", + "hide": false, + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} WAL fsync", + "metric": "etcd_disk_wal_fsync_duration_seconds_bucket", + "refId": "A", + "step": 4 + }, + { + "expr": "histogram_quantile(0.99, sum(rate(etcd_disk_backend_commit_duration_seconds_bucket{job=\"$cluster\"}[5m])) by (instance, le))", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} DB fsync", + "metric": "etcd_disk_backend_commit_duration_seconds_bucket", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Disk Sync Duration", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "s", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fill": 0, + "id": 29, + "isNew": true, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "process_resident_memory_bytes{job=\"$cluster\"}", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Resident Memory", + "metric": "process_resident_memory_bytes", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Memory", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "title": "New row" + }, + { + "collapse": false, + "editable": true, + "height": "250px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fill": 5, + "id": 22, + "isNew": true, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "rate(etcd_network_client_grpc_received_bytes_total{job=\"$cluster\"}[5m])", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Client Traffic In", + "metric": "etcd_network_client_grpc_received_bytes_total", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Client Traffic In", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fill": 5, + "id": 21, + "isNew": true, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "rate(etcd_network_client_grpc_sent_bytes_total{job=\"$cluster\"}[5m])", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Client Traffic Out", + "metric": "etcd_network_client_grpc_sent_bytes_total", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Client Traffic Out", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fill": 0, + "id": 20, + "isNew": true, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(etcd_network_peer_received_bytes_total{job=\"$cluster\"}[5m])) by (instance)", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Peer Traffic In", + "metric": "etcd_network_peer_received_bytes_total", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Peer Traffic In", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "decimals": null, + "editable": true, + "error": false, + "fill": 0, + "grid": {}, + "id": 16, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(etcd_network_peer_sent_bytes_total{job=\"$cluster\"}[5m])) by (instance)", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Peer Traffic Out", + "metric": "etcd_network_peer_sent_bytes_total", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Peer Traffic Out", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "title": "New row" + }, + { + "collapse": false, + "editable": true, + "height": "250px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fill": 0, + "id": 40, + "isNew": true, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(etcd_server_proposals_failed_total{job=\"$cluster\"}[5m]))", + "intervalFactor": 2, + "legendFormat": "Proposal Failure Rate", + "metric": "etcd_server_proposals_failed_total", + "refId": "A", + "step": 2 + }, + { + "expr": "sum(etcd_server_proposals_pending{job=\"$cluster\"})", + "intervalFactor": 2, + "legendFormat": "Proposal Pending Total", + "metric": "etcd_server_proposals_pending", + "refId": "B", + "step": 2 + }, + { + "expr": "sum(rate(etcd_server_proposals_committed_total{job=\"$cluster\"}[5m]))", + "intervalFactor": 2, + "legendFormat": "Proposal Commit Rate", + "metric": "etcd_server_proposals_committed_total", + "refId": "C", + "step": 2 + }, + { + "expr": "sum(rate(etcd_server_proposals_applied_total{job=\"$cluster\"}[5m]))", + "intervalFactor": 2, + "legendFormat": "Proposal Apply Rate", + "refId": "D", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Raft Proposals", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "decimals": 0, + "editable": true, + "error": false, + "fill": 0, + "id": 19, + "isNew": true, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "changes(etcd_server_leader_changes_seen_total{job=\"$cluster\"}[1d])", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Total Leader Elections Per Day", + "metric": "etcd_server_leader_changes_seen_total", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Total Leader Elections Per Day", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "title": "New row" + } + ], + "schemaVersion": 13, + "sharedCrosshair": false, + "style": "dark", + "tags": [], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "Prometheus" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [], + "query": "label_values(etcd_server_has_leader, job)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-15m", + "to": "now" + }, + "timepicker": { + "now": true, + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "browser", + "title": "etcd", + "uid": "c2f4e12cdf69feb95caa41a5a1b423d9", + "version": 215 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-coredns.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-coredns.yaml new file mode 100644 index 00000000..3665b57a --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-coredns.yaml @@ -0,0 +1,1531 @@ +{{- /* Added manually, can be changed in-place. */ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled .Values.coreDns.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "k8s-coredns" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + k8s-coredns.json: |- + { + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "description": "A dashboard for the CoreDNS DNS server with updated metrics for version 1.7.0+. Based on the CoreDNS dashboard by buhay.", + "editable": true, + "gnetId": 12539, + "graphTooltip": 0, + "iteration": 1603798405693, + "links": [ + { + "icon": "external link", + "tags": [], + "targetBlank": true, + "title": "CoreDNS.io", + "type": "link", + "url": "https://coredns.io" + } + ], + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 0 + }, + "hiddenSeries": false, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "total", + "yaxis": 2 + } + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(coredns_dns_request_count_total{instance=~\"$instance\"}[5m])) by (proto) or\nsum(rate(coredns_dns_requests_total{instance=~\"$instance\"}[5m])) by (proto)", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{"{{proto}}"}}", + "refId": "A", + "step": 60 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Requests (total)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "pps", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 8, + "x": 8, + "y": 0 + }, + "hiddenSeries": false, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "total", + "yaxis": 2 + }, + { + "alias": "other", + "yaxis": 2 + } + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(coredns_dns_request_type_count_total{instance=~\"$instance\"}[5m])) by (type) or \nsum(rate(coredns_dns_requests_total{instance=~\"$instance\"}[5m])) by (type)", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{"{{type}}"}}", + "refId": "A", + "step": 60 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Requests (by qtype)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "pps", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 8, + "x": 16, + "y": 0 + }, + "hiddenSeries": false, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "total", + "yaxis": 2 + } + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(coredns_dns_request_count_total{instance=~\"$instance\"}[5m])) by (zone) or\nsum(rate(coredns_dns_requests_total{instance=~\"$instance\"}[5m])) by (zone)", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{"{{zone}}"}}", + "refId": "A", + "step": 60 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Requests (by zone)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "pps", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 7 + }, + "hiddenSeries": false, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "total", + "yaxis": 2 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(coredns_dns_request_do_count_total{instance=~\"$instance\"}[5m])) or\nsum(rate(coredns_dns_do_requests_total{instance=~\"$instance\"}[5m]))", + "interval": "", + "intervalFactor": 2, + "legendFormat": "DO", + "refId": "A", + "step": 40 + }, + { + "expr": "sum(rate(coredns_dns_request_count_total{instance=~\"$instance\"}[5m])) or\nsum(rate(coredns_dns_requests_total{instance=~\"$instance\"}[5m]))", + "interval": "", + "intervalFactor": 2, + "legendFormat": "total", + "refId": "B", + "step": 40 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Requests (DO bit)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "pps", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 6, + "x": 12, + "y": 7 + }, + "hiddenSeries": false, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "tcp:90", + "yaxis": 2 + }, + { + "alias": "tcp:99 ", + "yaxis": 2 + }, + { + "alias": "tcp:50", + "yaxis": 2 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(coredns_dns_request_size_bytes_bucket{instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto))", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{"{{proto}}"}}:99 ", + "refId": "A", + "step": 60 + }, + { + "expr": "histogram_quantile(0.90, sum(rate(coredns_dns_request_size_bytes_bucket{instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto))", + "intervalFactor": 2, + "legendFormat": "{{"{{proto}}"}}:90", + "refId": "B", + "step": 60 + }, + { + "expr": "histogram_quantile(0.50, sum(rate(coredns_dns_request_size_bytes_bucket{instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto))", + "intervalFactor": 2, + "legendFormat": "{{"{{proto}}"}}:50", + "refId": "C", + "step": 60 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Requests (size, udp)", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 6, + "x": 18, + "y": 7 + }, + "hiddenSeries": false, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "tcp:90", + "yaxis": 1 + }, + { + "alias": "tcp:99 ", + "yaxis": 1 + }, + { + "alias": "tcp:50", + "yaxis": 1 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(coredns_dns_request_size_bytes_bucket{instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto))", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{"{{proto}}"}}:99 ", + "refId": "A", + "step": 60 + }, + { + "expr": "histogram_quantile(0.90, sum(rate(coredns_dns_request_size_bytes_bucket{instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto))", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{"{{proto}}"}}:90", + "refId": "B", + "step": 60 + }, + { + "expr": "histogram_quantile(0.50, sum(rate(coredns_dns_request_size_bytes_bucket{instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto))", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{"{{proto}}"}}:50", + "refId": "C", + "step": 60 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Requests (size,tcp)", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 14 + }, + "hiddenSeries": false, + "id": 14, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(coredns_dns_response_rcode_count_total{instance=~\"$instance\"}[5m])) by (rcode) or\nsum(rate(coredns_dns_responses_total{instance=~\"$instance\"}[5m])) by (rcode)", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{"{{rcode}}"}}", + "refId": "A", + "step": 40 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Responses (by rcode)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "pps", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 14 + }, + "hiddenSeries": false, + "id": 32, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(coredns_dns_request_duration_seconds_bucket{instance=~\"$instance\"}[5m])) by (le, job))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99%", + "refId": "A", + "step": 40 + }, + { + "expr": "histogram_quantile(0.90, sum(rate(coredns_dns_request_duration_seconds_bucket{instance=~\"$instance\"}[5m])) by (le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "90%", + "refId": "B", + "step": 40 + }, + { + "expr": "histogram_quantile(0.50, sum(rate(coredns_dns_request_duration_seconds_bucket{instance=~\"$instance\"}[5m])) by (le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50%", + "refId": "C", + "step": 40 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Responses (duration)", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "s", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 21 + }, + "hiddenSeries": false, + "id": 18, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "udp:50%", + "yaxis": 1 + }, + { + "alias": "tcp:50%", + "yaxis": 2 + }, + { + "alias": "tcp:90%", + "yaxis": 2 + }, + { + "alias": "tcp:99%", + "yaxis": 2 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(coredns_dns_response_size_bytes_bucket{instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto)) ", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{"{{proto}}"}}:99%", + "refId": "A", + "step": 40 + }, + { + "expr": "histogram_quantile(0.90, sum(rate(coredns_dns_response_size_bytes_bucket{instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto)) ", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{"{{proto}}"}}:90%", + "refId": "B", + "step": 40 + }, + { + "expr": "histogram_quantile(0.50, sum(rate(coredns_dns_response_size_bytes_bucket{instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto)) ", + "hide": false, + "intervalFactor": 2, + "legendFormat": "{{"{{proto}}"}}:50%", + "metric": "", + "refId": "C", + "step": 40 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Responses (size, udp)", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 21 + }, + "hiddenSeries": false, + "id": 20, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "udp:50%", + "yaxis": 1 + }, + { + "alias": "tcp:50%", + "yaxis": 1 + }, + { + "alias": "tcp:90%", + "yaxis": 1 + }, + { + "alias": "tcp:99%", + "yaxis": 1 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(coredns_dns_response_size_bytes_bucket{instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto)) ", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{"{{proto}}"}}:99%", + "refId": "A", + "step": 40 + }, + { + "expr": "histogram_quantile(0.90, sum(rate(coredns_dns_response_size_bytes_bucket{instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto)) ", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{"{{proto}}"}}:90%", + "refId": "B", + "step": 40 + }, + { + "expr": "histogram_quantile(0.50, sum(rate(coredns_dns_response_size_bytes_bucket{instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le, proto)) ", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{"{{proto}}"}}:50%", + "metric": "", + "refId": "C", + "step": 40 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Responses (size, tcp)", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 28 + }, + "hiddenSeries": false, + "id": 22, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(coredns_cache_size{instance=~\"$instance\"}) by (type) or\nsum(coredns_cache_entries{instance=~\"$instance\"}) by (type)", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{"{{type}}"}}", + "refId": "A", + "step": 40 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Cache (size)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "decbytes", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 28 + }, + "hiddenSeries": false, + "id": 24, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "misses", + "yaxis": 2 + } + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(coredns_cache_hits_total{instance=~\"$instance\"}[5m])) by (type)", + "hide": false, + "intervalFactor": 2, + "legendFormat": "hits:{{"{{type}}"}}", + "refId": "A", + "step": 40 + }, + { + "expr": "sum(rate(coredns_cache_misses_total{instance=~\"$instance\"}[5m])) by (type)", + "hide": false, + "intervalFactor": 2, + "legendFormat": "misses", + "refId": "B", + "step": 40 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Cache (hitrate)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "pps", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "refresh": "10s", + "schemaVersion": 26, + "style": "dark", + "tags": [ + "dns", + "coredns" + ], + "templating": { + "list": [ + { + "current": { + "selected": true, + "text": "default", + "value": "default" + }, + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "datasource", + "options": [], + "query": "prometheus", + "queryValue": "", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "definition": "label_values(up{job=\"coredns\"}, instance)", + "hide": 0, + "includeAll": true, + "label": "Instance", + "multi": false, + "name": "instance", + "options": [], + "query": "label_values(up{job=\"coredns\"}, instance)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 3, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-3h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ] + }, + "timezone": "utc", + "title": "CoreDNS", + "uid": "vkQ0UHxik", + "version": 2 + } +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-cluster.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-cluster.yaml new file mode 100644 index 00000000..b1aadb17 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-cluster.yaml @@ -0,0 +1,2582 @@ +{{- /* +Generated from 'k8s-resources-cluster' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "k8s-resources-cluster" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + k8s-resources-cluster.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "100px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 1, + "interval": "1m", + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "1 - avg(rate(node_cpu_seconds_total{mode=\"idle\", cluster=\"$cluster\"}[$__rate_interval]))", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable_cpu_cores{cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Requests Commitment", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable_cpu_cores{cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Limits Commitment", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "1 - sum(:node_memory_MemAvailable_bytes:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable_memory_bytes{cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable_memory_bytes{cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Requests Commitment", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable_memory_bytes{cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Limits Commitment", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Headlines", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Pods", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Workloads", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to workloads", + "linkUrl": "./d/a87fb0d919ec0ea5f6543124e16c42a5/k8s-resources-workloads-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Namespace", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell", + "pattern": "namespace", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(kube_pod_owner{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_rss{cluster=\"$cluster\", container!=\"\"}) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage (w/o cache)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Pods", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Workloads", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to workloads", + "linkUrl": "./d/a87fb0d919ec0ea5f6543124e16c42a5/k8s-resources-workloads-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Memory Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Namespace", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell", + "pattern": "namespace", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(kube_pod_owner{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{cluster=\"$cluster\", container!=\"\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Requests by Namespace", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Requests", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 11, + "interval": "1m", + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Current Receive Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Transmit Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Namespace", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell", + "pattern": "namespace", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Network Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 14, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Namespace: Received", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 15, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Namespace: Transmitted", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 16, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 17, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 18, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 19, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(node_cpu_seconds_total, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Compute Resources / Cluster", + "uid": "efa86fd1d0c121a26444b636a3f509a8", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-namespace.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-namespace.yaml new file mode 100644 index 00000000..4694b599 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-namespace.yaml @@ -0,0 +1,2286 @@ +{{- /* +Generated from 'k8s-resources-namespace' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "k8s-resources-namespace" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + k8s-resources-namespace.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "100px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation (from requests)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation (from limits)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilization (from requests)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilisation (from limits)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Headlines", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "quota - requests", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hideTooltip": true, + "legend": false, + "linewidth": 2, + "stack": false + }, + { + "alias": "quota - limits", + "color": "#FF9830", + "dashes": true, + "fill": 0, + "hideTooltip": true, + "legend": false, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - requests", + "legendLink": null, + "step": 10 + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - limits", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "quota - requests", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hideTooltip": true, + "legend": false, + "linewidth": 2, + "stack": false + }, + { + "alias": "quota - limits", + "color": "#FF9830", + "dashes": true, + "fill": 0, + "hideTooltip": true, + "legend": false, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - requests", + "legendLink": null, + "step": 10 + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - limits", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage (w/o cache)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Memory Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Usage (RSS)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Usage (Cache)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Usage (Swap)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #H", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(container_memory_cache{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + }, + { + "expr": "sum(container_memory_swap{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "H", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 9, + "interval": "1m", + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Current Receive Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Transmit Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Network Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 14, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 15, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Compute Resources / Namespace (Pods)", + "uid": "85a562078cdf77779eaa1add43ccec1e", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-node.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-node.yaml new file mode 100644 index 00000000..b99e40ff --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-node.yaml @@ -0,0 +1,978 @@ +{{- /* +Generated from 'k8s-resources-node' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "k8s-resources-node" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + k8s-resources-node.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\", container!=\"\"}) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage (w/o cache)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Memory Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Usage (RSS)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Usage (Cache)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Usage (Swap)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #H", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests_memory_bytes{node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits_memory_bytes{node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_memory_cache{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_memory_swap{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "H", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Quota", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": true, + "name": "node", + "options": [ + + ], + "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, node)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Compute Resources / Node (Pods)", + "uid": "200ac8fdbfbb74b39aff88118e4d1c2c", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-pod.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-pod.yaml new file mode 100644 index 00000000..acee659c --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-pod.yaml @@ -0,0 +1,1772 @@ +{{- /* +Generated from 'k8s-resources-pod' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "k8s-resources-pod" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + k8s-resources-pod.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "requests", + "color": "#F2495C", + "fill": 0, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + }, + { + "alias": "limits", + "color": "#FF9830", + "fill": 0, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", cluster=\"$cluster\"}) by (container)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}container{{`}}`}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"})\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "requests", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"})\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limits", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 2, + "legend": { + "avg": false, + "current": true, + "max": true, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(increase(container_cpu_cfs_throttled_periods_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\", cluster=\"$cluster\"}[5m])) by (container) /sum(increase(container_cpu_cfs_periods_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\", cluster=\"$cluster\"}[5m])) by (container)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}container{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + { + "colorMode": "critical", + "fill": true, + "line": true, + "op": "gt", + "value": 0.25, + "yaxis": "left" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Throttling", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Throttling", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Container", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "container", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "requests", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hideTooltip": true, + "legend": false, + "linewidth": 2, + "stack": false + }, + { + "alias": "limits", + "color": "#FF9830", + "dashes": true, + "fill": 0, + "hideTooltip": true, + "legend": false, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\", image!=\"\"}) by (container)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}container{{`}}`}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"})\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "requests", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"})\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limits", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Memory Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Usage (RSS)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Usage (Cache)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Usage (Swap)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #H", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Container", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "container", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\", image!=\"\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", image!=\"\"}) by (container) / sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container) / sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(container_memory_cache{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + }, + { + "expr": "sum(container_memory_swap{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "H", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "interval": "1m", + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "interval": "1m", + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "interval": "1m", + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "interval": "1m", + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "interval": "1m", + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "interval": "1m", + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "pod", + "options": [ + + ], + "query": "label_values(kube_pod_info{cluster=\"$cluster\", namespace=\"$namespace\"}, pod)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Compute Resources / Pod", + "uid": "6581e46e4e5c7ba40a07646395ef7b23", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-workload.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-workload.yaml new file mode 100644 index 00000000..0df1bea0 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-workload.yaml @@ -0,0 +1,2034 @@ +{{- /* +Generated from 'k8s-resources-workload' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "k8s-resources-workload" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + k8s-resources-workload.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Memory Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "interval": "1m", + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Current Receive Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Transmit Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Network Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Pod: Received", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Pod: Transmitted", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "workload", + "options": [ + + ], + "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\"}, workload)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "type", + "options": [ + + ], + "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\"}, workload_type)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Compute Resources / Workload", + "uid": "a164a7f0339f99e89cea5cb47e9be617", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-workloads-namespace.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-workloads-namespace.yaml new file mode 100644 index 00000000..9ff5394f --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-workloads-namespace.yaml @@ -0,0 +1,2195 @@ +{{- /* +Generated from 'k8s-resources-workloads-namespace' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "k8s-resources-workloads-namespace" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + k8s-resources-workloads-namespace.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "quota - requests", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hideTooltip": true, + "legend": false, + "linewidth": 2, + "stack": false + }, + { + "alias": "quota - limits", + "color": "#FF9830", + "dashes": true, + "fill": 0, + "hideTooltip": true, + "legend": false, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}workload{{`}}`}} - {{`{{`}}workload_type{{`}}`}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - requests", + "legendLink": null, + "step": 10 + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - limits", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Running Pods", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Workload", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2", + "pattern": "workload", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Workload Type", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "workload_type", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "quota - requests", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hideTooltip": true, + "legend": false, + "linewidth": 2, + "stack": false + }, + { + "alias": "quota - limits", + "color": "#FF9830", + "dashes": true, + "fill": 0, + "hideTooltip": true, + "legend": false, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}workload{{`}}`}} - {{`{{`}}workload_type{{`}}`}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - requests", + "legendLink": null, + "step": 10 + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - limits", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Running Pods", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Memory Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Workload", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2", + "pattern": "workload", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Workload Type", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "workload_type", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "interval": "1m", + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Current Receive Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Transmit Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Workload", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$type", + "pattern": "workload", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Workload Type", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "workload_type", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Network Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Workload: Received", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Workload: Transmitted", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "deployment", + "value": "deployment" + }, + "datasource": "$datasource", + "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{namespace=~\"$namespace\", workload=~\".+\"}, workload_type)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "type", + "options": [ + + ], + "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{namespace=~\"$namespace\", workload=~\".+\"}, workload_type)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Compute Resources / Namespace (Workloads)", + "uid": "a87fb0d919ec0ea5f6543124e16c42a5", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/kubelet.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/kubelet.yaml new file mode 100644 index 00000000..5f1b2a2f --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/kubelet.yaml @@ -0,0 +1,2533 @@ +{{- /* +Generated from 'kubelet' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled .Values.kubelet.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "kubelet" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + kubelet.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 2, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(up{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Up", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "min" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 3, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(kubelet_running_pods{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": "", + "title": "Running Pods", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "min" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 4, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(kubelet_running_containers{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": "", + "title": "Running Container", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "min" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 5, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\", state=\"actual_state_of_world\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": "", + "title": "Actual Volume Count", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "min" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 6, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",state=\"desired_state_of_world\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": "", + "title": "Desired Volume Count", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "min" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 7, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(rate(kubelet_node_config_error{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": "", + "title": "Config Error Count", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "min" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubelet_runtime_operations_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (operation_type, instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}operation_type{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Operation Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubelet_runtime_operations_errors_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, operation_type)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}operation_type{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Operation Error Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_runtime_operations_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, operation_type, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}operation_type{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Operation duration 99th quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 11, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} pod", + "refId": "A" + }, + { + "expr": "sum(rate(kubelet_pod_worker_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} worker", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Pod Start Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 12, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} pod", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} worker", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Pod Start Duration", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 13, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(storage_operation_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}operation_name{{`}}`}} {{`{{`}}volume_plugin{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Storage Operation Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 14, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(storage_operation_errors_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}operation_name{{`}}`}} {{`{{`}}volume_plugin{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Storage Operation Error Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 15, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(storage_operation_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}operation_name{{`}}`}} {{`{{`}}volume_plugin{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Storage Operation Duration 99th quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 16, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubelet_cgroup_manager_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m])) by (instance, operation_type)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}operation_type{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Cgroup manager operation rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 17, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_cgroup_manager_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m])) by (instance, operation_type, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}operation_type{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Cgroup manager 99th quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Pod lifecycle event generator", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 18, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubelet_pleg_relist_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m])) by (instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "PLEG relist rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 19, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_interval_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "PLEG relist interval", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 20, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "PLEG relist duration", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 21, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"2..\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "2xx", + "refId": "A" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"3..\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "3xx", + "refId": "B" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"4..\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "4xx", + "refId": "C" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"5..\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "5xx", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "RPC Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 22, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[5m])) by (instance, verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}verb{{`}}`}} {{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Request duration 99th quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 23, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "process_resident_memory_bytes{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 24, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 25, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "go_goroutines{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Goroutines", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_info, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(kubelet_runtime_operations_total{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"}, instance)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Kubelet", + "uid": "3138fa155d5915769fbded898ac09fd9", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/namespace-by-pod.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/namespace-by-pod.yaml new file mode 100644 index 00000000..e814ba74 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/namespace-by-pod.yaml @@ -0,0 +1,1464 @@ +{{- /* +Generated from 'namespace-by-pod' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "namespace-by-pod" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + namespace-by-pod.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "decimals": 0, + "format": "time_series", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 1 + }, + "height": 9, + "id": 3, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "minSpan": 12, + "nullPointMode": "connected", + "nullText": null, + "options": { + "fieldOptions": { + "calcs": [ + "last" + ], + "defaults": { + "max": 10000000000, + "min": 0, + "title": "$namespace", + "unit": "Bps" + }, + "mappings": [ + + ], + "override": { + + }, + "thresholds": [ + { + "color": "dark-green", + "index": 0, + "value": null + }, + { + "color": "dark-yellow", + "index": 1, + "value": 5000000000 + }, + { + "color": "dark-red", + "index": 2, + "value": 7000000000 + } + ], + "values": false + } + }, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 12, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution]))", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Received", + "type": "gauge", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "decimals": 0, + "format": "time_series", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 1 + }, + "height": 9, + "id": 4, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "minSpan": 12, + "nullPointMode": "connected", + "nullText": null, + "options": { + "fieldOptions": { + "calcs": [ + "last" + ], + "defaults": { + "max": 10000000000, + "min": 0, + "title": "$namespace", + "unit": "Bps" + }, + "mappings": [ + + ], + "override": { + + }, + "thresholds": [ + { + "color": "dark-green", + "index": 0, + "value": null + }, + { + "color": "dark-yellow", + "index": 1, + "value": 5000000000 + }, + { + "color": "dark-red", + "index": 2, + "value": 7000000000 + } + ], + "values": false + } + }, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 12, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution]))", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Transmitted", + "type": "gauge", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "columns": [ + { + "text": "Time", + "value": "Time" + }, + { + "text": "Value #A", + "value": "Value #A" + }, + { + "text": "Value #B", + "value": "Value #B" + }, + { + "text": "Value #C", + "value": "Value #C" + }, + { + "text": "Value #D", + "value": "Value #D" + }, + { + "text": "Value #E", + "value": "Value #E" + }, + { + "text": "Value #F", + "value": "Value #F" + }, + { + "text": "pod", + "value": "pod" + } + ], + "datasource": "$datasource", + "fill": 1, + "fontSize": "100%", + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 5, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null as zero", + "renderer": "flot", + "scroll": true, + "showHeader": true, + "sort": { + "col": 0, + "desc": false + }, + "spaceLength": 10, + "span": 24, + "styles": [ + { + "alias": "Time", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Time", + "thresholds": [ + + ], + "type": "hidden", + "unit": "short" + }, + { + "alias": "Bandwidth Received", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Bandwidth Transmitted", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down", + "linkUrl": "d/7a18067ce943a40ae25454675c19ff5c/kubernetes-networking-pod?orgId=1&refresh=30s&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Status", + "type": "table" + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 19 + }, + "id": 6, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 20 + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 20 + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 29 + }, + "id": 9, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 30 + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 30 + }, + "id": 11, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Packets", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 30 + }, + "id": 12, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 40 + }, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 40 + }, + "id": 14, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Errors", + "titleSize": "h6", + "type": "row" + } + ], + "refresh": "10s", + "rows": [ + + ], + "schemaVersion": 18, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "kube-system", + "value": "kube-system" + }, + "datasource": "$datasource", + "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "resolution", + "options": [ + { + "selected": false, + "text": "30s", + "value": "30s" + }, + { + "selected": true, + "text": "5m", + "value": "5m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + } + ], + "query": "30s,5m,1h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Networking / Namespace (Pods)", + "uid": "8b7a8b326d7a6f1f04244066368c67af", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/namespace-by-workload.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/namespace-by-workload.yaml new file mode 100644 index 00000000..a526290a --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/namespace-by-workload.yaml @@ -0,0 +1,1736 @@ +{{- /* +Generated from 'namespace-by-workload' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "namespace-by-workload" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + namespace-by-workload.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 1 + }, + "id": 3, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}} workload {{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Received", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 1 + }, + "id": 4, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}} workload {{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Transmitted", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "columns": [ + { + "text": "Time", + "value": "Time" + }, + { + "text": "Value #A", + "value": "Value #A" + }, + { + "text": "Value #B", + "value": "Value #B" + }, + { + "text": "Value #C", + "value": "Value #C" + }, + { + "text": "Value #D", + "value": "Value #D" + }, + { + "text": "Value #E", + "value": "Value #E" + }, + { + "text": "Value #F", + "value": "Value #F" + }, + { + "text": "Value #G", + "value": "Value #G" + }, + { + "text": "Value #H", + "value": "Value #H" + }, + { + "text": "workload", + "value": "workload" + } + ], + "datasource": "$datasource", + "fill": 1, + "fontSize": "90%", + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 5, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null as zero", + "renderer": "flot", + "scroll": true, + "showHeader": true, + "sort": { + "col": 0, + "desc": false + }, + "spaceLength": 10, + "span": 24, + "styles": [ + { + "alias": "Time", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Time", + "thresholds": [ + + ], + "type": "hidden", + "unit": "short" + }, + { + "alias": "Current Bandwidth Received", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Bandwidth Transmitted", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Average Bandwidth Received", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Average Bandwidth Transmitted", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #H", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Workload", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down", + "linkUrl": "d/728bf77cc1166d2f3133bf25846876cc/kubernetes-networking-workload?orgId=1&refresh=30s&var-namespace=$namespace&var-type=$type&var-workload=$__cell", + "pattern": "workload", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "H", + "step": 10 + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Status", + "type": "table" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 19 + }, + "id": 6, + "panels": [ + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 20 + }, + "id": 7, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}} workload {{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Rate of Bytes Received", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 20 + }, + "id": 8, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}} workload {{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Rate of Bytes Transmitted", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Average Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 29 + }, + "id": 9, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth HIstory", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 38 + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 38 + }, + "id": 11, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 39 + }, + "id": 12, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 40 + }, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 40 + }, + "id": 14, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Packets", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 40 + }, + "id": 15, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 41 + }, + "id": 16, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 41 + }, + "id": 17, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Errors", + "titleSize": "h6", + "type": "row" + } + ], + "refresh": "10s", + "rows": [ + + ], + "schemaVersion": 18, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "kube-system", + "value": "kube-system" + }, + "datasource": "$datasource", + "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "deployment", + "value": "deployment" + }, + "datasource": "$datasource", + "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\"}, workload_type)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "type", + "options": [ + + ], + "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\"}, workload_type)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "resolution", + "options": [ + { + "selected": false, + "text": "30s", + "value": "30s" + }, + { + "selected": true, + "text": "5m", + "value": "5m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + } + ], + "query": "30s,5m,1h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Networking / Namespace (Workload)", + "uid": "bbb2a765a623ae38130206c7d94a160f", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/node-cluster-rsrc-use.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/node-cluster-rsrc-use.yaml new file mode 100644 index 00000000..82b821a7 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/node-cluster-rsrc-use.yaml @@ -0,0 +1,964 @@ +{{- /* +Generated from 'node-cluster-rsrc-use' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled .Values.nodeExporter.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "node-cluster-rsrc-use" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + node-cluster-rsrc-use.