diff --git a/admin/upgrade_cluster.sh b/admin/upgrade_cluster.sh index 7e9b825d..653c7a21 100755 --- a/admin/upgrade_cluster.sh +++ b/admin/upgrade_cluster.sh @@ -169,6 +169,9 @@ kubectl delete deployment argocd-redis -n argocd || true kubectl delete deployment argocd-repo-server -n argocd || true kubectl delete statefulset argocd-application-controller -n argocd || true +# Delete prometheus-push gateway due to label changes +kubectl delete deploy -l app=prometheus-pushgateway -n monitoring || true + control_plane_upgrade "apply_cert-manager, apply_istio, apply_istio-ingress, apply_istio-private-ingress, apply_logging, apply_metrics, apply_argocd" # Final step is to commit the new argocd kubezero app diff --git a/charts/kubezero-metrics/Chart.yaml b/charts/kubezero-metrics/Chart.yaml index 97449d1f..43f0cc24 100644 --- a/charts/kubezero-metrics/Chart.yaml +++ b/charts/kubezero-metrics/Chart.yaml @@ -2,7 +2,7 @@ apiVersion: v2 name: kubezero-metrics description: KubeZero Umbrella Chart for Prometheus, Grafana and Alertmanager as well as all Kubernetes integrations. type: application -version: 0.8.7 +version: 0.8.8 home: https://kubezero.com icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png keywords: @@ -18,16 +18,16 @@ dependencies: version: ">= 0.1.5" repository: https://cdn.zero-downtime.net/charts/ - name: kube-prometheus-stack - version: 41.4.1 + version: 42.2.1 # Switch back to upstream once all alerts are fixed eg. etcd gpcr # repository: https://prometheus-community.github.io/helm-charts - name: prometheus-adapter - version: 3.4.0 + version: 3.4.2 repository: https://prometheus-community.github.io/helm-charts condition: prometheus-adapter.enabled - name: prometheus-pushgateway - version: 1.20.0 + version: 2.0.2 # Switch back to upstream once namespaces are supported - # repository: https://prometheus-community.github.io/helm-charts + repository: https://prometheus-community.github.io/helm-charts condition: prometheus-pushgateway.enabled kubeVersion: ">= 1.24.0" diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/Chart.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/Chart.yaml index 6129882b..6d9fdc7a 100644 --- a/charts/kubezero-metrics/charts/kube-prometheus-stack/Chart.yaml +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/Chart.yaml @@ -11,15 +11,15 @@ dependencies: - condition: kubeStateMetrics.enabled name: kube-state-metrics repository: https://prometheus-community.github.io/helm-charts - version: 4.20.* + version: 4.24.* - condition: nodeExporter.enabled name: prometheus-node-exporter repository: https://prometheus-community.github.io/helm-charts - version: 4.3.* + version: 4.8.* - condition: grafana.enabled name: grafana repository: https://grafana.github.io/helm-charts - version: 6.40.* + version: 6.45.* 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 @@ -34,8 +34,6 @@ kubeVersion: '>=1.16.0-0' maintainers: - email: andrew@quadcorps.co.uk name: andrewgkew -- email: cedric@desaintmartin.fr - name: desaintmartin - email: gianrubio@gmail.com name: gianrubio - email: github.gkarthiks@gmail.com @@ -46,9 +44,11 @@ maintainers: name: scottrigby - email: miroslav.hadzhiev@gmail.com name: Xtigyro +- email: quentin.bisson@gmail.com + name: QuentinBisson name: kube-prometheus-stack sources: - https://github.com/prometheus-community/helm-charts - https://github.com/prometheus-operator/kube-prometheus type: application -version: 41.4.1 +version: 42.2.1 diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/README.md b/charts/kubezero-metrics/charts/kube-prometheus-stack/README.md index e9081e46..9cee74eb 100644 --- a/charts/kubezero-metrics/charts/kube-prometheus-stack/README.md +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/README.md @@ -80,6 +80,29 @@ _See [helm upgrade](https://helm.sh/docs/helm/helm_upgrade/) for command documen A major chart version change (like v1.2.3 -> v2.0.0) indicates that there is an incompatible breaking change needing manual actions. +### From 41.x to 42.x + +This includes the overridability of container registry for all containers at the global level using `global.imageRegistry` or per container image. The defaults have not changed but if you were using a custom image, you will have to override the registry of said custom container image before you upgrade. + +For instance, the prometheus-config-reloader used to be configured as follow: + +```yaml + image: + repository: quay.io/prometheus-operator/prometheus-config-reloader + tag: v0.60.1 + sha: "" +``` + +But it now moved to: + +```yaml + image: + registry: quay.io + repository: prometheus-operator/prometheus-config-reloader + tag: v0.60.1 + sha: "" +``` + ### From 40.x to 41.x This version upgrades Prometheus-Operator to v0.60.1, Prometheus to v2.39.1 and Thanos to v0.28.1. 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 index bcd695cb..83233efb 100644 --- a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/Chart.yaml +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/Chart.yaml @@ -1,5 +1,5 @@ apiVersion: v2 -appVersion: 9.1.7 +appVersion: 9.3.0 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 @@ -19,4 +19,4 @@ name: grafana sources: - https://github.com/grafana/grafana type: application -version: 6.40.4 +version: 6.45.0 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 index 7399da72..b5dd1e69 100644 --- a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/README.md +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/README.md @@ -104,6 +104,7 @@ This version requires Helm >= 3.1.0. | `persistence.accessModes` | Persistence access modes | `[ReadWriteOnce]` | | `persistence.annotations` | PersistentVolumeClaim annotations | `{}` | | `persistence.finalizers` | PersistentVolumeClaim finalizers | `[ "kubernetes.io/pvc-protection" ]` | +| `persistence.extraPvcLabels` | Extra labels to apply to a PVC. | `{}` | | `persistence.subPath` | Mount a sub dir of the persistent volume (can be templated) | `nil` | | `persistence.inMemory.enabled` | If persistence is not enabled, whether to mount the local storage in-memory to improve performance | `false` | | `persistence.inMemory.sizeLimit` | SizeLimit for the in-memory local storage | `nil` | @@ -134,6 +135,7 @@ This version requires Helm >= 3.1.0. | `dashboards` | Dashboards to import | `{}` | | `dashboardsConfigMaps` | ConfigMaps reference that contains dashboards | `{}` | | `grafana.ini` | Grafana's primary configuration | `{}` | +| `global.imagePullSecrets` | Global image pull secrets (can be templated). Allows either an array of {name: pullSecret} maps (k8s-style), or an array of strings (more common helm-style). | `[]` | | `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 | `""` | @@ -206,6 +208,7 @@ This version requires Helm >= 3.1.0. | `serviceAccount.autoMount` | Automount the service account token in the pod| `true` | | `serviceAccount.annotations` | ServiceAccount annotations | | | `serviceAccount.create` | Create service account | `true` | +| `serviceAccount.labels` | ServiceAccount labels | `{}` | | `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` | diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/ci/with-extraconfigmapmounts-values.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/ci/with-extraconfigmapmounts-values.yaml index f2d55a83..5cc44a05 100644 --- a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/ci/with-extraconfigmapmounts-values.yaml +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/ci/with-extraconfigmapmounts-values.yaml @@ -1,6 +1,6 @@ extraConfigmapMounts: - - name: '{{ template "grafana.fullname" . }}' - configMap: '{{ template "grafana.fullname" . }}' + - name: '{{ include "grafana.fullname" . }}' + configMap: '{{ include "grafana.fullname" . }}' mountPath: /var/lib/grafana/dashboards/test-dashboard.json # This is not a realistic test, but for this we only care about extraConfigmapMounts not being empty and pointing to an existing ConfigMap subPath: grafana.ini 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 index 1fc8436d..f399f43f 100644 --- 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 @@ -1,10 +1,10 @@ 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 + kubectl get secret --namespace {{ include "grafana.namespace" . }} {{ include "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 + {{ include "grafana.fullname" . }}.