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n instance:node_cpu_utilisation:rate1m{job=\"node-exporter\"}\n*\n instance:node_num_cpu:sum{job=\"node-exporter\"}\n)\n/ scalar(sum(instance:node_num_cpu:sum{job=\"node-exporter\"}))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "legendLink": "/dashboard/file/node-rsrc-use.json", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_load1_per_cpu:ratio{job=\"node-exporter\"}\n/ scalar(count(instance:node_load1_per_cpu:ratio{job=\"node-exporter\"}))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "legendLink": "/dashboard/file/node-rsrc-use.json", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Saturation (load1 per CPU)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_memory_utilisation:ratio{job=\"node-exporter\"}\n/ scalar(count(instance:node_memory_utilisation:ratio{job=\"node-exporter\"}))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "legendLink": "/dashboard/file/node-rsrc-use.json", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_vmstat_pgmajfault:rate1m{job=\"node-exporter\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "legendLink": "/dashboard/file/node-rsrc-use.json", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Saturation (Major Page Faults)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "rps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/ Receive/", + "stack": "A" + }, + { + "alias": "/ Transmit/", + "stack": "B", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_network_receive_bytes_excluding_lo:rate1m{job=\"node-exporter\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Receive", + "legendLink": "/dashboard/file/node-rsrc-use.json", + "step": 10 + }, + { + "expr": "instance:node_network_transmit_bytes_excluding_lo:rate1m{job=\"node-exporter\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Transmit", + "legendLink": "/dashboard/file/node-rsrc-use.json", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Net Utilisation (Bytes Receive/Transmit)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/ Receive/", + "stack": "A" + }, + { + "alias": "/ Transmit/", + "stack": "B", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_network_receive_drop_excluding_lo:rate1m{job=\"node-exporter\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Receive", + "legendLink": "/dashboard/file/node-rsrc-use.json", + "step": 10 + }, + { + "expr": "instance:node_network_transmit_drop_excluding_lo:rate1m{job=\"node-exporter\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Transmit", + "legendLink": "/dashboard/file/node-rsrc-use.json", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Net Saturation (Drops Receive/Transmit)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "rps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance_device:node_disk_io_time_seconds:rate1m{job=\"node-exporter\"}\n/ scalar(count(instance_device:node_disk_io_time_seconds:rate1m{job=\"node-exporter\"}))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}device{{`}}`}}", + "legendLink": "/dashboard/file/node-rsrc-use.json", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk IO Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance_device:node_disk_io_time_weighted_seconds:rate1m{job=\"node-exporter\"}\n/ scalar(count(instance_device:node_disk_io_time_weighted_seconds:rate1m{job=\"node-exporter\"}))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}device{{`}}`}}", + "legendLink": "/dashboard/file/node-rsrc-use.json", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk IO Saturation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk IO", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum without (device) (\n max without (fstype, mountpoint) (\n node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\"} - node_filesystem_avail_bytes{job=\"node-exporter\", fstype!=\"\"}\n )\n) \n/ scalar(sum(max without (fstype, mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\"})))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "legendLink": "/dashboard/file/node-rsrc-use.json", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk Space Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk Space", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "USE Method / Cluster", + "uid": "3e97d1d02672cdd0861f4c97c64f89b2", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/node-rsrc-use.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/node-rsrc-use.yaml new file mode 100644 index 00000000..9cdfa645 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/node-rsrc-use.yaml @@ -0,0 +1,991 @@ +{{- /* +Generated from 'node-rsrc-use' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled .Values.nodeExporter.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "node-rsrc-use" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + node-rsrc-use.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_cpu_utilisation:rate1m{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Utilisation", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_load1_per_cpu:ratio{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Saturation", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Saturation (Load1 per CPU)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_memory_utilisation:ratio{job=\"node-exporter\", job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Memory", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_vmstat_pgmajfault:rate1m{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Major page faults", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Saturation (Major Page Faults)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/Receive/", + "stack": "A" + }, + { + "alias": "/Transmit/", + "stack": "B", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_network_receive_bytes_excluding_lo:rate1m{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Receive", + "legendLink": null, + "step": 10 + }, + { + "expr": "instance:node_network_transmit_bytes_excluding_lo:rate1m{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Transmit", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Net Utilisation (Bytes Receive/Transmit)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/Receive/", + "stack": "A" + }, + { + "alias": "/Transmit/", + "stack": "B", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_network_receive_drop_excluding_lo:rate1m{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Receive drops", + "legendLink": null, + "step": 10 + }, + { + "expr": "instance:node_network_transmit_drop_excluding_lo:rate1m{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Transmit drops", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Net Saturation (Drops Receive/Transmit)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "rps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Net", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "instance_device:node_disk_io_time_seconds:rate1m{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}device{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk IO Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "instance_device:node_disk_io_time_weighted_seconds:rate1m{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}device{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk IO Saturation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk IO", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "1 -\n(\n max without (mountpoint, fstype) (node_filesystem_avail_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\"})\n/\n max without (mountpoint, fstype) (node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\"})\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}device{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk Space Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk Space", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "instance", + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(up{job=\"node-exporter\"}, instance)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "USE Method / Node", + "uid": "fac67cfbe174d3ef53eb473d73d9212f", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/nodes.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/nodes.yaml new file mode 100644 index 00000000..b2935aee --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/nodes.yaml @@ -0,0 +1,1001 @@ +{{- /* +Generated from 'nodes' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "nodes" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + nodes.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n (1 - rate(node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\"}[$__interval]))\n/ ignoring(cpu) group_left\n count without (cpu)( node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\"})\n)\n", + "format": "time_series", + "interval": "1m", + "intervalFactor": 5, + "legendFormat": "{{`{{`}}cpu{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_load1{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "1m load average", + "refId": "A" + }, + { + "expr": "node_load5{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "5m load average", + "refId": "B" + }, + { + "expr": "node_load15{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "15m load average", + "refId": "C" + }, + { + "expr": "count(node_cpu_seconds_total{job=\"node-exporter\", instance=\"$instance\", mode=\"idle\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "logical cores", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Load Average", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 9, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"}\n-\n node_memory_MemFree_bytes{job=\"node-exporter\", instance=\"$instance\"}\n-\n node_memory_Buffers_bytes{job=\"node-exporter\", instance=\"$instance\"}\n-\n node_memory_Cached_bytes{job=\"node-exporter\", instance=\"$instance\"}\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "memory used", + "refId": "A" + }, + { + "expr": "node_memory_Buffers_bytes{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "memory buffers", + "refId": "B" + }, + { + "expr": "node_memory_Cached_bytes{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "memory cached", + "refId": "C" + }, + { + "expr": "node_memory_MemFree_bytes{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "memory free", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "$datasource", + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 5, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "100 -\n(\n avg(node_memory_MemAvailable_bytes{job=\"node-exporter\", instance=\"$instance\"})\n/\n avg(node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"})\n* 100\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "80, 90", + "title": "Memory Usage", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/ read| written/", + "yaxis": 1 + }, + { + "alias": "/ io time/", + "yaxis": 2 + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(node_disk_read_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\"}[$__interval])", + "format": "time_series", + "interval": "1m", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}device{{`}}`}} read", + "refId": "A" + }, + { + "expr": "rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\"}[$__interval])", + "format": "time_series", + "interval": "1m", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}device{{`}}`}} written", + "refId": "B" + }, + { + "expr": "rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\"}[$__interval])", + "format": "time_series", + "interval": "1m", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}device{{`}}`}} io time", + "refId": "C" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk I/O", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "used", + "color": "#E0B400" + }, + { + "alias": "available", + "color": "#73BF69" + } + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n max by (device) (\n node_filesystem_size_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\"}\n -\n node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\"}\n )\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "used", + "refId": "A" + }, + { + "expr": "sum(\n max by (device) (\n node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\"}\n )\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "available", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk Space Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__interval])", + "format": "time_series", + "interval": "1m", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}device{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Received", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__interval])", + "format": "time_series", + "interval": "1m", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}device{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Transmitted", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + + ], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "Prometheus" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(node_exporter_build_info{job=\"node-exporter\"}, instance)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Nodes", + "uid": "fa49a4706d07a042595b664c87fb33ea", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/persistentvolumesusage.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/persistentvolumesusage.yaml new file mode 100644 index 00000000..4ac20ce6 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/persistentvolumesusage.yaml @@ -0,0 +1,577 @@ +{{- /* +Generated from 'persistentvolumesusage' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "persistentvolumesusage" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + persistentvolumesusage.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 2, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 9, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n sum without(instance, node) (kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n -\n sum without(instance, node) (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Used Space", + "refId": "A" + }, + { + "expr": "sum without(instance, node) (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Free Space", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Volume Space Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "$datasource", + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 3, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "(\n kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n -\n kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n)\n/\nkubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n* 100\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "80, 90", + "title": "Volume Space Usage", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 9, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum without(instance, node) (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Used inodes", + "refId": "A" + }, + { + "expr": "(\n sum without(instance, node) (kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n -\n sum without(instance, node) (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": " Free inodes", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Volume inodes Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "$datasource", + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 5, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n/\nkubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n* 100\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "80, 90", + "title": "Volume inodes Usage", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kubelet_volume_stats_capacity_bytes, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "Namespace", + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"}, namespace)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "PersistentVolumeClaim", + "multi": false, + "name": "volume", + "options": [ + + ], + "query": "label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\"}, persistentvolumeclaim)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-7d", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Persistent Volumes", + "uid": "919b92a8e8041bd567af9edab12c840c", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/pod-total.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/pod-total.yaml new file mode 100644 index 00000000..76c2c6e0 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/pod-total.yaml @@ -0,0 +1,1228 @@ +{{- /* +Generated from 'pod-total' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "pod-total" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + pod-total.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "decimals": 0, + "format": "time_series", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 1 + }, + "height": 9, + "id": 3, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "minSpan": 12, + "nullPointMode": "connected", + "nullText": null, + "options": { + "fieldOptions": { + "calcs": [ + "last" + ], + "defaults": { + "max": 10000000000, + "min": 0, + "title": "$namespace: $pod", + "unit": "Bps" + }, + "mappings": [ + + ], + "override": { + + }, + "thresholds": [ + { + "color": "dark-green", + "index": 0, + "value": null + }, + { + "color": "dark-yellow", + "index": 1, + "value": 5000000000 + }, + { + "color": "dark-red", + "index": 2, + "value": 7000000000 + } + ], + "values": false + } + }, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 12, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution]))", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Received", + "type": "gauge", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "decimals": 0, + "format": "time_series", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 1 + }, + "height": 9, + "id": 4, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "minSpan": 12, + "nullPointMode": "connected", + "nullText": null, + "options": { + "fieldOptions": { + "calcs": [ + "last" + ], + "defaults": { + "max": 10000000000, + "min": 0, + "title": "$namespace: $pod", + "unit": "Bps" + }, + "mappings": [ + + ], + "override": { + + }, + "thresholds": [ + { + "color": "dark-green", + "index": 0, + "value": null + }, + { + "color": "dark-yellow", + "index": 1, + "value": 5000000000 + }, + { + "color": "dark-red", + "index": 2, + "value": 7000000000 + } + ], + "values": false + } + }, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 12, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution]))", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Transmitted", + "type": "gauge", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 5, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 11 + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 11 + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 20 + }, + "id": 8, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 21 + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 21 + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Packets", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 21 + }, + "id": 11, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 32 + }, + "id": 12, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 32 + }, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Errors", + "titleSize": "h6", + "type": "row" + } + ], + "refresh": "10s", + "rows": [ + + ], + "schemaVersion": 18, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "kube-system", + "value": "kube-system" + }, + "datasource": "$datasource", + "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}, pod)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "pod", + "options": [ + + ], + "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}, pod)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "resolution", + "options": [ + { + "selected": false, + "text": "30s", + "value": "30s" + }, + { + "selected": true, + "text": "5m", + "value": "5m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + } + ], + "query": "30s,5m,1h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Networking / Pod", + "uid": "7a18067ce943a40ae25454675c19ff5c", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/prometheus-remote-write.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/prometheus-remote-write.yaml new file mode 100644 index 00000000..950443a1 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/prometheus-remote-write.yaml @@ -0,0 +1,1670 @@ +{{- /* +Generated from 'prometheus-remote-write' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled .Values.prometheus.prometheusSpec.remoteWriteDashboards }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "prometheus-remote-write" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + prometheus-remote-write.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "(\n prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} \n- \n ignoring(remote_name, url) group_right(instance) prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}}:{{`{{`}}instance{{`}}`}} {{`{{`}}remote_name{{`}}`}}:{{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Highest Timestamp In vs. Highest Timestamp Sent", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "(\n rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) \n- \n ignoring (remote_name, url) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}}:{{`{{`}}instance{{`}}`}} {{`{{`}}remote_name{{`}}`}}:{{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate[5m]", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Timestamps", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(\n prometheus_remote_storage_samples_in_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n- \n ignoring(remote_name, url) group_right(instance) rate(prometheus_remote_storage_succeeded_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n- \n rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}}:{{`{{`}}instance{{`}}`}} {{`{{`}}remote_name{{`}}`}}:{{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate, in vs. succeeded or dropped [5m]", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Samples", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 5, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "minSpan": 6, + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}}:{{`{{`}}instance{{`}}`}} {{`{{`}}remote_name{{`}}`}}:{{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Shards", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_remote_storage_shards_max{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}}:{{`{{`}}instance{{`}}`}} {{`{{`}}remote_name{{`}}`}}:{{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Max Shards", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_remote_storage_shards_min{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}}:{{`{{`}}instance{{`}}`}} {{`{{`}}remote_name{{`}}`}}:{{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Min Shards", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_remote_storage_shards_desired{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}}:{{`{{`}}instance{{`}}`}} {{`{{`}}remote_name{{`}}`}}:{{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Desired Shards", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Shards", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_remote_storage_shard_capacity{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}}:{{`{{`}}instance{{`}}`}} {{`{{`}}remote_name{{`}}`}}:{{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Shard Capacity", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_remote_storage_pending_samples{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}}:{{`{{`}}instance{{`}}`}} {{`{{`}}remote_name{{`}}`}}:{{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Pending Samples", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Shard Details", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 11, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_tsdb_wal_segment_current{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}}:{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "TSDB Current Segment", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 12, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_wal_watcher_current_segment{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}}:{{`{{`}}instance{{`}}`}} {{`{{`}}consumer{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Remote Write Current Segment", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Segments", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}}:{{`{{`}}instance{{`}}`}} {{`{{`}}remote_name{{`}}`}}:{{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Dropped Samples", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 14, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(prometheus_remote_storage_failed_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}}:{{`{{`}}instance{{`}}`}} {{`{{`}}remote_name{{`}}`}}:{{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Failed Samples", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 15, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(prometheus_remote_storage_retried_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}}:{{`{{`}}instance{{`}}`}} {{`{{`}}remote_name{{`}}`}}:{{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Retried Samples", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 16, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(prometheus_remote_storage_enqueue_retries_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}}:{{`{{`}}instance{{`}}`}} {{`{{`}}remote_name{{`}}`}}:{{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Enqueue Retries", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Misc. Rates", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + + ], + "templating": { + "list": [ + { + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "value": { + "selected": true, + "text": "All", + "value": "$__all" + } + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(prometheus_build_info, instance)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "value": { + "selected": true, + "text": "All", + "value": "$__all" + } + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": true, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_container_info{image=~\".*prometheus.*\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "url", + "options": [ + + ], + "query": "label_values(prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}, url)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-6h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "browser", + "title": "Prometheus Remote Write", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/prometheus.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/prometheus.yaml new file mode 100644 index 00000000..dfd3f3df --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/prometheus.yaml @@ -0,0 +1,1227 @@ +{{- /* +Generated from 'prometheus' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "prometheus" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + prometheus.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Count", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "hidden", + "unit": "short" + }, + { + "alias": "Uptime", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Instance", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "instance", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Job", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "job", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Version", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "version", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "count by (job, instance, version) (prometheus_build_info{job=~\"$job\", instance=~\"$instance\"})", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "max by (job, instance) (time() - process_start_time_seconds{job=~\"$job\", instance=~\"$instance\"})", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Prometheus Stats", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Prometheus Stats", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(prometheus_target_sync_length_seconds_sum{job=~\"$job\",instance=~\"$instance\"}[5m])) by (scrape_job) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}scrape_job{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Target Sync", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(prometheus_sd_discovered_targets{job=~\"$job\",instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Targets", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Targets", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Discovery", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(prometheus_target_interval_length_seconds_sum{job=~\"$job\",instance=~\"$instance\"}[5m]) / rate(prometheus_target_interval_length_seconds_count{job=~\"$job\",instance=~\"$instance\"}[5m]) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}interval{{`}}`}} configured", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Scrape Interval Duration", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (job) (rate(prometheus_target_scrapes_exceeded_sample_limit_total[1m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "exceeded sample limit: {{`{{`}}job{{`}}`}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_duplicate_timestamp_total[1m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "duplicate timestamp: {{`{{`}}job{{`}}`}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_out_of_bounds_total[1m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "out of bounds: {{`{{`}}job{{`}}`}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_out_of_order_total[1m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "out of order: {{`{{`}}job{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Scrape failures", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "rate(prometheus_tsdb_head_samples_appended_total{job=~\"$job\",instance=~\"$instance\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}job{{`}}`}} {{`{{`}}instance{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Appended Samples", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Retrieval", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_tsdb_head_series{job=~\"$job\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}job{{`}}`}} {{`{{`}}instance{{`}}`}} head series", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Head Series", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_tsdb_head_chunks{job=~\"$job\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}job{{`}}`}} {{`{{`}}instance{{`}}`}} head chunks", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Head Chunks", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Storage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "rate(prometheus_engine_query_duration_seconds_count{job=~\"$job\",instance=~\"$instance\",slice=\"inner_eval\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}job{{`}}`}} {{`{{`}}instance{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Query Rate", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "max by (slice) (prometheus_engine_query_duration_seconds{quantile=\"0.9\",job=~\"$job\",instance=~\"$instance\"}) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}slice{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Stage Duration", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "job", + "multi": true, + "name": "job", + "options": [ + + ], + "query": "label_values(prometheus_build_info, job)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "instance", + "multi": true, + "name": "instance", + "options": [ + + ], + "query": "label_values(prometheus_build_info, instance)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Prometheus Overview", + "uid": "", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/proxy.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/proxy.yaml new file mode 100644 index 00000000..8c6b77c0 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/proxy.yaml @@ -0,0 +1,1231 @@ +{{- /* +Generated from 'proxy' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled .Values.kubeProxy.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "proxy" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + proxy.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 2, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(up{job=\"kube-proxy\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Up", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "min" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 5, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubeproxy_sync_proxy_rules_duration_seconds_count{job=\"kube-proxy\", instance=~\"$instance\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "rate", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rules Sync Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 5, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99,rate(kubeproxy_sync_proxy_rules_duration_seconds_bucket{job=\"kube-proxy\", instance=~\"$instance\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rule Sync Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 5, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubeproxy_network_programming_duration_seconds_count{job=\"kube-proxy\", instance=~\"$instance\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "rate", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Programming Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubeproxy_network_programming_duration_seconds_bucket{job=\"kube-proxy\", instance=~\"$instance\"}[5m])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Programming Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-proxy\", instance=~\"$instance\",code=~\"2..\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "2xx", + "refId": "A" + }, + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-proxy\", instance=~\"$instance\",code=~\"3..\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "3xx", + "refId": "B" + }, + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-proxy\", instance=~\"$instance\",code=~\"4..\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "4xx", + "refId": "C" + }, + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-proxy\", instance=~\"$instance\",code=~\"5..\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "5xx", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Kube API Request Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 8, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[5m])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}verb{{`}}`}} {{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Post Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}verb{{`}}`}} {{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Get Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "process_resident_memory_bytes{job=\"kube-proxy\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 11, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(process_cpu_seconds_total{job=\"kube-proxy\",instance=~\"$instance\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 12, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "go_goroutines{job=\"kube-proxy\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Goroutines", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(kubeproxy_network_programming_duration_seconds_bucket{job=\"kube-proxy\"}, instance)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Proxy", + "uid": "632e265de029684c40b21cb76bca4f94", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/scheduler.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/scheduler.yaml new file mode 100644 index 00000000..860fdc8b --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/scheduler.yaml @@ -0,0 +1,1074 @@ +{{- /* +Generated from 'scheduler' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled .Values.kubeScheduler.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "scheduler" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + scheduler.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 2, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(up{job=\"kube-scheduler\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Up", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "min" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 5, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(scheduler_e2e_scheduling_duration_seconds_count{job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} e2e", + "refId": "A" + }, + { + "expr": "sum(rate(scheduler_binding_duration_seconds_count{job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} binding", + "refId": "B" + }, + { + "expr": "sum(rate(scheduler_scheduling_algorithm_duration_seconds_count{job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} scheduling algorithm", + "refId": "C" + }, + { + "expr": "sum(rate(scheduler_volume_scheduling_duration_seconds_count{job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} volume", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Scheduling Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 5, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} e2e", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} binding", + "refId": "B" + }, + { + "expr": "histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} scheduling algorithm", + "refId": "C" + }, + { + "expr": "histogram_quantile(0.99, sum(rate(scheduler_volume_scheduling_duration_seconds_bucket{job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} volume", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Scheduling latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 5, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-scheduler\", instance=~\"$instance\",code=~\"2..\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "2xx", + "refId": "A" + }, + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-scheduler\", instance=~\"$instance\",code=~\"3..\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "3xx", + "refId": "B" + }, + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-scheduler\", instance=~\"$instance\",code=~\"4..\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "4xx", + "refId": "C" + }, + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-scheduler\", instance=~\"$instance\",code=~\"5..\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "5xx", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Kube API Request Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 8, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[5m])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}verb{{`}}`}} {{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Post Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}verb{{`}}`}} {{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Get Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "process_resident_memory_bytes{job=\"kube-scheduler\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(process_cpu_seconds_total{job=\"kube-scheduler\", instance=~\"$instance\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "go_goroutines{job=\"kube-scheduler\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Goroutines", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(process_cpu_seconds_total{job=\"kube-scheduler\"}, instance)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Scheduler", + "uid": "2e6b6a3b4bddf1427b3a55aa1311c656", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/statefulset.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/statefulset.yaml new file mode 100644 index 00000000..9b3ce7d6 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/statefulset.yaml @@ -0,0 +1,928 @@ +{{- /* +Generated from 'statefulset' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "statefulset" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + statefulset.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 2, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "cores", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 4, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(rate(container_cpu_usage_seconds_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\", namespace=\"$namespace\", pod=~\"$statefulset.*\"}[3m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "CPU", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "0", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 3, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "GB", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 4, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(container_memory_usage_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\", namespace=\"$namespace\", pod=~\"$statefulset.*\"}) / 1024^3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Memory", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "0", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 4, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "Bps", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 4, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$statefulset.*\"}[3m])) + sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",pod=~\"$statefulset.*\"}[3m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Network", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "0", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "height": "100px", + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 5, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "max(kube_statefulset_replicas{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Desired Replicas", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "0", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 6, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "min(kube_statefulset_status_replicas_current{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Replicas of current version", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "0", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 7, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "max(kube_statefulset_status_observed_generation{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Observed Generation", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "0", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 8, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "max(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Metadata Generation", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "0", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max(kube_statefulset_replicas{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "replicas specified", + "refId": "A" + }, + { + "expr": "max(kube_statefulset_status_replicas{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "replicas created", + "refId": "B" + }, + { + "expr": "min(kube_statefulset_status_replicas_ready{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "ready", + "refId": "C" + }, + { + "expr": "min(kube_statefulset_status_replicas_current{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "replicas of current version", + "refId": "D" + }, + { + "expr": "min(kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "updated", + "refId": "E" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Replicas", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_statefulset_metadata_generation, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "Namespace", + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "Name", + "multi": false, + "name": "statefulset", + "options": [ + + ], + "query": "label_values(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\"}, statefulset)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / StatefulSets", + "uid": "a31c1f46e6f727cb37c0d731a7245005", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/workload-total.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/workload-total.yaml new file mode 100644 index 00000000..08d8cfda --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/workload-total.yaml @@ -0,0 +1,1438 @@ +{{- /* +Generated from 'workload-total' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "workload-total" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + workload-total.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 1 + }, + "id": 3, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}} pod {{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Received", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 1 + }, + "id": 4, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}} pod {{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Transmitted", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 5, + "panels": [ + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 11 + }, + "id": 6, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}} pod {{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Rate of Bytes Received", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 11 + }, + "id": 7, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}} pod {{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Rate of Bytes Transmitted", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Average Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 11 + }, + "id": 8, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth HIstory", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 12 + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 12 + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 21 + }, + "id": 11, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 22 + }, + "id": 12, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 22 + }, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Packets", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 22 + }, + "id": 14, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 23 + }, + "id": 15, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 23 + }, + "id": 16, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Errors", + "titleSize": "h6", + "type": "row" + } + ], + "refresh": "10s", + "rows": [ + + ], + "schemaVersion": 18, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "kube-system", + "value": "kube-system" + }, + "datasource": "$datasource", + "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\"}, workload)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "workload", + "options": [ + + ], + "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\"}, workload)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "deployment", + "value": "deployment" + }, + "datasource": "$datasource", + "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\"}, workload_type)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "type", + "options": [ + + ], + "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\"}, workload_type)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "resolution", + "options": [ + { + "selected": false, + "text": "30s", + "value": "30s" + }, + { + "selected": true, + "text": "5m", + "value": "5m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + } + ], + "query": "30s,5m,1h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Networking / Workload", + "uid": "728bf77cc1166d2f3133bf25846876cc", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/etcd.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/etcd.yaml new file mode 100644 index 00000000..835a6901 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/etcd.yaml @@ -0,0 +1,1116 @@ +{{- /* +Generated from 'etcd' from https://raw.githubusercontent.com/etcd-io/etcd/master/Documentation/op-guide/grafana.json +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled .Values.kubeEtcd.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "etcd" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + etcd.json: |- + { + "annotations": { + "list": [] + }, + "description": "etcd sample Grafana dashboard with Prometheus", + "editable": true, + "gnetId": null, + "hideControls": false, + "links": [], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "editable": true, + "height": "250px", + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "$datasource", + "editable": true, + "error": false, + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "id": 28, + "interval": null, + "isNew": true, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "targets": [ + { + "expr": "sum(etcd_server_has_leader{job=\"$cluster\"})", + "intervalFactor": 2, + "legendFormat": "", + "metric": "etcd_server_has_leader", + "refId": "A", + "step": 20 + } + ], + "thresholds": "", + "title": "Up", + "type": "singlestat", + "valueFontSize": "200%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fill": 0, + "id": 23, + "isNew": true, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 5, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(grpc_server_started_total{job=\"$cluster\",grpc_type=\"unary\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "RPC Rate", + "metric": "grpc_server_started_total", + "refId": "A", + "step": 2 + }, + { + "expr": "sum(rate(grpc_server_handled_total{job=\"$cluster\",grpc_type=\"unary\",grpc_code!=\"OK\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "RPC Failed Rate", + "metric": "grpc_server_handled_total", + "refId": "B", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "RPC Rate", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fill": 0, + "id": 41, + "isNew": true, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(grpc_server_started_total{job=\"$cluster\",grpc_service=\"etcdserverpb.Watch\",grpc_type=\"bidi_stream\"}) - sum(grpc_server_handled_total{job=\"$cluster\",grpc_service=\"etcdserverpb.Watch\",grpc_type=\"bidi_stream\"})", + "intervalFactor": 2, + "legendFormat": "Watch Streams", + "metric": "grpc_server_handled_total", + "refId": "A", + "step": 4 + }, + { + "expr": "sum(grpc_server_started_total{job=\"$cluster\",grpc_service=\"etcdserverpb.Lease\",grpc_type=\"bidi_stream\"}) - sum(grpc_server_handled_total{job=\"$cluster\",grpc_service=\"etcdserverpb.Lease\",grpc_type=\"bidi_stream\"})", + "intervalFactor": 2, + "legendFormat": "Lease Streams", + "metric": "grpc_server_handled_total", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Active Streams", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "showTitle": false, + "title": "Row" + }, + { + "collapse": false, + "editable": true, + "height": "250px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "decimals": null, + "editable": true, + "error": false, + "fill": 0, + "grid": {}, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "etcd_mvcc_db_total_size_in_bytes{job=\"$cluster\"}", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} DB Size", + "metric": "", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "DB Size", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fill": 0, + "grid": {}, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 1, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 4, + "stack": false, + "steppedLine": true, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=\"$cluster\"}[5m])) by (instance, le))", + "hide": false, + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} WAL fsync", + "metric": "etcd_disk_wal_fsync_duration_seconds_bucket", + "refId": "A", + "step": 4 + }, + { + "expr": "histogram_quantile(0.99, sum(rate(etcd_disk_backend_commit_duration_seconds_bucket{job=\"$cluster\"}[5m])) by (instance, le))", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} DB fsync", + "metric": "etcd_disk_backend_commit_duration_seconds_bucket", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Disk Sync Duration", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "s", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fill": 0, + "id": 29, + "isNew": true, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "process_resident_memory_bytes{job=\"$cluster\"}", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Resident Memory", + "metric": "process_resident_memory_bytes", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Memory", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "title": "New row" + }, + { + "collapse": false, + "editable": true, + "height": "250px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fill": 5, + "id": 22, + "isNew": true, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "rate(etcd_network_client_grpc_received_bytes_total{job=\"$cluster\"}[5m])", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Client Traffic In", + "metric": "etcd_network_client_grpc_received_bytes_total", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Client Traffic In", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fill": 5, + "id": 21, + "isNew": true, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "rate(etcd_network_client_grpc_sent_bytes_total{job=\"$cluster\"}[5m])", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Client Traffic Out", + "metric": "etcd_network_client_grpc_sent_bytes_total", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Client Traffic Out", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fill": 0, + "id": 20, + "isNew": true, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(etcd_network_peer_received_bytes_total{job=\"$cluster\"}[5m])) by (instance)", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Peer Traffic In", + "metric": "etcd_network_peer_received_bytes_total", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Peer Traffic In", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "decimals": null, + "editable": true, + "error": false, + "fill": 0, + "grid": {}, + "id": 16, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(etcd_network_peer_sent_bytes_total{job=\"$cluster\"}[5m])) by (instance)", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Peer Traffic Out", + "metric": "etcd_network_peer_sent_bytes_total", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Peer Traffic Out", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "title": "New row" + }, + { + "collapse": false, + "editable": true, + "height": "250px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "editable": true, + "error": false, + "fill": 0, + "id": 40, + "isNew": true, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(etcd_server_proposals_failed_total{job=\"$cluster\"}[5m]))", + "intervalFactor": 2, + "legendFormat": "Proposal Failure Rate", + "metric": "etcd_server_proposals_failed_total", + "refId": "A", + "step": 2 + }, + { + "expr": "sum(etcd_server_proposals_pending{job=\"$cluster\"})", + "intervalFactor": 2, + "legendFormat": "Proposal Pending Total", + "metric": "etcd_server_proposals_pending", + "refId": "B", + "step": 2 + }, + { + "expr": "sum(rate(etcd_server_proposals_committed_total{job=\"$cluster\"}[5m]))", + "intervalFactor": 2, + "legendFormat": "Proposal Commit Rate", + "metric": "etcd_server_proposals_committed_total", + "refId": "C", + "step": 2 + }, + { + "expr": "sum(rate(etcd_server_proposals_applied_total{job=\"$cluster\"}[5m]))", + "intervalFactor": 2, + "legendFormat": "Proposal Apply Rate", + "refId": "D", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Raft Proposals", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$datasource", + "decimals": 0, + "editable": true, + "error": false, + "fill": 0, + "id": 19, + "isNew": true, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "changes(etcd_server_leader_changes_seen_total{job=\"$cluster\"}[1d])", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Total Leader Elections Per Day", + "metric": "etcd_server_leader_changes_seen_total", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Total Leader Elections Per Day", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "title": "New row" + } + ], + "schemaVersion": 13, + "sharedCrosshair": false, + "style": "dark", + "tags": [], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "Prometheus" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [], + "query": "label_values(etcd_server_has_leader, job)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-15m", + "to": "now" + }, + "timepicker": { + "now": true, + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "browser", + "title": "etcd", + "uid": "c2f4e12cdf69feb95caa41a5a1b423d9", + "version": 215 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-cluster-rsrc-use.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-cluster-rsrc-use.yaml new file mode 100644 index 00000000..fbe5e313 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-cluster-rsrc-use.yaml @@ -0,0 +1,959 @@ +{{- /* +Generated from 'k8s-cluster-rsrc-use' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "k8s-cluster-rsrc-use" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + k8s-cluster-rsrc-use.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node:cluster_cpu_utilisation:ratio{cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}node{{`}}`}}", + "legendLink": "./d/4ac4f123aae0ff6dbaf4f4f66120033b/k8s-node-rsrc-use", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node:node_cpu_saturation_load1:{cluster=\"$cluster\"} / scalar(sum(min(kube_pod_info{cluster=\"$cluster\"}) by (node)))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}node{{`}}`}}", + "legendLink": "./d/4ac4f123aae0ff6dbaf4f4f66120033b/k8s-node-rsrc-use", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Saturation (Load1)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node:cluster_memory_utilisation:ratio{cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}node{{`}}`}}", + "legendLink": "./d/4ac4f123aae0ff6dbaf4f4f66120033b/k8s-node-rsrc-use", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node:node_memory_swap_io_bytes:sum_rate{cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}node{{`}}`}}", + "legendLink": "./d/4ac4f123aae0ff6dbaf4f4f66120033b/k8s-node-rsrc-use", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Saturation (Swap I/O)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node:node_disk_utilisation:avg_irate{cluster=\"$cluster\"} / scalar(:kube_pod_info_node_count:{cluster=\"$cluster\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}node{{`}}`}}", + "legendLink": "./d/4ac4f123aae0ff6dbaf4f4f66120033b/k8s-node-rsrc-use", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk IO Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node:node_disk_saturation:avg_irate{cluster=\"$cluster\"} / scalar(:kube_pod_info_node_count:{cluster=\"$cluster\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}node{{`}}`}}", + "legendLink": "./d/4ac4f123aae0ff6dbaf4f4f66120033b/k8s-node-rsrc-use", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk IO Saturation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node:node_net_utilisation:sum_irate{cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}node{{`}}`}}", + "legendLink": "./d/4ac4f123aae0ff6dbaf4f4f66120033b/k8s-node-rsrc-use", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Net Utilisation (Transmitted)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "node:node_net_saturation:sum_irate{cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}node{{`}}`}}", + "legendLink": "./d/4ac4f123aae0ff6dbaf4f4f66120033b/k8s-node-rsrc-use", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Net Saturation (Dropped)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(max(node_filesystem_size_bytes{fstype=~\"ext[234]|btrfs|xfs|zfs\", cluster=\"$cluster\"} - node_filesystem_avail_bytes{fstype=~\"ext[234]|btrfs|xfs|zfs\", cluster=\"$cluster\"}) by (device,pod,namespace)) by (pod,namespace)\n/ scalar(sum(max(node_filesystem_size_bytes{fstype=~\"ext[234]|btrfs|xfs|zfs\", cluster=\"$cluster\"}) by (device,pod,namespace)))\n* on (namespace, pod) group_left (node) node_namespace_pod:kube_pod_info:{cluster=\"$cluster\"}\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}node{{`}}`}}", + "legendLink": "./d/4ac4f123aae0ff6dbaf4f4f66120033b/k8s-node-rsrc-use", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk Capacity", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Storage", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "Prometheus" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(:kube_pod_info_node_count:, cluster)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Kubernetes / USE Method / Cluster", + "uid": "a6e7d1362e1ddbb79db21d5bb40d7137", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-node-rsrc-use.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-node-rsrc-use.yaml new file mode 100644 index 00000000..6d015785 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-node-rsrc-use.yaml @@ -0,0 +1,986 @@ +{{- /* +Generated from 'k8s-node-rsrc-use' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "k8s-node-rsrc-use" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + k8s-node-rsrc-use.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node:node_cpu_utilisation:avg1m{cluster=\"$cluster\", node=\"$node\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Utilisation", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node:node_cpu_saturation_load1:{cluster=\"$cluster\", node=\"$node\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Saturation", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Saturation (Load1)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node:node_memory_utilisation:{cluster=\"$cluster\", node=\"$node\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Memory", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node:node_memory_swap_io_bytes:sum_rate{cluster=\"$cluster\", node=\"$node\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Swap IO", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Saturation (Swap I/O)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node:node_disk_utilisation:avg_irate{cluster=\"$cluster\", node=\"$node\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Utilisation", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk IO Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node:node_disk_saturation:avg_irate{cluster=\"$cluster\", node=\"$node\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Saturation", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk IO Saturation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node:node_net_utilisation:sum_irate{cluster=\"$cluster\", node=\"$node\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Utilisation", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Net Utilisation (Transmitted)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node:node_net_saturation:sum_irate{cluster=\"$cluster\", node=\"$node\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Saturation", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Net Saturation (Dropped)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Net", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node:node_filesystem_usage:{cluster=\"$cluster\"}\n* on (namespace, pod) group_left (node) node_namespace_pod:kube_pod_info:{cluster=\"$cluster\", node=\"$node\"}\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}device{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "Prometheus" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(:kube_pod_info_node_count:, cluster)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "node", + "multi": false, + "name": "node", + "options": [ + + ], + "query": "label_values(kube_node_info{cluster=\"$cluster\"}, node)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Kubernetes / USE Method / Node", + "uid": "4ac4f123aae0ff6dbaf4f4f66120033b", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-resources-cluster.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-resources-cluster.yaml new file mode 100644 index 00000000..ecfbb3cb --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-resources-cluster.yaml @@ -0,0 +1,1479 @@ +{{- /* +Generated from 'k8s-resources-cluster' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "k8s-resources-cluster" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + k8s-resources-cluster.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "100px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "1 - avg(rate(node_cpu_seconds_total{mode=\"idle\", cluster=\"$cluster\"}[1m]))", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\"}) / sum(node:node_num_cpu:sum{cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Requests Commitment", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\"}) / sum(node:node_num_cpu:sum{cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Limits Commitment", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "1 - sum(:node_memory_MemFreeCachedBuffers_bytes:sum{cluster=\"$cluster\"}) / sum(:node_memory_MemTotal_bytes:sum{cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilisation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\"}) / sum(:node_memory_MemTotal_bytes:sum{cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Requests Commitment", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\"}) / sum(:node_memory_MemTotal_bytes:sum{cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Limits Commitment", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Headlines", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Pods", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": true, + "linkTooltip": "Drill down to pods", + "linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Workloads", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": true, + "linkTooltip": "Drill down to workloads", + "linkUrl": "./d/a87fb0d919ec0ea5f6543124e16c42a5/k8s-resources-workloads-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Namespace", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down to pods", + "linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell", + "pattern": "namespace", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "count(mixin_pod_workload{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "count(avg(mixin_pod_workload{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_rss{cluster=\"$cluster\", container_name!=\"\"}) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage (w/o cache)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Pods", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": true, + "linkTooltip": "Drill down to pods", + "linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Workloads", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": true, + "linkTooltip": "Drill down to workloads", + "linkUrl": "./d/a87fb0d919ec0ea5f6543124e16c42a5/k8s-resources-workloads-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Memory Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Namespace", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down to pods", + "linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell", + "pattern": "namespace", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "count(mixin_pod_workload{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "count(avg(mixin_pod_workload{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{cluster=\"$cluster\", container_name!=\"\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{cluster=\"$cluster\", container_name!=\"\"}) by (namespace) / sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{cluster=\"$cluster\", container_name!=\"\"}) by (namespace) / sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Requests by Namespace", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Requests", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "Prometheus" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(:kube_pod_info_node_count:, cluster)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Kubernetes / Compute Resources / Cluster", + "uid": "efa86fd1d0c121a26444b636a3f509a8", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-resources-namespace.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-resources-namespace.yaml new file mode 100644 index 00000000..64da49cb --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-resources-namespace.yaml @@ -0,0 +1,963 @@ +{{- /* +Generated from 'k8s-resources-namespace' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "k8s-resources-namespace" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + k8s-resources-namespace.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod_name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod_name{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down", + "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(label_replace(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(label_replace(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(label_replace(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_usage_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container_name!=\"\"}) by (pod_name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod_name{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage (w/o cache)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Memory Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Usage (RSS)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Usage (Cache)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Usage (Swap", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #H", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down", + "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(label_replace(container_memory_usage_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container_name!=\"\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(label_replace(container_memory_usage_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container_name!=\"\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(label_replace(container_memory_usage_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container_name!=\"\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(label_replace(container_memory_rss{cluster=\"$cluster\", namespace=\"$namespace\",container_name!=\"\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(label_replace(container_memory_cache{cluster=\"$cluster\", namespace=\"$namespace\",container_name!=\"\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + }, + { + "expr": "sum(label_replace(container_memory_swap{cluster=\"$cluster\", namespace=\"$namespace\",container_name!=\"\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "H", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Quota", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "Prometheus" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(:kube_pod_info_node_count:, cluster)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Kubernetes / Compute Resources / Namespace (Pods)", + "uid": "85a562078cdf77779eaa1add43ccec1e", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-resources-pod.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-resources-pod.yaml new file mode 100644 index 00000000..78cd0452 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-resources-pod.yaml @@ -0,0 +1,1006 @@ +{{- /* +Generated from 'k8s-resources-pod' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "k8s-resources-pod" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + k8s-resources-pod.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{namespace=\"$namespace\", pod_name=\"$pod\", container_name!=\"POD\", cluster=\"$cluster\"}) by (container_name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}container_name{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Container", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "container", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(label_replace(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod_name=\"$pod\", container_name!=\"POD\"}, \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(label_replace(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod_name=\"$pod\"}, \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(label_replace(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod_name=\"$pod\"}, \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_rss{cluster=\"$cluster\", namespace=\"$namespace\", pod_name=\"$pod\", container_name!=\"POD\", container_name!=\"\"}) by (container_name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}container_name{{`}}`}} (RSS)", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(container_memory_cache{cluster=\"$cluster\", namespace=\"$namespace\", pod_name=\"$pod\", container_name!=\"POD\", container_name!=\"\"}) by (container_name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}container_name{{`}}`}} (Cache)", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(container_memory_swap{cluster=\"$cluster\", namespace=\"$namespace\", pod_name=\"$pod\", container_name!=\"POD\", container_name!=\"\"}) by (container_name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}container_name{{`}}`}} (Swap)", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Memory Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Usage (RSS)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Usage (Cache)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Usage (Swap", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #H", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Container", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "container", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(label_replace(container_memory_usage_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod_name=\"$pod\", container_name!=\"POD\", container_name!=\"\"}, \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(label_replace(container_memory_usage_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod_name=\"$pod\"}, \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(label_replace(container_memory_usage_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod_name=\"$pod\", container_name!=\"\"}, \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(label_replace(container_memory_rss{cluster=\"$cluster\", namespace=\"$namespace\", pod_name=\"$pod\", container_name != \"\", container_name != \"POD\"}, \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(label_replace(container_memory_cache{cluster=\"$cluster\", namespace=\"$namespace\", pod_name=\"$pod\", container_name != \"\", container_name != \"POD\"}, \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + }, + { + "expr": "sum(label_replace(container_memory_swap{cluster=\"$cluster\", namespace=\"$namespace\", pod_name=\"$pod\", container_name != \"\", container_name != \"POD\"}, \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "H", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Quota", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "Prometheus" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(:kube_pod_info_node_count:, cluster)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "pod", + "multi": false, + "name": "pod", + "options": [ + + ], + "query": "label_values(kube_pod_info{cluster=\"$cluster\", namespace=\"$namespace\"}, pod)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Kubernetes / Compute Resources / Pod", + "uid": "6581e46e4e5c7ba40a07646395ef7b23", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-resources-workload.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-resources-workload.yaml new file mode 100644 index 00000000..af1a153d --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-resources-workload.yaml @@ -0,0 +1,936 @@ +{{- /* +Generated from 'k8s-resources-workload' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "k8s-resources-workload" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + k8s-resources-workload.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n label_replace(\n namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"},\n \"pod\", \"$1\", \"pod_name\", \"(.*)\"\n ) * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down", + "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(\n label_replace(\n namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"},\n \"pod\", \"$1\", \"pod_name\", \"(.*)\"\n ) * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(\n label_replace(\n namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"},\n \"pod\", \"$1\", \"pod_name\", \"(.*)\"\n ) * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(\n label_replace(\n namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"},\n \"pod\", \"$1\", \"pod_name\", \"(.*)\"\n ) * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n label_replace(\n container_memory_usage_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container_name!=\"\"},\n \"pod\", \"$1\", \"pod_name\", \"(.*)\"\n ) * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n ) by (pod)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Memory Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down", + "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(\n label_replace(\n container_memory_usage_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container_name!=\"\"},\n \"pod\", \"$1\", \"pod_name\", \"(.*)\"\n ) * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n ) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(\n label_replace(\n container_memory_usage_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container_name!=\"\"},\n \"pod\", \"$1\", \"pod_name\", \"(.*)\"\n ) * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n ) by (pod)\n/sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(\n label_replace(\n container_memory_usage_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container_name!=\"\"},\n \"pod\", \"$1\", \"pod_name\", \"(.*)\"\n ) * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n ) by (pod)\n/sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Quota", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "Prometheus" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(:kube_pod_info_node_count:, cluster)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "workload", + "multi": false, + "name": "workload", + "options": [ + + ], + "query": "label_values(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}, workload)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "type", + "multi": false, + "name": "type", + "options": [ + + ], + "query": "label_values(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\"}, workload_type)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Kubernetes / Compute Resources / Workload", + "uid": "a164a7f0339f99e89cea5cb47e9be617", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-resources-workloads-namespace.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-resources-workloads-namespace.yaml new file mode 100644 index 00000000..c11f51bb --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/k8s-resources-workloads-namespace.yaml @@ -0,0 +1,972 @@ +{{- /* +Generated from 'k8s-resources-workloads-namespace' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "k8s-resources-workloads-namespace" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + k8s-resources-workloads-namespace.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n label_replace(\n namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"},\n \"pod\", \"$1\", \"pod_name\", \"(.*)\"\n ) * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}workload{{`}}`}} - {{`{{`}}workload_type{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Running Pods", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Workload", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down", + "linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2", + "pattern": "workload", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Workload Type", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "workload_type", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "count(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}) by (workload, workload_type)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(\n label_replace(\n namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"},\n \"pod\", \"$1\", \"pod_name\", \"(.*)\"\n ) * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(\n label_replace(\n namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"},\n \"pod\", \"$1\", \"pod_name\", \"(.*)\"\n ) * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(\n label_replace(\n namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"},\n \"pod\", \"$1\", \"pod_name\", \"(.*)\"\n ) * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n label_replace(\n container_memory_usage_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container_name!=\"\"},\n \"pod\", \"$1\", \"pod_name\", \"(.*)\"\n ) * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n ) by (workload, workload_type)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}workload{{`}}`}} - {{`{{`}}workload_type{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Running Pods", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Memory Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Workload", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down", + "linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2", + "pattern": "workload", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Workload Type", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "workload_type", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "count(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}) by (workload, workload_type)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(\n label_replace(\n container_memory_usage_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container_name!=\"\"},\n \"pod\", \"$1\", \"pod_name\", \"(.*)\"\n ) * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n ) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(\n label_replace(\n container_memory_usage_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container_name!=\"\"},\n \"pod\", \"$1\", \"pod_name\", \"(.*)\"\n ) * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n ) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(\n label_replace(\n container_memory_usage_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container_name!=\"\"},\n \"pod\", \"$1\", \"pod_name\", \"(.*)\"\n ) * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n ) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod) group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Quota", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Quota", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "Prometheus" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(:kube_pod_info_node_count:, cluster)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Kubernetes / Compute Resources / Namespace (Workloads)", + "uid": "a87fb0d919ec0ea5f6543124e16c42a5", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/nodes.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/nodes.yaml new file mode 100644 index 00000000..82d332a5 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/nodes.yaml @@ -0,0 +1,1383 @@ +{{- /* +Generated from 'nodes' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "nodes" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + nodes.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max(node_load1{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "load 1m", + "refId": "A" + }, + { + "expr": "max(node_load5{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "load 5m", + "refId": "B" + }, + { + "expr": "max(node_load15{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "load 15m", + "refId": "C" + }, + { + "expr": "count(node_cpu_seconds_total{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\", mode=\"user\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "logical cores", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "System load", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (cpu) (irate(node_cpu_seconds_total{cluster=\"$cluster\", job=\"node-exporter\", mode!=\"idle\", instance=\"$instance\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cpu{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Usage Per Core", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": "true", + "avg": "true", + "current": "true", + "max": "false", + "min": "false", + "rightSide": "true", + "show": "true", + "total": "false", + "values": "true" + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 9, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max (sum by (cpu) (irate(node_cpu_seconds_total{cluster=\"$cluster\", job=\"node-exporter\", mode!=\"idle\", instance=\"$instance\"}[2m])) ) * 100\n", + "format": "time_series", + "intervalFactor": 10, + "legendFormat": "{{`{{`}} cpu {{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilization", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percent", + "label": null, + "logBase": 1, + "max": 100, + "min": 0, + "show": true + }, + { + "format": "percent", + "label": null, + "logBase": 1, + "max": 100, + "min": 0, + "show": true + } + ] + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "$datasource", + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 5, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "avg(sum by (cpu) (irate(node_cpu_seconds_total{cluster=\"$cluster\", job=\"node-exporter\", mode!=\"idle\", instance=\"$instance\"}[2m]))) * 100\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "80, 90", + "title": "CPU Usage", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 9, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max(\n node_memory_MemTotal_bytes{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"}\n - node_memory_MemFree_bytes{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"}\n - node_memory_Buffers_bytes{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"}\n - node_memory_Cached_bytes{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"}\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "memory used", + "refId": "A" + }, + { + "expr": "max(node_memory_Buffers_bytes{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "memory buffers", + "refId": "B" + }, + { + "expr": "max(node_memory_Cached_bytes{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "memory cached", + "refId": "C" + }, + { + "expr": "max(node_memory_MemFree_bytes{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "memory free", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "$datasource", + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 7, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "max(\n (\n (\n node_memory_MemTotal_bytes{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"}\n - node_memory_MemFree_bytes{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"}\n - node_memory_Buffers_bytes{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"}\n - node_memory_Cached_bytes{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"}\n )\n / node_memory_MemTotal_bytes{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"}\n ) * 100)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "80, 90", + "title": "Memory Usage", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "read", + "yaxis": 1 + }, + { + "alias": "io time", + "yaxis": 2 + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max(rate(node_disk_read_bytes_total{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"}[2m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "read", + "refId": "A" + }, + { + "expr": "max(rate(node_disk_written_bytes_total{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"}[2m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "written", + "refId": "B" + }, + { + "expr": "max(rate(node_disk_io_time_seconds_total{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"}[2m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "io time", + "refId": "C" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk I/O", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by (namespace, pod, device) ((node_filesystem_size_bytes{cluster=\"$cluster\", fstype=~\"ext[234]|btrfs|xfs|zfs\", instance=\"$instance\", job=\"node-exporter\"} - node_filesystem_avail_bytes{cluster=\"$cluster\", fstype=~\"ext[234]|btrfs|xfs|zfs\", instance=\"$instance\", job=\"node-exporter\"}) / node_filesystem_size_bytes{cluster=\"$cluster\", fstype=~\"ext[234]|btrfs|xfs|zfs\", instance=\"$instance\", job=\"node-exporter\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "disk used", + "refId": "A" + }, + { + "expr": "max by (namespace, pod, device) (node_filesystem_avail_bytes{cluster=\"$cluster\", fstype=~\"ext[234]|btrfs|xfs|zfs\", instance=\"$instance\", job=\"node-exporter\"} / node_filesystem_size_bytes{cluster=\"$cluster\", fstype=~\"ext[234]|btrfs|xfs|zfs\", instance=\"$instance\", job=\"node-exporter\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "disk free", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk Space Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max(rate(node_network_receive_bytes_total{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\", device!~\"lo\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}device{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Received", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 11, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max(rate(node_network_transmit_bytes_total{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\", device!~\"lo\"}[5m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}device{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Transmitted", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 12, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 9, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max(\n node_filesystem_files{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"}\n - node_filesystem_files_free{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"}\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "inodes used", + "refId": "A" + }, + { + "expr": "max(node_filesystem_files_free{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "inodes free", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Inodes Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "$datasource", + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 13, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "max(\n (\n (\n node_filesystem_files{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"}\n - node_filesystem_files_free{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"}\n )\n / node_filesystem_files{cluster=\"$cluster\", job=\"node-exporter\", instance=\"$instance\"}\n ) * 100)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "80, 90", + "title": "Inodes Usage", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "Prometheus" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_info, cluster)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(node_boot_time_seconds{cluster=\"$cluster\", job=\"node-exporter\"}, instance)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Kubernetes / Nodes", + "uid": "fa49a4706d07a042595b664c87fb33ea", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/persistentvolumesusage.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/persistentvolumesusage.yaml new file mode 100644 index 00000000..3c51e117 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/persistentvolumesusage.yaml @@ -0,0 +1,573 @@ +{{- /* +Generated from 'persistentvolumesusage' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "persistentvolumesusage" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + persistentvolumesusage.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 2, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 9, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n sum without(instance, node) (kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n -\n sum without(instance, node) (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Used Space", + "refId": "A" + }, + { + "expr": "sum without(instance, node) (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Free Space", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Volume Space Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "$datasource", + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 3, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "(\n kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n -\n kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n)\n/\nkubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n* 100\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "80, 90", + "title": "Volume Space Usage", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 9, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum without(instance, node) (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Used inodes", + "refId": "A" + }, + { + "expr": "(\n sum without(instance, node) (kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n -\n sum without(instance, node) (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": " Free inodes", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Volume inodes Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "$datasource", + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 5, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n/\nkubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n* 100\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "80, 90", + "title": "Volume inodes Usage", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "Prometheus" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kubelet_volume_stats_capacity_bytes, cluster)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "Namespace", + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\"}, namespace)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "PersistentVolumeClaim", + "multi": false, + "name": "volume", + "options": [ + + ], + "query": "label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\"}, persistentvolumeclaim)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-7d", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Kubernetes / Persistent Volumes", + "uid": "919b92a8e8041bd567af9edab12c840c", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/pods.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/pods.yaml new file mode 100644 index 00000000..e2534d7f --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/pods.yaml @@ -0,0 +1,680 @@ +{{- /* +Generated from 'pods' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "pods" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + pods.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "$datasource", + "enable": true, + "expr": "time() == BOOL timestamp(rate(kube_pod_container_status_restarts_total{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[2m]) > 0)", + "hide": false, + "iconColor": "rgba(215, 44, 44, 1)", + "name": "Restarts", + "showIn": 0, + "tags": [ + "restart" + ], + "type": "rows" + } + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 2, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(container_name) (container_memory_usage_bytes{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", pod_name=\"$pod\", container_name=~\"$container\", container_name!=\"POD\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Current: {{`{{`}} container_name {{`}}`}}", + "refId": "A" + }, + { + "expr": "sum by(container) (kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\", pod=\"$pod\", container=~\"$container\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Requested: {{`{{`}} container {{`}}`}}", + "refId": "B" + }, + { + "expr": "sum by(container) (kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\", pod=\"$pod\", container=~\"$container\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Limit: {{`{{`}} container {{`}}`}}", + "refId": "C" + }, + { + "expr": "sum by(container_name) (container_memory_cache{job=\"kubelet\", namespace=\"$namespace\", pod_name=~\"$pod\", container_name=~\"$container\", container_name!=\"POD\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Cache: {{`{{`}} container_name {{`}}`}}", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 3, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (container_name) (rate(container_cpu_usage_seconds_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", image!=\"\", pod_name=\"$pod\", container_name=~\"$container\", container_name!=\"POD\"}[1m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Current: {{`{{`}} container_name {{`}}`}}", + "refId": "A" + }, + { + "expr": "sum by(container) (kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\", pod=\"$pod\", container=~\"$container\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Requested: {{`{{`}} container {{`}}`}}", + "refId": "B" + }, + { + "expr": "sum by(container) (kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\", pod=\"$pod\", container=~\"$container\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Limit: {{`{{`}} container {{`}}`}}", + "refId": "C" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum by (pod_name) (rate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", pod_name=\"$pod\"}[1m])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "RX: {{`{{`}} pod_name {{`}}`}}", + "refId": "A" + }, + { + "expr": "sort_desc(sum by (pod_name) (rate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", pod_name=\"$pod\"}[1m])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "TX: {{`{{`}} pod_name {{`}}`}}", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network I/O", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 5, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by (container) (kube_pod_container_status_restarts_total{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Restarts: {{`{{`}} container {{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Total Restarts Per Container", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "Prometheus" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_info, cluster)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "Namespace", + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "Pod", + "multi": false, + "name": "pod", + "options": [ + + ], + "query": "label_values(kube_pod_info{cluster=\"$cluster\", namespace=~\"$namespace\"}, pod)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "Container", + "multi": false, + "name": "container", + "options": [ + + ], + "query": "label_values(kube_pod_container_info{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}, container)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Kubernetes / Pods", + "uid": "ab4f13a9892a76a4d21ce8c2445bf4ea", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/statefulset.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/statefulset.yaml new file mode 100644 index 00000000..04b563be --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards/statefulset.yaml @@ -0,0 +1,926 @@ +{{- /* +Generated from 'statefulset' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/grafana-dashboardDefinitions.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.grafana.enabled .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "statefulset" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: "1" + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + statefulset.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 2, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "cores", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 4, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(rate(container_cpu_usage_seconds_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", pod_name=~\"$statefulset.*\"}[3m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "CPU", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "0", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 3, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "GB", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 4, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(container_memory_usage_bytes{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", pod_name=~\"$statefulset.*\"}) / 1024^3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Memory", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "0", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 4, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "Bps", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 4, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", pod_name=~\"$statefulset.*\"}[3m])) + sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\",pod_name=~\"$statefulset.*\"}[3m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Network", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "0", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "height": "100px", + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 5, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "max(kube_statefulset_replicas{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Desired Replicas", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "0", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 6, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "min(kube_statefulset_status_replicas_current{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Replicas of current version", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "0", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 7, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "max(kube_statefulset_status_observed_generation{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Observed Generation", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "0", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 8, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "max(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Metadata Generation", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "0", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max(kube_statefulset_replicas{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "replicas specified", + "refId": "A" + }, + { + "expr": "max(kube_statefulset_status_replicas{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "replicas created", + "refId": "B" + }, + { + "expr": "min(kube_statefulset_status_replicas_ready{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "ready", + "refId": "C" + }, + { + "expr": "min(kube_statefulset_status_replicas_current{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "replicas of current version", + "refId": "D" + }, + { + "expr": "min(kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "updated", + "refId": "E" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Replicas", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "Prometheus" + }, + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_statefulset_metadata_generation, cluster)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "Namespace", + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_statefulset_metadata_generation{job=\"kube-state-metrics\"}, namespace)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "Name", + "multi": false, + "name": "statefulset", + "options": [ + + ], + "query": "label_values(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", namespace=\"$namespace\"}, statefulset)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Kubernetes / StatefulSets", + "uid": "a31c1f46e6f727cb37c0d731a7245005", + "version": 0 + } +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/servicemonitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/servicemonitor.yaml new file mode 100644 index 00000000..1e839d70 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/servicemonitor.yaml @@ -0,0 +1,32 @@ +{{- if and .Values.grafana.enabled .Values.grafana.serviceMonitor.selfMonitor }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-grafana + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-grafana +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + selector: + matchLabels: + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: {{ $.Release.Name | quote }} + namespaceSelector: + matchNames: + - {{ printf "%s" (include "kube-prometheus-stack.namespace" .) | quote }} + endpoints: + - port: {{ .Values.grafana.service.portName }} + {{- if .Values.grafana.serviceMonitor.interval }} + interval: {{ .Values.grafana.serviceMonitor.interval }} + {{- end }} + path: {{ .Values.grafana.serviceMonitor.path | quote }} +{{- if .Values.grafana.serviceMonitor.metricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.grafana.serviceMonitor.metricRelabelings | indent 6) . }} +{{- end }} +{{- if .Values.grafana.serviceMonitor.relabelings }} + relabelings: +{{ toYaml .Values.grafana.serviceMonitor.relabelings | indent 6 }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/clusterrole.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/clusterrole.yaml new file mode 100644 index 00000000..7b31ab3f --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/clusterrole.yaml @@ -0,0 +1,33 @@ +{{- if and .Values.prometheusOperator.admissionWebhooks.enabled .Values.prometheusOperator.admissionWebhooks.patch.enabled .Values.global.rbac.create }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-admission + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + app: {{ template "kube-prometheus-stack.name" $ }}-admission +{{- include "kube-prometheus-stack.labels" $ | indent 4 }} +rules: + - apiGroups: + - admissionregistration.k8s.io + resources: + - validatingwebhookconfigurations + - mutatingwebhookconfigurations + verbs: + - get + - update +{{- if .Values.global.rbac.pspEnabled }} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if semverCompare "> 1.15.0-0" $kubeTargetVersion }} + - apiGroups: ['policy'] +{{- else }} + - apiGroups: ['extensions'] +{{- end }} + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: + - {{ template "kube-prometheus-stack.fullname" . }}-admission +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/clusterrolebinding.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/clusterrolebinding.yaml new file mode 100644 index 00000000..4f1f6166 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/clusterrolebinding.yaml @@ -0,0 +1,20 @@ +{{- if and .Values.prometheusOperator.admissionWebhooks.enabled .Values.prometheusOperator.admissionWebhooks.patch.enabled .Values.global.rbac.create }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-admission + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + app: {{ template "kube-prometheus-stack.name" $ }}-admission +{{- include "kube-prometheus-stack.labels" $ | indent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "kube-prometheus-stack.fullname" . }}-admission +subjects: + - kind: ServiceAccount + name: {{ template "kube-prometheus-stack.fullname" . }}-admission + namespace: {{ template "kube-prometheus-stack.namespace" . }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/job-createSecret.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/job-createSecret.yaml new file mode 100644 index 00000000..37a19a55 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/job-createSecret.yaml @@ -0,0 +1,65 @@ +{{- if and .Values.prometheusOperator.admissionWebhooks.enabled .Values.prometheusOperator.admissionWebhooks.patch.enabled }} +apiVersion: batch/v1 +kind: Job +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-admission-create + namespace: {{ template "kube-prometheus-stack.namespace" . }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + app: {{ template "kube-prometheus-stack.name" $ }}-admission-create +{{- include "kube-prometheus-stack.labels" $ | indent 4 }} +spec: + {{- if .Capabilities.APIVersions.Has "batch/v1alpha1" }} + # Alpha feature since k8s 1.12 + ttlSecondsAfterFinished: 0 + {{- end }} + template: + metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-admission-create +{{- with .Values.prometheusOperator.admissionWebhooks.patch.podAnnotations }} + annotations: +{{ toYaml . | indent 8 }} +{{- end }} + labels: + app: {{ template "kube-prometheus-stack.name" $ }}-admission-create +{{- include "kube-prometheus-stack.labels" $ | indent 8 }} + spec: + {{- if .Values.prometheusOperator.admissionWebhooks.patch.priorityClassName }} + priorityClassName: {{ .Values.prometheusOperator.admissionWebhooks.patch.priorityClassName }} + {{- end }} + containers: + - name: create + {{- if .Values.prometheusOperator.admissionWebhooks.patch.image.sha }} + image: {{ .Values.prometheusOperator.admissionWebhooks.patch.image.repository }}:{{ .Values.prometheusOperator.admissionWebhooks.patch.image.tag }}@sha256:{{ .Values.prometheusOperator.admissionWebhooks.patch.image.sha }} + {{- else }} + image: {{ .Values.prometheusOperator.admissionWebhooks.patch.image.repository }}:{{ .Values.prometheusOperator.admissionWebhooks.patch.image.tag }} + {{- end }} + imagePullPolicy: {{ .Values.prometheusOperator.admissionWebhooks.patch.image.pullPolicy }} + args: + - create + - --host={{ template "kube-prometheus-stack.operator.fullname" . }},{{ template "kube-prometheus-stack.operator.fullname" . }}.{{ template "kube-prometheus-stack.namespace" . }}.svc + - --namespace={{ template "kube-prometheus-stack.namespace" . }} + - --secret-name={{ template "kube-prometheus-stack.fullname" . }}-admission + resources: +{{ toYaml .Values.prometheusOperator.admissionWebhooks.patch.resources | indent 12 }} + restartPolicy: OnFailure + serviceAccountName: {{ template "kube-prometheus-stack.fullname" . }}-admission + {{- with .Values.prometheusOperator.admissionWebhooks.patch.nodeSelector }} + nodeSelector: +{{ toYaml . | indent 8 }} + {{- end }} + {{- with .Values.prometheusOperator.admissionWebhooks.patch.affinity }} + affinity: +{{ toYaml . | indent 8 }} + {{- end }} + {{- with .Values.prometheusOperator.admissionWebhooks.patch.tolerations }} + tolerations: +{{ toYaml . | indent 8 }} + {{- end }} + securityContext: + runAsGroup: 2000 + runAsNonRoot: true + runAsUser: 2000 +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/job-patchWebhook.