{{ include "grafana.namespace" . }}.svc.cluster.local {{ if .Values.ingress.enabled }} If you bind grafana to 80, please update values in values.yaml and reinstall: ``` @@ -24,24 +24,24 @@ Or grafana would always crash. From outside the cluster, the server URL(s) are: -{{- range .Values.ingress.hosts }} + {{- range .Values.ingress.hosts }} http://{{ . }} -{{- end }} -{{ else }} + {{- 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}") + {{- if contains "NodePort" .Values.service.type }} + export NODE_PORT=$(kubectl get --namespace {{ include "grafana.namespace" . }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "grafana.fullname" . }}) + export NODE_IP=$(kubectl get nodes --namespace {{ include "grafana.namespace" . }} -o jsonpath="{.items[0].status.addresses[0].address}") echo http://$NODE_IP:$NODE_PORT -{{ else if contains "LoadBalancer" .Values.service.type -}} + {{- 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=$(kubectl get svc --namespace {{ template "grafana.namespace" . }} {{ template "grafana.fullname" . }} -o jsonpath='{.status.loadBalancer.ingress[0].ip}') + You can watch the status of by running 'kubectl get svc --namespace {{ include "grafana.namespace" . }} -w {{ include "grafana.fullname" . }}' + export SERVICE_IP=$(kubectl get svc --namespace {{ include "grafana.namespace" . }} {{ include "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 $POD_NAME 3000 -{{- end }} + {{- else if contains "ClusterIP" .Values.service.type }} + export POD_NAME=$(kubectl get pods --namespace {{ include "grafana.namespace" . }} -l "app.kubernetes.io/name={{ include "grafana.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}") + kubectl --namespace {{ include "grafana.namespace" . }} port-forward $POD_NAME 3000 + {{- end }} {{- end }} 3. Login with the password from step 1 and the username: {{ .Values.adminUser }} 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 index 369e69fa..eb079b80 100644 --- 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 @@ -3,8 +3,8 @@ Expand the name of the chart. */}} {{- define "grafana.name" -}} -{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}} -{{- end -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }} +{{- end }} {{/* Create a default fully qualified app name. @@ -12,54 +12,54 @@ We truncate at 63 chars because some Kubernetes name fields are limited to this 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 -}} +{{- 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 -}} +{{- 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 -}} +{{- 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 -}} +{{- 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 -}} +{{- if .Values.namespaceOverride }} +{{- .Values.namespaceOverride }} +{{- else }} +{{- .Release.Namespace }} +{{- end }} +{{- end }} {{/* Common labels @@ -71,10 +71,10 @@ helm.sh/chart: {{ include "grafana.chart" . }} app.kubernetes.io/version: {{ .Values.image.tag | default .Chart.AppVersion | quote }} {{- end }} app.kubernetes.io/managed-by: {{ .Release.Service }} -{{- if .Values.extraLabels }} -{{ toYaml .Values.extraLabels }} +{{- with .Values.extraLabels }} +{{ toYaml . }} +{{- end }} {{- end }} -{{- end -}} {{/* Selector labels @@ -82,7 +82,7 @@ Selector labels {{- define "grafana.selectorLabels" -}} app.kubernetes.io/name: {{ include "grafana.name" . }} app.kubernetes.io/instance: {{ .Release.Name }} -{{- end -}} +{{- end }} {{/* Common labels @@ -94,7 +94,7 @@ helm.sh/chart: {{ include "grafana.chart" . }} app.kubernetes.io/version: {{ .Values.image.tag | default .Chart.AppVersion | quote }} {{- end }} app.kubernetes.io/managed-by: {{ .Release.Service }} -{{- end -}} +{{- end }} {{/* Selector labels ImageRenderer @@ -102,73 +102,87 @@ Selector labels ImageRenderer {{- define "grafana.imageRenderer.selectorLabels" -}} app.kubernetes.io/name: {{ include "grafana.name" . }}-image-renderer app.kubernetes.io/instance: {{ .Release.Name }} -{{- end -}} +{{- end }} {{/* Looks if there's an existing secret and reuse its password. If not it generates new password and use it. */}} {{- define "grafana.password" -}} -{{- $secret := (lookup "v1" "Secret" (include "grafana.namespace" .) (include "grafana.fullname" .) ) -}} - {{- if $secret -}} - {{- index $secret "data" "admin-password" -}} - {{- else -}} - {{- (randAlphaNum 40) | b64enc | quote -}} - {{- end -}} -{{- end -}} +{{- $secret := (lookup "v1" "Secret" (include "grafana.namespace" .) (include "grafana.fullname" .) ) }} +{{- if $secret }} +{{- index $secret "data" "admin-password" }} +{{- else }} +{{- (randAlphaNum 40) | b64enc | quote }} +{{- end }} +{{- end }} {{/* Return the appropriate apiVersion for rbac. */}} {{- define "grafana.rbac.apiVersion" -}} - {{- if .Capabilities.APIVersions.Has "rbac.authorization.k8s.io/v1" }} - {{- print "rbac.authorization.k8s.io/v1" -}} - {{- else -}} - {{- print "rbac.authorization.k8s.io/v1beta1" -}} - {{- end -}} -{{- end -}} +{{- if $.Capabilities.APIVersions.Has "rbac.authorization.k8s.io/v1" }} +{{- print "rbac.authorization.k8s.io/v1" }} +{{- else }} +{{- print "rbac.authorization.k8s.io/v1beta1" }} +{{- end }} +{{- end }} {{/* Return the appropriate apiVersion for ingress. */}} {{- define "grafana.ingress.apiVersion" -}} - {{- if and (.Capabilities.APIVersions.Has "networking.k8s.io/v1") (semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version) -}} - {{- print "networking.k8s.io/v1" -}} - {{- else if .Capabilities.APIVersions.Has "networking.k8s.io/v1beta1" -}} - {{- print "networking.k8s.io/v1beta1" -}} - {{- else -}} - {{- print "extensions/v1beta1" -}} - {{- end -}} -{{- end -}} +{{- if and ($.Capabilities.APIVersions.Has "networking.k8s.io/v1") (semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version) }} +{{- print "networking.k8s.io/v1" }} +{{- else if $.Capabilities.APIVersions.Has "networking.k8s.io/v1beta1" }} +{{- print "networking.k8s.io/v1beta1" }} +{{- else }} +{{- print "extensions/v1beta1" }} +{{- end }} +{{- end }} {{/* Return the appropriate apiVersion for podDisruptionBudget. */}} {{- define "grafana.podDisruptionBudget.apiVersion" -}} - {{- if $.Capabilities.APIVersions.Has "policy/v1/PodDisruptionBudget" -}} - {{- print "policy/v1" -}} - {{- else -}} - {{- print "policy/v1beta1" -}} - {{- end -}} -{{- end -}} +{{- if $.Capabilities.APIVersions.Has "policy/v1/PodDisruptionBudget" }} +{{- print "policy/v1" }} +{{- else }} +{{- print "policy/v1beta1" }} +{{- end }} +{{- end }} {{/* Return if ingress is stable. */}} {{- define "grafana.ingress.isStable" -}} - {{- eq (include "grafana.ingress.apiVersion" .) "networking.k8s.io/v1" -}} -{{- end -}} +{{- eq (include "grafana.ingress.apiVersion" .) "networking.k8s.io/v1" }} +{{- end }} {{/* Return if ingress supports ingressClassName. */}} {{- define "grafana.ingress.supportsIngressClassName" -}} - {{- or (eq (include "grafana.ingress.isStable" .) "true") (and (eq (include "grafana.ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) -}} -{{- end -}} +{{- or (eq (include "grafana.ingress.isStable" .) "true") (and (eq (include "grafana.ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) }} +{{- end }} {{/* Return if ingress supports pathType. */}} {{- define "grafana.ingress.supportsPathType" -}} - {{- or (eq (include "grafana.ingress.isStable" .) "true") (and (eq (include "grafana.ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) -}} -{{- end -}} +{{- or (eq (include "grafana.ingress.isStable" .) "true") (and (eq (include "grafana.ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) }} +{{- end }} + +{{/* +Formats imagePullSecrets. Input is (dict "root" . "imagePullSecrets" .