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/job-patchWebhook.yaml new file mode 100644 index 00000000..b74c6188 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/job-patchWebhook.yaml @@ -0,0 +1,66 @@ +{{- if and .Values.prometheusOperator.admissionWebhooks.enabled .Values.prometheusOperator.admissionWebhooks.patch.enabled }} +apiVersion: batch/v1 +kind: Job +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-admission-patch + namespace: {{ template "kube-prometheus-stack.namespace" . }} + annotations: + "helm.sh/hook": post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + app: {{ template "kube-prometheus-stack.name" $ }}-admission-patch +{{- include "kube-prometheus-stack.labels" $ | indent 4 }} +spec: + {{- if .Capabilities.APIVersions.Has "batch/v1alpha1" }} + # Alpha feature since k8s 1.12 + ttlSecondsAfterFinished: 0 + {{- end }} + template: + metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-admission-patch +{{- with .Values.prometheusOperator.admissionWebhooks.patch.podAnnotations }} + annotations: +{{ toYaml . | indent 8 }} +{{- end }} + labels: + app: {{ template "kube-prometheus-stack.name" $ }}-admission-patch +{{- include "kube-prometheus-stack.labels" $ | indent 8 }} + spec: + {{- if .Values.prometheusOperator.admissionWebhooks.patch.priorityClassName }} + priorityClassName: {{ .Values.prometheusOperator.admissionWebhooks.patch.priorityClassName }} + {{- end }} + containers: + - name: patch + {{- if .Values.prometheusOperator.admissionWebhooks.patch.image.sha }} + image: {{ .Values.prometheusOperator.admissionWebhooks.patch.image.repository }}:{{ .Values.prometheusOperator.admissionWebhooks.patch.image.tag }}@sha256:{{ .Values.prometheusOperator.admissionWebhooks.patch.image.sha }} + {{- else }} + image: {{ .Values.prometheusOperator.admissionWebhooks.patch.image.repository }}:{{ .Values.prometheusOperator.admissionWebhooks.patch.image.tag }} + {{- end }} + imagePullPolicy: {{ .Values.prometheusOperator.admissionWebhooks.patch.image.pullPolicy }} + args: + - patch + - --webhook-name={{ template "kube-prometheus-stack.fullname" . }}-admission + - --namespace={{ template "kube-prometheus-stack.namespace" . }} + - --secret-name={{ template "kube-prometheus-stack.fullname" . }}-admission + - --patch-failure-policy={{ .Values.prometheusOperator.admissionWebhooks.failurePolicy }} + resources: +{{ toYaml .Values.prometheusOperator.admissionWebhooks.patch.resources | indent 12 }} + restartPolicy: OnFailure + serviceAccountName: {{ template "kube-prometheus-stack.fullname" . }}-admission + {{- with .Values.prometheusOperator.admissionWebhooks.patch.nodeSelector }} + nodeSelector: +{{ toYaml . | indent 8 }} + {{- end }} + {{- with .Values.prometheusOperator.admissionWebhooks.patch.affinity }} + affinity: +{{ toYaml . | indent 8 }} + {{- end }} + {{- with .Values.prometheusOperator.admissionWebhooks.patch.tolerations }} + tolerations: +{{ toYaml . | indent 8 }} + {{- end }} + securityContext: + runAsGroup: 2000 + runAsNonRoot: true + runAsUser: 2000 +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/psp.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/psp.yaml new file mode 100644 index 00000000..98e002af --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/psp.yaml @@ -0,0 +1,54 @@ +{{- if and .Values.prometheusOperator.admissionWebhooks.enabled .Values.prometheusOperator.admissionWebhooks.patch.enabled .Values.global.rbac.create .Values.global.rbac.pspEnabled }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-admission + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + app: {{ template "kube-prometheus-stack.name" . }}-admission +{{- if .Values.global.rbac.pspAnnotations }} + annotations: +{{ toYaml .Values.global.rbac.pspAnnotations | indent 4 }} +{{- end }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + privileged: false + # Required to prevent escalations to root. + # allowPrivilegeEscalation: false + # This is redundant with non-root + disallow privilege escalation, + # but we can provide it for defense in depth. + #requiredDropCapabilities: + # - ALL + # Allow core volume types. + volumes: + - 'configMap' + - 'emptyDir' + - 'projected' + - 'secret' + - 'downwardAPI' + - 'persistentVolumeClaim' + hostNetwork: false + hostIPC: false + hostPID: false + runAsUser: + # Permits the container to run with root privileges as well. + rule: 'RunAsAny' + seLinux: + # This policy assumes the nodes are using AppArmor rather than SELinux. + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 0 + max: 65535 + fsGroup: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 0 + max: 65535 + readOnlyRootFilesystem: false +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/role.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/role.yaml new file mode 100644 index 00000000..3609fe95 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/role.yaml @@ -0,0 +1,21 @@ +{{- if and .Values.prometheusOperator.admissionWebhooks.enabled .Values.prometheusOperator.admissionWebhooks.patch.enabled .Values.global.rbac.create }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-admission + namespace: {{ template "kube-prometheus-stack.namespace" . }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + app: {{ template "kube-prometheus-stack.name" $ }}-admission +{{- include "kube-prometheus-stack.labels" $ | indent 4 }} +rules: + - apiGroups: + - "" + resources: + - secrets + verbs: + - get + - create +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/rolebinding.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/rolebinding.yaml new file mode 100644 index 00000000..dcb0fbcf --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/rolebinding.yaml @@ -0,0 +1,21 @@ +{{- if and .Values.prometheusOperator.admissionWebhooks.enabled .Values.prometheusOperator.admissionWebhooks.patch.enabled .Values.global.rbac.create }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-admission + namespace: {{ template "kube-prometheus-stack.namespace" . }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + app: {{ template "kube-prometheus-stack.name" $ }}-admission +{{- include "kube-prometheus-stack.labels" $ | indent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ template "kube-prometheus-stack.fullname" . }}-admission +subjects: + - kind: ServiceAccount + name: {{ template "kube-prometheus-stack.fullname" . }}-admission + namespace: {{ template "kube-prometheus-stack.namespace" . }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/serviceaccount.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/serviceaccount.yaml new file mode 100644 index 00000000..5296494d --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/serviceaccount.yaml @@ -0,0 +1,15 @@ +{{- if and .Values.prometheusOperator.admissionWebhooks.enabled .Values.prometheusOperator.admissionWebhooks.patch.enabled .Values.global.rbac.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-admission + namespace: {{ template "kube-prometheus-stack.namespace" . }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + app: {{ template "kube-prometheus-stack.name" $ }}-admission +{{- include "kube-prometheus-stack.labels" $ | indent 4 }} +imagePullSecrets: +{{ toYaml .Values.global.imagePullSecrets | indent 2 }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/mutatingWebhookConfiguration.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/mutatingWebhookConfiguration.yaml new file mode 100644 index 00000000..b2dacb0a --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/mutatingWebhookConfiguration.yaml @@ -0,0 +1,33 @@ +{{- if and .Values.prometheusOperator.admissionWebhooks.enabled }} +apiVersion: admissionregistration.k8s.io/v1 +kind: MutatingWebhookConfiguration +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-admission + labels: + app: {{ template "kube-prometheus-stack.name" $ }}-admission +{{- include "kube-prometheus-stack.labels" $ | indent 4 }} +webhooks: + - name: prometheusrulemutate.monitoring.coreos.com + {{- if .Values.prometheusOperator.admissionWebhooks.patch.enabled }} + failurePolicy: Ignore + {{- else }} + failurePolicy: {{ .Values.prometheusOperator.admissionWebhooks.failurePolicy }} + {{- end }} + rules: + - apiGroups: + - monitoring.coreos.com + apiVersions: + - "*" + resources: + - prometheusrules + operations: + - CREATE + - UPDATE + clientConfig: + service: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ template "kube-prometheus-stack.operator.fullname" $ }} + path: /admission-prometheusrules/mutate + admissionReviewVersions: ["v1", "v1beta1"] + sideEffects: None +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/validatingWebhookConfiguration.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/validatingWebhookConfiguration.yaml new file mode 100644 index 00000000..3d48cd84 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/validatingWebhookConfiguration.yaml @@ -0,0 +1,33 @@ +{{- if and .Values.prometheusOperator.admissionWebhooks.enabled }} +apiVersion: admissionregistration.k8s.io/v1 +kind: ValidatingWebhookConfiguration +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-admission + labels: + app: {{ template "kube-prometheus-stack.name" $ }}-admission +{{- include "kube-prometheus-stack.labels" $ | indent 4 }} +webhooks: + - name: prometheusrulemutate.monitoring.coreos.com + {{- if .Values.prometheusOperator.admissionWebhooks.patch.enabled }} + failurePolicy: Ignore + {{- else }} + failurePolicy: {{ .Values.prometheusOperator.admissionWebhooks.failurePolicy }} + {{- end }} + rules: + - apiGroups: + - monitoring.coreos.com + apiVersions: + - "*" + resources: + - prometheusrules + operations: + - CREATE + - UPDATE + clientConfig: + service: + namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ template "kube-prometheus-stack.operator.fullname" $ }} + path: /admission-prometheusrules/validate + admissionReviewVersions: ["v1", "v1beta1"] + sideEffects: None +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/clusterrole.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/clusterrole.yaml new file mode 100644 index 00000000..e5568534 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/clusterrole.yaml @@ -0,0 +1,80 @@ +{{- if and .Values.prometheusOperator.enabled .Values.global.rbac.create }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-operator + labels: + app: {{ template "kube-prometheus-stack.name" . }}-operator +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +rules: +- apiGroups: + - monitoring.coreos.com + resources: + - alertmanagers + - alertmanagers/finalizers + - alertmanagerconfigs + - prometheuses + - prometheuses/finalizers + - thanosrulers + - thanosrulers/finalizers + - servicemonitors + - podmonitors + - probes + - prometheusrules + verbs: + - '*' +- apiGroups: + - apps + resources: + - statefulsets + verbs: + - '*' +- apiGroups: + - "" + resources: + - configmaps + - secrets + verbs: + - '*' +- apiGroups: + - "" + resources: + - pods + verbs: + - list + - delete +- apiGroups: + - "" + resources: + - services + - services/finalizers + - endpoints + verbs: + - get + - create + - update + - delete +- apiGroups: + - "" + resources: + - nodes + verbs: + - list + - watch +- apiGroups: + - "" + resources: + - namespaces + verbs: + - get + - list + - watch +- apiGroups: + - networking.k8s.io + resources: + - ingresses + verbs: + - get + - list + - watch +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/clusterrolebinding.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/clusterrolebinding.yaml new file mode 100644 index 00000000..c9ab0ab8 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/clusterrolebinding.yaml @@ -0,0 +1,17 @@ +{{- if and .Values.prometheusOperator.enabled .Values.global.rbac.create }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-operator + labels: + app: {{ template "kube-prometheus-stack.name" . }}-operator +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "kube-prometheus-stack.fullname" . }}-operator +subjects: +- kind: ServiceAccount + name: {{ template "kube-prometheus-stack.operator.serviceAccountName" . }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/deployment.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/deployment.yaml new file mode 100644 index 00000000..c9917893 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/deployment.yaml @@ -0,0 +1,146 @@ +{{- $namespace := printf "%s" (include "kube-prometheus-stack.namespace" .) }} +{{- if .Values.prometheusOperator.enabled }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-operator + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-operator +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + replicas: 1 + selector: + matchLabels: + app: {{ template "kube-prometheus-stack.name" . }}-operator + release: {{ $.Release.Name | quote }} + template: + metadata: + labels: + app: {{ template "kube-prometheus-stack.name" . }}-operator +{{ include "kube-prometheus-stack.labels" . | indent 8 }} +{{- if .Values.prometheusOperator.podLabels }} +{{ toYaml .Values.prometheusOperator.podLabels | indent 8 }} +{{- end }} +{{- if .Values.prometheusOperator.podAnnotations }} + annotations: +{{ toYaml .Values.prometheusOperator.podAnnotations | indent 8 }} +{{- end }} + spec: + {{- if .Values.prometheusOperator.priorityClassName }} + priorityClassName: {{ .Values.prometheusOperator.priorityClassName }} + {{- end }} + containers: + - name: {{ template "kube-prometheus-stack.name" . }} + {{- if .Values.prometheusOperator.image.sha }} + image: "{{ .Values.prometheusOperator.image.repository }}:{{ .Values.prometheusOperator.image.tag }}@sha256:{{ .Values.prometheusOperator.image.sha }}" + {{- else }} + image: "{{ .Values.prometheusOperator.image.repository }}:{{ .Values.prometheusOperator.image.tag }}" + {{- end }} + imagePullPolicy: "{{ .Values.prometheusOperator.image.pullPolicy }}" + args: + {{- if .Values.prometheusOperator.kubeletService.enabled }} + - --kubelet-service={{ .Values.prometheusOperator.kubeletService.namespace }}/{{ template "kube-prometheus-stack.fullname" . }}-kubelet + {{- end }} + {{- if .Values.prometheusOperator.logFormat }} + - --log-format={{ .Values.prometheusOperator.logFormat }} + {{- end }} + {{- if .Values.prometheusOperator.logLevel }} + - --log-level={{ .Values.prometheusOperator.logLevel }} + {{- end }} + {{- if .Values.prometheusOperator.denyNamespaces }} + - --deny-namespaces={{ .Values.prometheusOperator.denyNamespaces | join "," }} + {{- end }} + {{- with $.Values.prometheusOperator.namespaces }} + {{ $ns := .additional }} + {{- if .releaseNamespace }} + {{- $ns = append $ns $namespace }} + {{- end }} + - --namespaces={{ $ns | join "," }} + {{- end }} + {{- if (semverCompare "< v0.44.0" .Values.prometheusOperator.image.tag) -}} + - --logtostderr=true + {{- end }} + - --localhost=127.0.0.1 + {{- if .Values.prometheusOperator.prometheusConfigReloaderImage.sha }} + - --prometheus-config-reloader={{ .Values.prometheusOperator.prometheusConfigReloaderImage.repository }}:{{ .Values.prometheusOperator.prometheusConfigReloaderImage.tag }}@sha256:{{ .Values.prometheusOperator.prometheusConfigReloaderImage.sha }} + {{- else }} + - --prometheus-config-reloader={{ .Values.prometheusOperator.prometheusConfigReloaderImage.repository }}:{{ .Values.prometheusOperator.prometheusConfigReloaderImage.tag }} + {{- end }} + # Empty if statement to catch non-semver master tags that do not need the --config-reloader-image flag + {{- if regexMatch "master.*" .Values.prometheusOperator.image.tag -}} + {{- else if (semverCompare "< v0.43.0" .Values.prometheusOperator.image.tag) -}} + {{- if .Values.prometheusOperator.configmapReloadImage.sha }} + - --config-reloader-image={{ .Values.prometheusOperator.configmapReloadImage.repository }}:{{ .Values.prometheusOperator.configmapReloadImage.tag }}@sha256:{{ .Values.prometheusOperator.configmapReloadImage.sha }} + {{- else }} + - --config-reloader-image={{ .Values.prometheusOperator.configmapReloadImage.repository }}:{{ .Values.prometheusOperator.configmapReloadImage.tag }} + {{- end }} + {{- end }} + - --config-reloader-cpu={{ .Values.prometheusOperator.configReloaderCpu }} + - --config-reloader-memory={{ .Values.prometheusOperator.configReloaderMemory }} + {{- if .Values.prometheusOperator.alertmanagerInstanceNamespaces }} + - --alertmanager-instance-namespaces={{ .Values.prometheusOperator.alertmanagerInstanceNamespaces | join "," }} + {{- end }} + {{- if .Values.prometheusOperator.prometheusInstanceNamespaces }} + - --prometheus-instance-namespaces={{ .Values.prometheusOperator.prometheusInstanceNamespaces | join "," }} + {{- end }} + {{- if .Values.prometheusOperator.thanosRulerInstanceNamespaces }} + - --thanos-ruler-instance-namespaces={{ .Values.prometheusOperator.thanosRulerInstanceNamespaces | join "," }} + {{- end }} + {{- if .Values.prometheusOperator.secretFieldSelector }} + - --secret-field-selector={{ .Values.prometheusOperator.secretFieldSelector }} + {{- end }} + {{- if .Values.prometheusOperator.tls.enabled }} + - --web.enable-tls=true + - --web.cert-file=cert/cert + - --web.key-file=cert/key + - --web.listen-address=:8443 + - --web.tls-min-version={{ .Values.prometheusOperator.tls.tlsMinVersion }} + ports: + - containerPort: 8443 + name: https + {{- else }} + ports: + - containerPort: 8080 + name: http + {{- end }} + resources: +{{ toYaml .Values.prometheusOperator.resources | indent 12 }} + securityContext: + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + {{- if .Values.prometheusOperator.tls.enabled }} + volumeMounts: + - name: tls-secret + mountPath: /cert + readOnly: true + {{- end }} +{{- if .Values.prometheusOperator.tls.enabled }} + volumes: + - name: tls-secret + secret: + defaultMode: 420 + secretName: {{ template "kube-prometheus-stack.fullname" . }}-admission +{{- end }} +{{- if .Values.prometheusOperator.securityContext }} + securityContext: +{{ toYaml .Values.prometheusOperator.securityContext | indent 8 }} +{{- end }} + serviceAccountName: {{ template "kube-prometheus-stack.operator.serviceAccountName" . }} +{{- if .Values.prometheusOperator.hostNetwork }} + hostNetwork: true + dnsPolicy: ClusterFirstWithHostNet +{{- end }} + {{- with .Values.prometheusOperator.nodeSelector }} + nodeSelector: +{{ toYaml . | indent 8 }} + {{- end }} + {{- with .Values.prometheusOperator.affinity }} + affinity: +{{ toYaml . | indent 8 }} + {{- end }} + {{- with .Values.prometheusOperator.tolerations }} + tolerations: +{{ toYaml . | indent 8 }} + {{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/psp-clusterrole.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/psp-clusterrole.yaml new file mode 100644 index 00000000..d667d627 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/psp-clusterrole.yaml @@ -0,0 +1,20 @@ +{{- if and .Values.prometheusOperator.enabled .Values.global.rbac.create .Values.global.rbac.pspEnabled }} +kind: ClusterRole +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-operator-psp + labels: + app: {{ template "kube-prometheus-stack.name" . }}-operator +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +rules: +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if semverCompare "> 1.15.0-0" $kubeTargetVersion }} +- apiGroups: ['policy'] +{{- else }} +- apiGroups: ['extensions'] +{{- end }} + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: + - {{ template "kube-prometheus-stack.fullname" . }}-operator +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/psp-clusterrolebinding.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/psp-clusterrolebinding.yaml new file mode 100644 index 00000000..c538cd17 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/psp-clusterrolebinding.yaml @@ -0,0 +1,17 @@ +{{- if and .Values.prometheusOperator.enabled .Values.global.rbac.create .Values.global.rbac.pspEnabled }} +kind: ClusterRoleBinding +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-operator-psp + labels: + app: {{ template "kube-prometheus-stack.name" . }}-operator +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "kube-prometheus-stack.fullname" . }}-operator-psp +subjects: + - kind: ServiceAccount + name: {{ template "kube-prometheus-stack.operator.serviceAccountName" . }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/psp.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/psp.yaml new file mode 100644 index 00000000..18d1d37d --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/psp.yaml @@ -0,0 +1,51 @@ +{{- if and .Values.prometheusOperator.enabled .Values.global.rbac.create .Values.global.rbac.pspEnabled }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-operator + labels: + app: {{ template "kube-prometheus-stack.name" . }}-operator +{{- if .Values.global.rbac.pspAnnotations }} + annotations: +{{ toYaml .Values.global.rbac.pspAnnotations | indent 4 }} +{{- end }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + privileged: false + # Required to prevent escalations to root. + # allowPrivilegeEscalation: false + # This is redundant with non-root + disallow privilege escalation, + # but we can provide it for defense in depth. + #requiredDropCapabilities: + # - ALL + # Allow core volume types. + volumes: + - 'configMap' + - 'emptyDir' + - 'projected' + - 'secret' + - 'downwardAPI' + - 'persistentVolumeClaim' + hostNetwork: {{ .Values.prometheusOperator.hostNetwork }} + hostIPC: false + hostPID: false + runAsUser: + # Permits the container to run with root privileges as well. + rule: 'RunAsAny' + seLinux: + # This policy assumes the nodes are using AppArmor rather than SELinux. + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 0 + max: 65535 + fsGroup: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 0 + max: 65535 + readOnlyRootFilesystem: false +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/service.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/service.yaml new file mode 100644 index 00000000..8ccb2bb2 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/service.yaml @@ -0,0 +1,55 @@ +{{- if .Values.prometheusOperator.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-operator + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-operator +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.prometheusOperator.service.labels }} +{{ toYaml .Values.prometheusOperator.service.labels | indent 4 }} +{{- end }} +{{- if .Values.prometheusOperator.service.annotations }} + annotations: +{{ toYaml .Values.prometheusOperator.service.annotations | indent 4 }} +{{- end }} +spec: +{{- if .Values.prometheusOperator.service.clusterIP }} + clusterIP: {{ .Values.prometheusOperator.service.clusterIP }} +{{- end }} +{{- if .Values.prometheusOperator.service.externalIPs }} + externalIPs: +{{ toYaml .Values.prometheusOperator.service.externalIPs | indent 4 }} +{{- end }} +{{- if .Values.prometheusOperator.service.loadBalancerIP }} + loadBalancerIP: {{ .Values.prometheusOperator.service.loadBalancerIP }} +{{- end }} +{{- if .Values.prometheusOperator.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: + {{- range $cidr := .Values.prometheusOperator.service.loadBalancerSourceRanges }} + - {{ $cidr }} + {{- end }} +{{- end }} + ports: + {{- if not .Values.prometheusOperator.tls.enabled }} + - name: http + {{- if eq .Values.prometheusOperator.service.type "NodePort" }} + nodePort: {{ .Values.prometheusOperator.service.nodePort }} + {{- end }} + port: 8080 + targetPort: http + {{- end }} + {{- if .Values.prometheusOperator.tls.enabled }} + - name: https + {{- if eq .Values.prometheusOperator.service.type "NodePort"}} + nodePort: {{ .Values.prometheusOperator.service.nodePortTls }} + {{- end }} + port: 443 + targetPort: https + {{- end }} + selector: + app: {{ template "kube-prometheus-stack.name" . }}-operator + release: {{ $.Release.Name | quote }} + type: "{{ .Values.prometheusOperator.service.type }}" +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/serviceaccount.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/serviceaccount.yaml new file mode 100644 index 00000000..ab41797e --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/serviceaccount.yaml @@ -0,0 +1,12 @@ +{{- if and .Values.prometheusOperator.enabled .Values.prometheusOperator.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ template "kube-prometheus-stack.operator.serviceAccountName" . }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-operator +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +imagePullSecrets: +{{ toYaml .Values.global.imagePullSecrets | indent 2 }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/servicemonitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/servicemonitor.yaml new file mode 100644 index 00000000..7524ddf4 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/servicemonitor.yaml @@ -0,0 +1,44 @@ +{{- if and .Values.prometheusOperator.enabled .Values.prometheusOperator.serviceMonitor.selfMonitor }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-operator + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-operator +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + endpoints: + {{- if .Values.prometheusOperator.tls.enabled }} + - port: https + scheme: https + tlsConfig: + serverName: {{ template "kube-prometheus-stack.operator.fullname" . }} + ca: + secret: + name: {{ template "kube-prometheus-stack.fullname" . }}-admission + key: ca + optional: false + {{- else }} + - port: http + {{- end }} + honorLabels: true + {{- if .Values.prometheusOperator.serviceMonitor.interval }} + interval: {{ .Values.prometheusOperator.serviceMonitor.interval }} + {{- end }} +{{- if .Values.prometheusOperator.serviceMonitor.metricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.prometheusOperator.serviceMonitor.metricRelabelings | indent 6) . }} +{{- end }} +{{- if .Values.prometheusOperator.serviceMonitor.relabelings }} + relabelings: +{{ toYaml .Values.prometheusOperator.serviceMonitor.relabelings | indent 6 }} +{{- end }} + selector: + matchLabels: + app: {{ template "kube-prometheus-stack.name" . }}-operator + release: {{ $.Release.Name | quote }} + namespaceSelector: + matchNames: + - {{ printf "%s" (include "kube-prometheus-stack.namespace" .) | quote }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/additionalAlertRelabelConfigs.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/additionalAlertRelabelConfigs.yaml new file mode 100644 index 00000000..bff93098 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/additionalAlertRelabelConfigs.yaml @@ -0,0 +1,16 @@ +{{- if and .Values.prometheus.enabled .Values.prometheus.prometheusSpec.additionalAlertRelabelConfigs }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus-am-relabel-confg + namespace: {{ template "kube-prometheus-stack.namespace" . }} +{{- if .Values.prometheus.prometheusSpec.additionalPrometheusSecretsAnnotations }} + annotations: +{{ toYaml .Values.prometheus.prometheusSpec.additionalPrometheusSecretsAnnotations | indent 4 }} +{{- end }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-prometheus-am-relabel-confg +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +data: + additional-alert-relabel-configs.yaml: {{ toYaml .Values.prometheus.prometheusSpec.additionalAlertRelabelConfigs | b64enc | quote }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/additionalAlertmanagerConfigs.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/additionalAlertmanagerConfigs.yaml new file mode 100644 index 00000000..8aebc96c --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/additionalAlertmanagerConfigs.yaml @@ -0,0 +1,16 @@ +{{- if and .Values.prometheus.enabled .Values.prometheus.prometheusSpec.additionalAlertManagerConfigs }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus-am-confg + namespace: {{ template "kube-prometheus-stack.namespace" . }} +{{- if .Values.prometheus.prometheusSpec.additionalPrometheusSecretsAnnotations }} + annotations: +{{ toYaml .Values.prometheus.prometheusSpec.additionalPrometheusSecretsAnnotations | indent 4 }} +{{- end }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-prometheus-am-confg +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +data: + additional-alertmanager-configs.yaml: {{ toYaml .Values.prometheus.prometheusSpec.additionalAlertManagerConfigs | b64enc | quote }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/additionalPrometheusRules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/additionalPrometheusRules.yaml new file mode 100644 index 00000000..794e9ad2 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/additionalPrometheusRules.yaml @@ -0,0 +1,40 @@ +{{- if or .Values.additionalPrometheusRules .Values.additionalPrometheusRulesMap}} +apiVersion: v1 +kind: List +items: +{{- if .Values.additionalPrometheusRulesMap }} +{{- range $prometheusRuleName, $prometheusRule := .Values.additionalPrometheusRulesMap }} + - apiVersion: monitoring.coreos.com/v1 + kind: PrometheusRule + metadata: + name: {{ template "kube-prometheus-stack.name" $ }}-{{ $prometheusRuleName }} + namespace: {{ template "kube-prometheus-stack.namespace" $ }} + labels: + app: {{ template "kube-prometheus-stack.name" $ }} +{{ include "kube-prometheus-stack.labels" $ | indent 8 }} + {{- if $prometheusRule.additionalLabels }} +{{ toYaml $prometheusRule.additionalLabels | indent 8 }} + {{- end }} + spec: + groups: +{{ toYaml $prometheusRule.groups| indent 8 }} +{{- end }} +{{- else }} +{{- range .Values.additionalPrometheusRules }} + - apiVersion: monitoring.coreos.com/v1 + kind: PrometheusRule + metadata: + name: {{ template "kube-prometheus-stack.name" $ }}-{{ .name }} + namespace: {{ template "kube-prometheus-stack.namespace" $ }} + labels: + app: {{ template "kube-prometheus-stack.name" $ }} +{{ include "kube-prometheus-stack.labels" $ | indent 8 }} + {{- if .additionalLabels }} +{{ toYaml .additionalLabels | indent 8 }} + {{- end }} + spec: + groups: +{{ toYaml .groups| indent 8 }} +{{- end }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/additionalScrapeConfigs.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/additionalScrapeConfigs.yaml new file mode 100644 index 00000000..21d9429d --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/additionalScrapeConfigs.yaml @@ -0,0 +1,16 @@ +{{- if and .Values.prometheus.enabled .Values.prometheus.prometheusSpec.additionalScrapeConfigs }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus-scrape-confg + namespace: {{ template "kube-prometheus-stack.namespace" . }} +{{- if .Values.prometheus.prometheusSpec.additionalPrometheusSecretsAnnotations }} + annotations: +{{ toYaml .Values.prometheus.prometheusSpec.additionalPrometheusSecretsAnnotations | indent 4 }} +{{- end }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-prometheus-scrape-confg +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +data: + additional-scrape-configs.yaml: {{ tpl (toYaml .Values.prometheus.prometheusSpec.additionalScrapeConfigs) $ | b64enc | quote }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/clusterrole.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/clusterrole.yaml new file mode 100644 index 00000000..3585b5db --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/clusterrole.yaml @@ -0,0 +1,30 @@ +{{- if and .Values.prometheus.enabled .Values.global.rbac.create }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus + labels: + app: {{ template "kube-prometheus-stack.name" . }}-prometheus +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +rules: +# This permission are not in the kube-prometheus repo +# they're grabbed from https://github.com/prometheus/prometheus/blob/master/documentation/examples/rbac-setup.yml +- apiGroups: [""] + resources: + - nodes + - nodes/metrics + - services + - endpoints + - pods + verbs: ["get", "list", "watch"] +- apiGroups: + - "networking.k8s.io" + resources: + - ingresses + verbs: ["get", "list", "watch"] +- nonResourceURLs: ["/metrics", "/metrics/cadvisor"] + verbs: ["get"] +{{- if .Values.prometheus.additionalRulesForClusterRole }} +{{ toYaml .Values.prometheus.additionalRulesForClusterRole | indent 0 }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/clusterrolebinding.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/clusterrolebinding.yaml new file mode 100644 index 00000000..9fc4f65d --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/clusterrolebinding.yaml @@ -0,0 +1,18 @@ +{{- if and .Values.prometheus.enabled .Values.global.rbac.create }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus + labels: + app: {{ template "kube-prometheus-stack.name" . }}-prometheus +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus +subjects: + - kind: ServiceAccount + name: {{ template "kube-prometheus-stack.prometheus.serviceAccountName" . }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} +{{- end }} + diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/ingress.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/ingress.yaml new file mode 100644 index 00000000..59bd4b6f --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/ingress.yaml @@ -0,0 +1,58 @@ +{{- if and .Values.prometheus.enabled .Values.prometheus.ingress.enabled }} +{{- $serviceName := printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "prometheus" }} +{{- $servicePort := .Values.prometheus.service.port -}} +{{- $routePrefix := list .Values.prometheus.prometheusSpec.routePrefix }} +{{- $paths := .Values.prometheus.ingress.paths | default $routePrefix -}} +{{- if .Capabilities.APIVersions.Has "networking.k8s.io/v1beta1" }} +apiVersion: networking.k8s.io/v1beta1 +{{ else }} +apiVersion: extensions/v1beta1 +{{ end -}} +kind: Ingress +metadata: +{{- if .Values.prometheus.ingress.annotations }} + annotations: +{{ toYaml .Values.prometheus.ingress.annotations | indent 4 }} +{{- end }} + name: {{ $serviceName }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-prometheus +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.prometheus.ingress.labels }} +{{ toYaml .Values.prometheus.ingress.labels | indent 4 }} +{{- end }} +spec: + {{- if or (.Capabilities.APIVersions.Has "networking.k8s.io/v1/IngressClass") (.Capabilities.APIVersions.Has "networking.k8s.io/v1beta1/IngressClass") }} + {{- if .Values.prometheus.ingress.ingressClassName }} + ingressClassName: {{ .Values.prometheus.ingress.ingressClassName }} + {{- end }} + {{- end }} + rules: + {{- if .Values.prometheus.ingress.hosts }} + {{- range $host := .Values.prometheus.ingress.hosts }} + - host: {{ tpl $host $ }} + http: + paths: + {{- range $p := $paths }} + - path: {{ tpl $p $ }} + backend: + serviceName: {{ $serviceName }} + servicePort: {{ $servicePort }} + {{- end -}} + {{- end -}} + {{- else }} + - http: + paths: + {{- range $p := $paths }} + - path: {{ tpl $p $ }} + backend: + serviceName: {{ $serviceName }} + servicePort: {{ $servicePort }} + {{- end -}} + {{- end -}} + {{- if .Values.prometheus.ingress.tls }} + tls: +{{ tpl (toYaml .Values.prometheus.ingress.tls | indent 4) . }} + {{- end -}} +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/ingressThanosSidecar.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/ingressThanosSidecar.yaml new file mode 100644 index 00000000..45f9cb28 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/ingressThanosSidecar.yaml @@ -0,0 +1,53 @@ +{{- if and .Values.prometheus.enabled .Values.prometheus.thanosIngress.enabled }} +{{- $serviceName := printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "prometheus" }} +{{- $thanosPort := .Values.prometheus.thanosIngress.servicePort -}} +{{- $routePrefix := list .Values.prometheus.prometheusSpec.routePrefix }} +{{- $paths := .Values.prometheus.thanosIngress.paths | default $routePrefix -}} +apiVersion: extensions/v1beta1 +kind: Ingress +metadata: +{{- if .Values.prometheus.thanosIngress.annotations }} + annotations: +{{ toYaml .Values.prometheus.thanosIngress.annotations | indent 4 }} +{{- end }} + name: {{ template "kube-prometheus-stack.fullname" . }}-thanos-gateway + labels: + app: {{ template "kube-prometheus-stack.name" . }}-prometheus +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.prometheus.thanosIngress.labels }} +{{ toYaml .Values.prometheus.thanosIngress.labels | indent 4 }} +{{- end }} +spec: + {{- if or (.Capabilities.APIVersions.Has "networking.k8s.io/v1/IngressClass") (.Capabilities.APIVersions.Has "networking.k8s.io/v1beta1/IngressClass") }} + {{- if .Values.prometheus.thanosIngress.ingressClassName }} + ingressClassName: {{ .Values.prometheus.thanosIngress.ingressClassName }} + {{- end }} + {{- end }} + rules: + {{- if .Values.prometheus.thanosIngress.hosts }} + {{- range $host := .Values.prometheus.thanosIngress.hosts }} + - host: {{ tpl $host $ }} + http: + paths: + {{- range $p := $paths }} + - path: {{ tpl $p $ }} + backend: + serviceName: {{ $serviceName }} + servicePort: {{ $thanosPort }} + {{- end -}} + {{- end -}} + {{- else }} + - http: + paths: + {{- range $p := $paths }} + - path: {{ tpl $p $ }} + backend: + serviceName: {{ $serviceName }} + servicePort: {{ $thanosPort }} + {{- end -}} + {{- end -}} + {{- if .Values.prometheus.thanosIngress.tls }} + tls: +{{ toYaml .Values.prometheus.thanosIngress.tls | indent 4 }} + {{- end -}} +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/ingressperreplica.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/ingressperreplica.yaml new file mode 100644 index 00000000..c1959c6d --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/ingressperreplica.yaml @@ -0,0 +1,58 @@ +{{- if and .Values.prometheus.enabled .Values.prometheus.servicePerReplica.enabled .Values.prometheus.ingressPerReplica.enabled }} +{{- $count := .Values.prometheus.prometheusSpec.replicas | int -}} +{{- $servicePort := .Values.prometheus.servicePerReplica.port -}} +{{- $ingressValues := .Values.prometheus.ingressPerReplica -}} +apiVersion: v1 +kind: List +metadata: + name: {{ include "kube-prometheus-stack.fullname" $ }}-prometheus-ingressperreplica + namespace: {{ template "kube-prometheus-stack.namespace" $ }} +items: +{{ range $i, $e := until $count }} + - kind: Ingress + {{- if $.Capabilities.APIVersions.Has "networking.k8s.io/v1beta1" }} + apiVersion: networking.k8s.io/v1beta1 + {{ else }} + apiVersion: extensions/v1beta1 + {{ end -}} + metadata: + name: {{ include "kube-prometheus-stack.fullname" $ }}-prometheus-{{ $i }} + namespace: {{ template "kube-prometheus-stack.namespace" $ }} + labels: + app: {{ include "kube-prometheus-stack.name" $ }}-prometheus +{{ include "kube-prometheus-stack.labels" $ | indent 8 }} + {{- if $ingressValues.labels }} +{{ toYaml $ingressValues.labels | indent 8 }} + {{- end }} + {{- if $ingressValues.annotations }} + annotations: +{{ toYaml $ingressValues.annotations | indent 8 }} + {{- end }} + spec: + {{- if or ($.Capabilities.APIVersions.Has "networking.k8s.io/v1/IngressClass") ($.Capabilities.APIVersions.Has "networking.k8s.io/v1beta1/IngressClass") }} + {{- if $ingressValues.ingressClassName }} + ingressClassName: {{ $ingressValues.ingressClassName }} + {{- end }} + {{- end }} + rules: + - host: {{ $ingressValues.hostPrefix }}-{{ $i }}.{{ $ingressValues.hostDomain }} + http: + paths: + {{- range $p := $ingressValues.paths }} + - path: {{ tpl $p $ }} + backend: + serviceName: {{ include "kube-prometheus-stack.fullname" $ }}-prometheus-{{ $i }} + servicePort: {{ $servicePort }} + {{- end -}} + {{- if or $ingressValues.tlsSecretName $ingressValues.tlsSecretPerReplica.enabled }} + tls: + - hosts: + - {{ $ingressValues.hostPrefix }}-{{ $i }}.{{ $ingressValues.hostDomain }} + {{- if $ingressValues.tlsSecretPerReplica.enabled }} + secretName: {{ $ingressValues.tlsSecretPerReplica.prefix }}-{{ $i }} + {{- else }} + secretName: {{ $ingressValues.tlsSecretName }} + {{- end }} + {{- end }} +{{- end -}} +{{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/podDisruptionBudget.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/podDisruptionBudget.yaml new file mode 100644 index 00000000..573317a3 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/podDisruptionBudget.yaml @@ -0,0 +1,21 @@ +{{- if and .Values.prometheus.enabled .Values.prometheus.podDisruptionBudget.enabled }} +apiVersion: policy/v1beta1 +kind: PodDisruptionBudget +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-prometheus +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + {{- if .Values.prometheus.podDisruptionBudget.minAvailable }} + minAvailable: {{ .Values.prometheus.podDisruptionBudget.minAvailable }} + {{- end }} + {{- if .Values.prometheus.podDisruptionBudget.maxUnavailable }} + maxUnavailable: {{ .Values.prometheus.podDisruptionBudget.maxUnavailable }} + {{- end }} + selector: + matchLabels: + app: prometheus + prometheus: {{ template "kube-prometheus-stack.fullname" . }}-prometheus +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/podmonitors.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/podmonitors.yaml new file mode 100644 index 00000000..95d568e1 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/podmonitors.yaml @@ -0,0 +1,37 @@ +{{- if and .Values.prometheus.enabled .Values.prometheus.additionalPodMonitors }} +apiVersion: v1 +kind: List +items: +{{- range .Values.prometheus.additionalPodMonitors }} + - apiVersion: monitoring.coreos.com/v1 + kind: PodMonitor + metadata: + name: {{ .name }} + namespace: {{ template "kube-prometheus-stack.namespace" $ }} + labels: + app: {{ template "kube-prometheus-stack.name" $ }}-prometheus +{{ include "kube-prometheus-stack.labels" $ | indent 8 }} + {{- if .additionalLabels }} +{{ toYaml .additionalLabels | indent 8 }} + {{- end }} + spec: + podMetricsEndpoints: +{{ toYaml .podMetricsEndpoints | indent 8 }} + {{- if .jobLabel }} + jobLabel: {{ .jobLabel }} + {{- end }} + {{- if .namespaceSelector }} + namespaceSelector: +{{ toYaml .namespaceSelector | indent 8 }} + {{- end }} + selector: +{{ toYaml .selector | indent 8 }} + {{- if .podTargetLabels }} + podTargetLabels: +{{ toYaml .podTargetLabels | indent 8 }} + {{- end }} + {{- if .sampleLimit }} + sampleLimit: {{ .sampleLimit }} + {{- end }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/prometheus.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/prometheus.yaml new file mode 100644 index 00000000..66ac5a88 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/prometheus.yaml @@ -0,0 +1,302 @@ +{{- if .Values.prometheus.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: Prometheus +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-prometheus +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.prometheus.annotations }} + annotations: +{{ toYaml .Values.prometheus.annotations | indent 4 }} +{{- end }} +spec: + alerting: + alertmanagers: +{{- if .Values.prometheus.prometheusSpec.alertingEndpoints }} +{{ toYaml .Values.prometheus.prometheusSpec.alertingEndpoints | indent 6 }} +{{- else if .Values.alertmanager.enabled }} + - namespace: {{ template "kube-prometheus-stack.namespace" . }} + name: {{ template "kube-prometheus-stack.fullname" . }}-alertmanager + port: {{ .Values.alertmanager.alertmanagerSpec.portName }} + {{- if .Values.alertmanager.alertmanagerSpec.routePrefix }} + pathPrefix: "{{ .Values.alertmanager.alertmanagerSpec.routePrefix }}" + {{- end }} + apiVersion: {{ .Values.alertmanager.apiVersion }} +{{- else }} + [] +{{- end }} +{{- if .Values.prometheus.prometheusSpec.apiserverConfig }} + apiserverConfig: +{{ toYaml .Values.prometheus.prometheusSpec.apiserverConfig | indent 4}} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.image }} + image: {{ .Values.prometheus.prometheusSpec.image.repository }}:{{ .Values.prometheus.prometheusSpec.image.tag }} + version: {{ .Values.prometheus.prometheusSpec.image.tag }} + {{- if .Values.prometheus.prometheusSpec.image.sha }} + sha: {{ .Values.prometheus.prometheusSpec.image.sha }} + {{- end }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.externalLabels }} + externalLabels: +{{ toYaml .Values.prometheus.prometheusSpec.externalLabels | indent 4}} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.prometheusExternalLabelNameClear }} + prometheusExternalLabelName: "" +{{- else if .Values.prometheus.prometheusSpec.prometheusExternalLabelName }} + prometheusExternalLabelName: "{{ .Values.prometheus.prometheusSpec.prometheusExternalLabelName }}" +{{- end }} +{{- if .Values.prometheus.prometheusSpec.replicaExternalLabelNameClear }} + replicaExternalLabelName: "" +{{- else if .Values.prometheus.prometheusSpec.replicaExternalLabelName }} + replicaExternalLabelName: "{{ .Values.prometheus.prometheusSpec.replicaExternalLabelName }}" +{{- end }} +{{- if .Values.prometheus.prometheusSpec.externalUrl }} + externalUrl: "{{ tpl .Values.prometheus.prometheusSpec.externalUrl . }}" +{{- else if and .Values.prometheus.ingress.enabled .Values.prometheus.ingress.hosts }} + externalUrl: "http://{{ tpl (index .Values.prometheus.ingress.hosts 0) . }}{{ .Values.prometheus.prometheusSpec.routePrefix }}" +{{- else }} + externalUrl: http://{{ template "kube-prometheus-stack.fullname" . }}-prometheus.{{ template "kube-prometheus-stack.namespace" . }}:{{ .Values.prometheus.service.port }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.nodeSelector }} + nodeSelector: +{{ toYaml .Values.prometheus.prometheusSpec.nodeSelector | indent 4 }} +{{- end }} + paused: {{ .Values.prometheus.prometheusSpec.paused }} + replicas: {{ .Values.prometheus.prometheusSpec.replicas }} + logLevel: {{ .Values.prometheus.prometheusSpec.logLevel }} + logFormat: {{ .Values.prometheus.prometheusSpec.logFormat }} + listenLocal: {{ .Values.prometheus.prometheusSpec.listenLocal }} + enableAdminAPI: {{ .Values.prometheus.prometheusSpec.enableAdminAPI }} +{{- if .Values.prometheus.prometheusSpec.scrapeInterval }} + scrapeInterval: {{ .Values.prometheus.prometheusSpec.scrapeInterval }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.scrapeTimeout }} + scrapeTimeout: {{ .Values.prometheus.prometheusSpec.scrapeTimeout }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.evaluationInterval }} + evaluationInterval: {{ .Values.prometheus.prometheusSpec.evaluationInterval }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.resources }} + resources: +{{ toYaml .Values.prometheus.prometheusSpec.resources | indent 4 }} +{{- end }} + retention: {{ .Values.prometheus.prometheusSpec.retention | quote }} +{{- if .Values.prometheus.prometheusSpec.retentionSize }} + retentionSize: {{ .Values.prometheus.prometheusSpec.retentionSize | quote }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.walCompression }} + walCompression: {{ .Values.prometheus.prometheusSpec.walCompression }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.routePrefix }} + routePrefix: {{ .Values.prometheus.prometheusSpec.routePrefix | quote }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.secrets }} + secrets: +{{ toYaml .Values.prometheus.prometheusSpec.secrets | indent 4 }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.configMaps }} + configMaps: +{{ toYaml .Values.prometheus.prometheusSpec.configMaps | indent 4 }} +{{- end }} + serviceAccountName: {{ template "kube-prometheus-stack.prometheus.serviceAccountName" . }} +{{- if .Values.prometheus.prometheusSpec.serviceMonitorSelector }} + serviceMonitorSelector: +{{ toYaml .Values.prometheus.prometheusSpec.serviceMonitorSelector | indent 4 }} +{{ else if .Values.prometheus.prometheusSpec.serviceMonitorSelectorNilUsesHelmValues }} + serviceMonitorSelector: + matchLabels: + release: {{ $.Release.Name | quote }} +{{ else }} + serviceMonitorSelector: {} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.serviceMonitorNamespaceSelector }} + serviceMonitorNamespaceSelector: +{{ toYaml .Values.prometheus.prometheusSpec.serviceMonitorNamespaceSelector | indent 4 }} +{{ else }} + serviceMonitorNamespaceSelector: {} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.podMonitorSelector }} + podMonitorSelector: +{{ toYaml .Values.prometheus.prometheusSpec.podMonitorSelector | indent 4 }} +{{ else if .Values.prometheus.prometheusSpec.podMonitorSelectorNilUsesHelmValues }} + podMonitorSelector: + matchLabels: + release: {{ $.Release.Name | quote }} +{{ else }} + podMonitorSelector: {} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.podMonitorNamespaceSelector }} + podMonitorNamespaceSelector: +{{ toYaml .Values.prometheus.prometheusSpec.podMonitorNamespaceSelector | indent 4 }} +{{ else }} + podMonitorNamespaceSelector: {} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.probeSelector }} + probeSelector: +{{ toYaml .Values.prometheus.prometheusSpec.probeSelector | indent 4 }} +{{ else if .Values.prometheus.prometheusSpec.probeSelectorNilUsesHelmValues }} + probeSelector: + matchLabels: + release: {{ $.Release.Name | quote }} +{{ else }} + probeSelector: {} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.probeNamespaceSelector }} + probeNamespaceSelector: +{{ toYaml .Values.prometheus.prometheusSpec.probeNamespaceSelector | indent 4 }} +{{ else }} + probeNamespaceSelector: {} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.remoteRead }} + remoteRead: +{{ toYaml .Values.prometheus.prometheusSpec.remoteRead | indent 4 }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.remoteWrite }} + remoteWrite: +{{ toYaml .Values.prometheus.prometheusSpec.remoteWrite | indent 4 }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.securityContext }} + securityContext: +{{ toYaml .Values.prometheus.prometheusSpec.securityContext | indent 4 }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.ruleNamespaceSelector }} + ruleNamespaceSelector: +{{ toYaml .Values.prometheus.prometheusSpec.ruleNamespaceSelector | indent 4 }} +{{ else }} + ruleNamespaceSelector: {} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.ruleSelector }} + ruleSelector: +{{ toYaml .Values.prometheus.prometheusSpec.ruleSelector | indent 4}} +{{- else if .Values.prometheus.prometheusSpec.ruleSelectorNilUsesHelmValues }} + ruleSelector: + matchLabels: + app: {{ template "kube-prometheus-stack.name" . }} + release: {{ $.Release.Name | quote }} +{{ else }} + ruleSelector: {} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.storageSpec }} + storage: +{{ toYaml .Values.prometheus.prometheusSpec.storageSpec | indent 4 }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.podMetadata }} + podMetadata: +{{ tpl (toYaml .Values.prometheus.prometheusSpec.podMetadata | indent 4) . }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.query }} + query: +{{ toYaml .Values.prometheus.prometheusSpec.query | indent 4}} +{{- end }} +{{- if or .Values.prometheus.prometheusSpec.podAntiAffinity .Values.prometheus.prometheusSpec.affinity }} + affinity: +{{- if .Values.prometheus.prometheusSpec.affinity }} +{{ toYaml .Values.prometheus.prometheusSpec.affinity | indent 4 }} +{{- end }} +{{- if eq .Values.prometheus.prometheusSpec.podAntiAffinity "hard" }} + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - topologyKey: {{ .Values.prometheus.prometheusSpec.podAntiAffinityTopologyKey }} + labelSelector: + matchLabels: + app: prometheus + prometheus: {{ template "kube-prometheus-stack.fullname" . }}-prometheus +{{- else if eq .Values.prometheus.prometheusSpec.podAntiAffinity "soft" }} + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + topologyKey: {{ .Values.prometheus.prometheusSpec.podAntiAffinityTopologyKey }} + labelSelector: + matchLabels: + app: prometheus + prometheus: {{ template "kube-prometheus-stack.fullname" . }}-prometheus +{{- end }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.tolerations }} + tolerations: +{{ toYaml .Values.prometheus.prometheusSpec.tolerations | indent 4 }} +{{- end }} +{{- if .Values.global.imagePullSecrets }} + imagePullSecrets: +{{ toYaml .Values.global.imagePullSecrets | indent 4 }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.additionalScrapeConfigs }} + additionalScrapeConfigs: + name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus-scrape-confg + key: additional-scrape-configs.yaml +{{- end }} +{{- if .Values.prometheus.prometheusSpec.additionalScrapeConfigsSecret.enabled }} + additionalScrapeConfigs: + name: {{ .Values.prometheus.prometheusSpec.additionalScrapeConfigsSecret.name }} + key: {{ .Values.prometheus.prometheusSpec.additionalScrapeConfigsSecret.key }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.additionalAlertManagerConfigs }} + additionalAlertManagerConfigs: + name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus-am-confg + key: additional-alertmanager-configs.yaml +{{- end }} +{{- if .Values.prometheus.prometheusSpec.additionalAlertRelabelConfigs }} + additionalAlertRelabelConfigs: + name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus-am-relabel-confg + key: additional-alert-relabel-configs.yaml +{{- end }} +{{- if .Values.prometheus.prometheusSpec.containers }} + containers: +{{ toYaml .Values.prometheus.prometheusSpec.containers | indent 4 }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.initContainers }} + initContainers: +{{ toYaml .Values.prometheus.prometheusSpec.initContainers | indent 4 }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.priorityClassName }} + priorityClassName: {{ .Values.prometheus.prometheusSpec.priorityClassName }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.thanos }} + thanos: +{{ toYaml .Values.prometheus.prometheusSpec.thanos | indent 4 }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.disableCompaction }} + disableCompaction: {{ .Values.prometheus.prometheusSpec.disableCompaction }} +{{- end }} + portName: {{ .Values.prometheus.prometheusSpec.portName }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.enforcedNamespaceLabel }} + enforcedNamespaceLabel: {{ .Values.prometheus.prometheusSpec.enforcedNamespaceLabel }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.volumes }} + volumes: +{{ toYaml .Values.prometheus.prometheusSpec.volumes | indent 4 }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.volumeMounts }} + volumeMounts: +{{ toYaml .Values.prometheus.prometheusSpec.volumeMounts | indent 4 }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.arbitraryFSAccessThroughSMs }} + arbitraryFSAccessThroughSMs: +{{ toYaml .Values.prometheus.prometheusSpec.arbitraryFSAccessThroughSMs | indent 4 }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.overrideHonorLabels }} + overrideHonorLabels: {{ .Values.prometheus.prometheusSpec.overrideHonorLabels }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.overrideHonorTimestamps }} + overrideHonorTimestamps: {{ .Values.prometheus.prometheusSpec.overrideHonorTimestamps }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.ignoreNamespaceSelectors }} + ignoreNamespaceSelectors: {{ .Values.prometheus.prometheusSpec.ignoreNamespaceSelectors }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.prometheusRulesExcludedFromEnforce }} + prometheusRulesExcludedFromEnforce: +{{ toYaml .Values.prometheus.prometheusSpec.prometheusRulesExcludedFromEnforce | indent 4 }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.queryLogFile }} + queryLogFile: {{ .Values.prometheus.prometheusSpec.queryLogFile }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.enforcedSampleLimit }} + enforcedSampleLimit: {{ .Values.prometheus.prometheusSpec.enforcedSampleLimit }} +{{- end }} +{{- if .Values.prometheus.prometheusSpec.allowOverlappingBlocks }} + allowOverlappingBlocks: {{ .Values.prometheus.prometheusSpec.allowOverlappingBlocks }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/psp-clusterrole.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/psp-clusterrole.yaml new file mode 100644 index 00000000..a279fb24 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/psp-clusterrole.yaml @@ -0,0 +1,20 @@ +{{- if and .Values.prometheus.enabled .Values.global.rbac.create .Values.global.rbac.pspEnabled }} +kind: ClusterRole +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus-psp + labels: + app: {{ template "kube-prometheus-stack.name" . }}-prometheus +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +rules: +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if semverCompare "> 1.15.0-0" $kubeTargetVersion }} +- apiGroups: ['policy'] +{{- else }} +- apiGroups: ['extensions'] +{{- end }} + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: + - {{ template "kube-prometheus-stack.fullname" . }}-prometheus +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/psp-clusterrolebinding.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/psp-clusterrolebinding.yaml new file mode 100644 index 00000000..27b73b74 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/psp-clusterrolebinding.yaml @@ -0,0 +1,18 @@ +{{- if and .Values.prometheus.enabled .Values.global.rbac.create .Values.global.rbac.pspEnabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus-psp + labels: + app: {{ template "kube-prometheus-stack.name" . }}-prometheus +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus-psp +subjects: + - kind: ServiceAccount + name: {{ template "kube-prometheus-stack.prometheus.serviceAccountName" . }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} +{{- end }} + diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/psp.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/psp.yaml new file mode 100644 index 00000000..bd2b270d --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/psp.yaml @@ -0,0 +1,55 @@ +{{- if and .Values.prometheus.enabled .Values.global.rbac.create .Values.global.rbac.pspEnabled }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus + labels: + app: {{ template "kube-prometheus-stack.name" . }}-prometheus +{{- if .Values.global.rbac.pspAnnotations }} + annotations: +{{ toYaml .Values.global.rbac.pspAnnotations | indent 4 }} +{{- end }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + privileged: false + # Required to prevent escalations to root. + # allowPrivilegeEscalation: false + # This is redundant with non-root + disallow privilege escalation, + # but we can provide it for defense in depth. + #requiredDropCapabilities: + # - ALL + # Allow core volume types. + volumes: + - 'configMap' + - 'emptyDir' + - 'projected' + - 'secret' + - 'downwardAPI' + - 'persistentVolumeClaim' + hostNetwork: false + hostIPC: false + hostPID: false + runAsUser: + # Permits the container to run with root privileges as well. + rule: 'RunAsAny' + seLinux: + # This policy assumes the nodes are using AppArmor rather than SELinux. + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 0 + max: 65535 + fsGroup: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 0 + max: 65535 + readOnlyRootFilesystem: false +{{- if .Values.prometheus.podSecurityPolicy.allowedCapabilities }} + allowedCapabilities: +{{ toYaml .Values.prometheus.podSecurityPolicy.allowedCapabilities | indent 4 }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/alertmanager.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/alertmanager.rules.yaml new file mode 100644 index 00000000..387a6771 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/alertmanager.rules.yaml @@ -0,0 +1,70 @@ +{{- /* +Generated from 'alertmanager.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.alertmanager }} +{{- $alertmanagerJob := printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "alertmanager" }} +{{- $namespace := printf "%s" (include "kube-prometheus-stack.namespace" .) }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "alertmanager.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: alertmanager.rules + rules: + - alert: AlertmanagerConfigInconsistent + annotations: + message: 'The configuration of the instances of the Alertmanager cluster `{{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.service {{`}}`}}` are out of sync. + + {{`{{`}} range printf "alertmanager_config_hash{namespace=\"%s\",service=\"%s\"}" $labels.namespace $labels.service | query {{`}}`}} + + Configuration hash for pod {{`{{`}} .Labels.pod {{`}}`}} is "{{`{{`}} printf "%.f" .Value {{`}}`}}" + + {{`{{`}} end {{`}}`}} + + ' + expr: count by(namespace,service) (count_values by(namespace,service) ("config_hash", alertmanager_config_hash{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"})) != 1 + for: 5m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: AlertmanagerFailedReload + annotations: + message: Reloading Alertmanager's configuration has failed for {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod{{`}}`}}. + expr: alertmanager_config_last_reload_successful{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"} == 0 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: AlertmanagerMembersInconsistent + annotations: + message: Alertmanager has not found all other members of the cluster. + expr: |- + alertmanager_cluster_members{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"} + != on (service) GROUP_LEFT() + count by (service) (alertmanager_cluster_members{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}) + for: 5m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/etcd.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/etcd.yaml new file mode 100644 index 00000000..83587043 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/etcd.yaml @@ -0,0 +1,169 @@ +{{- /* +Generated from 'etcd' group from https://raw.githubusercontent.com/etcd-io/etcd/master/Documentation/op-guide/etcd3_alert.rules.yml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.kubeEtcd.enabled .Values.defaultRules.rules.etcd }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "etcd" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: etcd + rules: + - alert: etcdMembersDown + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": members are down ({{`{{`}} $value {{`}}`}}).' + expr: |- + max by (job) ( + sum by (job) (up{job=~".*etcd.*"} == bool 0) + or + count by (job,endpoint) ( + sum by (job,endpoint,To) (rate(etcd_network_peer_sent_failures_total{job=~".*etcd.*"}[3m])) > 0.01 + ) + ) + > 0 + for: 3m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdInsufficientMembers + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": insufficient members ({{`{{`}} $value {{`}}`}}).' + expr: sum(up{job=~".*etcd.*"} == bool 1) by (job) < ((count(up{job=~".*etcd.*"}) by (job) + 1) / 2) + for: 3m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdNoLeader + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": member {{`{{`}} $labels.instance {{`}}`}} has no leader.' + expr: etcd_server_has_leader{job=~".*etcd.*"} == 0 + for: 1m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdHighNumberOfLeaderChanges + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": {{`{{`}} $value {{`}}`}} leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated.' + expr: increase((max by (job) (etcd_server_leader_changes_seen_total{job=~".*etcd.*"}) or 0*absent(etcd_server_leader_changes_seen_total{job=~".*etcd.*"}))[15m:1m]) >= 3 + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdGRPCRequestsSlow + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": gRPC requests to {{`{{`}} $labels.grpc_method {{`}}`}} are taking {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + expr: |- + histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_type="unary"}[5m])) by (job, instance, grpc_service, grpc_method, le)) + > 0.15 + for: 10m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdMemberCommunicationSlow + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": member communication with {{`{{`}} $labels.To {{`}}`}} is taking {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + expr: |- + histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~".*etcd.*"}[5m])) + > 0.15 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdHighNumberOfFailedProposals + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": {{`{{`}} $value {{`}}`}} proposal failures within the last 30 minutes on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + expr: rate(etcd_server_proposals_failed_total{job=~".*etcd.*"}[15m]) > 5 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdHighFsyncDurations + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": 99th percentile fync durations are {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + expr: |- + histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~".*etcd.*"}[5m])) + > 0.5 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdHighCommitDurations + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": 99th percentile commit durations {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + expr: |- + histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket{job=~".*etcd.*"}[5m])) + > 0.25 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdHighNumberOfFailedHTTPRequests + annotations: + message: '{{`{{`}} $value {{`}}`}}% of requests for {{`{{`}} $labels.method {{`}}`}} failed on etcd instance {{`{{`}} $labels.instance {{`}}`}}' + expr: |- + sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m])) + BY (method) > 0.01 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdHighNumberOfFailedHTTPRequests + annotations: + message: '{{`{{`}} $value {{`}}`}}% of requests for {{`{{`}} $labels.method {{`}}`}} failed on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + expr: |- + sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m])) + BY (method) > 0.05 + for: 10m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdHTTPRequestsSlow + annotations: + message: etcd instance {{`{{`}} $labels.instance {{`}}`}} HTTP requests to {{`{{`}} $labels.method {{`}}`}} are slow. + expr: |- + histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m])) + > 0.15 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/general.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/general.rules.yaml new file mode 100644 index 00000000..80771f4f --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/general.rules.yaml @@ -0,0 +1,56 @@ +{{- /* +Generated from 'general.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.general }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "general.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: general.rules + rules: + - alert: TargetDown + annotations: + message: '{{`{{`}} printf "%.4g" $value {{`}}`}}% of the {{`{{`}} $labels.job {{`}}`}}/{{`{{`}} $labels.service {{`}}`}} targets in {{`{{`}} $labels.namespace {{`}}`}} namespace are down.' + expr: 100 * (count(up == 0) BY (job, namespace, service) / count(up) BY (job, namespace, service)) > 10 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: Watchdog + annotations: + message: 'This is an alert meant to ensure that the entire alerting pipeline is functional. + + This alert is always firing, therefore it should always be firing in Alertmanager + + and always fire against a receiver. There are integrations with various notification + + mechanisms that send a notification when this alert is not firing. For example the + + "DeadMansSnitch" integration in PagerDuty. + + ' + expr: vector(1) + labels: + severity: none +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.yaml new file mode 100644 index 00000000..35e4edeb --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.yaml @@ -0,0 +1,121 @@ +{{- /* +Generated from 'k8s.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.k8s }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "k8s.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: k8s.rules + rules: + - expr: sum(rate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!="", container!="POD"}[5m])) by (namespace) + record: namespace:container_cpu_usage_seconds_total:sum_rate + - expr: |- + sum by (cluster, namespace, pod, container) ( + rate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!="", container!="POD"}[5m]) + ) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) ( + 1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate + - expr: |- + container_memory_working_set_bytes{job="kubelet", metrics_path="/metrics/cadvisor", image!=""} + * on (namespace, pod) group_left(node) topk by(namespace, pod) (1, + max by(namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_memory_working_set_bytes + - expr: |- + container_memory_rss{job="kubelet", metrics_path="/metrics/cadvisor", image!=""} + * on (namespace, pod) group_left(node) topk by(namespace, pod) (1, + max by(namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_memory_rss + - expr: |- + container_memory_cache{job="kubelet", metrics_path="/metrics/cadvisor", image!=""} + * on (namespace, pod) group_left(node) topk by(namespace, pod) (1, + max by(namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_memory_cache + - expr: |- + container_memory_swap{job="kubelet", metrics_path="/metrics/cadvisor", image!=""} + * on (namespace, pod) group_left(node) topk by(namespace, pod) (1, + max by(namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_memory_swap + - expr: sum(container_memory_usage_bytes{job="kubelet", metrics_path="/metrics/cadvisor", image!="", container!="POD"}) by (namespace) + record: namespace:container_memory_usage_bytes:sum + - expr: |- + sum by (namespace) ( + sum by (namespace, pod) ( + max by (namespace, pod, container) ( + kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"} + ) * on(namespace, pod) group_left() max by (namespace, pod) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace:kube_pod_container_resource_requests_memory_bytes:sum + - expr: |- + sum by (namespace) ( + sum by (namespace, pod) ( + max by (namespace, pod, container) ( + kube_pod_container_resource_requests_cpu_cores{job="kube-state-metrics"} + ) * on(namespace, pod) group_left() max by (namespace, pod) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace:kube_pod_container_resource_requests_cpu_cores:sum + - expr: |- + max by (cluster, namespace, workload, pod) ( + label_replace( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="ReplicaSet"}, + "replicaset", "$1", "owner_name", "(.*)" + ) * on(replicaset, namespace) group_left(owner_name) topk by(replicaset, namespace) ( + 1, max by (replicaset, namespace, owner_name) ( + kube_replicaset_owner{job="kube-state-metrics"} + ) + ), + "workload", "$1", "owner_name", "(.*)" + ) + ) + labels: + workload_type: deployment + record: namespace_workload_pod:kube_pod_owner:relabel + - expr: |- + max by (cluster, namespace, workload, pod) ( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="DaemonSet"}, + "workload", "$1", "owner_name", "(.*)" + ) + ) + labels: + workload_type: daemonset + record: namespace_workload_pod:kube_pod_owner:relabel + - expr: |- + max by (cluster, namespace, workload, pod) ( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="StatefulSet"}, + "workload", "$1", "owner_name", "(.*)" + ) + ) + labels: + workload_type: statefulset + record: namespace_workload_pod:kube_pod_owner:relabel +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-availability.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-availability.rules.yaml new file mode 100644 index 00000000..78a09e32 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-availability.rules.yaml @@ -0,0 +1,158 @@ +{{- /* +Generated from 'kube-apiserver-availability.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.kubeApiServer.enabled .Values.defaultRules.rules.kubeApiserverAvailability }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kube-apiserver-availability.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - interval: 3m + name: kube-apiserver-availability.rules + rules: + - expr: |- + 1 - ( + ( + # write too slow + sum(increase(apiserver_request_duration_seconds_count{verb=~"POST|PUT|PATCH|DELETE"}[30d])) + - + sum(increase(apiserver_request_duration_seconds_bucket{verb=~"POST|PUT|PATCH|DELETE",le="1"}[30d])) + ) + + ( + # read too slow + sum(increase(apiserver_request_duration_seconds_count{verb=~"LIST|GET"}[30d])) + - + ( + ( + sum(increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope=~"resource|",le="0.1"}[30d])) + or + vector(0) + ) + + + sum(increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope="namespace",le="0.5"}[30d])) + + + sum(increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope="cluster",le="5"}[30d])) + ) + ) + + # errors + sum(code:apiserver_request_total:increase30d{code=~"5.."} or vector(0)) + ) + / + sum(code:apiserver_request_total:increase30d) + labels: + verb: all + record: apiserver_request:availability30d + - expr: |- + 1 - ( + sum(increase(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[30d])) + - + ( + # too slow + ( + sum(increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[30d])) + or + vector(0) + ) + + + sum(increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[30d])) + + + sum(increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[30d])) + ) + + + # errors + sum(code:apiserver_request_total:increase30d{verb="read",code=~"5.."} or vector(0)) + ) + / + sum(code:apiserver_request_total:increase30d{verb="read"}) + labels: + verb: read + record: apiserver_request:availability30d + - expr: |- + 1 - ( + ( + # too slow + sum(increase(apiserver_request_duration_seconds_count{verb=~"POST|PUT|PATCH|DELETE"}[30d])) + - + sum(increase(apiserver_request_duration_seconds_bucket{verb=~"POST|PUT|PATCH|DELETE",le="1"}[30d])) + ) + + + # errors + sum(code:apiserver_request_total:increase30d{verb="write",code=~"5.."} or vector(0)) + ) + / + sum(code:apiserver_request_total:increase30d{verb="write"}) + labels: + verb: write + record: apiserver_request:availability30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"2.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"2.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"2.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"2.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"2.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"2.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"3.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"3.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"3.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"3.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"3.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"3.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"4.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"4.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"4.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"4.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"4.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"4.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"5.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"5.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"5.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"5.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"5.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"5.."}[30d])) + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (code) (code_verb:apiserver_request_total:increase30d{verb=~"LIST|GET"}) + labels: + verb: read + record: code:apiserver_request_total:increase30d + - expr: sum by (code) (code_verb:apiserver_request_total:increase30d{verb=~"POST|PUT|PATCH|DELETE"}) + labels: + verb: write + record: code:apiserver_request_total:increase30d +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-slos.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-slos.yaml new file mode 100644 index 00000000..da0de91a --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-slos.yaml @@ -0,0 +1,95 @@ +{{- /* +Generated from 'kube-apiserver-slos' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.kubeApiServer.enabled .Values.defaultRules.rules.kubeApiserverSlos }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kube-apiserver-slos" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kube-apiserver-slos + rules: + - alert: KubeAPIErrorBudgetBurn + annotations: + description: The API server is burning too much error budget. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeapierrorbudgetburn + summary: The API server is burning too much error budget. + expr: |- + sum(apiserver_request:burnrate1h) > (14.40 * 0.01000) + and + sum(apiserver_request:burnrate5m) > (14.40 * 0.01000) + for: 2m + labels: + long: 1h + severity: critical + short: 5m +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeAPIErrorBudgetBurn + annotations: + description: The API server is burning too much error budget. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeapierrorbudgetburn + summary: The API server is burning too much error budget. + expr: |- + sum(apiserver_request:burnrate6h) > (6.00 * 0.01000) + and + sum(apiserver_request:burnrate30m) > (6.00 * 0.01000) + for: 15m + labels: + long: 6h + severity: critical + short: 30m +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeAPIErrorBudgetBurn + annotations: + description: The API server is burning too much error budget. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeapierrorbudgetburn + summary: The API server is burning too much error budget. + expr: |- + sum(apiserver_request:burnrate1d) > (3.00 * 0.01000) + and + sum(apiserver_request:burnrate2h) > (3.00 * 0.01000) + for: 1h + labels: + long: 1d + severity: warning + short: 2h +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeAPIErrorBudgetBurn + annotations: + description: The API server is burning too much error budget. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeapierrorbudgetburn + summary: The API server is burning too much error budget. + expr: |- + sum(apiserver_request:burnrate3d) > (1.00 * 0.01000) + and + sum(apiserver_request:burnrate6h) > (1.00 * 0.01000) + for: 3h + labels: + long: 3d + severity: warning + short: 6h +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver.rules.yaml new file mode 100644 index 00000000..b4d1a0f3 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver.rules.yaml @@ -0,0 +1,363 @@ +{{- /* +Generated from 'kube-apiserver.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.kubeApiServer.enabled .Values.defaultRules.rules.kubeApiserver }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kube-apiserver.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kube-apiserver.rules + rules: + - expr: |- + ( + ( + # too slow + sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[1d])) + - + ( + ( + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[1d])) + or + vector(0) + ) + + + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[1d])) + + + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[1d])) + ) + ) + + + # errors + sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1d])) + ) + / + sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1d])) + labels: + verb: read + record: apiserver_request:burnrate1d + - expr: |- + ( + ( + # too slow + sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[1h])) + - + ( + ( + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[1h])) + or + vector(0) + ) + + + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[1h])) + + + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[1h])) + ) + ) + + + # errors + sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1h])) + ) + / + sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1h])) + labels: + verb: read + record: apiserver_request:burnrate1h + - expr: |- + ( + ( + # too slow + sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[2h])) + - + ( + ( + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[2h])) + or + vector(0) + ) + + + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[2h])) + + + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[2h])) + ) + ) + + + # errors + sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[2h])) + ) + / + sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[2h])) + labels: + verb: read + record: apiserver_request:burnrate2h + - expr: |- + ( + ( + # too slow + sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[30m])) + - + ( + ( + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[30m])) + or + vector(0) + ) + + + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[30m])) + + + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[30m])) + ) + ) + + + # errors + sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[30m])) + ) + / + sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[30m])) + labels: + verb: read + record: apiserver_request:burnrate30m + - expr: |- + ( + ( + # too slow + sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[3d])) + - + ( + ( + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[3d])) + or + vector(0) + ) + + + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[3d])) + + + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[3d])) + ) + ) + + + # errors + sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[3d])) + ) + / + sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[3d])) + labels: + verb: read + record: apiserver_request:burnrate3d + - expr: |- + ( + ( + # too slow + sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[5m])) + - + ( + ( + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[5m])) + or + vector(0) + ) + + + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[5m])) + + + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[5m])) + ) + ) + + + # errors + sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[5m])) + ) + / + sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m])) + labels: + verb: read + record: apiserver_request:burnrate5m + - expr: |- + ( + ( + # too slow + sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[6h])) + - + ( + ( + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[6h])) + or + vector(0) + ) + + + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[6h])) + + + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[6h])) + ) + ) + + + # errors + sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[6h])) + ) + / + sum(rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[6h])) + labels: + verb: read + record: apiserver_request:burnrate6h + - expr: |- + ( + ( + # too slow + sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d])) + - + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[1d])) + ) + + + sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1d])) + ) + / + sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d])) + labels: + verb: write + record: apiserver_request:burnrate1d + - expr: |- + ( + ( + # too slow + sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h])) + - + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[1h])) + ) + + + sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1h])) + ) + / + sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h])) + labels: + verb: write + record: apiserver_request:burnrate1h + - expr: |- + ( + ( + # too slow + sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h])) + - + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[2h])) + ) + + + sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[2h])) + ) + / + sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h])) + labels: + verb: write + record: apiserver_request:burnrate2h + - expr: |- + ( + ( + # too slow + sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m])) + - + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[30m])) + ) + + + sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[30m])) + ) + / + sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m])) + labels: + verb: write + record: apiserver_request:burnrate30m + - expr: |- + ( + ( + # too slow + sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d])) + - + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[3d])) + ) + + + sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[3d])) + ) + / + sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d])) + labels: + verb: write + record: apiserver_request:burnrate3d + - expr: |- + ( + ( + # too slow + sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m])) + - + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[5m])) + ) + + + sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[5m])) + ) + / + sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m])) + labels: + verb: write + record: apiserver_request:burnrate5m + - expr: |- + ( + ( + # too slow + sum(rate(apiserver_request_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h])) + - + sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[6h])) + ) + + + sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[6h])) + ) + / + sum(rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h])) + labels: + verb: write + record: apiserver_request:burnrate6h + - expr: sum by (code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m])) + labels: + verb: read + record: code_resource:apiserver_request_total:rate5m + - expr: sum by (code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m])) + labels: + verb: write + record: code_resource:apiserver_request_total:rate5m + - expr: histogram_quantile(0.99, sum by (le, resource) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET"}[5m]))) > 0 + labels: + quantile: '0.99' + verb: read + record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.99, sum by (le, resource) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))) > 0 + labels: + quantile: '0.99' + verb: write + record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile + - expr: |- + sum(rate(apiserver_request_duration_seconds_sum{subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod) + / + sum(rate(apiserver_request_duration_seconds_count{subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod) + record: cluster:apiserver_request_duration_seconds:mean5m + - expr: histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod)) + labels: + quantile: '0.99' + record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod)) + labels: + quantile: '0.9' + record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.5, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod)) + labels: + quantile: '0.5' + record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-prometheus-general.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-prometheus-general.rules.yaml new file mode 100644 index 00000000..e54bee58 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-prometheus-general.rules.yaml @@ -0,0 +1,31 @@ +{{- /* +Generated from 'kube-prometheus-general.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubePrometheusGeneral }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kube-prometheus-general.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kube-prometheus-general.rules + rules: + - expr: count without(instance, pod, node) (up == 1) + record: count:up1 + - expr: count without(instance, pod, node) (up == 0) + record: count:up0 +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-prometheus-node-recording.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-prometheus-node-recording.rules.yaml new file mode 100644 index 00000000..27271f1b --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-prometheus-node-recording.rules.yaml @@ -0,0 +1,39 @@ +{{- /* +Generated from 'kube-prometheus-node-recording.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubePrometheusNodeRecording }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kube-prometheus-node-recording.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kube-prometheus-node-recording.rules + rules: + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[3m])) BY (instance) + record: instance:node_cpu:rate:sum + - expr: sum(rate(node_network_receive_bytes_total[3m])) BY (instance) + record: instance:node_network_receive_bytes:rate:sum + - expr: sum(rate(node_network_transmit_bytes_total[3m])) BY (instance) + record: instance:node_network_transmit_bytes:rate:sum + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m])) WITHOUT (cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance, cpu)) BY (instance) + record: instance:node_cpu:ratio + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m])) + record: cluster:node_cpu:sum_rate5m + - expr: cluster:node_cpu_seconds_total:rate5m / count(sum(node_cpu_seconds_total) BY (instance, cpu)) + record: cluster:node_cpu:ratio +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-scheduler.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-scheduler.rules.yaml new file mode 100644 index 00000000..594f1bb3 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-scheduler.rules.yaml @@ -0,0 +1,63 @@ +{{- /* +Generated from 'kube-scheduler.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.kubeScheduler.enabled .Values.defaultRules.rules.kubeScheduler }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kube-scheduler.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kube-scheduler.rules + rules: + - expr: histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.99' + record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.99' + record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.99' + record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.9, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.9' + record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.9, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.9' + record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.9, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.9' + record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.5, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.5' + record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.5, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.5' + record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.5, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.5' + record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-state-metrics.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-state-metrics.yaml new file mode 100644 index 00000000..0fa5032b --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-state-metrics.yaml @@ -0,0 +1,59 @@ +{{- /* +Generated from 'kube-state-metrics' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubeStateMetrics }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kube-state-metrics" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kube-state-metrics + rules: + - alert: KubeStateMetricsListErrors + annotations: + description: kube-state-metrics is experiencing errors at an elevated rate in list operations. This is likely causing it to not be able to expose metrics about Kubernetes objects correctly or at all. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubestatemetricslisterrors + summary: kube-state-metrics is experiencing errors in list operations. + expr: |- + (sum(rate(kube_state_metrics_list_total{job="kube-state-metrics",result="error"}[5m])) + / + sum(rate(kube_state_metrics_list_total{job="kube-state-metrics"}[5m]))) + > 0.01 + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeStateMetricsWatchErrors + annotations: + description: kube-state-metrics is experiencing errors at an elevated rate in watch operations. This is likely causing it to not be able to expose metrics about Kubernetes objects correctly or at all. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubestatemetricswatcherrors + summary: kube-state-metrics is experiencing errors in watch operations. + expr: |- + (sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics",result="error"}[5m])) + / + sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics"}[5m]))) + > 0.01 + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubelet.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubelet.rules.yaml new file mode 100644 index 00000000..f9bd1ccd --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubelet.rules.yaml @@ -0,0 +1,39 @@ +{{- /* +Generated from 'kubelet.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.kubelet.enabled .Values.defaultRules.rules.kubelet }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubelet.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kubelet.rules + rules: + - expr: histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) + labels: + quantile: '0.99' + record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.9, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) + labels: + quantile: '0.9' + record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.5, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) + labels: + quantile: '0.5' + record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-apps.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-apps.yaml new file mode 100644 index 00000000..6eb5e029 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-apps.yaml @@ -0,0 +1,298 @@ +{{- /* +Generated from 'kubernetes-apps' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubernetesApps }} +{{- $targetNamespace := .Values.defaultRules.appNamespacesTarget }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubernetes-apps" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kubernetes-apps + rules: + - alert: KubePodCrashLooping + annotations: + description: Pod {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} ({{`{{`}} $labels.container {{`}}`}}) is restarting {{`{{`}} printf "%.2f" $value {{`}}`}} times / 5 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubepodcrashlooping + summary: Pod is crash looping. + expr: rate(kube_pod_container_status_restarts_total{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}[5m]) * 60 * 5 > 0 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubePodNotReady + annotations: + description: Pod {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} has been in a non-ready state for longer than 15 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubepodnotready + summary: Pod has been in a non-ready state for more than 15 minutes. + expr: |- + sum by (namespace, pod) ( + max by(namespace, pod) ( + kube_pod_status_phase{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}", phase=~"Pending|Unknown"} + ) * on(namespace, pod) group_left(owner_kind) topk by(namespace, pod) ( + 1, max by(namespace, pod, owner_kind) (kube_pod_owner{owner_kind!="Job"}) + ) + ) > 0 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeDeploymentGenerationMismatch + annotations: + description: Deployment generation for {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.deployment {{`}}`}} does not match, this indicates that the Deployment has failed but has not been rolled back. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubedeploymentgenerationmismatch + summary: Deployment generation mismatch due to possible roll-back + expr: |- + kube_deployment_status_observed_generation{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + != + kube_deployment_metadata_generation{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeDeploymentReplicasMismatch + annotations: + description: Deployment {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.deployment {{`}}`}} has not matched the expected number of replicas for longer than 15 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubedeploymentreplicasmismatch + summary: Deployment has not matched the expected number of replicas. + expr: |- + ( + kube_deployment_spec_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + != + kube_deployment_status_replicas_available{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + ) and ( + changes(kube_deployment_status_replicas_updated{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}[5m]) + == + 0 + ) + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeStatefulSetReplicasMismatch + annotations: + description: StatefulSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.statefulset {{`}}`}} has not matched the expected number of replicas for longer than 15 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubestatefulsetreplicasmismatch + summary: Deployment has not matched the expected number of replicas. + expr: |- + ( + kube_statefulset_status_replicas_ready{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + != + kube_statefulset_status_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + ) and ( + changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}[5m]) + == + 0 + ) + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeStatefulSetGenerationMismatch + annotations: + description: StatefulSet generation for {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.statefulset {{`}}`}} does not match, this indicates that the StatefulSet has failed but has not been rolled back. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubestatefulsetgenerationmismatch + summary: StatefulSet generation mismatch due to possible roll-back + expr: |- + kube_statefulset_status_observed_generation{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + != + kube_statefulset_metadata_generation{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeStatefulSetUpdateNotRolledOut + annotations: + description: StatefulSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.statefulset {{`}}`}} update has not been rolled out. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubestatefulsetupdatenotrolledout + summary: StatefulSet update has not been rolled out. + expr: |- + ( + max without (revision) ( + kube_statefulset_status_current_revision{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + unless + kube_statefulset_status_update_revision{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + ) + * + ( + kube_statefulset_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + != + kube_statefulset_status_replicas_updated{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + ) + ) and ( + changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}[5m]) + == + 0 + ) + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeDaemonSetRolloutStuck + annotations: + description: DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} has not finished or progressed for at least 15 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubedaemonsetrolloutstuck + summary: DaemonSet rollout is stuck. + expr: |- + ( + ( + kube_daemonset_status_current_number_scheduled{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + != + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + ) or ( + kube_daemonset_status_number_misscheduled{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + != + 0 + ) or ( + kube_daemonset_updated_number_scheduled{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + != + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + ) or ( + kube_daemonset_status_number_available{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + != + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + ) + ) and ( + changes(kube_daemonset_updated_number_scheduled{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}[5m]) + == + 0 + ) + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeContainerWaiting + annotations: + description: Pod {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} container {{`{{`}} $labels.container{{`}}`}} has been in waiting state for longer than 1 hour. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubecontainerwaiting + summary: Pod container waiting longer than 1 hour + expr: sum by (namespace, pod, container) (kube_pod_container_status_waiting_reason{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}) > 0 + for: 1h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeDaemonSetNotScheduled + annotations: + description: '{{`{{`}} $value {{`}}`}} Pods of DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} are not scheduled.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubedaemonsetnotscheduled + summary: DaemonSet pods are not scheduled. + expr: |- + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + - + kube_daemonset_status_current_number_scheduled{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} > 0 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeDaemonSetMisScheduled + annotations: + description: '{{`{{`}} $value {{`}}`}} Pods of DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} are running where they are not supposed to run.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubedaemonsetmisscheduled + summary: DaemonSet pods are misscheduled. + expr: kube_daemonset_status_number_misscheduled{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} > 0 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeJobCompletion + annotations: + description: Job {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.job_name {{`}}`}} is taking more than 12 hours to complete. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubejobcompletion + summary: Job did not complete in time + expr: kube_job_spec_completions{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} - kube_job_status_succeeded{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} > 0 + for: 12h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeJobFailed + annotations: + description: Job {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.job_name {{`}}`}} failed to complete. Removing failed job after investigation should clear this alert. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubejobfailed + summary: Job failed to complete. + expr: kube_job_failed{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} > 0 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeHpaReplicasMismatch + annotations: + description: HPA {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.hpa {{`}}`}} has not matched the desired number of replicas for longer than 15 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubehpareplicasmismatch + summary: HPA has not matched descired number of replicas. + expr: |- + (kube_hpa_status_desired_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + != + kube_hpa_status_current_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}) + and + (kube_hpa_status_current_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + > + kube_hpa_spec_min_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}) + and + (kube_hpa_status_current_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + < + kube_hpa_spec_max_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}) + and + changes(kube_hpa_status_current_replicas[15m]) == 0 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeHpaMaxedOut + annotations: + description: HPA {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.hpa {{`}}`}} has been running at max replicas for longer than 15 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubehpamaxedout + summary: HPA is running at max replicas + expr: |- + kube_hpa_status_current_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + == + kube_hpa_spec_max_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-resources.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-resources.yaml new file mode 100644 index 00000000..87933e5b --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-resources.yaml @@ -0,0 +1,159 @@ +{{- /* +Generated from 'kubernetes-resources' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubernetesResources }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubernetes-resources" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kubernetes-resources + rules: + - alert: KubeCPUOvercommit + annotations: + description: Cluster has overcommitted CPU resource requests for Pods and cannot tolerate node failure. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubecpuovercommit + summary: Cluster has overcommitted CPU resource requests. + expr: |- + sum(namespace:kube_pod_container_resource_requests_cpu_cores:sum{}) + / + sum(kube_node_status_allocatable_cpu_cores) + > + (count(kube_node_status_allocatable_cpu_cores)-1) / count(kube_node_status_allocatable_cpu_cores) + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeMemoryOvercommit + annotations: + description: Cluster has overcommitted memory resource requests for Pods and cannot tolerate node failure. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubememoryovercommit + summary: Cluster has overcommitted memory resource requests. + expr: |- + sum(namespace:kube_pod_container_resource_requests_memory_bytes:sum{}) + / + sum(kube_node_status_allocatable_memory_bytes) + > + (count(kube_node_status_allocatable_memory_bytes)-1) + / + count(kube_node_status_allocatable_memory_bytes) + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeCPUQuotaOvercommit + annotations: + description: Cluster has overcommitted CPU resource requests for Namespaces. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubecpuquotaovercommit + summary: Cluster has overcommitted CPU resource requests. + expr: |- + sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="cpu"}) + / + sum(kube_node_status_allocatable_cpu_cores) + > 1.5 + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeMemoryQuotaOvercommit + annotations: + description: Cluster has overcommitted memory resource requests for Namespaces. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubememoryquotaovercommit + summary: Cluster has overcommitted memory resource requests. + expr: |- + sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="memory"}) + / + sum(kube_node_status_allocatable_memory_bytes{job="kube-state-metrics"}) + > 1.5 + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeQuotaAlmostFull + annotations: + description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubequotaalmostfull + summary: Namespace quota is going to be full. + expr: |- + kube_resourcequota{job="kube-state-metrics", type="used"} + / ignoring(instance, job, type) + (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0) + > 0.9 < 1 + for: 15m + labels: + severity: info +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeQuotaFullyUsed + annotations: + description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubequotafullyused + summary: Namespace quota is fully used. + expr: |- + kube_resourcequota{job="kube-state-metrics", type="used"} + / ignoring(instance, job, type) + (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0) + == 1 + for: 15m + labels: + severity: info +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeQuotaExceeded + annotations: + description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubequotaexceeded + summary: Namespace quota has exceeded the limits. + expr: |- + kube_resourcequota{job="kube-state-metrics", type="used"} + / ignoring(instance, job, type) + (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0) + > 1 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: CPUThrottlingHigh + annotations: + description: '{{`{{`}} $value | humanizePercentage {{`}}`}} throttling of CPU in namespace {{`{{`}} $labels.namespace {{`}}`}} for container {{`{{`}} $labels.container {{`}}`}} in pod {{`{{`}} $labels.pod {{`}}`}}.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-cputhrottlinghigh + summary: Processes experience elevated CPU throttling. + expr: |- + sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (container, pod, namespace) + / + sum(increase(container_cpu_cfs_periods_total{}[5m])) by (container, pod, namespace) + > ( 25 / 100 ) + for: 15m + labels: + severity: info +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-storage.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-storage.yaml new file mode 100644 index 00000000..1fadb59f --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-storage.yaml @@ -0,0 +1,75 @@ +{{- /* +Generated from 'kubernetes-storage' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubernetesStorage }} +{{- $targetNamespace := .Values.defaultRules.appNamespacesTarget }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubernetes-storage" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kubernetes-storage + rules: + - alert: KubePersistentVolumeFillingUp + annotations: + description: The PersistentVolume claimed by {{`{{`}} $labels.persistentvolumeclaim {{`}}`}} in Namespace {{`{{`}} $labels.namespace {{`}}`}} is only {{`{{`}} $value | humanizePercentage {{`}}`}} free. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubepersistentvolumefillingup + summary: PersistentVolume is filling up. + expr: |- + kubelet_volume_stats_available_bytes{job="kubelet", namespace=~"{{ $targetNamespace }}", metrics_path="/metrics"} + / + kubelet_volume_stats_capacity_bytes{job="kubelet", namespace=~"{{ $targetNamespace }}", metrics_path="/metrics"} + < 0.03 + for: 1m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubePersistentVolumeFillingUp + annotations: + description: Based on recent sampling, the PersistentVolume claimed by {{`{{`}} $labels.persistentvolumeclaim {{`}}`}} in Namespace {{`{{`}} $labels.namespace {{`}}`}} is expected to fill up within four days. Currently {{`{{`}} $value | humanizePercentage {{`}}`}} is available. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubepersistentvolumefillingup + summary: PersistentVolume is filling up. + expr: |- + ( + kubelet_volume_stats_available_bytes{job="kubelet", namespace=~"{{ $targetNamespace }}", metrics_path="/metrics"} + / + kubelet_volume_stats_capacity_bytes{job="kubelet", namespace=~"{{ $targetNamespace }}", metrics_path="/metrics"} + ) < 0.15 + and + predict_linear(kubelet_volume_stats_available_bytes{job="kubelet", namespace=~"{{ $targetNamespace }}", metrics_path="/metrics"}[6h], 4 * 24 * 3600) < 0 + for: 1h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubePersistentVolumeErrors + annotations: + description: The persistent volume {{`{{`}} $labels.persistentvolume {{`}}`}} has status {{`{{`}} $labels.phase {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubepersistentvolumeerrors + summary: PersistentVolume is having issues with provisioning. + expr: kube_persistentvolume_status_phase{phase=~"Failed|Pending",job="kube-state-metrics"} > 0 + for: 5m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-apiserver.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-apiserver.yaml new file mode 100644 index 00000000..f9acb6a5 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-apiserver.yaml @@ -0,0 +1,88 @@ +{{- /* +Generated from 'kubernetes-system-apiserver' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubernetesSystem }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubernetes-system-apiserver" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kubernetes-system-apiserver + rules: + - alert: KubeClientCertificateExpiration + annotations: + description: A client certificate used to authenticate to the apiserver is expiring in less than 7.0 days. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeclientcertificateexpiration + summary: Client certificate is about to expire. + expr: apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and on(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 604800 + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeClientCertificateExpiration + annotations: + description: A client certificate used to authenticate to the apiserver is expiring in less than 24.0 hours. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeclientcertificateexpiration + summary: Client certificate is about to expire. + expr: apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and on(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 86400 + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: AggregatedAPIErrors + annotations: + description: An aggregated API {{`{{`}} $labels.name {{`}}`}}/{{`{{`}} $labels.namespace {{`}}`}} has reported errors. The number of errors have increased for it in the past five minutes. High values indicate that the availability of the service changes too often. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-aggregatedapierrors + summary: An aggregated API has reported errors. + expr: sum by(name, namespace)(increase(aggregator_unavailable_apiservice_count[5m])) > 2 + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- if semverCompare ">=1.18.0-0" $kubeTargetVersion }} + - alert: AggregatedAPIDown + annotations: + description: An aggregated API {{`{{`}} $labels.name {{`}}`}}/{{`{{`}} $labels.namespace {{`}}`}} has been only {{`{{`}} $value | humanize {{`}}`}}% available over the last 10m. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-aggregatedapidown + summary: An aggregated API is down. + expr: (1 - max by(name, namespace)(avg_over_time(aggregator_unavailable_apiservice[10m]))) * 100 < 85 + for: 5m + labels: + severity: warning +{{- end }} +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- if .Values.kubeApiServer.enabled }} + - alert: KubeAPIDown + annotations: + description: KubeAPI has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeapidown + summary: Target disappeared from Prometheus target discovery. + expr: absent(up{job="apiserver"} == 1) + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-controller-manager.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-controller-manager.yaml new file mode 100644 index 00000000..bc9dab86 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-controller-manager.yaml @@ -0,0 +1,41 @@ +{{- /* +Generated from 'kubernetes-system-controller-manager' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.kubeControllerManager.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubernetes-system-controller-manager" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kubernetes-system-controller-manager + rules: +{{- if .Values.kubeControllerManager.enabled }} + - alert: KubeControllerManagerDown + annotations: + description: KubeControllerManager has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubecontrollermanagerdown + summary: Target disappeared from Prometheus target discovery. + expr: absent(up{job="kube-controller-manager"} == 1) + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-kubelet.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-kubelet.yaml new file mode 100644 index 00000000..cde9da43 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-kubelet.yaml @@ -0,0 +1,188 @@ +{{- /* +Generated from 'kubernetes-system-kubelet' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubernetesSystem }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubernetes-system-kubelet" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kubernetes-system-kubelet + rules: + - alert: KubeNodeNotReady + annotations: + description: '{{`{{`}} $labels.node {{`}}`}} has been unready for more than 15 minutes.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubenodenotready + summary: Node is not ready. + expr: kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeNodeUnreachable + annotations: + description: '{{`{{`}} $labels.node {{`}}`}} is unreachable and some workloads may be rescheduled.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubenodeunreachable + summary: Node is unreachable. + expr: (kube_node_spec_taint{job="kube-state-metrics",key="node.kubernetes.io/unreachable",effect="NoSchedule"} unless ignoring(key,value) kube_node_spec_taint{job="kube-state-metrics",key=~"ToBeDeletedByClusterAutoscaler|cloud.google.com/impending-node-termination|aws-node-termination-handler/spot-itn"}) == 1 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeletTooManyPods + annotations: + description: Kubelet '{{`{{`}} $labels.node {{`}}`}}' is running at {{`{{`}} $value | humanizePercentage {{`}}`}} of its Pod capacity. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubelettoomanypods + summary: Kubelet is running at capacity. + expr: |- + count by(node) ( + (kube_pod_status_phase{job="kube-state-metrics",phase="Running"} == 1) * on(instance,pod,namespace,cluster) group_left(node) topk by(instance,pod,namespace,cluster) (1, kube_pod_info{job="kube-state-metrics"}) + ) + / + max by(node) ( + kube_node_status_capacity_pods{job="kube-state-metrics"} != 1 + ) > 0.95 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeNodeReadinessFlapping + annotations: + description: The readiness status of node {{`{{`}} $labels.node {{`}}`}} has changed {{`{{`}} $value {{`}}`}} times in the last 15 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubenodereadinessflapping + summary: Node readiness status is flapping. + expr: sum(changes(kube_node_status_condition{status="true",condition="Ready"}[15m])) by (node) > 2 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeletPlegDurationHigh + annotations: + description: The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{`{{`}} $value {{`}}`}} seconds on node {{`{{`}} $labels.node {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletplegdurationhigh + summary: Kubelet Pod Lifecycle Event Generator is taking too long to relist. + expr: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile="0.99"} >= 10 + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeletPodStartUpLatencyHigh + annotations: + description: Kubelet Pod startup 99th percentile latency is {{`{{`}} $value {{`}}`}} seconds on node {{`{{`}} $labels.node {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletpodstartuplatencyhigh + summary: Kubelet Pod startup latency is too high. + expr: histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (instance, le)) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"} > 60 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeletClientCertificateExpiration + annotations: + description: Client certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletclientcertificateexpiration + summary: Kubelet client certificate is about to expire. + expr: kubelet_certificate_manager_client_ttl_seconds < 604800 + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeletClientCertificateExpiration + annotations: + description: Client certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletclientcertificateexpiration + summary: Kubelet client certificate is about to expire. + expr: kubelet_certificate_manager_client_ttl_seconds < 86400 + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeletServerCertificateExpiration + annotations: + description: Server certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletservercertificateexpiration + summary: Kubelet server certificate is about to expire. + expr: kubelet_certificate_manager_server_ttl_seconds < 604800 + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeletServerCertificateExpiration + annotations: + description: Server certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletservercertificateexpiration + summary: Kubelet server certificate is about to expire. + expr: kubelet_certificate_manager_server_ttl_seconds < 86400 + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeletClientCertificateRenewalErrors + annotations: + description: Kubelet on node {{`{{`}} $labels.node {{`}}`}} has failed to renew its client certificate ({{`{{`}} $value | humanize {{`}}`}} errors in the last 5 minutes). + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletclientcertificaterenewalerrors + summary: Kubelet has failed to renew its client certificate. + expr: increase(kubelet_certificate_manager_client_expiration_renew_errors[5m]) > 0 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeletServerCertificateRenewalErrors + annotations: + description: Kubelet on node {{`{{`}} $labels.node {{`}}`}} has failed to renew its server certificate ({{`{{`}} $value | humanize {{`}}`}} errors in the last 5 minutes). + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletservercertificaterenewalerrors + summary: Kubelet has failed to renew its server certificate. + expr: increase(kubelet_server_expiration_renew_errors[5m]) > 0 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- if .Values.prometheusOperator.kubeletService.enabled }} + - alert: KubeletDown + annotations: + description: Kubelet has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletdown + summary: Target disappeared from Prometheus target discovery. + expr: absent(up{job="kubelet", metrics_path="/metrics"} == 1) + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-scheduler.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-scheduler.yaml new file mode 100644 index 00000000..a2c12725 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-scheduler.yaml @@ -0,0 +1,41 @@ +{{- /* +Generated from 'kubernetes-system-scheduler' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.kubeScheduler.enabled .Values.defaultRules.rules.kubeScheduler }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubernetes-system-scheduler" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kubernetes-system-scheduler + rules: +{{- if .Values.kubeScheduler.enabled }} + - alert: KubeSchedulerDown + annotations: + description: KubeScheduler has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeschedulerdown + summary: Target disappeared from Prometheus target discovery. + expr: absent(up{job="kube-scheduler"} == 1) + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system.yaml new file mode 100644 index 00000000..3aca2e6c --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system.yaml @@ -0,0 +1,55 @@ +{{- /* +Generated from 'kubernetes-system' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubernetesSystem }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubernetes-system" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kubernetes-system + rules: + - alert: KubeVersionMismatch + annotations: + description: There are {{`{{`}} $value {{`}}`}} different semantic versions of Kubernetes components running. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeversionmismatch + summary: Different semantic versions of Kubernetes components running. + expr: count(count by (gitVersion) (label_replace(kubernetes_build_info{job!~"kube-dns|coredns"},"gitVersion","$1","gitVersion","(v[0-9]*.[0-9]*).*"))) > 1 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeClientErrors + annotations: + description: Kubernetes API server client '{{`{{`}} $labels.job {{`}}`}}/{{`{{`}} $labels.instance {{`}}`}}' is experiencing {{`{{`}} $value | humanizePercentage {{`}}`}} errors.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeclienterrors + summary: Kubernetes API server client is experiencing errors. + expr: |- + (sum(rate(rest_client_requests_total{code=~"5.."}[5m])) by (instance, job) + / + sum(rate(rest_client_requests_total[5m])) by (instance, job)) + > 0.01 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.rules.yaml new file mode 100644 index 00000000..b6ae1bbe --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.rules.yaml @@ -0,0 +1,79 @@ +{{- /* +Generated from 'node-exporter.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.node }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "node-exporter.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: node-exporter.rules + rules: + - expr: |- + count without (cpu) ( + count without (mode) ( + node_cpu_seconds_total{job="node-exporter"} + ) + ) + record: instance:node_num_cpu:sum + - expr: |- + 1 - avg without (cpu, mode) ( + rate(node_cpu_seconds_total{job="node-exporter", mode="idle"}[1m]) + ) + record: instance:node_cpu_utilisation:rate1m + - expr: |- + ( + node_load1{job="node-exporter"} + / + instance:node_num_cpu:sum{job="node-exporter"} + ) + record: instance:node_load1_per_cpu:ratio + - expr: |- + 1 - ( + node_memory_MemAvailable_bytes{job="node-exporter"} + / + node_memory_MemTotal_bytes{job="node-exporter"} + ) + record: instance:node_memory_utilisation:ratio + - expr: rate(node_vmstat_pgmajfault{job="node-exporter"}[1m]) + record: instance:node_vmstat_pgmajfault:rate1m + - expr: rate(node_disk_io_time_seconds_total{job="node-exporter", device=~"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+"}[1m]) + record: instance_device:node_disk_io_time_seconds:rate1m + - expr: rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+"}[1m]) + record: instance_device:node_disk_io_time_weighted_seconds:rate1m + - expr: |- + sum without (device) ( + rate(node_network_receive_bytes_total{job="node-exporter", device!="lo"}[1m]) + ) + record: instance:node_network_receive_bytes_excluding_lo:rate1m + - expr: |- + sum without (device) ( + rate(node_network_transmit_bytes_total{job="node-exporter", device!="lo"}[1m]) + ) + record: instance:node_network_transmit_bytes_excluding_lo:rate1m + - expr: |- + sum without (device) ( + rate(node_network_receive_drop_total{job="node-exporter", device!="lo"}[1m]) + ) + record: instance:node_network_receive_drop_excluding_lo:rate1m + - expr: |- + sum without (device) ( + rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[1m]) + ) + record: instance:node_network_transmit_drop_excluding_lo:rate1m +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.yaml new file mode 100644 index 00000000..7d5ab7dc --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.yaml @@ -0,0 +1,278 @@ +{{- /* +Generated from 'node-exporter' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.node }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "node-exporter" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: node-exporter + rules: + - alert: NodeFilesystemSpaceFillingUp + annotations: + description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left and is filling up. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemspacefillingup + summary: Filesystem is predicted to run out of space within the next 24 hours. + expr: |- + ( + node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 40 + and + predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!=""}[6h], 24*60*60) < 0 + and + node_filesystem_readonly{job="node-exporter",fstype!=""} == 0 + ) + for: 1h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NodeFilesystemSpaceFillingUp + annotations: + description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left and is filling up fast. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemspacefillingup + summary: Filesystem is predicted to run out of space within the next 4 hours. + expr: |- + ( + node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 15 + and + predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!=""}[6h], 4*60*60) < 0 + and + node_filesystem_readonly{job="node-exporter",fstype!=""} == 0 + ) + for: 1h + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NodeFilesystemAlmostOutOfSpace + annotations: + description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemalmostoutofspace + summary: Filesystem has less than 5% space left. + expr: |- + ( + node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 5 + and + node_filesystem_readonly{job="node-exporter",fstype!=""} == 0 + ) + for: 1h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NodeFilesystemAlmostOutOfSpace + annotations: + description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemalmostoutofspace + summary: Filesystem has less than 3% space left. + expr: |- + ( + node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 3 + and + node_filesystem_readonly{job="node-exporter",fstype!=""} == 0 + ) + for: 1h + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NodeFilesystemFilesFillingUp + annotations: + description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left and is filling up. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemfilesfillingup + summary: Filesystem is predicted to run out of inodes within the next 24 hours. + expr: |- + ( + node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 40 + and + predict_linear(node_filesystem_files_free{job="node-exporter",fstype!=""}[6h], 24*60*60) < 0 + and + node_filesystem_readonly{job="node-exporter",fstype!=""} == 0 + ) + for: 1h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NodeFilesystemFilesFillingUp + annotations: + description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left and is filling up fast. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemfilesfillingup + summary: Filesystem is predicted to run out of inodes within the next 4 hours. + expr: |- + ( + node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 20 + and + predict_linear(node_filesystem_files_free{job="node-exporter",fstype!=""}[6h], 4*60*60) < 0 + and + node_filesystem_readonly{job="node-exporter",fstype!=""} == 0 + ) + for: 1h + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NodeFilesystemAlmostOutOfFiles + annotations: + description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemalmostoutoffiles + summary: Filesystem has less than 5% inodes left. + expr: |- + ( + node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 5 + and + node_filesystem_readonly{job="node-exporter",fstype!=""} == 0 + ) + for: 1h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NodeFilesystemAlmostOutOfFiles + annotations: + description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemalmostoutoffiles + summary: Filesystem has less than 3% inodes left. + expr: |- + ( + node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 3 + and + node_filesystem_readonly{job="node-exporter",fstype!=""} == 0 + ) + for: 1h + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NodeNetworkReceiveErrs + annotations: + description: '{{`{{`}} $labels.instance {{`}}`}} interface {{`{{`}} $labels.device {{`}}`}} has encountered {{`{{`}} printf "%.0f" $value {{`}}`}} receive errors in the last two minutes.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodenetworkreceiveerrs + summary: Network interface is reporting many receive errors. + expr: rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01 + for: 1h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NodeNetworkTransmitErrs + annotations: + description: '{{`{{`}} $labels.instance {{`}}`}} interface {{`{{`}} $labels.device {{`}}`}} has encountered {{`{{`}} printf "%.0f" $value {{`}}`}} transmit errors in the last two minutes.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodenetworktransmiterrs + summary: Network interface is reporting many transmit errors. + expr: rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01 + for: 1h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NodeHighNumberConntrackEntriesUsed + annotations: + description: '{{`{{`}} $value | humanizePercentage {{`}}`}} of conntrack entries are used.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodehighnumberconntrackentriesused + summary: Number of conntrack are getting close to the limit. + expr: (node_nf_conntrack_entries / node_nf_conntrack_entries_limit) > 0.75 + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NodeTextFileCollectorScrapeError + annotations: + description: Node Exporter text file collector failed to scrape. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodetextfilecollectorscrapeerror + summary: Node Exporter text file collector failed to scrape. + expr: node_textfile_scrape_error{job="node-exporter"} == 1 + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NodeClockSkewDetected + annotations: + message: Clock on {{`{{`}} $labels.instance {{`}}`}} is out of sync by more than 300s. Ensure NTP is configured correctly on this host. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodeclockskewdetected + summary: Clock skew detected. + expr: |- + ( + node_timex_offset_seconds > 0.05 + and + deriv(node_timex_offset_seconds[5m]) >= 0 + ) + or + ( + node_timex_offset_seconds < -0.05 + and + deriv(node_timex_offset_seconds[5m]) <= 0 + ) + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NodeClockNotSynchronising + annotations: + message: Clock on {{`{{`}} $labels.instance {{`}}`}} is not synchronising. Ensure NTP is configured on this host. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodeclocknotsynchronising + summary: Clock not synchronising. + expr: |- + min_over_time(node_timex_sync_status[5m]) == 0 + and + node_timex_maxerror_seconds >= 16 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NodeRAIDDegraded + annotations: + description: RAID array '{{`{{`}} $labels.device {{`}}`}}' on {{`{{`}} $labels.instance {{`}}`}} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-noderaiddegraded + summary: RAID Array is degraded + expr: node_md_disks_required - ignoring (state) (node_md_disks{state="active"}) > 0 + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NodeRAIDDiskFailure + annotations: + description: At least one device in RAID array on {{`{{`}} $labels.instance {{`}}`}} failed. Array '{{`{{`}} $labels.device {{`}}`}}' needs attention and possibly a disk swap. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-noderaiddiskfailure + summary: Failed device in RAID array + expr: node_md_disks{state="fail"} > 0 + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-network.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-network.yaml new file mode 100644 index 00000000..9a6955ae --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-network.yaml @@ -0,0 +1,37 @@ +{{- /* +Generated from 'node-network' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.network }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "node-network" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: node-network + rules: + - alert: NodeNetworkInterfaceFlapping + annotations: + message: Network interface "{{`{{`}} $labels.device {{`}}`}}" changing it's up status often on node-exporter {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}}" + expr: changes(node_network_up{job="node-exporter",device!~"veth.+"}[2m]) > 2 + for: 2m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node.rules.yaml new file mode 100644 index 00000000..7253b311 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node.rules.yaml @@ -0,0 +1,53 @@ +{{- /* +Generated from 'node.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.node }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "node.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: node.rules + rules: + - expr: sum(min(kube_pod_info{node!=""}) by (cluster, node)) + record: ':kube_pod_info_node_count:' + - expr: |- + topk by(namespace, pod) (1, + max by (node, namespace, pod) ( + label_replace(kube_pod_info{job="kube-state-metrics",node!=""}, "pod", "$1", "pod", "(.*)") + )) + record: 'node_namespace_pod:kube_pod_info:' + - expr: |- + count by (cluster, node) (sum by (node, cpu) ( + node_cpu_seconds_total{job="node-exporter"} + * on (namespace, pod) group_left(node) + node_namespace_pod:kube_pod_info: + )) + record: node:node_num_cpu:sum + - expr: |- + sum( + node_memory_MemAvailable_bytes{job="node-exporter"} or + ( + node_memory_Buffers_bytes{job="node-exporter"} + + node_memory_Cached_bytes{job="node-exporter"} + + node_memory_MemFree_bytes{job="node-exporter"} + + node_memory_Slab_bytes{job="node-exporter"} + ) + ) by (cluster) + record: :node_memory_MemAvailable_bytes:sum +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/prometheus-operator.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/prometheus-operator.yaml new file mode 100644 index 00000000..d1c1f654 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/prometheus-operator.yaml @@ -0,0 +1,113 @@ +{{- /* +Generated from 'prometheus-operator' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.prometheusOperator }} +{{- $operatorJob := printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "operator" }} +{{- $namespace := printf "%s" (include "kube-prometheus-stack.namespace" .) }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "prometheus-operator" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: prometheus-operator + rules: + - alert: PrometheusOperatorListErrors + annotations: + description: Errors while performing List operations in controller {{`{{`}}$labels.controller{{`}}`}} in {{`{{`}}$labels.namespace{{`}}`}} namespace. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusoperatorlisterrors + summary: Errors while performing list operations in controller. + expr: (sum by (controller,namespace) (rate(prometheus_operator_list_operations_failed_total{job="{{ $operatorJob }}",namespace="{{ $namespace }}"}[10m])) / sum by (controller,namespace) (rate(prometheus_operator_list_operations_total{job="{{ $operatorJob }}",namespace="{{ $namespace }}"}[10m]))) > 0.4 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusOperatorWatchErrors + annotations: + description: Errors while performing watch operations in controller {{`{{`}}$labels.controller{{`}}`}} in {{`{{`}}$labels.namespace{{`}}`}} namespace. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusoperatorwatcherrors + summary: Errors while performing watch operations in controller. + expr: (sum by (controller,namespace) (rate(prometheus_operator_watch_operations_failed_total{job="{{ $operatorJob }}",namespace="{{ $namespace }}"}[10m])) / sum by (controller,namespace) (rate(prometheus_operator_watch_operations_total{job="{{ $operatorJob }}",namespace="{{ $namespace }}"}[10m]))) > 0.4 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusOperatorSyncFailed + annotations: + description: Controller {{`{{`}} $labels.controller {{`}}`}} in {{`{{`}} $labels.namespace {{`}}`}} namespace fails to reconcile {{`{{`}} $value {{`}}`}} objects. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusoperatorsyncfailed + summary: Last controller reconciliation failed + expr: min_over_time(prometheus_operator_syncs{status="failed",job="{{ $operatorJob }}",namespace="{{ $namespace }}"}[5m]) > 0 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusOperatorReconcileErrors + annotations: + description: '{{`{{`}} $value | humanizePercentage {{`}}`}} of reconciling operations failed for {{`{{`}} $labels.controller {{`}}`}} controller in {{`{{`}} $labels.namespace {{`}}`}} namespace.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusoperatorreconcileerrors + summary: Errors while reconciling controller. + expr: (sum by (controller,namespace) (rate(prometheus_operator_reconcile_errors_total{job="{{ $operatorJob }}",namespace="{{ $namespace }}"}[5m]))) / (sum by (controller,namespace) (rate(prometheus_operator_reconcile_operations_total{job="{{ $operatorJob }}",namespace="{{ $namespace }}"}[5m]))) > 0.1 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusOperatorNodeLookupErrors + annotations: + description: Errors while reconciling Prometheus in {{`{{`}} $labels.namespace {{`}}`}} Namespace. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusoperatornodelookuperrors + summary: Errors while reconciling Prometheus. + expr: rate(prometheus_operator_node_address_lookup_errors_total{job="{{ $operatorJob }}",namespace="{{ $namespace }}"}[5m]) > 0.1 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusOperatorNotReady + annotations: + description: Prometheus operator in {{`{{`}} $labels.namespace {{`}}`}} namespace isn't ready to reconcile {{`{{`}} $labels.controller {{`}}`}} resources. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusoperatornotready + summary: Prometheus operator not ready + expr: min by(namespace, controller) (max_over_time(prometheus_operator_ready{job="{{ $operatorJob }}",namespace="{{ $namespace }}"}[5m]) == 0) + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusOperatorRejectedResources + annotations: + description: Prometheus operator in {{`{{`}} $labels.namespace {{`}}`}} namespace rejected {{`{{`}} printf "%0.0f" $value {{`}}`}} {{`{{`}} $labels.controller {{`}}`}}/{{`{{`}} $labels.resource {{`}}`}} resources. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusoperatorrejectedresources + summary: Resources rejected by Prometheus operator + expr: min_over_time(prometheus_operator_managed_resources{state="rejected",job="{{ $operatorJob }}",namespace="{{ $namespace }}"}[5m]) > 0 + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/prometheus.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/prometheus.yaml new file mode 100644 index 00000000..c9c805ee --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/prometheus.yaml @@ -0,0 +1,258 @@ +{{- /* +Generated from 'prometheus' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.prometheus }} +{{- $prometheusJob := printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "prometheus" }} +{{- $namespace := printf "%s" (include "kube-prometheus-stack.namespace" .) }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "prometheus" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: prometheus + rules: + - alert: PrometheusBadConfig + annotations: + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has failed to reload its configuration. + summary: Failed Prometheus configuration reload. + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(prometheus_config_last_reload_successful{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) == 0 + for: 10m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusNotificationQueueRunningFull + annotations: + description: Alert notification queue of Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is running full. + summary: Prometheus alert notification queue predicted to run full in less than 30m. + expr: |- + # Without min_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + ( + predict_linear(prometheus_notifications_queue_length{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m], 60 * 30) + > + min_over_time(prometheus_notifications_queue_capacity{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) + ) + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusErrorSendingAlertsToSomeAlertmanagers + annotations: + description: '{{`{{`}} printf "%.1f" $value {{`}}`}}% errors while sending alerts from Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} to Alertmanager {{`{{`}}$labels.alertmanager{{`}}`}}.' + summary: Prometheus has encountered more than 1% errors sending alerts to a specific Alertmanager. + expr: |- + ( + rate(prometheus_notifications_errors_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) + / + rate(prometheus_notifications_sent_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) + ) + * 100 + > 1 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusErrorSendingAlertsToAnyAlertmanager + annotations: + description: '{{`{{`}} printf "%.1f" $value {{`}}`}}% minimum errors while sending alerts from Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} to any Alertmanager.' + summary: Prometheus encounters more than 3% errors sending alerts to any Alertmanager. + expr: |- + min without(alertmanager) ( + rate(prometheus_notifications_errors_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) + / + rate(prometheus_notifications_sent_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) + ) + * 100 + > 3 + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusNotConnectedToAlertmanagers + annotations: + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is not connected to any Alertmanagers. + summary: Prometheus is not connected to any Alertmanagers. + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(prometheus_notifications_alertmanagers_discovered{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) < 1 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusTSDBReloadsFailing + annotations: + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has detected {{`{{`}}$value | humanize{{`}}`}} reload failures over the last 3h. + summary: Prometheus has issues reloading blocks from disk. + expr: increase(prometheus_tsdb_reloads_failures_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[3h]) > 0 + for: 4h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusTSDBCompactionsFailing + annotations: + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has detected {{`{{`}}$value | humanize{{`}}`}} compaction failures over the last 3h. + summary: Prometheus has issues compacting blocks. + expr: increase(prometheus_tsdb_compactions_failed_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[3h]) > 0 + for: 4h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusNotIngestingSamples + annotations: + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is not ingesting samples. + summary: Prometheus is not ingesting samples. + expr: rate(prometheus_tsdb_head_samples_appended_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) <= 0 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusDuplicateTimestamps + annotations: + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is dropping {{`{{`}} printf "%.4g" $value {{`}}`}} samples/s with different values but duplicated timestamp. + summary: Prometheus is dropping samples with duplicate timestamps. + expr: rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusOutOfOrderTimestamps + annotations: + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is dropping {{`{{`}} printf "%.4g" $value {{`}}`}} samples/s with timestamps arriving out of order. + summary: Prometheus drops samples with out-of-order timestamps. + expr: rate(prometheus_target_scrapes_sample_out_of_order_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusRemoteStorageFailures + annotations: + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} failed to send {{`{{`}} printf "%.1f" $value {{`}}`}}% of the samples to {{`{{`}} $labels.remote_name{{`}}`}}:{{`{{`}} $labels.url {{`}}`}} + summary: Prometheus fails to send samples to remote storage. + expr: |- + ( + rate(prometheus_remote_storage_failed_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) + / + ( + rate(prometheus_remote_storage_failed_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) + + + rate(prometheus_remote_storage_succeeded_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) + ) + ) + * 100 + > 1 + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusRemoteWriteBehind + annotations: + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} remote write is {{`{{`}} printf "%.1f" $value {{`}}`}}s behind for {{`{{`}} $labels.remote_name{{`}}`}}:{{`{{`}} $labels.url {{`}}`}}. + summary: Prometheus remote write is behind. + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + ( + max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) + - on(job, instance) group_right + max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) + ) + > 120 + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusRemoteWriteDesiredShards + annotations: + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} remote write desired shards calculation wants to run {{`{{`}} $value {{`}}`}} shards for queue {{`{{`}} $labels.remote_name{{`}}`}}:{{`{{`}} $labels.url {{`}}`}}, which is more than the max of {{`{{`}} printf `prometheus_remote_storage_shards_max{instance="%s",job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}` $labels.instance | query | first | value {{`}}`}}. + summary: Prometheus remote write desired shards calculation wants to run more than configured max shards. + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + ( + max_over_time(prometheus_remote_storage_shards_desired{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) + > + max_over_time(prometheus_remote_storage_shards_max{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) + ) + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusRuleFailures + annotations: + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has failed to evaluate {{`{{`}} printf "%.0f" $value {{`}}`}} rules in the last 5m. + summary: Prometheus is failing rule evaluations. + expr: increase(prometheus_rule_evaluation_failures_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0 + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusMissingRuleEvaluations + annotations: + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has missed {{`{{`}} printf "%.0f" $value {{`}}`}} rule group evaluations in the last 5m. + summary: Prometheus is missing rule evaluations due to slow rule group evaluation. + expr: increase(prometheus_rule_group_iterations_missed_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusTargetLimitHit + annotations: + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has dropped {{`{{`}} printf "%.0f" $value {{`}}`}} targets because the number of targets exceeded the configured target_limit. + summary: Prometheus has dropped targets because some scrape configs have exceeded the targets limit. + expr: increase(prometheus_target_scrape_pool_exceeded_target_limit_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/alertmanager.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/alertmanager.rules.yaml new file mode 100644 index 00000000..71159849 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/alertmanager.rules.yaml @@ -0,0 +1,63 @@ +{{- /* +Generated from 'alertmanager.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.alertmanager }} +{{- $operatorJob := printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "operator" }} +{{- $alertmanagerJob := printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "alertmanager" }} +{{- $namespace := printf "%s" (include "kube-prometheus-stack.namespace" .) }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "alertmanager.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: alertmanager.rules + rules: + - alert: AlertmanagerConfigInconsistent + annotations: + message: The configuration of the instances of the Alertmanager cluster `{{`{{`}}$labels.service{{`}}`}}` are out of sync. + expr: count_values("config_hash", alertmanager_config_hash{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}) BY (service) / ON(service) GROUP_LEFT() label_replace(max(prometheus_operator_spec_replicas{job="{{ $operatorJob }}",namespace="{{ $namespace }}",controller="alertmanager"}) by (name, job, namespace, controller), "service", "$1", "name", "(.*)") != 1 + for: 5m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: AlertmanagerFailedReload + annotations: + message: Reloading Alertmanager's configuration has failed for {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod{{`}}`}}. + expr: alertmanager_config_last_reload_successful{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"} == 0 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: AlertmanagerMembersInconsistent + annotations: + message: Alertmanager has not found all other members of the cluster. + expr: |- + alertmanager_cluster_members{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"} + != on (service) GROUP_LEFT() + count by (service) (alertmanager_cluster_members{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}) + for: 5m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/etcd.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/etcd.yaml new file mode 100644 index 00000000..e9c4f6cb --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/etcd.yaml @@ -0,0 +1,197 @@ +{{- /* +Generated from 'etcd' group from https://raw.githubusercontent.com/etcd-io/etcd/master/Documentation/op-guide/etcd3_alert.rules.yml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.kubeEtcd.enabled .Values.defaultRules.rules.etcd }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "etcd" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: etcd + rules: + - alert: etcdMembersDown + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": members are down ({{`{{`}} $value {{`}}`}}).' + expr: |- + max by (job) ( + sum by (job) (up{job=~".*etcd.*"} == bool 0) + or + count by (job,endpoint) ( + sum by (job,endpoint,To) (rate(etcd_network_peer_sent_failures_total{job=~".*etcd.*"}[3m])) > 0.01 + ) + ) + > 0 + for: 3m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdInsufficientMembers + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": insufficient members ({{`{{`}} $value {{`}}`}}).' + expr: sum(up{job=~".*etcd.*"} == bool 1) by (job) < ((count(up{job=~".*etcd.*"}) by (job) + 1) / 2) + for: 3m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdNoLeader + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": member {{`{{`}} $labels.instance {{`}}`}} has no leader.' + expr: etcd_server_has_leader{job=~".*etcd.*"} == 0 + for: 1m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdHighNumberOfLeaderChanges + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": {{`{{`}} $value {{`}}`}} leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated.' + expr: increase((max by (job) (etcd_server_leader_changes_seen_total{job=~".*etcd.*"}) or 0*absent(etcd_server_leader_changes_seen_total{job=~".*etcd.*"}))[15m:1m]) >= 3 + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdHighNumberOfFailedGRPCRequests + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": {{`{{`}} $value {{`}}`}}% of requests for {{`{{`}} $labels.grpc_method {{`}}`}} failed on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + expr: |- + 100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method) + / + sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) BY (job, instance, grpc_service, grpc_method) + > 1 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdHighNumberOfFailedGRPCRequests + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": {{`{{`}} $value {{`}}`}}% of requests for {{`{{`}} $labels.grpc_method {{`}}`}} failed on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + expr: |- + 100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method) + / + sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) BY (job, instance, grpc_service, grpc_method) + > 5 + for: 5m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdGRPCRequestsSlow + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": gRPC requests to {{`{{`}} $labels.grpc_method {{`}}`}} are taking {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + expr: |- + histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_type="unary"}[5m])) by (job, instance, grpc_service, grpc_method, le)) + > 0.15 + for: 10m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdMemberCommunicationSlow + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": member communication with {{`{{`}} $labels.To {{`}}`}} is taking {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + expr: |- + histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~".*etcd.*"}[5m])) + > 0.15 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdHighNumberOfFailedProposals + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": {{`{{`}} $value {{`}}`}} proposal failures within the last 30 minutes on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + expr: rate(etcd_server_proposals_failed_total{job=~".*etcd.*"}[15m]) > 5 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdHighFsyncDurations + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": 99th percentile fync durations are {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + expr: |- + histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~".*etcd.*"}[5m])) + > 0.5 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdHighCommitDurations + annotations: + message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": 99th percentile commit durations {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + expr: |- + histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket{job=~".*etcd.*"}[5m])) + > 0.25 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdHighNumberOfFailedHTTPRequests + annotations: + message: '{{`{{`}} $value {{`}}`}}% of requests for {{`{{`}} $labels.method {{`}}`}} failed on etcd instance {{`{{`}} $labels.instance {{`}}`}}' + expr: |- + sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m])) + BY (method) > 0.01 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdHighNumberOfFailedHTTPRequests + annotations: + message: '{{`{{`}} $value {{`}}`}}% of requests for {{`{{`}} $labels.method {{`}}`}} failed on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + expr: |- + sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m])) + BY (method) > 0.05 + for: 10m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: etcdHTTPRequestsSlow + annotations: + message: etcd instance {{`{{`}} $labels.instance {{`}}`}} HTTP requests to {{`{{`}} $labels.method {{`}}`}} are slow. + expr: |- + histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m])) + > 0.15 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/general.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/general.rules.yaml new file mode 100644 index 00000000..cde6feb5 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/general.rules.yaml @@ -0,0 +1,56 @@ +{{- /* +Generated from 'general.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.general }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "general.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: general.rules + rules: + - alert: TargetDown + annotations: + message: '{{`{{`}} $value {{`}}`}}% of the {{`{{`}} $labels.job {{`}}`}} targets are down.' + expr: 100 * (count(up == 0) BY (job) / count(up) BY (job)) > 10 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: Watchdog + annotations: + message: 'This is an alert meant to ensure that the entire alerting pipeline is functional. + + This alert is always firing, therefore it should always be firing in Alertmanager + + and always fire against a receiver. There are integrations with various notification + + mechanisms that send a notification when this alert is not firing. For example the + + "DeadMansSnitch" integration in PagerDuty. + + ' + expr: vector(1) + labels: + severity: none +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/k8s.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/k8s.rules.yaml new file mode 100644 index 00000000..08aa7fe2 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/k8s.rules.yaml @@ -0,0 +1,83 @@ +{{- /* +Generated from 'k8s.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.k8s }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "k8s.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: k8s.rules + rules: + - expr: sum(rate(container_cpu_usage_seconds_total{job="kubelet", image!="", container_name!=""}[5m])) by (namespace) + record: namespace:container_cpu_usage_seconds_total:sum_rate + - expr: sum(container_memory_usage_bytes{job="kubelet", image!="", container_name!=""}) by (namespace) + record: namespace:container_memory_usage_bytes:sum + - expr: |- + sum by (namespace, pod_name, container_name) ( + rate(container_cpu_usage_seconds_total{job="kubelet", image!="", container_name!=""}[5m]) + ) + record: namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate + - expr: |- + sum by(namespace) ( + kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"} + * on (endpoint, instance, job, namespace, pod, service) + group_left(phase) (kube_pod_status_phase{phase=~"^(Pending|Running)$"} == 1) + ) + record: namespace_name:kube_pod_container_resource_requests_memory_bytes:sum + - expr: |- + sum by (namespace) ( + kube_pod_container_resource_requests_cpu_cores{job="kube-state-metrics"} + * on (endpoint, instance, job, namespace, pod, service) + group_left(phase) (kube_pod_status_phase{phase=~"^(Pending|Running)$"} == 1) + ) + record: namespace_name:kube_pod_container_resource_requests_cpu_cores:sum + - expr: |- + sum( + label_replace( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="ReplicaSet"}, + "replicaset", "$1", "owner_name", "(.*)" + ) * on(replicaset, namespace) group_left(owner_name) kube_replicaset_owner{job="kube-state-metrics"}, + "workload", "$1", "owner_name", "(.*)" + ) + ) by (namespace, workload, pod) + labels: + workload_type: deployment + record: mixin_pod_workload + - expr: |- + sum( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="DaemonSet"}, + "workload", "$1", "owner_name", "(.*)" + ) + ) by (namespace, workload, pod) + labels: + workload_type: daemonset + record: mixin_pod_workload + - expr: |- + sum( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="StatefulSet"}, + "workload", "$1", "owner_name", "(.*)" + ) + ) by (namespace, workload, pod) + labels: + workload_type: statefulset + record: mixin_pod_workload +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kube-apiserver.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kube-apiserver.rules.yaml new file mode 100644 index 00000000..e3a92969 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kube-apiserver.rules.yaml @@ -0,0 +1,39 @@ +{{- /* +Generated from 'kube-apiserver.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.kubeApiServer.enabled .Values.defaultRules.rules.kubeApiserver }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kube-apiserver.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kube-apiserver.rules + rules: + - expr: histogram_quantile(0.99, sum(rate(apiserver_request_latencies_bucket{job="apiserver"}[5m])) without(instance, pod)) / 1e+06 + labels: + quantile: '0.99' + record: cluster_quantile:apiserver_request_latencies:histogram_quantile + - expr: histogram_quantile(0.9, sum(rate(apiserver_request_latencies_bucket{job="apiserver"}[5m])) without(instance, pod)) / 1e+06 + labels: + quantile: '0.9' + record: cluster_quantile:apiserver_request_latencies:histogram_quantile + - expr: histogram_quantile(0.5, sum(rate(apiserver_request_latencies_bucket{job="apiserver"}[5m])) without(instance, pod)) / 1e+06 + labels: + quantile: '0.5' + record: cluster_quantile:apiserver_request_latencies:histogram_quantile +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kube-prometheus-node-alerting.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kube-prometheus-node-alerting.rules.yaml new file mode 100644 index 00000000..a8d5400c --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kube-prometheus-node-alerting.rules.yaml @@ -0,0 +1,47 @@ +{{- /* +Generated from 'kube-prometheus-node-alerting.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubePrometheusNodeAlerting }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kube-prometheus-node-alerting.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kube-prometheus-node-alerting.rules + rules: + - alert: NodeDiskRunningFull + annotations: + message: Device {{`{{`}} $labels.device {{`}}`}} of node-exporter {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} will be full within the next 24 hours. + expr: '(node:node_filesystem_usage: > 0.85) and (predict_linear(node:node_filesystem_avail:[6h], 3600 * 24) < 0)' + for: 30m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NodeDiskRunningFull + annotations: + message: Device {{`{{`}} $labels.device {{`}}`}} of node-exporter {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} will be full within the next 2 hours. + expr: '(node:node_filesystem_usage: > 0.85) and (predict_linear(node:node_filesystem_avail:[30m], 3600 * 2) < 0)' + for: 10m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kube-prometheus-node-recording.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kube-prometheus-node-recording.rules.yaml new file mode 100644 index 00000000..87f072fd --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kube-prometheus-node-recording.rules.yaml @@ -0,0 +1,41 @@ +{{- /* +Generated from 'kube-prometheus-node-recording.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubePrometheusNodeRecording }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kube-prometheus-node-recording.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kube-prometheus-node-recording.rules + rules: + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[3m])) BY (instance) + record: instance:node_cpu:rate:sum + - expr: sum((node_filesystem_size_bytes{mountpoint="/"} - node_filesystem_free_bytes{mountpoint="/"})) BY (instance) + record: instance:node_filesystem_usage:sum + - expr: sum(rate(node_network_receive_bytes_total[3m])) BY (instance) + record: instance:node_network_receive_bytes:rate:sum + - expr: sum(rate(node_network_transmit_bytes_total[3m])) BY (instance) + record: instance:node_network_transmit_bytes:rate:sum + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[5m])) WITHOUT (cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance, cpu)) BY (instance) + record: instance:node_cpu:ratio + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[5m])) + record: cluster:node_cpu:sum_rate5m + - expr: cluster:node_cpu_seconds_total:rate5m / count(sum(node_cpu_seconds_total) BY (instance, cpu)) + record: cluster:node_cpu:ratio +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kube-scheduler.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kube-scheduler.rules.yaml new file mode 100644 index 00000000..46c8d1d4 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kube-scheduler.rules.yaml @@ -0,0 +1,63 @@ +{{- /* +Generated from 'kube-scheduler.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.kubeScheduler.enabled .Values.defaultRules.rules.kubeScheduler }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kube-scheduler.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kube-scheduler.rules + rules: + - expr: histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06 + labels: + quantile: '0.99' + record: cluster_quantile:scheduler_e2e_scheduling_latency:histogram_quantile + - expr: histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06 + labels: + quantile: '0.99' + record: cluster_quantile:scheduler_scheduling_algorithm_latency:histogram_quantile + - expr: histogram_quantile(0.99, sum(rate(scheduler_binding_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06 + labels: + quantile: '0.99' + record: cluster_quantile:scheduler_binding_latency:histogram_quantile + - expr: histogram_quantile(0.9, sum(rate(scheduler_e2e_scheduling_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06 + labels: + quantile: '0.9' + record: cluster_quantile:scheduler_e2e_scheduling_latency:histogram_quantile + - expr: histogram_quantile(0.9, sum(rate(scheduler_scheduling_algorithm_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06 + labels: + quantile: '0.9' + record: cluster_quantile:scheduler_scheduling_algorithm_latency:histogram_quantile + - expr: histogram_quantile(0.9, sum(rate(scheduler_binding_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06 + labels: + quantile: '0.9' + record: cluster_quantile:scheduler_binding_latency:histogram_quantile + - expr: histogram_quantile(0.5, sum(rate(scheduler_e2e_scheduling_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06 + labels: + quantile: '0.5' + record: cluster_quantile:scheduler_e2e_scheduling_latency:histogram_quantile + - expr: histogram_quantile(0.5, sum(rate(scheduler_scheduling_algorithm_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06 + labels: + quantile: '0.5' + record: cluster_quantile:scheduler_scheduling_algorithm_latency:histogram_quantile + - expr: histogram_quantile(0.5, sum(rate(scheduler_binding_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06 + labels: + quantile: '0.5' + record: cluster_quantile:scheduler_binding_latency:histogram_quantile +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kubernetes-absent.