{specific imagePullSecrets}) +*/}} +{{- define "grafana.imagePullSecrets" -}} +{{- $root := .root }} +{{- range (concat .root.Values.global.imagePullSecrets .imagePullSecrets) }} +{{- if eq (typeOf .) "map[string]interface {}" }} +- {{ toYaml (dict "name" (tpl .name $root)) | trim }} +{{- else }} +- name: {{ tpl . $root }} +{{- end }} +{{- end }} +{{- 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 index 81493f4f..95795bb1 100644 --- 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 @@ -1,8 +1,9 @@ {{- define "grafana.pod" -}} -{{- if .Values.schedulerName }} -schedulerName: "{{ .Values.schedulerName }}" +{{- $root := . -}} +{{- with .Values.schedulerName }} +schedulerName: "{{ . }}" {{- end }} -serviceAccountName: {{ template "grafana.serviceAccountName" . }} +serviceAccountName: {{ include "grafana.serviceAccountName" . }} automountServiceAccountToken: {{ .Values.serviceAccount.autoMount }} {{- with .Values.securityContext }} securityContext: @@ -12,8 +13,8 @@ securityContext: hostAliases: {{- toYaml . | nindent 2 }} {{- end }} -{{- if .Values.priorityClassName }} -priorityClassName: {{ .Values.priorityClassName }} +{{- with .Values.priorityClassName }} +priorityClassName: {{ . }} {{- end }} {{- if ( or .Values.persistence.enabled .Values.dashboards .Values.extraInitContainers (and .Values.sidecar.datasources.enabled .Values.sidecar.datasources.initDatasources) (and .Values.sidecar.notifiers.enabled .Values.sidecar.notifiers.initNotifiers)) }} initContainers: @@ -26,10 +27,15 @@ initContainers: image: "{{ .Values.initChownData.image.repository }}:{{ .Values.initChownData.image.tag }}" {{- end }} imagePullPolicy: {{ .Values.initChownData.image.pullPolicy }} + {{- with .Values.initChownData.securityContext }} securityContext: - runAsNonRoot: false - runAsUser: 0 - command: ["chown", "-R", "{{ .Values.securityContext.runAsUser }}:{{ .Values.securityContext.runAsGroup }}", "/var/lib/grafana"] + {{- toYaml . | nindent 6 }} + {{- end }} + command: + - chown + - -R + - {{ .Values.securityContext.runAsUser }}:{{ .Values.securityContext.runAsGroup }} + - /var/lib/grafana {{- with .Values.initChownData.resources }} resources: {{- toYaml . | nindent 6 }} @@ -37,9 +43,9 @@ initContainers: volumeMounts: - name: storage mountPath: "/var/lib/grafana" -{{- if .Values.persistence.subPath }} - subPath: {{ tpl .Values.persistence.subPath . }} -{{- end }} + {{- with .Values.persistence.subPath }} + subPath: {{ tpl . $root }} + {{- end }} {{- end }} {{- if .Values.dashboards }} - name: download-dashboards @@ -56,36 +62,41 @@ initContainers: {{- toYaml . | nindent 6 }} {{- end }} env: -{{- range $key, $value := .Values.downloadDashboards.env }} + {{- range $key, $value := .Values.downloadDashboards.env }} - name: "{{ $key }}" value: "{{ $value }}" -{{- end }} + {{- end }} + {{- range $key, $value := .Values.downloadDashboards.envValueFrom }} + - name: {{ $key | quote }} + valueFrom: + {{- tpl (toYaml $value) $ | nindent 10 }} + {{- end }} {{- with .Values.downloadDashboards.securityContext }} securityContext: {{- toYaml . | nindent 6 }} {{- end }} -{{- if .Values.downloadDashboards.envFromSecret }} + {{- with .Values.downloadDashboards.envFromSecret }} envFrom: - secretRef: - name: {{ tpl .Values.downloadDashboards.envFromSecret . }} -{{- end }} + name: {{ tpl . $root }} + {{- 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: {{ tpl .Values.persistence.subPath . }} -{{- end }} - {{- range .Values.extraSecretMounts }} + {{- with .Values.persistence.subPath }} + subPath: {{ tpl . $root }} + {{- end }} + {{- range .Values.extraSecretMounts }} - name: {{ .name }} mountPath: {{ .mountPath }} readOnly: {{ .readOnly }} - {{- end }} + {{- end }} {{- end }} {{- if and .Values.sidecar.datasources.enabled .Values.sidecar.datasources.initDatasources }} - - name: {{ template "grafana.name" . }}-init-sc-datasources + - name: {{ include "grafana.name" . }}-init-sc-datasources {{- if .Values.sidecar.image.sha }} image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" {{- else }} @@ -105,9 +116,9 @@ initContainers: value: "LIST" - name: LABEL value: "{{ .Values.sidecar.datasources.label }}" - {{- if .Values.sidecar.datasources.labelValue }} + {{- with .Values.sidecar.datasources.labelValue }} - name: LABEL_VALUE - value: {{ quote .Values.sidecar.datasources.labelValue }} + value: {{ quote . }} {{- end }} {{- if or .Values.sidecar.logLevel .Values.sidecar.datasources.logLevel }} - name: LOG_LEVEL @@ -117,17 +128,17 @@ initContainers: value: "/etc/grafana/provisioning/datasources" - name: RESOURCE value: {{ quote .Values.sidecar.datasources.resource }} - {{- if .Values.sidecar.enableUniqueFilenames }} + {{- with .Values.sidecar.enableUniqueFilenames }} - name: UNIQUE_FILENAMES - value: "{{ .Values.sidecar.enableUniqueFilenames }}" + value: "{{ . }}" {{- end }} {{- if .Values.sidecar.datasources.searchNamespace }} - name: NAMESPACE value: "{{ tpl (.Values.sidecar.datasources.searchNamespace | join ",") . }}" {{- end }} - {{- if .Values.sidecar.skipTlsVerify }} + {{- with .Values.sidecar.skipTlsVerify }} - name: SKIP_TLS_VERIFY - value: "{{ .Values.sidecar.skipTlsVerify }}" + value: "{{ . }}" {{- end }} {{- with .Values.sidecar.resources }} resources: @@ -142,7 +153,7 @@ initContainers: mountPath: "/etc/grafana/provisioning/datasources" {{- end }} {{- if and .Values.sidecar.notifiers.enabled .Values.sidecar.notifiers.initNotifiers }} - - name: {{ template "grafana.name" . }}-init-sc-notifiers + - name: {{ include "grafana.name" . }}-init-sc-notifiers {{- if .Values.sidecar.image.sha }} image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" {{- else }} @@ -162,9 +173,9 @@ initContainers: value: LIST - name: LABEL value: "{{ .Values.sidecar.notifiers.label }}" - {{- if .Values.sidecar.notifiers.labelValue }} + {{- with .Values.sidecar.notifiers.labelValue }} - name: LABEL_VALUE - value: {{ quote .Values.sidecar.notifiers.labelValue }} + value: {{ quote . }} {{- end }} {{- if or .Values.sidecar.logLevel .Values.sidecar.notifiers.logLevel }} - name: LOG_LEVEL @@ -174,17 +185,17 @@ initContainers: value: "/etc/grafana/provisioning/notifiers" - name: RESOURCE value: {{ quote .Values.sidecar.notifiers.resource }} - {{- if .Values.sidecar.enableUniqueFilenames }} + {{- with .Values.sidecar.enableUniqueFilenames }} - name: UNIQUE_FILENAMES - value: "{{ .Values.sidecar.enableUniqueFilenames }}" + value: "{{ . }}" {{- end }} - {{- if .Values.sidecar.notifiers.searchNamespace }} + {{- with .Values.sidecar.notifiers.searchNamespace }} - name: NAMESPACE - value: "{{ tpl (.Values.sidecar.notifiers.searchNamespace | join ",") . }}" + value: "{{ tpl (. | join ",") $root }}" {{- end }} - {{- if .Values.sidecar.skipTlsVerify }} + {{- with .Values.sidecar.skipTlsVerify }} - name: SKIP_TLS_VERIFY - value: "{{ .Values.sidecar.skipTlsVerify }}" + value: "{{ . }}" {{- end }} {{- with .Values.sidecar.livenessProbe }} livenessProbe: @@ -206,22 +217,19 @@ initContainers: - name: sc-notifiers-volume mountPath: "/etc/grafana/provisioning/notifiers" {{- end}} -{{- if .Values.extraInitContainers }} -{{ tpl (toYaml .Values.extraInitContainers) . | indent 2 }} +{{- with .Values.extraInitContainers }} + {{- tpl (toYaml .) $root | nindent 2 }} {{- end }} -{{- if .Values.image.pullSecrets }} +{{- if or .Values.image.pullSecrets .Values.global.imagePullSecrets }} imagePullSecrets: -{{- $root := . }} -{{- range .Values.image.pullSecrets }} - - name: {{ tpl . $root }} -{{- end}} + {{- include "grafana.imagePullSecrets" (dict "root" $root "imagePullSecrets" .Values.image.pullSecrets) | nindent 2 }} {{- end }} {{- if not .Values.enableKubeBackwardCompatibility }} enableServiceLinks: {{ .Values.enableServiceLinks }} {{- end }} containers: {{- if .Values.sidecar.alerts.enabled }} - - name: {{ template "grafana.name" . }}-sc-alerts + - name: {{ include "grafana.name" . }}-sc-alerts {{- if .Values.sidecar.image.sha }} image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" {{- else }} @@ -253,11 +261,11 @@ containers: value: "/etc/grafana/provisioning/alerting" - name: RESOURCE value: {{ quote .Values.sidecar.alerts.resource }} - {{- if .Values.sidecar.enableUniqueFilenames }} + {{- with .Values.sidecar.enableUniqueFilenames }} - name: UNIQUE_FILENAMES - value: "{{ .Values.sidecar.enableUniqueFilenames }}" + value: "{{ . }}" {{- end }} - {{- with .Values.sidecar.alerts.searchNamespace }} + {{- with .Values.sidecar.alerts.searchNamespace }} - name: NAMESPACE value: {{ . | join "," | quote }} {{- end }} @@ -324,7 +332,7 @@ containers: mountPath: "/etc/grafana/provisioning/alerting" {{- end}} {{- if .Values.sidecar.dashboards.enabled }} - - name: {{ template "grafana.name" . }}-sc-dashboard + - name: {{ include "grafana.name" . }}-sc-dashboard {{- if .Values.sidecar.image.sha }} image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" {{- else }} @@ -344,9 +352,9 @@ containers: value: {{ .Values.sidecar.dashboards.watchMethod }} - name: LABEL value: "{{ .Values.sidecar.dashboards.label }}" - {{- if .Values.sidecar.dashboards.labelValue }} + {{- with .Values.sidecar.dashboards.labelValue }} - name: LABEL_VALUE - value: {{ quote .Values.sidecar.dashboards.labelValue }} + value: {{ quote . }} {{- end }} {{- if or .Values.sidecar.logLevel .Values.sidecar.dashboards.logLevel }} - name: LOG_LEVEL @@ -356,25 +364,25 @@ containers: value: "{{ .Values.sidecar.dashboards.folder }}{{- with .Values.sidecar.dashboards.defaultFolderName }}/{{ . }}{{- end }}" - name: RESOURCE value: {{ quote .Values.sidecar.dashboards.resource }} - {{- if .Values.sidecar.enableUniqueFilenames }} + {{- with .Values.sidecar.enableUniqueFilenames }} - name: UNIQUE_FILENAMES - value: "{{ .Values.sidecar.enableUniqueFilenames }}" + value: "{{ . }}" {{- end }} - {{- if .Values.sidecar.dashboards.searchNamespace }} + {{- with .Values.sidecar.dashboards.searchNamespace }} - name: NAMESPACE - value: "{{ tpl (.Values.sidecar.dashboards.searchNamespace | join ",") . }}" + value: "{{ tpl (. | join ",") $root }}" {{- end }} - {{- if .Values.sidecar.skipTlsVerify }} + {{- with .Values.sidecar.skipTlsVerify }} - name: SKIP_TLS_VERIFY - value: "{{ .Values.sidecar.skipTlsVerify }}" + value: "{{ . }}" {{- end }} - {{- if .Values.sidecar.dashboards.folderAnnotation }} + {{- with .Values.sidecar.dashboards.folderAnnotation }} - name: FOLDER_ANNOTATION - value: "{{ .Values.sidecar.dashboards.folderAnnotation }}" + value: "{{ . }}" {{- end }} - {{- if .Values.sidecar.dashboards.script }} + {{- with .Values.sidecar.dashboards.script }} - name: SCRIPT - value: "{{ .Values.sidecar.dashboards.script }}" + value: "{{ . }}" {{- end }} {{- if .Values.sidecar.dashboards.watchServerTimeout }} {{- if ne .Values.sidecar.dashboards.watchMethod "WATCH" }} @@ -388,7 +396,7 @@ containers: {{- fail (printf "Cannot use .Values.sidecar.dashboards.watchClientTimeout with .Values.sidecar.dashboards.watchMethod %s" .Values.sidecar.dashboards.watchMethod) }} {{- end }} - name: WATCH_CLIENT_TIMEOUT - value: "{{ .Values.sidecar.dashboards.watchClientTimeout }}" + value: {{ .Values.sidecar.dashboards.watchClientTimeout | quote }} {{- end }} {{- with .Values.sidecar.livenessProbe }} livenessProbe: @@ -409,12 +417,12 @@ containers: volumeMounts: - name: sc-dashboard-volume mountPath: {{ .Values.sidecar.dashboards.folder | quote }} - {{- if .Values.sidecar.dashboards.extraMounts }} - {{- toYaml .Values.sidecar.dashboards.extraMounts | trim | nindent 6}} + {{- with .Values.sidecar.dashboards.extraMounts }} + {{- toYaml . | trim | nindent 6 }} {{- end }} {{- end}} {{- if .Values.sidecar.datasources.enabled }} - - name: {{ template "grafana.name" . }}-sc-datasources + - name: {{ include "grafana.name" . }}-sc-datasources {{- if .Values.sidecar.image.sha }} image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" {{- else }} @@ -434,9 +442,9 @@ containers: value: {{ .Values.sidecar.datasources.watchMethod }} - name: LABEL value: "{{ .Values.sidecar.datasources.label }}" - {{- if .Values.sidecar.datasources.labelValue }} + {{- with .Values.sidecar.datasources.labelValue }} - name: LABEL_VALUE - value: {{ quote .Values.sidecar.datasources.labelValue }} + value: {{ quote . }} {{- end }} {{- if or .Values.sidecar.logLevel .Values.sidecar.datasources.logLevel }} - name: LOG_LEVEL @@ -446,13 +454,13 @@ containers: value: "/etc/grafana/provisioning/datasources" - name: RESOURCE value: {{ quote .Values.sidecar.datasources.resource }} - {{- if .Values.sidecar.enableUniqueFilenames }} + {{- with .Values.sidecar.enableUniqueFilenames }} - name: UNIQUE_FILENAMES - value: "{{ .Values.sidecar.enableUniqueFilenames }}" + value: "{{ . }}" {{- end }} - {{- if .Values.sidecar.datasources.searchNamespace }} + {{- with .Values.sidecar.datasources.searchNamespace }} - name: NAMESPACE - value: "{{ tpl (.Values.sidecar.datasources.searchNamespace | join ",") . }}" + value: "{{ tpl (. | join ",") $root }}" {{- end }} {{- if .Values.sidecar.skipTlsVerify }} - name: SKIP_TLS_VERIFY @@ -517,7 +525,7 @@ containers: mountPath: "/etc/grafana/provisioning/datasources" {{- end}} {{- if .Values.sidecar.notifiers.enabled }} - - name: {{ template "grafana.name" . }}-sc-notifiers + - name: {{ include "grafana.name" . }}-sc-notifiers {{- if .Values.sidecar.image.sha }} image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" {{- else }} @@ -537,9 +545,9 @@ containers: value: {{ .Values.sidecar.notifiers.watchMethod }} - name: LABEL value: "{{ .Values.sidecar.notifiers.label }}" - {{- if .Values.sidecar.notifiers.labelValue }} + {{- with .Values.sidecar.notifiers.labelValue }} - name: LABEL_VALUE - value: {{ quote .Values.sidecar.notifiers.labelValue }} + value: {{ quote . }} {{- end }} {{- if or .Values.sidecar.logLevel .Values.sidecar.notifiers.logLevel }} - name: LOG_LEVEL @@ -555,11 +563,11 @@ containers: {{- end }} {{- if .Values.sidecar.notifiers.searchNamespace }} - name: NAMESPACE - value: "{{ tpl (.Values.sidecar.notifiers.searchNamespace | join ",") . }}" + value: "{{ tpl (. | join ",") $root }}" {{- end }} - {{- if .Values.sidecar.skipTlsVerify }} + {{- with .Values.sidecar.skipTlsVerify }} - name: SKIP_TLS_VERIFY - value: "{{ .Values.sidecar.skipTlsVerify }}" + value: "{{ . }}" {{- end }} {{- if .Values.sidecar.notifiers.script }} - name: SCRIPT @@ -620,7 +628,7 @@ containers: mountPath: "/etc/grafana/provisioning/notifiers" {{- end}} {{- if .Values.sidecar.plugins.enabled }} - - name: {{ template "grafana.name" . }}-sc-plugins + - name: {{ include "grafana.name" . }}-sc-plugins {{- if .Values.sidecar.image.sha }} image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" {{- else }} @@ -652,21 +660,21 @@ containers: value: "/etc/grafana/provisioning/plugins" - name: RESOURCE value: {{ quote .Values.sidecar.plugins.resource }} - {{- if .Values.sidecar.enableUniqueFilenames }} + {{- with .Values.sidecar.enableUniqueFilenames }} - name: UNIQUE_FILENAMES - value: "{{ .Values.sidecar.enableUniqueFilenames }}" + value: "{{ . }}" {{- end }} - {{- if .Values.sidecar.plugins.searchNamespace }} + {{- with .Values.sidecar.plugins.searchNamespace }} - name: NAMESPACE - value: "{{ tpl (.Values.sidecar.plugins.searchNamespace | join ",") . }}" + value: "{{ tpl (. | join ",") $root }}" {{- end }} - {{- if .Values.sidecar.plugins.script }} + {{- with .Values.sidecar.plugins.script }} - name: SCRIPT - value: "{{ .Values.sidecar.plugins.script }}" + value: "{{ . }}" {{- end }} - {{- if .Values.sidecar.skipTlsVerify }} + {{- with .Values.sidecar.skipTlsVerify }} - name: SKIP_TLS_VERIFY - value: "{{ .Values.sidecar.skipTlsVerify }}" + value: "{{ . }}" {{- end }} {{- if and (not .Values.env.GF_SECURITY_ADMIN_USER) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} - name: REQ_USERNAME @@ -729,12 +737,12 @@ containers: image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" {{- end }} imagePullPolicy: {{ .Values.image.pullPolicy }} - {{- if .Values.command }} + {{- if .Values.command }} command: {{- range .Values.command }} - {{ . | quote }} {{- end }} - {{- end}} + {{- end}} {{- with .Values.containerSecurityContext }} securityContext: {{- toYaml . | nindent 6 }} @@ -748,7 +756,6 @@ containers: mountPath: "/etc/grafana/ldap.toml" subPath: ldap.toml {{- end }} - {{- $root := . }} {{- range .Values.extraConfigmapMounts }} - name: {{ tpl .name $root }} mountPath: {{ tpl .mountPath $root }} @@ -757,95 +764,95 @@ containers: {{- end }} - name: storage mountPath: "/var/lib/grafana" -{{- if .Values.persistence.subPath }} - subPath: {{ tpl .Values.persistence.subPath . }} -{{- end }} -{{- if .Values.dashboards }} -{{- range $provider, $dashboards := .Values.dashboards }} -{{- range $key, $value := $dashboards }} -{{- if (or (hasKey $value "json") (hasKey $value "file")) }} + {{- with .Values.persistence.subPath }} + subPath: {{ tpl . $root }} + {{- end }} + {{- with .Values.dashboards }} + {{- range $provider, $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) }} + {{- end }} + {{- end }} + {{- end }} + {{- end }} + {{- with .Values.dashboardsConfigMaps }} + {{- range (keys . | sortAlpha) }} - name: dashboards-{{ . }} mountPath: "/var/lib/grafana/dashboards/{{ . }}" -{{- end }} -{{- end }} -{{- if .Values.datasources }} -{{- range (keys .Values.datasources | sortAlpha) }} + {{- end }} + {{- end }} + {{- with .Values.datasources }} + {{- range (keys . | sortAlpha) }} - name: config mountPath: "/etc/grafana/provisioning/datasources/{{ . }}" subPath: {{ . | quote }} -{{- end }} -{{- end }} -{{- if .Values.notifiers }} -{{- range (keys .Values.notifiers | sortAlpha) }} + {{- end }} + {{- end }} + {{- with .Values.notifiers }} + {{- range (keys . | sortAlpha) }} - name: config mountPath: "/etc/grafana/provisioning/notifiers/{{ . }}" subPath: {{ . | quote }} -{{- end }} -{{- end }} -{{- if .Values.alerting }} -{{- range (keys .Values.alerting | sortAlpha) }} + {{- end }} + {{- end }} + {{- with .Values.alerting }} + {{- range (keys . | sortAlpha) }} - name: config mountPath: "/etc/grafana/provisioning/alerting/{{ . }}" subPath: {{ . | quote }} -{{- end }} -{{- end }} -{{- if .Values.dashboardProviders }} -{{- range (keys .Values.dashboardProviders | sortAlpha) }} + {{- end }} + {{- end }} + {{- with .Values.dashboardProviders }} + {{- range (keys . | sortAlpha) }} - name: config mountPath: "/etc/grafana/provisioning/dashboards/{{ . }}" subPath: {{ . | quote }} -{{- end }} -{{- end }} -{{- with .Values.sidecar.alerts.enabled }} + {{- end }} + {{- end }} + {{- with .Values.sidecar.alerts.enabled }} - name: sc-alerts-volume mountPath: "/etc/grafana/provisioning/alerting" -{{- end}} -{{- if .Values.sidecar.dashboards.enabled }} + {{- end}} + {{- if .Values.sidecar.dashboards.enabled }} - name: sc-dashboard-volume mountPath: {{ .Values.sidecar.dashboards.folder | quote }} -{{ if .Values.sidecar.dashboards.SCProvider }} + {{- 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 }} + {{- end}} + {{- end}} + {{- if .Values.sidecar.datasources.enabled }} - name: sc-datasources-volume mountPath: "/etc/grafana/provisioning/datasources" -{{- end}} -{{- if .Values.sidecar.plugins.enabled }} + {{- end}} + {{- if .Values.sidecar.plugins.enabled }} - name: sc-plugins-volume mountPath: "/etc/grafana/provisioning/plugins" -{{- end}} -{{- if .Values.sidecar.notifiers.enabled }} + {{- end}} + {{- if .Values.sidecar.notifiers.enabled }} - name: sc-notifiers-volume mountPath: "/etc/grafana/provisioning/notifiers" -{{- end}} - {{- range .Values.extraSecretMounts }} + {{- end}} + {{- range .Values.extraSecretMounts }} - name: {{ .name }} mountPath: {{ .mountPath }} readOnly: {{ .readOnly }} subPath: {{ .subPath | default "" }} - {{- end }} - {{- range .Values.extraVolumeMounts }} + {{- end }} + {{- range .Values.extraVolumeMounts }} - name: {{ .name }} mountPath: {{ .mountPath }} subPath: {{ .subPath | default "" }} readOnly: {{ .readOnly }} - {{- end }} - {{- range .Values.extraEmptyDirMounts }} + {{- end }} + {{- range .Values.extraEmptyDirMounts }} - name: {{ .name }} mountPath: {{ .mountPath }} - {{- end }} + {{- end }} ports: - name: {{ .Values.podPortName }} containerPort: {{ .Values.service.targetPort }} @@ -869,7 +876,7 @@ containers: - name: GF_INSTALL_PLUGINS valueFrom: configMapKeyRef: - name: {{ template "grafana.fullname" . }} + name: {{ include "grafana.fullname" . }} key: plugins {{- end }} {{- if .Values.smtp.existingSecret }} @@ -886,9 +893,9 @@ containers: {{- 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 + value: http://{{ include "grafana.fullname" . }}-image-renderer.{{ include "grafana.namespace" . }}:{{ .Values.imageRenderer.service.port }}/render - name: GF_RENDERING_CALLBACK_URL - value: {{ .Values.imageRenderer.grafanaProtocol }}://{{ template "grafana.fullname" . }}.{{ template "grafana.namespace" . }}:{{ .Values.service.port }}/{{ .Values.imageRenderer.grafanaSubPath }} + value: {{ .Values.imageRenderer.grafanaProtocol }}://{{ include "grafana.fullname" . }}.{{ include "grafana.namespace" . }}:{{ .Values.service.port }}/{{ .Values.imageRenderer.grafanaSubPath }} {{- end }} - name: GF_PATHS_DATA value: {{ (get .Values "grafana.ini").paths.data }} @@ -898,35 +905,35 @@ containers: value: {{ (get .Values "grafana.ini").paths.plugins }} - name: GF_PATHS_PROVISIONING value: {{ (get .Values "grafana.ini").paths.provisioning }} - {{- range $key, $value := .Values.envValueFrom }} + {{- range $key, $value := .Values.envValueFrom }} - name: {{ $key | quote }} valueFrom: -{{ tpl (toYaml $value) $ | indent 10 }} - {{- end }} -{{- range $key, $value := .Values.env }} + {{- tpl (toYaml $value) $ | nindent 10 }} + {{- end }} + {{- range $key, $value := .Values.env }} - name: "{{ tpl $key $ }}" value: "{{ tpl (print $value) $ }}" -{{- end }} + {{- end }} {{- if or .Values.envFromSecret (or .Values.envRenderSecret .Values.envFromSecrets) .Values.envFromConfigMaps }} envFrom: - {{- if .Values.envFromSecret }} + {{- if .Values.envFromSecret }} - secretRef: name: {{ tpl .Values.envFromSecret . }} - {{- end }} - {{- if .Values.envRenderSecret }} + {{- end }} + {{- if .Values.envRenderSecret }} - secretRef: - name: {{ template "grafana.fullname" . }}-env - {{- end }} - {{- range .Values.envFromSecrets }} + name: {{ include "grafana.fullname" . }}-env + {{- end }} + {{- range .Values.envFromSecrets }} - secretRef: name: {{ tpl .name $ }} optional: {{ .optional | default false }} - {{- end }} - {{- range .Values.envFromConfigMaps }} + {{- end }} + {{- range .Values.envFromConfigMaps }} - configMapRef: name: {{ tpl .name $ }} optional: {{ .optional | default false }} - {{- end }} + {{- end }} {{- end }} {{- with .Values.livenessProbe }} livenessProbe: @@ -936,24 +943,24 @@ containers: readinessProbe: {{- toYaml . | nindent 6 }} {{- end }} -{{- if .Values.lifecycleHooks }} - lifecycle: {{ tpl (.Values.lifecycleHooks | toYaml) . | nindent 6 }} -{{- end }} + {{- with .Values.lifecycleHooks }} + lifecycle: + {{- tpl (toYaml .) $root | nindent 6 }} + {{- end }} {{- with .Values.resources }} resources: {{- toYaml . | nindent 6 }} {{- end }} {{- with .Values.extraContainers }} -{{ tpl . $ | indent 2 }} + {{- tpl . $ | nindent 2 }} {{- end }} {{- with .Values.nodeSelector }} nodeSelector: {{- toYaml . | nindent 2 }} {{- end }} -{{- $root := . }} {{- with .Values.affinity }} affinity: -{{ tpl (toYaml .) $root | indent 2 }} + {{- tpl (toYaml .) $root | nindent 2 }} {{- end }} {{- with .Values.topologySpreadConstraints }} topologySpreadConstraints: @@ -966,30 +973,29 @@ tolerations: volumes: - name: config configMap: - name: {{ template "grafana.fullname" . }} -{{- $root := . }} -{{- range .Values.extraConfigmapMounts }} + name: {{ include "grafana.fullname" . }} + {{- range .Values.extraConfigmapMounts }} - name: {{ tpl .name $root }} configMap: name: {{ tpl .configMap $root }} - {{- if .items }} - items: {{ toYaml .items | nindent 6 }} + {{- with .items }} + items: + {{- toYaml . | nindent 8 }} {{- end }} -{{- end }} + {{- end }} {{- if .Values.dashboards }} - {{- range (keys .Values.dashboards | sortAlpha) }} + {{- range (keys .Values.dashboards | sortAlpha) }} - name: dashboards-{{ . }} configMap: - name: {{ template "grafana.fullname" $ }}-dashboards-{{ . }} - {{- end }} + name: {{ include "grafana.fullname" $ }}-dashboards-{{ . }} + {{- end }} {{- end }} {{- if .Values.dashboardsConfigMaps }} - {{ $root := . }} - {{- range $provider, $name := .Values.dashboardsConfigMaps }} + {{- range $provider, $name := .Values.dashboardsConfigMaps }} - name: dashboards-{{ $provider }} configMap: name: {{ tpl $name $root }} - {{- end }} + {{- end }} {{- end }} {{- if .Values.ldap.enabled }} - name: ldap @@ -997,98 +1003,101 @@ volumes: {{- if .Values.ldap.existingSecret }} secretName: {{ .Values.ldap.existingSecret }} {{- else }} - secretName: {{ template "grafana.fullname" . }} + secretName: {{ include "grafana.fullname" . }} {{- end }} items: - key: ldap-toml path: ldap.toml {{- end }} -{{- if and .Values.persistence.enabled (eq .Values.persistence.type "pvc") }} + {{- if and .Values.persistence.enabled (eq .Values.persistence.type "pvc") }} - name: storage persistentVolumeClaim: claimName: {{ tpl (.Values.persistence.existingClaim | default (include "grafana.fullname" .)) . }} -{{- else if and .Values.persistence.enabled (eq .Values.persistence.type "statefulset") }} -# nothing -{{- else }} + {{- else if and .Values.persistence.enabled (eq .Values.persistence.type "statefulset") }} + # nothing + {{- else }} - name: storage -{{- if .Values.persistence.inMemory.enabled }} + {{- if .Values.persistence.inMemory.enabled }} emptyDir: medium: Memory -{{- if .Values.persistence.inMemory.sizeLimit }} - sizeLimit: {{ .Values.persistence.inMemory.sizeLimit }} -{{- end -}} -{{- else }} + {{- with .Values.persistence.inMemory.sizeLimit }} + sizeLimit: {{ . }} + {{- end }} + {{- else }} emptyDir: {} -{{- end -}} -{{- end -}} -{{- if .Values.sidecar.alerts.enabled }} + {{- end }} + {{- end }} + {{- if .Values.sidecar.alerts.enabled }} - name: sc-alerts-volume -{{- if .Values.sidecar.alerts.sizeLimit }} emptyDir: - sizeLimit: {{ .Values.sidecar.alerts.sizeLimit }} -{{- else }} - emptyDir: {} -{{- end -}} -{{- end -}} -{{- if .Values.sidecar.dashboards.enabled }} + {{- with .Values.sidecar.alerts.sizeLimit }} + sizeLimit: {{ . }} + {{- else }} + {} + {{- end }} + {{- end }} + {{- if .Values.sidecar.dashboards.enabled }} - name: sc-dashboard-volume -{{- if .Values.sidecar.dashboards.sizeLimit }} emptyDir: - sizeLimit: {{ .Values.sidecar.dashboards.sizeLimit }} -{{- else }} - emptyDir: {} -{{- end -}} -{{- if .Values.sidecar.dashboards.SCProvider }} + {{- with .Values.sidecar.dashboards.sizeLimit }} + sizeLimit: {{ . }} + {{- else }} + {} + {{- end }} + {{- if .Values.sidecar.dashboards.SCProvider }} - name: sc-dashboard-provider configMap: - name: {{ template "grafana.fullname" . }}-config-dashboards -{{- end }} -{{- end }} -{{- if .Values.sidecar.datasources.enabled }} + name: {{ include "grafana.fullname" . }}-config-dashboards + {{- end }} + {{- end }} + {{- if .Values.sidecar.datasources.enabled }} - name: sc-datasources-volume -{{- if .Values.sidecar.datasources.sizeLimit }} emptyDir: - sizeLimit: {{ .Values.sidecar.datasources.sizeLimit }} -{{- else }} - emptyDir: {} -{{- end -}} -{{- end -}} -{{- if .Values.sidecar.plugins.enabled }} + {{- with .Values.sidecar.datasources.sizeLimit }} + sizeLimit: {{ . }} + {{- else }} + {} + {{- end }} + {{- end }} + {{- if .Values.sidecar.plugins.enabled }} - name: sc-plugins-volume -{{- if .Values.sidecar.plugins.sizeLimit }} emptyDir: - sizeLimit: {{ .Values.sidecar.plugins.sizeLimit }} -{{- else }} - emptyDir: {} -{{- end -}} -{{- end -}} -{{- if .Values.sidecar.notifiers.enabled }} + {{- with .Values.sidecar.plugins.sizeLimit }} + sizeLimit: {{ . }} + {{- else }} + {} + {{- end }} + {{- end }} + {{- if .Values.sidecar.notifiers.enabled }} - name: sc-notifiers-volume -{{- if .Values.sidecar.notifiers.sizeLimit }} emptyDir: - sizeLimit: {{ .Values.sidecar.notifiers.sizeLimit }} -{{- else }} - emptyDir: {} -{{- end -}} -{{- end -}} -{{- range .Values.extraSecretMounts }} -{{- if .secretName }} + {{- with .Values.sidecar.notifiers.sizeLimit }} + sizeLimit: {{ . }} + {{- else }} + {} + {{- end }} + {{- end }} + {{- range .Values.extraSecretMounts }} + {{- if .secretName }} - name: {{ .name }} secret: secretName: {{ .secretName }} defaultMode: {{ .defaultMode }} - {{- if .items }} - items: {{ toYaml .items | nindent 6 }} + {{- with .items }} + items: + {{- toYaml . | nindent 8 }} {{- end }} -{{- else if .projected }} + {{- else if .projected }} - name: {{ .name }} - projected: {{- toYaml .projected | nindent 6 }} -{{- else if .csi }} + projected: + {{- toYaml .projected | nindent 6 }} + {{- else if .csi }} - name: {{ .name }} - csi: {{- toYaml .csi | nindent 6 }} -{{- end }} -{{- end }} -{{- range .Values.extraVolumeMounts }} + csi: + {{- toYaml .csi | nindent 6 }} + {{- end }} + {{- end }} + {{- range .Values.extraVolumeMounts }} - name: {{ .name }} {{- if .existingClaim }} persistentVolumeClaim: @@ -1099,16 +1108,16 @@ volumes: {{- else if .csi }} csi: data: - {{ toYaml .data | nindent 6 }} + {{- toYaml .data | nindent 8 }} {{- else }} emptyDir: {} {{- end }} -{{- end }} -{{- range .Values.extraEmptyDirMounts }} + {{- end }} + {{- range .Values.extraEmptyDirMounts }} - name: {{ .name }} emptyDir: {} -{{- end -}} -{{- if .Values.extraContainerVolumes }} -{{ tpl (toYaml .Values.extraContainerVolumes) . | indent 2 }} -{{- end }} + {{- end }} + {{- with .Values.extraContainerVolumes }} + {{- tpl (toYaml .) $root | nindent 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 index 154658b5..3396713a 100644 --- 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 @@ -4,21 +4,21 @@ apiVersion: rbac.authorization.k8s.io/v1 metadata: labels: {{- include "grafana.labels" . | nindent 4 }} -{{- with .Values.annotations }} + {{- with .Values.annotations }} annotations: -{{ toYaml . | indent 4 }} -{{- end }} - name: {{ template "grafana.fullname" . }}-clusterrole + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "grafana.fullname" . }}-clusterrole {{- if or .Values.sidecar.dashboards.enabled (or .Values.rbac.extraClusterRoleRules (or .Values.sidecar.datasources.enabled .Values.sidecar.plugins.enabled)) }} rules: -{{- if or .Values.sidecar.dashboards.enabled (or .Values.sidecar.datasources.enabled .Values.sidecar.plugins.enabled) }} -- apiGroups: [""] # "" indicates the core API group - resources: ["configmaps", "secrets"] - verbs: ["get", "watch", "list"] -{{- end}} -{{- with .Values.rbac.extraClusterRoleRules }} -{{ toYaml . | indent 0 }} -{{- end}} + {{- if or .Values.sidecar.dashboards.enabled (or .Values.sidecar.datasources.enabled .Values.sidecar.plugins.enabled) }} + - apiGroups: [""] # "" indicates the core API group + resources: ["configmaps", "secrets"] + verbs: ["get", "watch", "list"] + {{- end}} + {{- with .Values.rbac.extraClusterRoleRules }} + {{- toYaml . | nindent 2 }} + {{- end}} {{- else }} rules: [] {{- 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 index 4accbfac..48411fe8 100644 --- 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 @@ -2,23 +2,23 @@ kind: ClusterRoleBinding apiVersion: rbac.authorization.k8s.io/v1 metadata: - name: {{ template "grafana.fullname" . }}-clusterrolebinding + name: {{ include "grafana.fullname" . }}-clusterrolebinding labels: {{- include "grafana.labels" . | nindent 4 }} -{{- with .Values.annotations }} + {{- with .Values.annotations }} annotations: -{{ toYaml . | indent 4 }} -{{- end }} + {{- toYaml . | nindent 4 }} + {{- end }} subjects: - kind: ServiceAccount - name: {{ template "grafana.serviceAccountName" . }} - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.serviceAccountName" . }} + namespace: {{ include "grafana.namespace" . }} roleRef: kind: ClusterRole -{{- if (not .Values.rbac.useExistingRole) }} - name: {{ template "grafana.fullname" . }}-clusterrole -{{- else }} + {{- if .Values.rbac.useExistingRole }} name: {{ .Values.rbac.useExistingRole }} -{{- end }} + {{- else }} + name: {{ include "grafana.fullname" . }}-clusterrole + {{- end }} apiGroup: rbac.authorization.k8s.io -{{- end -}} +{{- 