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kubernetes-absent.yaml new file mode 100644 index 00000000..5c1ebce9 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kubernetes-absent.yaml @@ -0,0 +1,159 @@ +{{- /* +Generated from 'kubernetes-absent' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubernetesAbsent }} +{{- $operatorJob := printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "operator" }} +{{- $prometheusJob := printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "prometheus" }} +{{- $alertmanagerJob := printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "alertmanager" }} +{{- $namespace := printf "%s" (include "kube-prometheus-stack.namespace" .) }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubernetes-absent" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kubernetes-absent + rules: +{{- if .Values.alertmanager.enabled }} + - alert: AlertmanagerDown + annotations: + message: Alertmanager has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-alertmanagerdown + expr: absent(up{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"} == 1) + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if .Values.kubeDns.enabled }} + - alert: CoreDNSDown + annotations: + message: CoreDNS has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-corednsdown + expr: absent(up{job="kube-dns"} == 1) + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if .Values.kubeApiServer.enabled }} + - alert: KubeAPIDown + annotations: + message: KubeAPI has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeapidown + expr: absent(up{job="apiserver"} == 1) + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if .Values.kubeControllerManager.enabled }} + - alert: KubeControllerManagerDown + annotations: + message: KubeControllerManager has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubecontrollermanagerdown + expr: absent(up{job="kube-controller-manager"} == 1) + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if .Values.kubeScheduler.enabled }} + - alert: KubeSchedulerDown + annotations: + message: KubeScheduler has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeschedulerdown + expr: absent(up{job="kube-scheduler"} == 1) + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if .Values.kubeStateMetrics.enabled }} + - alert: KubeStateMetricsDown + annotations: + message: KubeStateMetrics has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubestatemetricsdown + expr: absent(up{job="kube-state-metrics"} == 1) + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if .Values.prometheusOperator.kubeletService.enabled }} + - alert: KubeletDown + annotations: + message: Kubelet has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletdown + expr: absent(up{job="kubelet"} == 1) + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if .Values.nodeExporter.enabled }} + - alert: NodeExporterDown + annotations: + message: NodeExporter has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodeexporterdown + expr: absent(up{job="node-exporter"} == 1) + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} + - alert: PrometheusDown + annotations: + message: Prometheus has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusdown + expr: absent(up{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"} == 1) + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- if .Values.prometheusOperator.enabled }} + - alert: PrometheusOperatorDown + annotations: + message: PrometheusOperator has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusoperatordown + expr: absent(up{job="{{ $operatorJob }}",namespace="{{ $namespace }}"} == 1) + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kubernetes-apps.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kubernetes-apps.yaml new file mode 100644 index 00000000..e7a41ca2 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kubernetes-apps.yaml @@ -0,0 +1,200 @@ +{{- /* +Generated from 'kubernetes-apps' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubernetesApps }} +{{- $targetNamespace := .Values.defaultRules.appNamespacesTarget }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubernetes-apps" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kubernetes-apps + rules: + - alert: KubePodCrashLooping + annotations: + message: Pod {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} ({{`{{`}} $labels.container {{`}}`}}) is restarting {{`{{`}} printf "%.2f" $value {{`}}`}} times / 5 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubepodcrashlooping + expr: rate(kube_pod_container_status_restarts_total{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}[15m]) * 60 * 5 > 0 + for: 1h + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubePodNotReady + annotations: + message: Pod {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} has been in a non-ready state for longer than an hour. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubepodnotready + expr: sum by (namespace, pod) (kube_pod_status_phase{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}", phase=~"Pending|Unknown"}) > 0 + for: 1h + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeDeploymentGenerationMismatch + annotations: + message: Deployment generation for {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.deployment {{`}}`}} does not match, this indicates that the Deployment has failed but has not been rolled back. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubedeploymentgenerationmismatch + expr: |- + kube_deployment_status_observed_generation{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + != + kube_deployment_metadata_generation{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeDeploymentReplicasMismatch + annotations: + message: Deployment {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.deployment {{`}}`}} has not matched the expected number of replicas for longer than an hour. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubedeploymentreplicasmismatch + expr: |- + kube_deployment_spec_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + != + kube_deployment_status_replicas_available{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + for: 1h + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeStatefulSetReplicasMismatch + annotations: + message: StatefulSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.statefulset {{`}}`}} has not matched the expected number of replicas for longer than 15 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubestatefulsetreplicasmismatch + expr: |- + kube_statefulset_status_replicas_ready{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + != + kube_statefulset_status_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeStatefulSetGenerationMismatch + annotations: + message: StatefulSet generation for {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.statefulset {{`}}`}} does not match, this indicates that the StatefulSet has failed but has not been rolled back. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubestatefulsetgenerationmismatch + expr: |- + kube_statefulset_status_observed_generation{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + != + kube_statefulset_metadata_generation{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeStatefulSetUpdateNotRolledOut + annotations: + message: StatefulSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.statefulset {{`}}`}} update has not been rolled out. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubestatefulsetupdatenotrolledout + expr: |- + max without (revision) ( + kube_statefulset_status_current_revision{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + unless + kube_statefulset_status_update_revision{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + ) + * + ( + kube_statefulset_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + != + kube_statefulset_status_replicas_updated{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + ) + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeDaemonSetRolloutStuck + annotations: + message: Only {{`{{`}} $value {{`}}`}}% of the desired Pods of DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} are scheduled and ready. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubedaemonsetrolloutstuck + expr: |- + kube_daemonset_status_number_ready{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + / + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} * 100 < 100 + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeDaemonSetNotScheduled + annotations: + message: '{{`{{`}} $value {{`}}`}} Pods of DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} are not scheduled.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubedaemonsetnotscheduled + expr: |- + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + - + kube_daemonset_status_current_number_scheduled{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} > 0 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeDaemonSetMisScheduled + annotations: + message: '{{`{{`}} $value {{`}}`}} Pods of DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} are running where they are not supposed to run.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubedaemonsetmisscheduled + expr: kube_daemonset_status_number_misscheduled{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} > 0 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeCronJobRunning + annotations: + message: CronJob {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.cronjob {{`}}`}} is taking more than 1h to complete. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubecronjobrunning + expr: time() - kube_cronjob_next_schedule_time{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} > 3600 + for: 1h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeJobCompletion + annotations: + message: Job {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.job_name {{`}}`}} is taking more than one hour to complete. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubejobcompletion + expr: kube_job_spec_completions{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} - kube_job_status_succeeded{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} > 0 + for: 1h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeJobFailed + annotations: + message: Job {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.job_name {{`}}`}} failed to complete. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubejobfailed + expr: kube_job_status_failed{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} > 0 + for: 1h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kubernetes-resources.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kubernetes-resources.yaml new file mode 100644 index 00000000..b34b442f --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kubernetes-resources.yaml @@ -0,0 +1,121 @@ +{{- /* +Generated from 'kubernetes-resources' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubernetesResources }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubernetes-resources" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kubernetes-resources + rules: + - alert: KubeCPUOvercommit + annotations: + message: Cluster has overcommitted CPU resource requests for Pods and cannot tolerate node failure. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubecpuovercommit + expr: |- + sum(namespace_name:kube_pod_container_resource_requests_cpu_cores:sum) + / + sum(node:node_num_cpu:sum) + > + (count(node:node_num_cpu:sum)-1) / count(node:node_num_cpu:sum) + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeMemOvercommit + annotations: + message: Cluster has overcommitted memory resource requests for Pods and cannot tolerate node failure. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubememovercommit + expr: |- + sum(namespace_name:kube_pod_container_resource_requests_memory_bytes:sum) + / + sum(node_memory_MemTotal_bytes) + > + (count(node:node_num_cpu:sum)-1) + / + count(node:node_num_cpu:sum) + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeCPUOvercommit + annotations: + message: Cluster has overcommitted CPU resource requests for Namespaces. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubecpuovercommit + expr: |- + sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="cpu"}) + / + sum(node:node_num_cpu:sum) + > 1.5 + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeMemOvercommit + annotations: + message: Cluster has overcommitted memory resource requests for Namespaces. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubememovercommit + expr: |- + sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="memory"}) + / + sum(node_memory_MemTotal_bytes{job="node-exporter"}) + > 1.5 + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeQuotaExceeded + annotations: + message: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} printf "%0.0f" $value {{`}}`}}% of its {{`{{`}} $labels.resource {{`}}`}} quota. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubequotaexceeded + expr: |- + 100 * kube_resourcequota{job="kube-state-metrics", type="used"} + / ignoring(instance, job, type) + (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0) + > 90 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: CPUThrottlingHigh + annotations: + message: '{{`{{`}} printf "%0.0f" $value {{`}}`}}% throttling of CPU in namespace {{`{{`}} $labels.namespace {{`}}`}} for container {{`{{`}} $labels.container_name {{`}}`}} in pod {{`{{`}} $labels.pod_name {{`}}`}}.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-cputhrottlinghigh + expr: |- + 100 * sum(increase(container_cpu_cfs_throttled_periods_total{container_name!="", }[5m])) by (container_name, pod_name, namespace) + / + sum(increase(container_cpu_cfs_periods_total{}[5m])) by (container_name, pod_name, namespace) + > 25 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kubernetes-storage.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kubernetes-storage.yaml new file mode 100644 index 00000000..6469fffc --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kubernetes-storage.yaml @@ -0,0 +1,72 @@ +{{- /* +Generated from 'kubernetes-storage' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubernetesStorage }} +{{- $targetNamespace := .Values.defaultRules.appNamespacesTarget }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubernetes-storage" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kubernetes-storage + rules: + - alert: KubePersistentVolumeUsageCritical + annotations: + message: The PersistentVolume claimed by {{`{{`}} $labels.persistentvolumeclaim {{`}}`}} in Namespace {{`{{`}} $labels.namespace {{`}}`}} is only {{`{{`}} printf "%0.2f" $value {{`}}`}}% free. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubepersistentvolumeusagecritical + expr: |- + 100 * kubelet_volume_stats_available_bytes{job="kubelet", namespace=~"{{ $targetNamespace }}"} + / + kubelet_volume_stats_capacity_bytes{job="kubelet", namespace=~"{{ $targetNamespace }}"} + < 3 + for: 1m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubePersistentVolumeFullInFourDays + annotations: + message: Based on recent sampling, the PersistentVolume claimed by {{`{{`}} $labels.persistentvolumeclaim {{`}}`}} in Namespace {{`{{`}} $labels.namespace {{`}}`}} is expected to fill up within four days. Currently {{`{{`}} printf "%0.2f" $value {{`}}`}}% is available. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubepersistentvolumefullinfourdays + expr: |- + 100 * ( + kubelet_volume_stats_available_bytes{job="kubelet", namespace=~"{{ $targetNamespace }}"} + / + kubelet_volume_stats_capacity_bytes{job="kubelet", namespace=~"{{ $targetNamespace }}"} + ) < 15 + and + predict_linear(kubelet_volume_stats_available_bytes{job="kubelet", namespace=~"{{ $targetNamespace }}"}[6h], 4 * 24 * 3600) < 0 + for: 5m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubePersistentVolumeErrors + annotations: + message: The persistent volume {{`{{`}} $labels.persistentvolume {{`}}`}} has status {{`{{`}} $labels.phase {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubepersistentvolumeerrors + expr: kube_persistentvolume_status_phase{phase=~"Failed|Pending",job="kube-state-metrics"} > 0 + for: 5m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kubernetes-system.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kubernetes-system.yaml new file mode 100644 index 00000000..da232057 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/kubernetes-system.yaml @@ -0,0 +1,184 @@ +{{- /* +Generated from 'kubernetes-system' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubernetesSystem }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubernetes-system" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: kubernetes-system + rules: + - alert: KubeNodeNotReady + annotations: + message: '{{`{{`}} $labels.node {{`}}`}} has been unready for more than an hour.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubenodenotready + expr: kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0 + for: 1h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeVersionMismatch + annotations: + message: There are {{`{{`}} $value {{`}}`}} different semantic versions of Kubernetes components running. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeversionmismatch + expr: count(count by (gitVersion) (label_replace(kubernetes_build_info{job!~"kube-dns|coredns"},"gitVersion","$1","gitVersion","(v[0-9]*.[0-9]*.[0-9]*).*"))) > 1 + for: 1h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeClientErrors + annotations: + message: Kubernetes API server client '{{`{{`}} $labels.job {{`}}`}}/{{`{{`}} $labels.instance {{`}}`}}' is experiencing {{`{{`}} printf "%0.0f" $value {{`}}`}}% errors.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeclienterrors + expr: |- + (sum(rate(rest_client_requests_total{code=~"5.."}[5m])) by (instance, job) + / + sum(rate(rest_client_requests_total[5m])) by (instance, job)) + * 100 > 1 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeClientErrors + annotations: + message: Kubernetes API server client '{{`{{`}} $labels.job {{`}}`}}/{{`{{`}} $labels.instance {{`}}`}}' is experiencing {{`{{`}} printf "%0.0f" $value {{`}}`}} errors / second. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeclienterrors + expr: sum(rate(ksm_scrape_error_total{job="kube-state-metrics"}[5m])) by (instance, job) > 0.1 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeletTooManyPods + annotations: + message: Kubelet {{`{{`}} $labels.instance {{`}}`}} is running {{`{{`}} $value {{`}}`}} Pods, close to the limit of 110. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubelettoomanypods + expr: kubelet_running_pod_count{job="kubelet"} > 110 * 0.9 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeAPILatencyHigh + annotations: + message: The API server has a 99th percentile latency of {{`{{`}} $value {{`}}`}} seconds for {{`{{`}} $labels.verb {{`}}`}} {{`{{`}} $labels.resource {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeapilatencyhigh + expr: cluster_quantile:apiserver_request_latencies:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"^(?:LIST|WATCH|WATCHLIST|PROXY|CONNECT)$"} > 1 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeAPILatencyHigh + annotations: + message: The API server has a 99th percentile latency of {{`{{`}} $value {{`}}`}} seconds for {{`{{`}} $labels.verb {{`}}`}} {{`{{`}} $labels.resource {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeapilatencyhigh + expr: cluster_quantile:apiserver_request_latencies:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"^(?:LIST|WATCH|WATCHLIST|PROXY|CONNECT)$"} > 4 + for: 10m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeAPIErrorsHigh + annotations: + message: API server is returning errors for {{`{{`}} $value {{`}}`}}% of requests. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeapierrorshigh + expr: |- + sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m])) + / + sum(rate(apiserver_request_count{job="apiserver"}[5m])) * 100 > 3 + for: 10m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeAPIErrorsHigh + annotations: + message: API server is returning errors for {{`{{`}} $value {{`}}`}}% of requests. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeapierrorshigh + expr: |- + sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m])) + / + sum(rate(apiserver_request_count{job="apiserver"}[5m])) * 100 > 1 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeAPIErrorsHigh + annotations: + message: API server is returning errors for {{`{{`}} $value {{`}}`}}% of requests for {{`{{`}} $labels.verb {{`}}`}} {{`{{`}} $labels.resource {{`}}`}} {{`{{`}} $labels.subresource {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeapierrorshigh + expr: |- + sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m])) by (resource,subresource,verb) + / + sum(rate(apiserver_request_count{job="apiserver"}[5m])) by (resource,subresource,verb) * 100 > 10 + for: 10m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeAPIErrorsHigh + annotations: + message: API server is returning errors for {{`{{`}} $value {{`}}`}}% of requests for {{`{{`}} $labels.verb {{`}}`}} {{`{{`}} $labels.resource {{`}}`}} {{`{{`}} $labels.subresource {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeapierrorshigh + expr: |- + sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m])) by (resource,subresource,verb) + / + sum(rate(apiserver_request_count{job="apiserver"}[5m])) by (resource,subresource,verb) * 100 > 5 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeClientCertificateExpiration + annotations: + message: A client certificate used to authenticate to the apiserver is expiring in less than 7.0 days. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeclientcertificateexpiration + expr: apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 604800 + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: KubeClientCertificateExpiration + annotations: + message: A client certificate used to authenticate to the apiserver is expiring in less than 24.0 hours. + runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeclientcertificateexpiration + expr: apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 86400 + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/node-network.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/node-network.yaml new file mode 100644 index 00000000..c75f1ae0 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/node-network.yaml @@ -0,0 +1,57 @@ +{{- /* +Generated from 'node-network' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.network }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "node-network" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: node-network + rules: + - alert: NetworkReceiveErrors + annotations: + message: Network interface "{{`{{`}} $labels.device {{`}}`}}" showing receive errors on node-exporter {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}}" + expr: rate(node_network_receive_errs_total{job="node-exporter",device!~"veth.+"}[2m]) > 0 + for: 2m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NetworkTransmitErrors + annotations: + message: Network interface "{{`{{`}} $labels.device {{`}}`}}" showing transmit errors on node-exporter {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}}" + expr: rate(node_network_transmit_errs_total{job="node-exporter",device!~"veth.+"}[2m]) > 0 + for: 2m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: NodeNetworkInterfaceFlapping + annotations: + message: Network interface "{{`{{`}} $labels.device {{`}}`}}" changing it's up status often on node-exporter {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}}" + expr: changes(node_network_up{job="node-exporter",device!~"veth.+"}[2m]) > 2 + for: 2m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/node-time.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/node-time.yaml new file mode 100644 index 00000000..b7a2fc92 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/node-time.yaml @@ -0,0 +1,37 @@ +{{- /* +Generated from 'node-time' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.time }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "node-time" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: node-time + rules: + - alert: ClockSkewDetected + annotations: + message: Clock skew detected on node-exporter {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}}. Ensure NTP is configured correctly on this host. + expr: abs(node_timex_offset_seconds{job="node-exporter"}) > 0.03 + for: 2m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/node.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/node.rules.yaml new file mode 100644 index 00000000..2bc7af3a --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/node.rules.yaml @@ -0,0 +1,202 @@ +{{- /* +Generated from 'node.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.node }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "node.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: node.rules + rules: + - expr: sum(min(kube_pod_info) by (node)) + record: ':kube_pod_info_node_count:' + - expr: max(label_replace(kube_pod_info{job="kube-state-metrics"}, "pod", "$1", "pod", "(.*)")) by (node, namespace, pod) + record: 'node_namespace_pod:kube_pod_info:' + - expr: |- + count by (node) (sum by (node, cpu) ( + node_cpu_seconds_total{job="node-exporter"} + * on (namespace, pod) group_left(node) + node_namespace_pod:kube_pod_info: + )) + record: node:node_num_cpu:sum + - expr: 1 - avg(rate(node_cpu_seconds_total{job="node-exporter",mode="idle"}[1m])) + record: :node_cpu_utilisation:avg1m + - expr: |- + 1 - avg by (node) ( + rate(node_cpu_seconds_total{job="node-exporter",mode="idle"}[1m]) + * on (namespace, pod) group_left(node) + node_namespace_pod:kube_pod_info:) + record: node:node_cpu_utilisation:avg1m + - expr: |- + node:node_cpu_utilisation:avg1m + * + node:node_num_cpu:sum + / + scalar(sum(node:node_num_cpu:sum)) + record: node:cluster_cpu_utilisation:ratio + - expr: |- + sum(node_load1{job="node-exporter"}) + / + sum(node:node_num_cpu:sum) + record: ':node_cpu_saturation_load1:' + - expr: |- + sum by (node) ( + node_load1{job="node-exporter"} + * on (namespace, pod) group_left(node) + node_namespace_pod:kube_pod_info: + ) + / + node:node_num_cpu:sum + record: 'node:node_cpu_saturation_load1:' + - expr: |- + 1 - + sum(node_memory_MemFree_bytes{job="node-exporter"} + node_memory_Cached_bytes{job="node-exporter"} + node_memory_Buffers_bytes{job="node-exporter"}) + / + sum(node_memory_MemTotal_bytes{job="node-exporter"}) + record: ':node_memory_utilisation:' + - expr: sum(node_memory_MemFree_bytes{job="node-exporter"} + node_memory_Cached_bytes{job="node-exporter"} + node_memory_Buffers_bytes{job="node-exporter"}) + record: :node_memory_MemFreeCachedBuffers_bytes:sum + - expr: sum(node_memory_MemTotal_bytes{job="node-exporter"}) + record: :node_memory_MemTotal_bytes:sum + - expr: |- + sum by (node) ( + (node_memory_MemFree_bytes{job="node-exporter"} + node_memory_Cached_bytes{job="node-exporter"} + node_memory_Buffers_bytes{job="node-exporter"}) + * on (namespace, pod) group_left(node) + node_namespace_pod:kube_pod_info: + ) + record: node:node_memory_bytes_available:sum + - expr: |- + sum by (node) ( + node_memory_MemTotal_bytes{job="node-exporter"} + * on (namespace, pod) group_left(node) + node_namespace_pod:kube_pod_info: + ) + record: node:node_memory_bytes_total:sum + - expr: |- + (node:node_memory_bytes_total:sum - node:node_memory_bytes_available:sum) + / + node:node_memory_bytes_total:sum + record: node:node_memory_utilisation:ratio + - expr: |- + (node:node_memory_bytes_total:sum - node:node_memory_bytes_available:sum) + / + scalar(sum(node:node_memory_bytes_total:sum)) + record: node:cluster_memory_utilisation:ratio + - expr: |- + 1e3 * sum( + (rate(node_vmstat_pgpgin{job="node-exporter"}[1m]) + + rate(node_vmstat_pgpgout{job="node-exporter"}[1m])) + ) + record: :node_memory_swap_io_bytes:sum_rate + - expr: |- + 1 - + sum by (node) ( + (node_memory_MemFree_bytes{job="node-exporter"} + node_memory_Cached_bytes{job="node-exporter"} + node_memory_Buffers_bytes{job="node-exporter"}) + * on (namespace, pod) group_left(node) + node_namespace_pod:kube_pod_info: + ) + / + sum by (node) ( + node_memory_MemTotal_bytes{job="node-exporter"} + * on (namespace, pod) group_left(node) + node_namespace_pod:kube_pod_info: + ) + record: 'node:node_memory_utilisation:' + - expr: 1 - (node:node_memory_bytes_available:sum / node:node_memory_bytes_total:sum) + record: 'node:node_memory_utilisation_2:' + - expr: |- + 1e3 * sum by (node) ( + (rate(node_vmstat_pgpgin{job="node-exporter"}[1m]) + + rate(node_vmstat_pgpgout{job="node-exporter"}[1m])) + * on (namespace, pod) group_left(node) + node_namespace_pod:kube_pod_info: + ) + record: node:node_memory_swap_io_bytes:sum_rate + - expr: avg(irate(node_disk_io_time_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m])) + record: :node_disk_utilisation:avg_irate + - expr: |- + avg by (node) ( + irate(node_disk_io_time_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m]) + * on (namespace, pod) group_left(node) + node_namespace_pod:kube_pod_info: + ) + record: node:node_disk_utilisation:avg_irate + - expr: avg(irate(node_disk_io_time_weighted_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m])) + record: :node_disk_saturation:avg_irate + - expr: |- + avg by (node) ( + irate(node_disk_io_time_weighted_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m]) + * on (namespace, pod) group_left(node) + node_namespace_pod:kube_pod_info: + ) + record: node:node_disk_saturation:avg_irate + - expr: |- + max by (instance, namespace, pod, device) ((node_filesystem_size_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"} + - node_filesystem_avail_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"}) + / node_filesystem_size_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"}) + record: 'node:node_filesystem_usage:' + - expr: max by (instance, namespace, pod, device) (node_filesystem_avail_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"} / node_filesystem_size_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"}) + record: 'node:node_filesystem_avail:' + - expr: |- + sum(irate(node_network_receive_bytes_total{job="node-exporter",device!~"veth.+"}[1m])) + + sum(irate(node_network_transmit_bytes_total{job="node-exporter",device!~"veth.+"}[1m])) + record: :node_net_utilisation:sum_irate + - expr: |- + sum by (node) ( + (irate(node_network_receive_bytes_total{job="node-exporter",device!~"veth.+"}[1m]) + + irate(node_network_transmit_bytes_total{job="node-exporter",device!~"veth.+"}[1m])) + * on (namespace, pod) group_left(node) + node_namespace_pod:kube_pod_info: + ) + record: node:node_net_utilisation:sum_irate + - expr: |- + sum(irate(node_network_receive_drop_total{job="node-exporter",device!~"veth.+"}[1m])) + + sum(irate(node_network_transmit_drop_total{job="node-exporter",device!~"veth.+"}[1m])) + record: :node_net_saturation:sum_irate + - expr: |- + sum by (node) ( + (irate(node_network_receive_drop_total{job="node-exporter",device!~"veth.+"}[1m]) + + irate(node_network_transmit_drop_total{job="node-exporter",device!~"veth.+"}[1m])) + * on (namespace, pod) group_left(node) + node_namespace_pod:kube_pod_info: + ) + record: node:node_net_saturation:sum_irate + - expr: |- + max( + max( + kube_pod_info{job="kube-state-metrics", host_ip!=""} + ) by (node, host_ip) + * on (host_ip) group_right (node) + label_replace( + (max(node_filesystem_files{job="node-exporter", mountpoint="/"}) by (instance)), "host_ip", "$1", "instance", "(.*):.*" + ) + ) by (node) + record: 'node:node_inodes_total:' + - expr: |- + max( + max( + kube_pod_info{job="kube-state-metrics", host_ip!=""} + ) by (node, host_ip) + * on (host_ip) group_right (node) + label_replace( + (max(node_filesystem_files_free{job="node-exporter", mountpoint="/"}) by (instance)), "host_ip", "$1", "instance", "(.*):.*" + ) + ) by (node) + record: 'node:node_inodes_free:' +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/prometheus-operator.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/prometheus-operator.yaml new file mode 100644 index 00000000..a8a8915b --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/prometheus-operator.yaml @@ -0,0 +1,49 @@ +{{- /* +Generated from 'prometheus-operator' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.prometheusOperator }} +{{- $operatorJob := printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "operator" }} +{{- $namespace := printf "%s" (include "kube-prometheus-stack.namespace" .) }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "prometheus-operator" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: prometheus-operator + rules: + - alert: PrometheusOperatorReconcileErrors + annotations: + message: Errors while reconciling {{`{{`}} $labels.controller {{`}}`}} in {{`{{`}} $labels.namespace {{`}}`}} Namespace. + expr: rate(prometheus_operator_reconcile_errors_total{job="{{ $operatorJob }}",namespace="{{ $namespace }}"}[5m]) > 0.1 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusOperatorNodeLookupErrors + annotations: + message: Errors while reconciling Prometheus in {{`{{`}} $labels.namespace {{`}}`}} Namespace. + expr: rate(prometheus_operator_node_address_lookup_errors_total{job="{{ $operatorJob }}",namespace="{{ $namespace }}"}[5m]) > 0.1 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/prometheus.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/prometheus.rules.yaml new file mode 100644 index 00000000..0480c83b --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules/prometheus.rules.yaml @@ -0,0 +1,139 @@ +{{- /* +Generated from 'prometheus.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/manifests/prometheus-rules.yaml +Do not change in-place! In order to change this file first read following link: +https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack +*/ -}} +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if and (semverCompare ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.prometheus }} +{{- $prometheusJob := printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "prometheus" }} +{{- $namespace := printf "%s" (include "kube-prometheus-stack.namespace" .) }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "prometheus.rules" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: prometheus.rules + rules: + - alert: PrometheusConfigReloadFailed + annotations: + description: Reloading Prometheus' configuration has failed for {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} + summary: Reloading Prometheus' configuration failed + expr: prometheus_config_last_reload_successful{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"} == 0 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusNotificationQueueRunningFull + annotations: + description: Prometheus' alert notification queue is running full for {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}} $labels.pod{{`}}`}} + summary: Prometheus' alert notification queue is running full + expr: predict_linear(prometheus_notifications_queue_length{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m], 60 * 30) > prometheus_notifications_queue_capacity{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"} + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusErrorSendingAlerts + annotations: + description: Errors while sending alerts from Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}} $labels.pod{{`}}`}} to Alertmanager {{`{{`}}$labels.Alertmanager{{`}}`}} + summary: Errors while sending alert from Prometheus + expr: rate(prometheus_notifications_errors_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) / rate(prometheus_notifications_sent_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0.01 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusErrorSendingAlerts + annotations: + description: Errors while sending alerts from Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}} $labels.pod{{`}}`}} to Alertmanager {{`{{`}}$labels.Alertmanager{{`}}`}} + summary: Errors while sending alerts from Prometheus + expr: rate(prometheus_notifications_errors_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) / rate(prometheus_notifications_sent_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0.03 + for: 10m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusNotConnectedToAlertmanagers + annotations: + description: Prometheus {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod{{`}}`}} is not connected to any Alertmanagers + summary: Prometheus is not connected to any Alertmanagers + expr: prometheus_notifications_alertmanagers_discovered{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"} < 1 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusTSDBReloadsFailing + annotations: + description: '{{`{{`}}$labels.job{{`}}`}} at {{`{{`}}$labels.instance{{`}}`}} had {{`{{`}}$value | humanize{{`}}`}} reload failures over the last four hours.' + summary: Prometheus has issues reloading data blocks from disk + expr: increase(prometheus_tsdb_reloads_failures_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[2h]) > 0 + for: 12h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusTSDBCompactionsFailing + annotations: + description: '{{`{{`}}$labels.job{{`}}`}} at {{`{{`}}$labels.instance{{`}}`}} had {{`{{`}}$value | humanize{{`}}`}} compaction failures over the last four hours.' + summary: Prometheus has issues compacting sample blocks + expr: increase(prometheus_tsdb_compactions_failed_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[2h]) > 0 + for: 12h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusTSDBWALCorruptions + annotations: + description: '{{`{{`}}$labels.job{{`}}`}} at {{`{{`}}$labels.instance{{`}}`}} has a corrupted write-ahead log (WAL).' + summary: Prometheus write-ahead log is corrupted + expr: prometheus_tsdb_wal_corruptions_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"} > 0 + for: 4h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusNotIngestingSamples + annotations: + description: Prometheus {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod{{`}}`}} isn't ingesting samples. + summary: Prometheus isn't ingesting samples + expr: rate(prometheus_tsdb_head_samples_appended_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) <= 0 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} + - alert: PrometheusTargetScrapesDuplicate + annotations: + description: '{{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has many samples rejected due to duplicate timestamps but different values' + summary: Prometheus has many samples rejected + expr: increase(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/service.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/service.yaml new file mode 100644 index 00000000..cb831c7a --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/service.yaml @@ -0,0 +1,52 @@ +{{- if .Values.prometheus.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-prometheus + self-monitor: {{ .Values.prometheus.serviceMonitor.selfMonitor | quote }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.prometheus.service.labels }} +{{ toYaml .Values.prometheus.service.labels | indent 4 }} +{{- end }} +{{- if .Values.prometheus.service.annotations }} + annotations: +{{ toYaml .Values.prometheus.service.annotations | indent 4 }} +{{- end }} +spec: +{{- if .Values.prometheus.service.clusterIP }} + clusterIP: {{ .Values.prometheus.service.clusterIP }} +{{- end }} +{{- if .Values.prometheus.service.externalIPs }} + externalIPs: +{{ toYaml .Values.prometheus.service.externalIPs | indent 4 }} +{{- end }} +{{- if .Values.prometheus.service.loadBalancerIP }} + loadBalancerIP: {{ .Values.prometheus.service.loadBalancerIP }} +{{- end }} +{{- if .Values.prometheus.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: + {{- range $cidr := .Values.prometheus.service.loadBalancerSourceRanges }} + - {{ $cidr }} + {{- end }} +{{- end }} + ports: + - name: {{ .Values.prometheus.prometheusSpec.portName }} + {{- if eq .Values.prometheus.service.type "NodePort" }} + nodePort: {{ .Values.prometheus.service.nodePort }} + {{- end }} + port: {{ .Values.prometheus.service.port }} + targetPort: {{ .Values.prometheus.service.targetPort }} +{{- if .Values.prometheus.service.additionalPorts }} +{{ toYaml .Values.prometheus.service.additionalPorts | indent 2 }} +{{- end }} + selector: + app: prometheus + prometheus: {{ template "kube-prometheus-stack.fullname" . }}-prometheus +{{- if .Values.prometheus.service.sessionAffinity }} + sessionAffinity: {{ .Values.prometheus.service.sessionAffinity }} +{{- end }} + type: "{{ .Values.prometheus.service.type }}" +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/serviceaccount.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/serviceaccount.yaml new file mode 100644 index 00000000..862d5f8e --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/serviceaccount.yaml @@ -0,0 +1,16 @@ +{{- if and .Values.prometheus.enabled .Values.prometheus.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ template "kube-prometheus-stack.prometheus.serviceAccountName" . }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-prometheus +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.prometheus.serviceAccount.annotations }} + annotations: +{{ toYaml .Values.prometheus.serviceAccount.annotations | indent 4 }} +{{- end }} +imagePullSecrets: +{{ toYaml .Values.global.imagePullSecrets | indent 2 }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/servicemonitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/servicemonitor.yaml new file mode 100644 index 00000000..356c013f --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/servicemonitor.yaml @@ -0,0 +1,42 @@ +{{- if and .Values.prometheus.enabled .Values.prometheus.serviceMonitor.selfMonitor }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-prometheus +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +spec: + selector: + matchLabels: + app: {{ template "kube-prometheus-stack.name" . }}-prometheus + release: {{ $.Release.Name | quote }} + self-monitor: "true" + namespaceSelector: + matchNames: + - {{ printf "%s" (include "kube-prometheus-stack.namespace" .) | quote }} + endpoints: + - port: {{ .Values.prometheus.prometheusSpec.portName }} + {{- if .Values.prometheus.serviceMonitor.interval }} + interval: {{ .Values.prometheus.serviceMonitor.interval }} + {{- end }} + {{- if .Values.prometheus.serviceMonitor.scheme }} + scheme: {{ .Values.prometheus.serviceMonitor.scheme }} + {{- end }} + {{- if .Values.prometheus.serviceMonitor.tlsConfig }} + tlsConfig: {{ toYaml .Values.prometheus.serviceMonitor.tlsConfig | nindent 6 }} + {{- end }} + {{- if .Values.prometheus.serviceMonitor.bearerTokenFile }} + bearerTokenFile: {{ .Values.prometheus.serviceMonitor.bearerTokenFile }} + {{- end }} + path: "{{ trimSuffix "/" .Values.prometheus.prometheusSpec.routePrefix }}/metrics" +{{- if .Values.prometheus.serviceMonitor.metricRelabelings }} + metricRelabelings: +{{ tpl (toYaml .Values.prometheus.serviceMonitor.metricRelabelings | indent 6) . }} +{{- end }} +{{- if .Values.prometheus.serviceMonitor.relabelings }} + relabelings: +{{ toYaml .Values.prometheus.serviceMonitor.relabelings | indent 6 }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/servicemonitors.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/servicemonitors.yaml new file mode 100644 index 00000000..959df212 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/servicemonitors.yaml @@ -0,0 +1,34 @@ +{{- if and .Values.prometheus.enabled .Values.prometheus.additionalServiceMonitors }} +apiVersion: v1 +kind: List +items: +{{- range .Values.prometheus.additionalServiceMonitors }} + - apiVersion: monitoring.coreos.com/v1 + kind: ServiceMonitor + metadata: + name: {{ .name }} + namespace: {{ template "kube-prometheus-stack.namespace" $ }} + labels: + app: {{ template "kube-prometheus-stack.name" $ }}-prometheus +{{ include "kube-prometheus-stack.labels" $ | indent 8 }} + {{- if .additionalLabels }} +{{ toYaml .additionalLabels | indent 8 }} + {{- end }} + spec: + endpoints: +{{ toYaml .endpoints | indent 8 }} + {{- if .jobLabel }} + jobLabel: {{ .jobLabel }} + {{- end }} + {{- if .namespaceSelector }} + namespaceSelector: +{{ toYaml .namespaceSelector | indent 8 }} + {{- end }} + selector: +{{ toYaml .selector | indent 8 }} + {{- if .targetLabels }} + targetLabels: +{{ toYaml .targetLabels | indent 8 }} + {{- end }} +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/serviceperreplica.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/serviceperreplica.yaml new file mode 100644 index 00000000..1a554336 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/serviceperreplica.yaml @@ -0,0 +1,46 @@ +{{- if and .Values.prometheus.enabled .Values.prometheus.servicePerReplica.enabled }} +{{- $count := .Values.prometheus.prometheusSpec.replicas | int -}} +{{- $serviceValues := .Values.prometheus.servicePerReplica -}} +apiVersion: v1 +kind: List +metadata: + name: {{ include "kube-prometheus-stack.fullname" $ }}-prometheus-serviceperreplica + namespace: {{ template "kube-prometheus-stack.namespace" . }} +items: +{{- range $i, $e := until $count }} + - apiVersion: v1 + kind: Service + metadata: + name: {{ include "kube-prometheus-stack.fullname" $ }}-prometheus-{{ $i }} + namespace: {{ template "kube-prometheus-stack.namespace" $ }} + labels: + app: {{ include "kube-prometheus-stack.name" $ }}-prometheus +{{ include "kube-prometheus-stack.labels" $ | indent 8 }} + {{- if $serviceValues.annotations }} + annotations: +{{ toYaml $serviceValues.annotations | indent 8 }} + {{- end }} + spec: + {{- if $serviceValues.clusterIP }} + clusterIP: {{ $serviceValues.clusterIP }} + {{- end }} + {{- if $serviceValues.loadBalancerSourceRanges }} + loadBalancerSourceRanges: + {{- range $cidr := $serviceValues.loadBalancerSourceRanges }} + - {{ $cidr }} + {{- end }} + {{- end }} + ports: + - name: {{ $.Values.prometheus.prometheusSpec.portName }} + {{- if eq $serviceValues.type "NodePort" }} + nodePort: {{ $serviceValues.nodePort }} + {{- end }} + port: {{ $serviceValues.port }} + targetPort: {{ $serviceValues.targetPort }} + selector: + app: prometheus + prometheus: {{ include "kube-prometheus-stack.fullname" $ }}-prometheus + statefulset.kubernetes.io/pod-name: prometheus-{{ include "kube-prometheus-stack.fullname" $ }}-prometheus-{{ $i }} + type: "{{ $serviceValues.type }}" +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/values.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/values.yaml new file mode 100644 index 00000000..3aa810fa --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/values.yaml @@ -0,0 +1,2272 @@ +# Default values for kube-prometheus-stack. +# This is a YAML-formatted file. +# Declare variables to be passed into your templates. + +## Provide a name in place of kube-prometheus-stack for `app:` labels +## +nameOverride: "" + +## Override the deployment namespace +## +namespaceOverride: "" + +## Provide a k8s version to auto dashboard import script example: kubeTargetVersionOverride: 1.16.6 +## +kubeTargetVersionOverride: "" + +## Provide a name to substitute for the full names of resources +## +fullnameOverride: "" + +## Labels to apply to all resources +## +commonLabels: {} +# scmhash: abc123 +# myLabel: aakkmd + +## Create default rules for monitoring the cluster +## +defaultRules: + create: true + rules: + alertmanager: true + etcd: true + general: true + k8s: true + kubeApiserver: true + kubeApiserverAvailability: true + kubeApiserverError: true + kubeApiserverSlos: true + kubelet: true + kubePrometheusGeneral: true + kubePrometheusNodeAlerting: true + kubePrometheusNodeRecording: true + kubernetesAbsent: true + kubernetesApps: true + kubernetesResources: true + kubernetesStorage: true + kubernetesSystem: true + kubeScheduler: true + kubeStateMetrics: true + network: true + node: true + prometheus: true + prometheusOperator: true + time: true + + ## Runbook url prefix for default rules + runbookUrl: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md# + ## Reduce app namespace alert scope + appNamespacesTarget: ".*" + + ## Labels for default rules + labels: {} + ## Annotations for default rules + annotations: {} + + ## Additional labels for PrometheusRule alerts + additionalRuleLabels: {} + +## Deprecated way to provide custom recording or alerting rules to be deployed into the cluster. +## +# additionalPrometheusRules: [] +# - name: my-rule-file +# groups: +# - name: my_group +# rules: +# - record: my_record +# expr: 100 * my_record + +## Provide custom recording or alerting rules to be deployed into the cluster. +## +additionalPrometheusRulesMap: {} +# rule-name: +# groups: +# - name: my_group +# rules: +# - record: my_record +# expr: 100 * my_record + +## +global: + rbac: + create: true + pspEnabled: true + pspAnnotations: {} + ## Specify pod annotations + ## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/#apparmor + ## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/#seccomp + ## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/#sysctl + ## + # seccomp.security.alpha.kubernetes.io/allowedProfileNames: '*' + # seccomp.security.alpha.kubernetes.io/defaultProfileName: 'docker/default' + # apparmor.security.beta.kubernetes.io/defaultProfileName: 'runtime/default' + + ## Reference to one or more secrets to be used when pulling images + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## + imagePullSecrets: [] + # - name: "image-pull-secret" + +## Configuration for alertmanager +## ref: https://prometheus.io/docs/alerting/alertmanager/ +## +alertmanager: + + ## Deploy alertmanager + ## + enabled: true + + ## Api that prometheus will use to communicate with alertmanager. Possible values are v1, v2 + ## + apiVersion: v2 + + ## Service account for Alertmanager to use. + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/ + ## + serviceAccount: + create: true + name: "" + annotations: {} + + ## Configure pod disruption budgets for Alertmanager + ## ref: https://kubernetes.io/docs/tasks/run-application/configure-pdb/#specifying-a-poddisruptionbudget + ## This configuration is immutable once created and will require the PDB to be deleted to be changed + ## https://github.com/kubernetes/kubernetes/issues/45398 + ## + podDisruptionBudget: + enabled: false + minAvailable: 1 + maxUnavailable: "" + + ## Alertmanager configuration directives + ## ref: https://prometheus.io/docs/alerting/configuration/#configuration-file + ## https://prometheus.io/webtools/alerting/routing-tree-editor/ + ## + config: + global: + resolve_timeout: 5m + route: + group_by: ['job'] + group_wait: 30s + group_interval: 5m + repeat_interval: 12h + receiver: 'null' + routes: + - match: + alertname: Watchdog + receiver: 'null' + receivers: + - name: 'null' + + ## Pass the Alertmanager configuration directives through Helm's templating + ## engine. If the Alertmanager configuration contains Alertmanager templates, + ## they'll need to be properly escaped so that they are not interpreted by + ## Helm + ## ref: https://helm.sh/docs/developing_charts/#using-the-tpl-function + ## https://prometheus.io/docs/alerting/configuration/#tmpl_string + ## https://prometheus.io/docs/alerting/notifications/ + ## https://prometheus.io/docs/alerting/notification_examples/ + tplConfig: false + + ## Alertmanager template files to format alerts + ## ref: https://prometheus.io/docs/alerting/notifications/ + ## https://prometheus.io/docs/alerting/notification_examples/ + ## + templateFiles: {} + # + ## An example template: + # template_1.tmpl: |- + # {{ define "cluster" }}{{ .ExternalURL | reReplaceAll ".*alertmanager\\.(.*)" "$1" }}{{ end }} + # + # {{ define "slack.myorg.text" }} + # {{- $root := . -}} + # {{ range .Alerts }} + # *Alert:* {{ .Annotations.summary }} - `{{ .Labels.severity }}` + # *Cluster:* {{ template "cluster" $root }} + # *Description:* {{ .Annotations.description }} + # *Graph:* <{{ .GeneratorURL }}|:chart_with_upwards_trend:> + # *Runbook:* <{{ .Annotations.runbook }}|:spiral_note_pad:> + # *Details:* + # {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}` + # {{ end }} + # {{ end }} + # {{ end }} + + ingress: + enabled: false + + # For Kubernetes >= 1.18 you should specify the ingress-controller via the field ingressClassName + # See https://kubernetes.io/blog/2020/04/02/improvements-to-the-ingress-api-in-kubernetes-1.18/#specifying-the-class-of-an-ingress + # ingressClassName: nginx + + annotations: {} + + labels: {} + + ## Hosts must be provided if Ingress is enabled. + ## + hosts: [] + # - alertmanager.domain.com + + ## Paths to use for ingress rules - one path should match the alertmanagerSpec.routePrefix + ## + paths: [] + # - / + + ## TLS configuration for Alertmanager Ingress + ## Secret must be manually created in the namespace + ## + tls: [] + # - secretName: alertmanager-general-tls + # hosts: + # - alertmanager.example.com + + ## Configuration for Alertmanager secret + ## + secret: + annotations: {} + + ## Configuration for creating an Ingress that will map to each Alertmanager replica service + ## alertmanager.servicePerReplica must be enabled + ## + ingressPerReplica: + enabled: false + + # For Kubernetes >= 1.18 you should specify the ingress-controller via the field ingressClassName + # See https://kubernetes.io/blog/2020/04/02/improvements-to-the-ingress-api-in-kubernetes-1.18/#specifying-the-class-of-an-ingress + # ingressClassName: nginx + + annotations: {} + labels: {} + + ## Final form of the hostname for each per replica ingress is + ## {{ ingressPerReplica.hostPrefix }}-{{ $replicaNumber }}.