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 index ff78adb2..1f706a8b 100644 --- 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 @@ -4,26 +4,26 @@ kind: ConfigMap metadata: labels: {{- include "grafana.labels" . | nindent 4 }} -{{- with .Values.annotations }} + {{- with .Values.annotations }} annotations: -{{ toYaml . | indent 4 }} -{{- end }} - name: {{ template "grafana.fullname" . }}-config-dashboards - namespace: {{ template "grafana.namespace" . }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "grafana.fullname" . }}-config-dashboards + namespace: {{ include "grafana.namespace" . }} data: provider.yaml: |- apiVersion: 1 providers: - - name: '{{ .Values.sidecar.dashboards.provider.name }}' - orgId: {{ .Values.sidecar.dashboards.provider.orgid }} - {{- if not .Values.sidecar.dashboards.provider.foldersFromFilesStructure }} - folder: '{{ .Values.sidecar.dashboards.provider.folder }}' - {{- end}} - type: {{ .Values.sidecar.dashboards.provider.type }} - disableDeletion: {{ .Values.sidecar.dashboards.provider.disableDelete }} - allowUiUpdates: {{ .Values.sidecar.dashboards.provider.allowUiUpdates }} - updateIntervalSeconds: {{ .Values.sidecar.dashboards.provider.updateIntervalSeconds | default 30 }} - options: - foldersFromFilesStructure: {{ .Values.sidecar.dashboards.provider.foldersFromFilesStructure }} - path: {{ .Values.sidecar.dashboards.folder }}{{- with .Values.sidecar.dashboards.defaultFolderName }}/{{ . }}{{- end }} -{{- end}} + - name: '{{ .Values.sidecar.dashboards.provider.name }}' + orgId: {{ .Values.sidecar.dashboards.provider.orgid }} + {{- if not .Values.sidecar.dashboards.provider.foldersFromFilesStructure }} + folder: '{{ .Values.sidecar.dashboards.provider.folder }}' + {{- end }} + type: {{ .Values.sidecar.dashboards.provider.type }} + disableDeletion: {{ .Values.sidecar.dashboards.provider.disableDelete }} + allowUiUpdates: {{ .Values.sidecar.dashboards.provider.allowUiUpdates }} + updateIntervalSeconds: {{ .Values.sidecar.dashboards.provider.updateIntervalSeconds | default 30 }} + 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 index 1f3db0bd..b0735a2b 100644 --- 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 @@ -1,21 +1,22 @@ {{- if .Values.createConfigmap }} +{{- $root := . -}} apiVersion: v1 kind: ConfigMap metadata: - name: {{ template "grafana.fullname" . }} - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} labels: {{- include "grafana.labels" . | nindent 4 }} -{{- with .Values.annotations }} + {{- with .Values.annotations }} annotations: -{{ toYaml . | indent 4 }} -{{- end }} + {{- toYaml . | nindent 4 }} + {{- end }} data: -{{- if .Values.plugins }} - plugins: {{ join "," .Values.plugins }} -{{- end }} + {{- with .Values.plugins }} + plugins: {{ join "," . }} + {{- end }} grafana.ini: | -{{- range $elem, $elemVal := index .Values "grafana.ini" }} + {{- range $elem, $elemVal := index .Values "grafana.ini" }} {{- if not (kindIs "map" $elemVal) }} {{- if kindIs "invalid" $elemVal }} {{ $elem }} = @@ -25,8 +26,8 @@ data: {{ $elem }} = {{ $elemVal }} {{- end }} {{- end }} -{{- end }} -{{- range $key, $value := index .Values "grafana.ini" }} + {{- end }} + {{- range $key, $value := index .Values "grafana.ini" }} {{- if kindIs "map" $value }} [{{ $key }}] {{- range $elem, $elemVal := $value }} @@ -39,37 +40,27 @@ data: {{- end }} {{- end }} {{- end }} -{{- end }} + {{- end }} -{{- if .Values.datasources }} -{{ $root := . }} {{- range $key, $value := .Values.datasources }} - {{ $key }}: | -{{ tpl (toYaml $value | indent 4) $root }} - {{- end -}} -{{- end -}} + {{- $key | nindent 2 }}: | + {{- tpl (toYaml $value | nindent 4) $root }} + {{- end }} -{{- if .Values.notifiers }} {{- range $key, $value := .Values.notifiers }} - {{ $key }}: | -{{ toYaml $value | indent 4 }} - {{- end -}} -{{- end -}} + {{- $key | nindent 2 }}: | + {{- toYaml $value | nindent 4 }} + {{- end }} -{{- if .Values.alerting }} -{{ $root := . }} {{- range $key, $value := .Values.alerting }} - {{ $key }}: | -{{ tpl (toYaml $value | indent 4) $root }} - {{- end -}} -{{- end -}} + {{- $key | nindent 2 }}: | + {{- tpl (toYaml $value | nindent 4) $root }} + {{- end }} -{{- if .Values.dashboardProviders }} {{- range $key, $value := .Values.dashboardProviders }} - {{ $key }}: | -{{ toYaml $value | indent 4 }} - {{- end -}} -{{- end -}} + {{- $key | nindent 2 }}: | + {{- toYaml $value | nindent 4 }} + {{- end }} {{- if .Values.dashboards }} download_dashboards.sh: | @@ -101,34 +92,34 @@ data: -H "PRIVATE-TOKEN: {{ $value.gitlabToken }}" \ {{- end }} -H "Content-Type: application/json;charset=UTF-8" \ - {{- end -}} + {{- end }} {{- $dpPath := "" -}} - {{- range $kd := (index $dashboardProviders "dashboardproviders.yaml").providers -}} - {{- if eq $kd.name $provider -}} - {{- $dpPath = $kd.options.path -}} - {{- end -}} - {{- end -}} + {{- range $kd := (index $dashboardProviders "dashboardproviders.yaml").providers }} + {{- if eq $kd.name $provider }} + {{- $dpPath = $kd.options.path }} + {{- end }} + {{- 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 -}} + {{- end }} {{- if $value.datasource }} {{- if kindIs "string" $value.datasource }} | sed '/-- .* --/! s/"datasource":.*,/"datasource": "{{ $value.datasource }}",/g' \ - {{- end -}} - {{- if kindIs "slice" $value.datasource -}} + {{- end }} + {{- if kindIs "slice" $value.datasource }} {{- range $value.datasource }} | sed '/-- .* --/! s/${{"{"}}{{ .name }}}/{{ .value }}/g' \ - {{- end -}} - {{- end -}} - {{- end -}} + {{- end }} + {{- end }} + {{- end }} {{- if $value.b64content }} | base64 -d \ {{- end }} > "{{- if $dpPath -}}{{ $dpPath }}{{- else -}}/var/lib/grafana/dashboards/{{ $provider }}{{- end -}}/{{ $key }}.json" {{ end }} - {{- end -}} + {{- 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 index 59e0be64..df0ed0d8 100644 --- 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 @@ -4,8 +4,8 @@ apiVersion: v1 kind: ConfigMap metadata: - name: {{ template "grafana.fullname" $ }}-dashboards-{{ $provider }} - namespace: {{ template "grafana.namespace" $ }} + name: {{ include "grafana.fullname" $ }}-dashboards-{{ $provider }} + namespace: {{ include "grafana.namespace" $ }} labels: {{- include "grafana.labels" $ | nindent 4 }} dashboard-provider: {{ $provider }} @@ -15,14 +15,14 @@ data: {{- range $key, $value := $dashboards }} {{- if (or (hasKey $value "json") (hasKey $value "file")) }} {{- $dashboardFound = true }} -{{ print $key | indent 2 }}.json: -{{- if hasKey $value "json" }} + {{- print $key | nindent 2 }}.json: + {{- if hasKey $value "json" }} |- -{{ $value.json | indent 6 }} -{{- end }} -{{- if hasKey $value "file" }} -{{ toYaml ( $files.Get $value.file ) | indent 4}} -{{- end }} + {{- $value.json | nindent 6 }} + {{- end }} + {{- if hasKey $value "file" }} + {{- toYaml ( $files.Get $value.file ) | nindent 4}} + {{- end }} {{- end }} {{- end }} {{- if not $dashboardFound }} 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 index fee9c335..96eac4d2 100644 --- 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 @@ -1,18 +1,18 @@ -{{ if (and (not .Values.useStatefulSet) (or (not .Values.persistence.enabled) (eq .Values.persistence.type "pvc"))) }} +{{- if (and (not .Values.useStatefulSet) (or (not .Values.persistence.enabled) (eq .Values.persistence.type "pvc"))) }} apiVersion: apps/v1 kind: Deployment metadata: - name: {{ template "grafana.fullname" . }} - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} labels: {{- include "grafana.labels" . | nindent 4 }} -{{- if .Values.labels }} -{{ toYaml .Values.labels | indent 4 }} -{{- end }} -{{- with .Values.annotations }} + {{- with .Values.