{{ ingressPerReplica.hostDomain }} + ## + ## Prefix for the per replica ingress that will have `-$replicaNumber` + ## appended to the end + hostPrefix: "" + ## Domain that will be used for the per replica ingress + hostDomain: "" + + ## Paths to use for ingress rules + ## + paths: [] + # - / + + ## Secret name containing the TLS certificate for alertmanager per replica ingress + ## Secret must be manually created in the namespace + tlsSecretName: "" + + ## Separated secret for each per replica Ingress. Can be used together with cert-manager + ## + tlsSecretPerReplica: + enabled: false + ## Final form of the secret for each per replica ingress is + ## {{ tlsSecretPerReplica.prefix }}-{{ $replicaNumber }} + ## + prefix: "alertmanager" + + ## Configuration for Alertmanager service + ## + service: + annotations: {} + labels: {} + clusterIP: "" + + ## Port for Alertmanager Service to listen on + ## + port: 9093 + ## To be used with a proxy extraContainer port + ## + targetPort: 9093 + ## Port to expose on each node + ## Only used if service.type is 'NodePort' + ## + nodePort: 30903 + ## List of IP addresses at which the Prometheus server service is available + ## Ref: https://kubernetes.io/docs/user-guide/services/#external-ips + ## + + ## Additional ports to open for Alertmanager service + additionalPorts: [] + + externalIPs: [] + loadBalancerIP: "" + loadBalancerSourceRanges: [] + ## Service type + ## + type: ClusterIP + + ## Configuration for creating a separate Service for each statefulset Alertmanager replica + ## + servicePerReplica: + enabled: false + annotations: {} + + ## Port for Alertmanager Service per replica to listen on + ## + port: 9093 + + ## To be used with a proxy extraContainer port + targetPort: 9093 + + ## Port to expose on each node + ## Only used if servicePerReplica.type is 'NodePort' + ## + nodePort: 30904 + + ## Loadbalancer source IP ranges + ## Only used if servicePerReplica.type is "loadbalancer" + loadBalancerSourceRanges: [] + ## Service type + ## + type: ClusterIP + + ## If true, create a serviceMonitor for alertmanager + ## + serviceMonitor: + ## Scrape interval. If not set, the Prometheus default scrape interval is used. + ## + interval: "" + selfMonitor: true + + ## scheme: HTTP scheme to use for scraping. Can be used with `tlsConfig` for example if using istio mTLS. + scheme: "" + + ## tlsConfig: TLS configuration to use when scraping the endpoint. For example if using istio mTLS. + ## Of type: https://github.com/coreos/prometheus-operator/blob/master/Documentation/api.md#tlsconfig + tlsConfig: {} + + bearerTokenFile: + + ## metric relabel configs to apply to samples before ingestion. + ## + metricRelabelings: [] + # - action: keep + # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+' + # sourceLabels: [__name__] + + # relabel configs to apply to samples before ingestion. + ## + relabelings: [] + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + + ## Settings affecting alertmanagerSpec + ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#alertmanagerspec + ## + alertmanagerSpec: + ## Standard object’s metadata. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#metadata + ## Metadata Labels and Annotations gets propagated to the Alertmanager pods. + ## + podMetadata: {} + + ## Image of Alertmanager + ## + image: + repository: quay.io/prometheus/alertmanager + tag: v0.21.0 + sha: "" + + ## If true then the user will be responsible to provide a secret with alertmanager configuration + ## So when true the config part will be ignored (including templateFiles) and the one in the secret will be used + ## + useExistingSecret: false + + ## Secrets is a list of Secrets in the same namespace as the Alertmanager object, which shall be mounted into the + ## Alertmanager Pods. The Secrets are mounted into /etc/alertmanager/secrets/. + ## + secrets: [] + + ## ConfigMaps is a list of ConfigMaps in the same namespace as the Alertmanager object, which shall be mounted into the Alertmanager Pods. + ## The ConfigMaps are mounted into /etc/alertmanager/configmaps/. + ## + configMaps: [] + + ## ConfigSecret is the name of a Kubernetes Secret in the same namespace as the Alertmanager object, which contains configuration for + ## this Alertmanager instance. Defaults to 'alertmanager-' The secret is mounted into /etc/alertmanager/config. + ## + # configSecret: + + ## AlertmanagerConfigs to be selected to merge and configure Alertmanager with. + ## + alertmanagerConfigSelector: {} + ## Example which selects all alertmanagerConfig resources + ## with label "alertconfig" with values any of "example-config" or "example-config-2" + # alertmanagerConfigSelector: + # matchExpressions: + # - key: alertconfig + # operator: In + # values: + # - example-config + # - example-config-2 + # + ## Example which selects all alertmanagerConfig resources with label "role" set to "example-config" + # alertmanagerConfigSelector: + # matchLabels: + # role: example-config + + ## Namespaces to be selected for AlertmanagerConfig discovery. If nil, only check own namespace. + ## + alertmanagerConfigNamespaceSelector: {} + ## Example which selects all namespaces + ## with label "alertmanagerconfig" with values any of "example-namespace" or "example-namespace-2" + # alertmanagerConfigNamespaceSelector: + # matchExpressions: + # - key: alertmanagerconfig + # operator: In + # values: + # - example-namespace + # - example-namespace-2 + + ## Example which selects all namespaces with label "alertmanagerconfig" set to "enabled" + # alertmanagerConfigNamespaceSelector: + # matchLabels: + # alertmanagerconfig: enabled + + ## Define Log Format + # Use logfmt (default) or json logging + logFormat: logfmt + + ## Log level for Alertmanager to be configured with. + ## + logLevel: info + + ## Size is the expected size of the alertmanager cluster. The controller will eventually make the size of the + ## running cluster equal to the expected size. + replicas: 1 + + ## Time duration Alertmanager shall retain data for. Default is '120h', and must match the regular expression + ## [0-9]+(ms|s|m|h) (milliseconds seconds minutes hours). + ## + retention: 120h + + ## Storage is the definition of how storage will be used by the Alertmanager instances. + ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/user-guides/storage.md + ## + storage: {} + # volumeClaimTemplate: + # spec: + # storageClassName: gluster + # accessModes: ["ReadWriteOnce"] + # resources: + # requests: + # storage: 50Gi + # selector: {} + + + ## The external URL the Alertmanager instances will be available under. This is necessary to generate correct URLs. This is necessary if Alertmanager is not served from root of a DNS name. string false + ## + externalUrl: + + ## The route prefix Alertmanager registers HTTP handlers for. This is useful, if using ExternalURL and a proxy is rewriting HTTP routes of a request, and the actual ExternalURL is still true, + ## but the server serves requests under a different route prefix. For example for use with kubectl proxy. + ## + routePrefix: / + + ## If set to true all actions on the underlying managed objects are not going to be performed, except for delete actions. + ## + paused: false + + ## Define which Nodes the Pods are scheduled on. + ## ref: https://kubernetes.io/docs/user-guide/node-selection/ + ## + nodeSelector: {} + + ## Define resources requests and limits for single Pods. + ## ref: https://kubernetes.io/docs/user-guide/compute-resources/ + ## + resources: {} + # requests: + # memory: 400Mi + + ## Pod anti-affinity can prevent the scheduler from placing Prometheus replicas on the same node. + ## The default value "soft" means that the scheduler should *prefer* to not schedule two replica pods onto the same node but no guarantee is provided. + ## The value "hard" means that the scheduler is *required* to not schedule two replica pods onto the same node. + ## The value "" will disable pod anti-affinity so that no anti-affinity rules will be configured. + ## + podAntiAffinity: "" + + ## If anti-affinity is enabled sets the topologyKey to use for anti-affinity. + ## This can be changed to, for example, failure-domain.beta.kubernetes.io/zone + ## + podAntiAffinityTopologyKey: kubernetes.io/hostname + + ## Assign custom affinity rules to the alertmanager instance + ## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/ + ## + affinity: {} + # nodeAffinity: + # requiredDuringSchedulingIgnoredDuringExecution: + # nodeSelectorTerms: + # - matchExpressions: + # - key: kubernetes.io/e2e-az-name + # operator: In + # values: + # - e2e-az1 + # - e2e-az2 + + ## If specified, the pod's tolerations. + ## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ + ## + tolerations: [] + # - key: "key" + # operator: "Equal" + # value: "value" + # effect: "NoSchedule" + + ## SecurityContext holds pod-level security attributes and common container settings. + ## This defaults to non root user with uid 1000 and gid 2000. *v1.PodSecurityContext false + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/ + ## + securityContext: + runAsGroup: 2000 + runAsNonRoot: true + runAsUser: 1000 + fsGroup: 2000 + + ## ListenLocal makes the Alertmanager server listen on loopback, so that it does not bind against the Pod IP. + ## Note this is only for the Alertmanager UI, not the gossip communication. + ## + listenLocal: false + + ## Containers allows injecting additional containers. This is meant to allow adding an authentication proxy to an Alertmanager pod. + ## + containers: [] + + # Additional volumes on the output StatefulSet definition. + volumes: [] + + # Additional VolumeMounts on the output StatefulSet definition. + volumeMounts: [] + + ## InitContainers allows injecting additional initContainers. This is meant to allow doing some changes + ## (permissions, dir tree) on mounted volumes before starting prometheus + initContainers: [] + + ## Priority class assigned to the Pods + ## + priorityClassName: "" + + ## AdditionalPeers allows injecting a set of additional Alertmanagers to peer with to form a highly available cluster. + ## + additionalPeers: [] + + ## PortName to use for Alert Manager. + ## + portName: "web" + + ## ClusterAdvertiseAddress is the explicit address to advertise in cluster. Needs to be provided for non RFC1918 [1] (public) addresses. [1] RFC1918: https://tools.ietf.org/html/rfc1918 + ## + clusterAdvertiseAddress: false + + ## ForceEnableClusterMode ensures Alertmanager does not deactivate the cluster mode when running with a single replica. + ## Use case is e.g. spanning an Alertmanager cluster across Kubernetes clusters with a single replica in each. + forceEnableClusterMode: false + + +## Using default values from https://github.com/grafana/helm-charts/blob/main/charts/grafana/values.yaml +## +grafana: + enabled: true + namespaceOverride: "" + + ## Deploy default dashboards. + ## + defaultDashboardsEnabled: true + + adminPassword: prom-operator + + ingress: + ## If true, Grafana Ingress will be created + ## + enabled: false + + ## Annotations for Grafana Ingress + ## + annotations: {} + # kubernetes.io/ingress.class: nginx + # kubernetes.io/tls-acme: "true" + + ## Labels to be added to the Ingress + ## + labels: {} + + ## Hostnames. + ## Must be provided if Ingress is enable. + ## + # hosts: + # - grafana.domain.com + hosts: [] + + ## Path for grafana ingress + path: / + + ## TLS configuration for grafana Ingress + ## Secret must be manually created in the namespace + ## + tls: [] + # - secretName: grafana-general-tls + # hosts: + # - grafana.example.com + + sidecar: + dashboards: + enabled: true + label: grafana_dashboard + + ## Annotations for Grafana dashboard configmaps + ## + annotations: {} + multicluster: false + datasources: + enabled: true + defaultDatasourceEnabled: true + + ## Annotations for Grafana datasource configmaps + ## + annotations: {} + + ## Create datasource for each Pod of Prometheus StatefulSet; + ## this uses headless service `prometheus-operated` which is + ## created by Prometheus Operator + ## ref: https://git.io/fjaBS + createPrometheusReplicasDatasources: false + label: grafana_datasource + + extraConfigmapMounts: [] + # - name: certs-configmap + # mountPath: /etc/grafana/ssl/ + # configMap: certs-configmap + # readOnly: true + + ## Configure additional grafana datasources (passed through tpl) + ## ref: http://docs.grafana.org/administration/provisioning/#datasources + additionalDataSources: [] + # - name: prometheus-sample + # access: proxy + # basicAuth: true + # basicAuthPassword: pass + # basicAuthUser: daco + # editable: false + # jsonData: + # tlsSkipVerify: true + # orgId: 1 + # type: prometheus + # url: https://{{ printf "%s-prometheus.svc" .Release.Name }}:9090 + # version: 1 + + ## Passed to grafana subchart and used by servicemonitor below + ## + service: + portName: service + + ## If true, create a serviceMonitor for grafana + ## + serviceMonitor: + ## Scrape interval. If not set, the Prometheus default scrape interval is used. + ## + interval: "" + selfMonitor: true + + # Path to use for scraping metrics. Might be different if server.root_url is set + # in grafana.ini + path: "/metrics" + + ## metric relabel configs to apply to samples before ingestion. + ## + metricRelabelings: [] + # - action: keep + # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+' + # sourceLabels: [__name__] + + # relabel configs to apply to samples before ingestion. + ## + relabelings: [] + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + +## Component scraping the kube api server +## +kubeApiServer: + enabled: true + tlsConfig: + serverName: kubernetes + insecureSkipVerify: false + + ## If your API endpoint address is not reachable (as in AKS) you can replace it with the kubernetes service + ## + relabelings: [] + # - sourceLabels: + # - __meta_kubernetes_namespace + # - __meta_kubernetes_service_name + # - __meta_kubernetes_endpoint_port_name + # action: keep + # regex: default;kubernetes;https + # - targetLabel: __address__ + # replacement: kubernetes.default.svc:443 + + serviceMonitor: + ## Scrape interval. If not set, the Prometheus default scrape interval is used. + ## + interval: "" + jobLabel: component + selector: + matchLabels: + component: apiserver + provider: kubernetes + + ## metric relabel configs to apply to samples before ingestion. + ## + metricRelabelings: [] + # - action: keep + # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+' + # sourceLabels: [__name__] + +## Component scraping the kubelet and kubelet-hosted cAdvisor +## +kubelet: + enabled: true + namespace: kube-system + + serviceMonitor: + ## Scrape interval. If not set, the Prometheus default scrape interval is used. + ## + interval: "" + + ## Enable scraping the kubelet over https. For requirements to enable this see + ## https://github.com/prometheus-operator/prometheus-operator/issues/926 + ## + https: true + + ## Enable scraping /metrics/cadvisor from kubelet's service + ## + cAdvisor: true + + ## Enable scraping /metrics/probes from kubelet's service + ## + probes: true + + ## Enable scraping /metrics/resource from kubelet's service + ## This is disabled by default because container metrics are already exposed by cAdvisor + ## + resource: false + # From kubernetes 1.18, /metrics/resource/v1alpha1 renamed to /metrics/resource + resourcePath: "/metrics/resource/v1alpha1" + ## Metric relabellings to apply to samples before ingestion + ## + cAdvisorMetricRelabelings: [] + # - sourceLabels: [__name__, image] + # separator: ; + # regex: container_([a-z_]+); + # replacement: $1 + # action: drop + # - sourceLabels: [__name__] + # separator: ; + # regex: container_(network_tcp_usage_total|network_udp_usage_total|tasks_state|cpu_load_average_10s) + # replacement: $1 + # action: drop + + ## Metric relabellings to apply to samples before ingestion + ## + probesMetricRelabelings: [] + # - sourceLabels: [__name__, image] + # separator: ; + # regex: container_([a-z_]+); + # replacement: $1 + # action: drop + # - sourceLabels: [__name__] + # separator: ; + # regex: container_(network_tcp_usage_total|network_udp_usage_total|tasks_state|cpu_load_average_10s) + # replacement: $1 + # action: drop + + # relabel configs to apply to samples before ingestion. + # metrics_path is required to match upstream rules and charts + ## + cAdvisorRelabelings: + - sourceLabels: [__metrics_path__] + targetLabel: metrics_path + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + + probesRelabelings: + - sourceLabels: [__metrics_path__] + targetLabel: metrics_path + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + + resourceRelabelings: + - sourceLabels: [__metrics_path__] + targetLabel: metrics_path + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + + metricRelabelings: [] + # - sourceLabels: [__name__, image] + # separator: ; + # regex: container_([a-z_]+); + # replacement: $1 + # action: drop + # - sourceLabels: [__name__] + # separator: ; + # regex: container_(network_tcp_usage_total|network_udp_usage_total|tasks_state|cpu_load_average_10s) + # replacement: $1 + # action: drop + + # relabel configs to apply to samples before ingestion. + # metrics_path is required to match upstream rules and charts + ## + relabelings: + - sourceLabels: [__metrics_path__] + targetLabel: metrics_path + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + +## Component scraping the kube controller manager +## +kubeControllerManager: + enabled: true + + ## If your kube controller manager is not deployed as a pod, specify IPs it can be found on + ## + endpoints: [] + # - 10.141.4.22 + # - 10.141.4.23 + # - 10.141.4.24 + + ## If using kubeControllerManager.endpoints only the port and targetPort are used + ## + service: + port: 10252 + targetPort: 10252 + # selector: + # component: kube-controller-manager + + serviceMonitor: + ## Scrape interval. If not set, the Prometheus default scrape interval is used. + ## + interval: "" + + ## Enable scraping kube-controller-manager over https. + ## Requires proper certs (not self-signed) and delegated authentication/authorization checks + ## + https: false + + # Skip TLS certificate validation when scraping + insecureSkipVerify: null + + # Name of the server to use when validating TLS certificate + serverName: null + + ## metric relabel configs to apply to samples before ingestion. + ## + metricRelabelings: [] + # - action: keep + # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+' + # sourceLabels: [__name__] + + # relabel configs to apply to samples before ingestion. + ## + relabelings: [] + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + +## Component scraping coreDns. Use either this or kubeDns +## +coreDns: + enabled: true + service: + port: 9153 + targetPort: 9153 + # selector: + # k8s-app: kube-dns + serviceMonitor: + ## Scrape interval. If not set, the Prometheus default scrape interval is used. + ## + interval: "" + + ## metric relabel configs to apply to samples before ingestion. + ## + metricRelabelings: [] + # - action: keep + # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+' + # sourceLabels: [__name__] + + # relabel configs to apply to samples before ingestion. + ## + relabelings: [] + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + +## Component scraping kubeDns. Use either this or coreDns +## +kubeDns: + enabled: false + service: + dnsmasq: + port: 10054 + targetPort: 10054 + skydns: + port: 10055 + targetPort: 10055 + # selector: + # k8s-app: kube-dns + serviceMonitor: + ## Scrape interval. If not set, the Prometheus default scrape interval is used. + ## + interval: "" + + ## metric relabel configs to apply to samples before ingestion. + ## + metricRelabelings: [] + # - action: keep + # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+' + # sourceLabels: [__name__] + + # relabel configs to apply to samples before ingestion. + ## + relabelings: [] + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + dnsmasqMetricRelabelings: [] + # - action: keep + # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+' + # sourceLabels: [__name__] + + # relabel configs to apply to samples before ingestion. + ## + dnsmasqRelabelings: [] + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + +## Component scraping etcd +## +kubeEtcd: + enabled: true + + ## If your etcd is not deployed as a pod, specify IPs it can be found on + ## + endpoints: [] + # - 10.141.4.22 + # - 10.141.4.23 + # - 10.141.4.24 + + ## Etcd service. If using kubeEtcd.endpoints only the port and targetPort are used + ## + service: + port: 2379 + targetPort: 2379 + # selector: + # component: etcd + + ## Configure secure access to the etcd cluster by loading a secret into prometheus and + ## specifying security configuration below. For example, with a secret named etcd-client-cert + ## + ## serviceMonitor: + ## scheme: https + ## insecureSkipVerify: false + ## serverName: localhost + ## caFile: /etc/prometheus/secrets/etcd-client-cert/etcd-ca + ## certFile: /etc/prometheus/secrets/etcd-client-cert/etcd-client + ## keyFile: /etc/prometheus/secrets/etcd-client-cert/etcd-client-key + ## + serviceMonitor: + ## Scrape interval. If not set, the Prometheus default scrape interval is used. + ## + interval: "" + scheme: http + insecureSkipVerify: false + serverName: "" + caFile: "" + certFile: "" + keyFile: "" + + ## metric relabel configs to apply to samples before ingestion. + ## + metricRelabelings: [] + # - action: keep + # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+' + # sourceLabels: [__name__] + + # relabel configs to apply to samples before ingestion. + ## + relabelings: [] + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + + +## Component scraping kube scheduler +## +kubeScheduler: + enabled: true + + ## If your kube scheduler is not deployed as a pod, specify IPs it can be found on + ## + endpoints: [] + # - 10.141.4.22 + # - 10.141.4.23 + # - 10.141.4.24 + + ## If using kubeScheduler.endpoints only the port and targetPort are used + ## + service: + port: 10251 + targetPort: 10251 + # selector: + # component: kube-scheduler + + serviceMonitor: + ## Scrape interval. If not set, the Prometheus default scrape interval is used. + ## + interval: "" + ## Enable scraping kube-scheduler over https. + ## Requires proper certs (not self-signed) and delegated authentication/authorization checks + ## + https: false + + ## Skip TLS certificate validation when scraping + insecureSkipVerify: null + + ## Name of the server to use when validating TLS certificate + serverName: null + + ## metric relabel configs to apply to samples before ingestion. + ## + metricRelabelings: [] + # - action: keep + # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+' + # sourceLabels: [__name__] + + # relabel configs to apply to samples before ingestion. + ## + relabelings: [] + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + + +## Component scraping kube proxy +## +kubeProxy: + enabled: true + + ## If your kube proxy is not deployed as a pod, specify IPs it can be found on + ## + endpoints: [] + # - 10.141.4.22 + # - 10.141.4.23 + # - 10.141.4.24 + + service: + port: 10249 + targetPort: 10249 + # selector: + # k8s-app: kube-proxy + + serviceMonitor: + ## Scrape interval. If not set, the Prometheus default scrape interval is used. + ## + interval: "" + + ## Enable scraping kube-proxy over https. + ## Requires proper certs (not self-signed) and delegated authentication/authorization checks + ## + https: false + + ## metric relabel configs to apply to samples before ingestion. + ## + metricRelabelings: [] + # - action: keep + # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+' + # sourceLabels: [__name__] + + # relabel configs to apply to samples before ingestion. + ## + relabelings: [] + # - action: keep + # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+' + # sourceLabels: [__name__] + + +## Component scraping kube state metrics +## +kubeStateMetrics: + enabled: true + serviceMonitor: + ## Scrape interval. If not set, the Prometheus default scrape interval is used. + ## + interval: "" + + ## metric relabel configs to apply to samples before ingestion. + ## + metricRelabelings: [] + # - action: keep + # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+' + # sourceLabels: [__name__] + + # relabel configs to apply to samples before ingestion. + ## + relabelings: [] + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + +## Configuration for kube-state-metrics subchart +## +kube-state-metrics: + namespaceOverride: "" + rbac: + create: true + podSecurityPolicy: + enabled: true + +## Deploy node exporter as a daemonset to all nodes +## +nodeExporter: + enabled: true + + ## Use the value configured in prometheus-node-exporter.podLabels + ## + jobLabel: jobLabel + + serviceMonitor: + ## Scrape interval. If not set, the Prometheus default scrape interval is used. + ## + interval: "" + + ## How long until a scrape request times out. If not set, the Prometheus default scape timeout is used. + ## + scrapeTimeout: "" + + ## metric relabel configs to apply to samples before ingestion. + ## + metricRelabelings: [] + # - sourceLabels: [__name__] + # separator: ; + # regex: ^node_mountstats_nfs_(event|operations|transport)_.+ + # replacement: $1 + # action: drop + + ## relabel configs to apply to samples before ingestion. + ## + relabelings: [] + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + +## Configuration for prometheus-node-exporter subchart +## +prometheus-node-exporter: + namespaceOverride: "" + podLabels: + ## Add the 'node-exporter' label to be used by serviceMonitor to match standard common usage in rules and grafana dashboards + ## + jobLabel: node-exporter + extraArgs: + - --collector.filesystem.ignored-mount-points=^/(dev|proc|sys|var/lib/docker/.+)($|/) + - --collector.filesystem.ignored-fs-types=^(autofs|binfmt_misc|cgroup|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|mqueue|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|sysfs|tracefs)$ + +## Manages Prometheus and Alertmanager components +## +prometheusOperator: + enabled: true + + # Prometheus-Operator v0.39.0 and later support TLS natively. + tls: + enabled: true + # Value must match version names from https://golang.org/pkg/crypto/tls/#pkg-constants + tlsMinVersion: VersionTLS13 + + ## Admission webhook support for PrometheusRules resources added in Prometheus Operator 0.30 can be enabled to prevent incorrectly formatted + ## rules from making their way into prometheus and potentially preventing the container from starting + admissionWebhooks: + failurePolicy: Fail + enabled: true + ## If enabled, generate a self-signed certificate, then patch the webhook configurations with the generated data. + ## On chart upgrades (or if the secret exists) the cert will not be re-generated. You can use this to provide your own + ## certs ahead of time if you wish. + ## + patch: + enabled: true + image: + repository: jettech/kube-webhook-certgen + tag: v1.5.0 + sha: "" + pullPolicy: IfNotPresent + resources: {} + ## Provide a priority class name to the webhook patching job + ## + priorityClassName: "" + podAnnotations: {} + nodeSelector: {} + affinity: {} + tolerations: [] + + ## Namespaces to scope the interaction of the Prometheus Operator and the apiserver (allow list). + ## This is mutually exclusive with denyNamespaces. Setting this to an empty object will disable the configuration + ## + namespaces: {} + # releaseNamespace: true + # additional: + # - kube-system + + ## Namespaces not to scope the interaction of the Prometheus Operator (deny list). + ## + denyNamespaces: [] + + ## Filter namespaces to look for prometheus-operator custom resources + ## + alertmanagerInstanceNamespaces: [] + prometheusInstanceNamespaces: [] + thanosRulerInstanceNamespaces: [] + + ## Service account for Alertmanager to use. + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/ + ## + serviceAccount: + create: true + name: "" + + ## Configuration for Prometheus operator service + ## + service: + annotations: {} + labels: {} + clusterIP: "" + + ## Port to expose on each node + ## Only used if service.type is 'NodePort' + ## + nodePort: 30080 + + nodePortTls: 30443 + + ## Additional ports to open for Prometheus service + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#multi-port-services + ## + additionalPorts: [] + + ## Loadbalancer IP + ## Only use if service.type is "loadbalancer" + ## + loadBalancerIP: "" + loadBalancerSourceRanges: [] + + ## Service type + ## NodePort, ClusterIP, loadbalancer + ## + type: ClusterIP + + ## List of IP addresses at which the Prometheus server service is available + ## Ref: https://kubernetes.io/docs/user-guide/services/#external-ips + ## + externalIPs: [] + + ## Labels to add to the operator pod + ## + podLabels: {} + + ## Annotations to add to the operator pod + ## + podAnnotations: {} + + ## Assign a PriorityClassName to pods if set + # priorityClassName: "" + + ## Define Log Format + # Use logfmt (default) or json logging + # logFormat: logfmt + + ## Decrease log verbosity to errors only + # logLevel: error + + ## If true, the operator will create and maintain a service for scraping kubelets + ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/helm/prometheus-operator/README.md + ## + kubeletService: + enabled: true + namespace: kube-system + + ## Create a servicemonitor for the operator + ## + serviceMonitor: + ## Scrape interval. If not set, the Prometheus default scrape interval is used. + ## + interval: "" + ## Scrape timeout. If not set, the Prometheus default scrape timeout is used. + scrapeTimeout: "" + selfMonitor: true + + ## metric relabel configs to apply to samples before ingestion. + ## + metricRelabelings: [] + # - action: keep + # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+' + # sourceLabels: [__name__] + + # relabel configs to apply to samples before ingestion. + ## + relabelings: [] + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + + ## Resource limits & requests + ## + resources: {} + # limits: + # cpu: 200m + # memory: 200Mi + # requests: + # cpu: 100m + # memory: 100Mi + + # Required for use in managed kubernetes clusters (such as AWS EKS) with custom CNI (such as calico), + # because control-plane managed by AWS cannot communicate with pods' IP CIDR and admission webhooks are not working + ## + hostNetwork: false + + ## Define which Nodes the Pods are scheduled on. + ## ref: https://kubernetes.io/docs/user-guide/node-selection/ + ## + nodeSelector: {} + + ## Tolerations for use with node taints + ## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ + ## + tolerations: [] + # - key: "key" + # operator: "Equal" + # value: "value" + # effect: "NoSchedule" + + ## Assign custom affinity rules to the prometheus operator + ## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/ + ## + affinity: {} + # nodeAffinity: + # requiredDuringSchedulingIgnoredDuringExecution: + # nodeSelectorTerms: + # - matchExpressions: + # - key: kubernetes.io/e2e-az-name + # operator: In + # values: + # - e2e-az1 + # - e2e-az2 + + securityContext: + fsGroup: 65534 + runAsGroup: 65534 + runAsNonRoot: true + runAsUser: 65534 + + ## Prometheus-operator image + ## + image: + repository: quay.io/prometheus-operator/prometheus-operator + tag: v0.44.0 + sha: "" + pullPolicy: IfNotPresent + + ## Configmap-reload image to use for reloading configmaps + ## + configmapReloadImage: + repository: docker.io/jimmidyson/configmap-reload + tag: v0.4.0 + sha: "" + + ## Prometheus-config-reloader image to use for config and rule reloading + ## + prometheusConfigReloaderImage: + repository: quay.io/prometheus-operator/prometheus-config-reloader + tag: v0.44.0 + sha: "" + + ## Set the prometheus config reloader side-car CPU limit + ## + configReloaderCpu: 100m + + ## Set the prometheus config reloader side-car memory limit + ## + configReloaderMemory: 25Mi + + ## Set a Field Selector to filter watched secrets + ## + secretFieldSelector: "" + +## Deploy a Prometheus instance +## +prometheus: + + enabled: true + + ## Annotations for Prometheus + ## + annotations: {} + + ## Service account for Prometheuses to use. + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/ + ## + serviceAccount: + create: true + name: "" + + ## Configuration for Prometheus service + ## + service: + annotations: {} + labels: {} + clusterIP: "" + + ## Port for Prometheus Service to listen on + ## + port: 9090 + + ## To be used with a proxy extraContainer port + targetPort: 9090 + + ## List of IP addresses at which the Prometheus server service is available + ## Ref: https://kubernetes.io/docs/user-guide/services/#external-ips + ## + externalIPs: [] + + ## Port to expose on each node + ## Only used if service.type is 'NodePort' + ## + nodePort: 30090 + + ## Loadbalancer IP + ## Only use if service.type is "loadbalancer" + loadBalancerIP: "" + loadBalancerSourceRanges: [] + ## Service type + ## + type: ClusterIP + + sessionAffinity: "" + + ## Configuration for creating a separate Service for each statefulset Prometheus replica + ## + servicePerReplica: + enabled: false + annotations: {} + + ## Port for Prometheus Service per replica to listen on + ## + port: 9090 + + ## To be used with a proxy extraContainer port + targetPort: 9090 + + ## Port to expose on each node + ## Only used if servicePerReplica.type is 'NodePort' + ## + nodePort: 30091 + + ## Loadbalancer source IP ranges + ## Only used if servicePerReplica.type is "loadbalancer" + loadBalancerSourceRanges: [] + ## Service type + ## + type: ClusterIP + + ## Configure pod disruption budgets for Prometheus + ## ref: https://kubernetes.io/docs/tasks/run-application/configure-pdb/#specifying-a-poddisruptionbudget + ## This configuration is immutable once created and will require the PDB to be deleted to be changed + ## https://github.com/kubernetes/kubernetes/issues/45398 + ## + podDisruptionBudget: + enabled: false + minAvailable: 1 + maxUnavailable: "" + + # Ingress exposes thanos sidecar outside the clsuter + thanosIngress: + enabled: false + + # For Kubernetes >= 1.18 you should specify the ingress-controller via the field ingressClassName + # See https://kubernetes.io/blog/2020/04/02/improvements-to-the-ingress-api-in-kubernetes-1.18/#specifying-the-class-of-an-ingress + # ingressClassName: nginx + + annotations: {} + labels: {} + servicePort: 10901 + ## Hosts must be provided if Ingress is enabled. + ## + hosts: [] + # - thanos-gateway.domain.com + + ## Paths to use for ingress rules + ## + paths: [] + # - / + + ## TLS configuration for Alertmanager Ingress + ## Secret must be manually created in the namespace + ## + tls: [] + # - secretName: thanos-gateway-tls + # hosts: + # - thanos-gateway.domain.com + + ingress: + enabled: false + + # For Kubernetes >= 1.18 you should specify the ingress-controller via the field ingressClassName + # See https://kubernetes.io/blog/2020/04/02/improvements-to-the-ingress-api-in-kubernetes-1.18/#specifying-the-class-of-an-ingress + # ingressClassName: nginx + + annotations: {} + labels: {} + + ## Hostnames. + ## Must be provided if Ingress is enabled. + ## + # hosts: + # - prometheus.domain.com + hosts: [] + + ## Paths to use for ingress rules - one path should match the prometheusSpec.routePrefix + ## + paths: [] + # - / + + ## TLS configuration for Prometheus Ingress + ## Secret must be manually created in the namespace + ## + tls: [] + # - secretName: prometheus-general-tls + # hosts: + # - prometheus.example.com + + ## Configuration for creating an Ingress that will map to each Prometheus replica service + ## prometheus.servicePerReplica must be enabled + ## + ingressPerReplica: + enabled: false + + # For Kubernetes >= 1.18 you should specify the ingress-controller via the field ingressClassName + # See https://kubernetes.io/blog/2020/04/02/improvements-to-the-ingress-api-in-kubernetes-1.18/#specifying-the-class-of-an-ingress + # ingressClassName: nginx + + annotations: {} + labels: {} + + ## Final form of the hostname for each per replica ingress is + ## {{ ingressPerReplica.hostPrefix }}-{{ $replicaNumber }}.{{ ingressPerReplica.hostDomain }} + ## + ## Prefix for the per replica ingress that will have `-$replicaNumber` + ## appended to the end + hostPrefix: "" + ## Domain that will be used for the per replica ingress + hostDomain: "" + + ## Paths to use for ingress rules + ## + paths: [] + # - / + + ## Secret name containing the TLS certificate for Prometheus per replica ingress + ## Secret must be manually created in the namespace + tlsSecretName: "" + + ## Separated secret for each per replica Ingress. Can be used together with cert-manager + ## + tlsSecretPerReplica: + enabled: false + ## Final form of the secret for each per replica ingress is + ## {{ tlsSecretPerReplica.prefix }}-{{ $replicaNumber }} + ## + prefix: "prometheus" + + ## Configure additional options for default pod security policy for Prometheus + ## ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/ + podSecurityPolicy: + allowedCapabilities: [] + + serviceMonitor: + ## Scrape interval. If not set, the Prometheus default scrape interval is used. + ## + interval: "" + selfMonitor: true + + ## scheme: HTTP scheme to use for scraping. Can be used with `tlsConfig` for example if using istio mTLS. + scheme: "" + + ## tlsConfig: TLS configuration to use when scraping the endpoint. For example if using istio mTLS. + ## Of type: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#tlsconfig + tlsConfig: {} + + bearerTokenFile: + + ## metric relabel configs to apply to samples before ingestion. + ## + metricRelabelings: [] + # - action: keep + # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+' + # sourceLabels: [__name__] + + # relabel configs to apply to samples before ingestion. + ## + relabelings: [] + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + + ## Settings affecting prometheusSpec + ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#prometheusspec + ## + prometheusSpec: + ## If true, pass --storage.tsdb.max-block-duration=2h to prometheus. This is already done if using Thanos + ## + disableCompaction: false + ## APIServerConfig + ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#apiserverconfig + ## + apiserverConfig: {} + + ## Interval between consecutive scrapes. + ## Defaults to 30s. + ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/release-0.44/pkg/prometheus/promcfg.go#L180-L183 + ## + scrapeInterval: "" + + ## Number of seconds to wait for target to respond before erroring + ## + scrapeTimeout: "" + + ## Interval between consecutive evaluations. + ## + evaluationInterval: "" + + ## ListenLocal makes the Prometheus server listen on loopback, so that it does not bind against the Pod IP. + ## + listenLocal: false + + ## EnableAdminAPI enables Prometheus the administrative HTTP API which includes functionality such as deleting time series. + ## This is disabled by default. + ## ref: https://prometheus.io/docs/prometheus/latest/querying/api/#tsdb-admin-apis + ## + enableAdminAPI: false + + ## Image of Prometheus. + ## + image: + repository: quay.io/prometheus/prometheus + tag: v2.22.1 + sha: "" + + ## Tolerations for use with node taints + ## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ + ## + tolerations: [] + # - key: "key" + # operator: "Equal" + # value: "value" + # effect: "NoSchedule" + + ## Alertmanagers to which alerts will be sent + ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#alertmanagerendpoints + ## + ## Default configuration will connect to the alertmanager deployed as part of this release + ## + alertingEndpoints: [] + # - name: "" + # namespace: "" + # port: http + # scheme: http + # pathPrefix: "" + # tlsConfig: {} + # bearerTokenFile: "" + # apiVersion: v2 + + ## External labels to add to any time series or alerts when communicating with external systems + ## + externalLabels: {} + + ## Name of the external label used to denote replica name + ## + replicaExternalLabelName: "" + + ## If true, the Operator won't add the external label used to denote replica name + ## + replicaExternalLabelNameClear: false + + ## Name of the external label used to denote Prometheus instance name + ## + prometheusExternalLabelName: "" + + ## If true, the Operator won't add the external label used to denote Prometheus instance name + ## + prometheusExternalLabelNameClear: false + + ## External URL at which Prometheus will be reachable. + ## + externalUrl: "" + + ## Define which Nodes the Pods are scheduled on. + ## ref: https://kubernetes.io/docs/user-guide/node-selection/ + ## + nodeSelector: {} + + ## Secrets is a list of Secrets in the same namespace as the Prometheus object, which shall be mounted into the Prometheus Pods. + ## The Secrets are mounted into /etc/prometheus/secrets/. Secrets changes after initial creation of a Prometheus object are not + ## reflected in the running Pods. To change the secrets mounted into the Prometheus Pods, the object must be deleted and recreated + ## with the new list of secrets. + ## + secrets: [] + + ## ConfigMaps is a list of ConfigMaps in the same namespace as the Prometheus object, which shall be mounted into the Prometheus Pods. + ## The ConfigMaps are mounted into /etc/prometheus/configmaps/. + ## + configMaps: [] + + ## QuerySpec defines the query command line flags when starting Prometheus. + ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#queryspec + ## + query: {} + + ## Namespaces to be selected for PrometheusRules discovery. + ## If nil, select own namespace. Namespaces to be selected for ServiceMonitor discovery. + ## See https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#namespaceselector for usage + ## + ruleNamespaceSelector: {} + + ## If true, a nil or {} value for prometheus.prometheusSpec.ruleSelector will cause the + ## prometheus resource to be created with selectors based on values in the helm deployment, + ## which will also match the PrometheusRule resources created + ## + ruleSelectorNilUsesHelmValues: true + + ## PrometheusRules to be selected for target discovery. + ## If {}, select all ServiceMonitors + ## + ruleSelector: {} + ## Example which select all prometheusrules resources + ## with label "prometheus" with values any of "example-rules" or "example-rules-2" + # ruleSelector: + # matchExpressions: + # - key: prometheus + # operator: In + # values: + # - example-rules + # - example-rules-2 + # + ## Example which select all prometheusrules resources with label "role" set to "example-rules" + # ruleSelector: + # matchLabels: + # role: example-rules + + ## If true, a nil or {} value for prometheus.prometheusSpec.serviceMonitorSelector will cause the + ## prometheus resource to be created with selectors based on values in the helm deployment, + ## which will also match the servicemonitors created + ## + serviceMonitorSelectorNilUsesHelmValues: true + + ## ServiceMonitors to be selected for target discovery. + ## If {}, select all ServiceMonitors + ## + serviceMonitorSelector: {} + ## Example which selects ServiceMonitors with label "prometheus" set to "somelabel" + # serviceMonitorSelector: + # matchLabels: + # prometheus: somelabel + + ## Namespaces to be selected for ServiceMonitor discovery. + ## See https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#namespaceselector for usage + ## + serviceMonitorNamespaceSelector: {} + + ## If true, a nil or {} value for prometheus.prometheusSpec.podMonitorSelector will cause the + ## prometheus resource to be created with selectors based on values in the helm deployment, + ## which will also match the podmonitors created + ## + podMonitorSelectorNilUsesHelmValues: true + + ## PodMonitors to be selected for target discovery. + ## If {}, select all PodMonitors + ## + podMonitorSelector: {} + ## Example which selects PodMonitors with label "prometheus" set to "somelabel" + # podMonitorSelector: + # matchLabels: + # prometheus: somelabel + + ## Namespaces to be selected for PodMonitor discovery. + ## See https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#namespaceselector for usage + ## + podMonitorNamespaceSelector: {} + + ## If true, a nil or {} value for prometheus.prometheusSpec.probeSelector will cause the + ## prometheus resource to be created with selectors based on values in the helm deployment, + ## which will also match the probes created + ## + probeSelectorNilUsesHelmValues: true + + ## Probes to be selected for target discovery. + ## If {}, select all Probes + ## + probeSelector: {} + ## Example which selects Probes with label "prometheus" set to "somelabel" + # probeSelector: + # matchLabels: + # prometheus: somelabel + + ## Namespaces to be selected for Probe discovery. + ## See https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#namespaceselector for usage + ## + probeNamespaceSelector: {} + + ## How long to retain metrics + ## + retention: 10d + + ## Maximum size of metrics + ## + retentionSize: "" + + ## Enable compression of the write-ahead log using Snappy. + ## + walCompression: false + + ## If true, the Operator won't process any Prometheus configuration changes + ## + paused: false + + ## Number of Prometheus replicas desired + ## + replicas: 1 + + ## Log level for Prometheus be configured in + ## + logLevel: info + + ## Log format for Prometheus be configured in + ## + logFormat: logfmt + + ## Prefix used to register routes, overriding externalUrl route. + ## Useful for proxies that rewrite URLs. + ## + routePrefix: / + + ## Standard object’s metadata. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#metadata + ## Metadata Labels and Annotations gets propagated to the prometheus pods. + ## + podMetadata: {} + # labels: + # app: prometheus + # k8s-app: prometheus + + ## Pod anti-affinity can prevent the scheduler from placing Prometheus replicas on the same node. + ## The default value "soft" means that the scheduler should *prefer* to not schedule two replica pods onto the same node but no guarantee is provided. + ## The value "hard" means that the scheduler is *required* to not schedule two replica pods onto the same node. + ## The value "" will disable pod anti-affinity so that no anti-affinity rules will be configured. + podAntiAffinity: "" + + ## If anti-affinity is enabled sets the topologyKey to use for anti-affinity. + ## This can be changed to, for example, failure-domain.beta.kubernetes.io/zone + ## + podAntiAffinityTopologyKey: kubernetes.io/hostname + + ## Assign custom affinity rules to the prometheus instance + ## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/ + ## + affinity: {} + # nodeAffinity: + # requiredDuringSchedulingIgnoredDuringExecution: + # nodeSelectorTerms: + # - matchExpressions: + # - key: kubernetes.io/e2e-az-name + # operator: In + # values: + # - e2e-az1 + # - e2e-az2 + + ## The remote_read spec configuration for Prometheus. + ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#remotereadspec + remoteRead: [] + # - url: http://remote1/read + + ## The remote_write spec configuration for Prometheus. + ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#remotewritespec + remoteWrite: [] + # - url: http://remote1/push + + ## Enable/Disable Grafana dashboards provisioning for prometheus remote write feature + remoteWriteDashboards: false + + ## Resource limits & requests + ## + resources: {} + # requests: + # memory: 400Mi + + ## Prometheus StorageSpec for persistent data + ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/user-guides/storage.md + ## + storageSpec: {} + ## Using PersistentVolumeClaim + ## + # volumeClaimTemplate: + # spec: + # storageClassName: gluster + # accessModes: ["ReadWriteOnce"] + # resources: + # requests: + # storage: 50Gi + # selector: {} + + ## Using tmpfs volume + ## + # emptyDir: + # medium: Memory + + # Additional volumes on the output StatefulSet definition. + volumes: [] + + # Additional VolumeMounts on the output StatefulSet definition. + volumeMounts: [] + + ## AdditionalScrapeConfigs allows specifying additional Prometheus scrape configurations. Scrape configurations + ## are appended to the configurations generated by the Prometheus Operator. Job configurations must have the form + ## as specified in the official Prometheus documentation: + ## https://prometheus.io/docs/prometheus/latest/configuration/configuration/#scrape_config. As scrape configs are + ## appended, the user is responsible to make sure it is valid. Note that using this feature may expose the possibility + ## to break upgrades of Prometheus. It is advised to review Prometheus release notes to ensure that no incompatible + ## scrape configs are going to break Prometheus after the upgrade. + ## + ## The scrape configuration example below will find master nodes, provided they have the name .*mst.*, relabel the + ## port to 2379 and allow etcd scraping provided it is running on all Kubernetes master nodes + ## + additionalScrapeConfigs: [] + # - job_name: kube-etcd + # kubernetes_sd_configs: + # - role: node + # scheme: https + # tls_config: + # ca_file: /etc/prometheus/secrets/etcd-client-cert/etcd-ca + # cert_file: /etc/prometheus/secrets/etcd-client-cert/etcd-client + # key_file: /etc/prometheus/secrets/etcd-client-cert/etcd-client-key + # relabel_configs: + # - action: labelmap + # regex: __meta_kubernetes_node_label_(.+) + # - source_labels: [__address__] + # action: replace + # targetLabel: __address__ + # regex: ([^:;]+):(\d+) + # replacement: ${1}:2379 + # - source_labels: [__meta_kubernetes_node_name] + # action: keep + # regex: .*mst.* + # - source_labels: [__meta_kubernetes_node_name] + # action: replace + # targetLabel: node + # regex: (.*) + # replacement: ${1} + # metric_relabel_configs: + # - regex: (kubernetes_io_hostname|failure_domain_beta_kubernetes_io_region|beta_kubernetes_io_os|beta_kubernetes_io_arch|beta_kubernetes_io_instance_type|failure_domain_beta_kubernetes_io_zone) + # action: labeldrop + + ## If additional scrape configurations are already deployed in a single secret file you can use this section. + ## Expected values are the secret name and key + ## Cannot be used with additionalScrapeConfigs + additionalScrapeConfigsSecret: {} + # enabled: false + # name: + # key: + + ## additionalPrometheusSecretsAnnotations allows to add annotations to the kubernetes secret. This can be useful + ## when deploying via spinnaker to disable versioning on the secret, strategy.spinnaker.io/versioned: 'false' + additionalPrometheusSecretsAnnotations: {} + + ## AdditionalAlertManagerConfigs allows for manual configuration of alertmanager jobs in the form as specified + ## in the official Prometheus documentation https://prometheus.io/docs/prometheus/latest/configuration/configuration/#. + ## AlertManager configurations specified are appended to the configurations generated by the Prometheus Operator. + ## As AlertManager configs are appended, the user is responsible to make sure it is valid. Note that using this + ## feature may expose the possibility to break upgrades of Prometheus. It is advised to review Prometheus release + ## notes to ensure that no incompatible AlertManager configs are going to break Prometheus after the upgrade. + ## + additionalAlertManagerConfigs: [] + # - consul_sd_configs: + # - server: consul.dev.test:8500 + # scheme: http + # datacenter: dev + # tag_separator: ',' + # services: + # - metrics-prometheus-alertmanager + + ## AdditionalAlertRelabelConfigs allows specifying Prometheus alert relabel configurations. Alert relabel configurations specified are appended + ## to the configurations generated by the Prometheus Operator. Alert relabel configurations specified must have the form as specified in the + ## official Prometheus documentation: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#alert_relabel_configs. + ## As alert relabel configs are appended, the user is responsible to make sure it is valid. Note that using this feature may expose the + ## possibility to break upgrades of Prometheus. It is advised to review Prometheus release notes to ensure that no incompatible alert relabel + ## configs are going to break Prometheus after the upgrade. + ## + additionalAlertRelabelConfigs: [] + # - separator: ; + # regex: prometheus_replica + # replacement: $1 + # action: labeldrop + + ## SecurityContext holds pod-level security attributes and common container settings. + ## This defaults to non root user with uid 1000 and gid 2000. + ## https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md + ## + securityContext: + runAsGroup: 2000 + runAsNonRoot: true + runAsUser: 1000 + fsGroup: 2000 + + ## Priority class assigned to the Pods + ## + priorityClassName: "" + + ## Thanos configuration allows configuring various aspects of a Prometheus server in a Thanos environment. + ## This section is experimental, it may change significantly without deprecation notice in any release. + ## This is experimental and may change significantly without backward compatibility in any release. + ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#thanosspec + ## + thanos: {} + + ## Containers allows injecting additional containers. This is meant to allow adding an authentication proxy to a Prometheus pod. + ## if using proxy extraContainer update targetPort with proxy container port + containers: [] + + ## InitContainers allows injecting additional initContainers. This is meant to allow doing some changes + ## (permissions, dir tree) on mounted volumes before starting prometheus + initContainers: [] + + ## PortName to use for Prometheus. + ## + portName: "web" + + ## ArbitraryFSAccessThroughSMs configures whether configuration based on a service monitor can access arbitrary files + ## on the file system of the Prometheus container e.g. bearer token files. + arbitraryFSAccessThroughSMs: false + + ## OverrideHonorLabels if set to true overrides all user configured honor_labels. If HonorLabels is set in ServiceMonitor + ## or PodMonitor to true, this overrides honor_labels to false. + overrideHonorLabels: false + + ## OverrideHonorTimestamps allows to globally enforce honoring timestamps in all scrape configs. + overrideHonorTimestamps: false + + ## IgnoreNamespaceSelectors if set to true will ignore NamespaceSelector settings from the podmonitor and servicemonitor + ## configs, and they will only discover endpoints within their current namespace. Defaults to false. + ignoreNamespaceSelectors: false + + ## PrometheusRulesExcludedFromEnforce - list of prometheus rules to be excluded from enforcing of adding namespace labels. + ## Works only if enforcedNamespaceLabel set to true. Make sure both ruleNamespace and ruleName are set for each pair + prometheusRulesExcludedFromEnforce: false + + ## QueryLogFile specifies the file to which PromQL queries are logged. Note that this location must be writable, + ## and can be persisted using an attached volume. Alternatively, the location can be set to a stdout location such + ## as /dev/stdout to log querie information to the default Prometheus log stream. This is only available in versions + ## of Prometheus >= 2.16.0. For more details, see the Prometheus docs (https://prometheus.io/docs/guides/query-log/) + queryLogFile: false + + ## EnforcedSampleLimit defines global limit on number of scraped samples that will be accepted. This overrides any SampleLimit + ## set per ServiceMonitor or/and PodMonitor. It is meant to be used by admins to enforce the SampleLimit to keep overall + ## number of samples/series under the desired limit. Note that if SampleLimit is lower that value will be taken instead. + enforcedSampleLimit: false + + ## AllowOverlappingBlocks enables vertical compaction and vertical query merge in Prometheus. This is still experimental + ## in Prometheus so it may change in any upcoming release. + allowOverlappingBlocks: false + + additionalRulesForClusterRole: [] + # - apiGroups: [ "" ] + # resources: + # - nodes/proxy + # verbs: [ "get", "list", "watch" ] + + additionalServiceMonitors: [] + ## Name of the ServiceMonitor to create + ## + # - name: "" + + ## Additional labels to set used for the ServiceMonitorSelector. Together with standard labels from + ## the chart + ## + # additionalLabels: {} + + ## Service label for use in assembling a job name of the form