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.annotations }} annotations: -{{ toYaml . | indent 4 }} -{{- end }} + {{- toYaml . | nindent 4 }} + {{- end }} spec: {{- if and (not .Values.autoscaling.enabled) (.Values.replicas) }} replicas: {{ .Values.replicas }} @@ -21,30 +21,30 @@ spec: selector: matchLabels: {{- include "grafana.selectorLabels" . | nindent 6 }} -{{- with .Values.deploymentStrategy }} + {{- with .Values.deploymentStrategy }} strategy: -{{ toYaml . | trim | indent 4 }} -{{- end }} + {{- toYaml . | trim | nindent 4 }} + {{- end }} template: metadata: labels: {{- include "grafana.selectorLabels" . | nindent 8 }} -{{- with .Values.podLabels }} -{{ toYaml . | indent 8 }} -{{- end }} + {{- with .Values.podLabels }} + {{- toYaml . | nindent 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 and (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))) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + {{- if and (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))) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} checksum/secret: {{ include (print $.Template.BasePath "/secret.yaml") . | sha256sum }} -{{- end }} -{{- if .Values.envRenderSecret }} + {{- end }} + {{- if .Values.envRenderSecret }} checksum/secret-env: {{ include (print $.Template.BasePath "/secret-env.yaml") . | sha256sum }} -{{- end }} -{{- with .Values.podAnnotations }} -{{ toYaml . | indent 8 }} -{{- end }} + {{- end }} + {{- with .Values.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} spec: - {{- include "grafana.pod" . | indent 6 }} + {{- 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 index b5faddcf..1140a2d8 100644 --- 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 @@ -1,15 +1,16 @@ -{{- if or .Values.headlessService (and .Values.persistence.enabled (not .Values.persistence.existingClaim) (eq .Values.persistence.type "statefulset"))}} +{{- $sts := list "sts" "StatefulSet" -}} +{{- if or .Values.headlessService (and .Values.persistence.enabled (not .Values.persistence.existingClaim) (has .Values.persistence.type $sts)) }} apiVersion: v1 kind: Service metadata: - name: {{ template "grafana.fullname" . }}-headless - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.fullname" . }}-headless + namespace: {{ include "grafana.namespace" . }} labels: {{- include "grafana.labels" . | nindent 4 }} -{{- with .Values.annotations }} + {{- with .Values.annotations }} annotations: -{{ toYaml . | indent 4 }} -{{- end }} + {{- toYaml . | nindent 4 }} + {{- end }} spec: clusterIP: None selector: diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/hpa.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/hpa.yaml index 05723974..42d7c67f 100644 --- a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/hpa.yaml +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/hpa.yaml @@ -1,21 +1,26 @@ +{{- $sts := list "sts" "StatefulSet" -}} {{- if .Values.autoscaling.enabled }} apiVersion: autoscaling/v2beta1 kind: HorizontalPodAutoscaler metadata: - name: {{ template "grafana.fullname" . }} - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} labels: - app.kubernetes.io/name: {{ template "grafana.name" . }} - helm.sh/chart: {{ template "grafana.chart" . }} + app.kubernetes.io/name: {{ include "grafana.name" . }} + helm.sh/chart: {{ include "grafana.chart" . }} app.kubernetes.io/managed-by: {{ .Release.Service }} app.kubernetes.io/instance: {{ .Release.Name }} spec: scaleTargetRef: apiVersion: apps/v1 + {{- if has .Values.persistence.type $sts }} + kind: StatefulSet + {{- else }} kind: Deployment - name: {{ template "grafana.fullname" . }} + {{- end }} + name: {{ include "grafana.fullname" . }} minReplicas: {{ .Values.autoscaling.minReplicas }} maxReplicas: {{ .Values.autoscaling.maxReplicas }} metrics: -{{ toYaml .Values.autoscaling.metrics | indent 4 }} + {{- toYaml .Values.autoscaling.metrics | nindent 4 }} {{- 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 index c558a86a..b087179f 100644 --- 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 @@ -1,65 +1,65 @@ {{ if .Values.imageRenderer.enabled }} +{{- $root := . -}} apiVersion: apps/v1 kind: Deployment metadata: - name: {{ template "grafana.fullname" . }}-image-renderer - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.fullname" . }}-image-renderer + namespace: {{ include "grafana.namespace" . }} labels: {{- include "grafana.imageRenderer.labels" . | nindent 4 }} -{{- if .Values.imageRenderer.labels }} -{{ toYaml .Values.imageRenderer.labels | indent 4 }} -{{- end }} -{{- with .Values.imageRenderer.annotations }} + {{- with .Values.imageRenderer.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.imageRenderer.annotations }} annotations: -{{ toYaml . | indent 4 }} -{{- end }} + {{- toYaml . | nindent 4 }} + {{- end }} spec: replicas: {{ .Values.imageRenderer.replicas }} revisionHistoryLimit: {{ .Values.imageRenderer.revisionHistoryLimit }} selector: matchLabels: {{- include "grafana.imageRenderer.selectorLabels" . | nindent 6 }} -{{- with .Values.imageRenderer.deploymentStrategy }} + + {{- with .Values.imageRenderer.deploymentStrategy }} strategy: -{{ toYaml . | trim | indent 4 }} -{{- end }} + {{- toYaml . | trim | nindent 4 }} + {{- end }} template: metadata: labels: {{- include "grafana.imageRenderer.selectorLabels" . | nindent 8 }} -{{- with .Values.imageRenderer.podLabels }} -{{ toYaml . | indent 8 }} -{{- end }} + {{- with .Values.imageRenderer.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} annotations: checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} -{{- with .Values.imageRenderer.podAnnotations }} -{{ toYaml . | indent 8 }} -{{- end }} + {{- with .Values.imageRenderer.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} spec: - - {{- if .Values.imageRenderer.schedulerName }} - schedulerName: "{{ .Values.imageRenderer.schedulerName }}" + {{- with .Values.imageRenderer.schedulerName }} + schedulerName: "{{ . }}" {{- end }} - {{- if .Values.imageRenderer.serviceAccountName }} - serviceAccountName: "{{ .Values.imageRenderer.serviceAccountName }}" + {{- with .Values.imageRenderer.serviceAccountName }} + serviceAccountName: "{{ . }}" {{- end }} - {{- if .Values.imageRenderer.securityContext }} + {{- with .Values.imageRenderer.securityContext }} securityContext: - {{- toYaml .Values.imageRenderer.securityContext | nindent 8 }} + {{- toYaml . | nindent 8 }} {{- end }} - {{- if .Values.imageRenderer.hostAliases }} + {{- with .Values.imageRenderer.hostAliases }} hostAliases: - {{- toYaml .Values.imageRenderer.hostAliases | nindent 8 }} + {{- toYaml . | nindent 8 }} {{- end }} - {{- if .Values.imageRenderer.priorityClassName }} - priorityClassName: {{ .Values.imageRenderer.priorityClassName }} + {{- with .Values.imageRenderer.priorityClassName }} + priorityClassName: {{ . }} {{- end }} - {{- if .Values.imageRenderer.image.pullSecrets }} + {{- with .Values.imageRenderer.image.pullSecrets }} imagePullSecrets: - {{- $root := . }} - {{- range .Values.imageRenderer.image.pullSecrets }} + {{- range . }} - name: {{ tpl . $root }} - {{- end}} + {{- end}} {{- end }} containers: - name: {{ .Chart.Name }}-image-renderer @@ -69,12 +69,12 @@ spec: image: "{{ .Values.imageRenderer.image.repository }}:{{ .Values.imageRenderer.image.tag }}" {{- end }} imagePullPolicy: {{ .Values.imageRenderer.image.pullPolicy }} - {{- if .Values.imageRenderer.command }} + {{- if .Values.imageRenderer.command }} command: - {{- range .Values.imageRenderer.command }} + {{- range .Values.imageRenderer.command }} - {{ . }} - {{- end }} - {{- end}} + {{- end }} + {{- end}} ports: - name: {{ .Values.imageRenderer.service.portName }} containerPort: {{ .Values.imageRenderer.service.targetPort }} @@ -90,30 +90,28 @@ spec: - name: {{ $key | quote }} value: {{ $value | quote }} {{- end }} + {{- with .Values.imageRenderer.containerSecurityContext }} securityContext: - capabilities: - drop: ['all'] - allowPrivilegeEscalation: false - readOnlyRootFilesystem: true + {{- toYaml . | nindent 12 }} + {{- end }} volumeMounts: - mountPath: /tmp name: image-renderer-tmpfs - {{- with .Values.imageRenderer.resources }} + {{- with .Values.imageRenderer.resources }} resources: -{{ toYaml . | indent 12 }} - {{- end }} + {{- toYaml . | nindent 12 }} + {{- end }} {{- with .Values.imageRenderer.nodeSelector }} nodeSelector: -{{ toYaml . | indent 8 }} + {{- toYaml . | nindent 8 }} {{- end }} - {{- $root := . }} {{- with .Values.imageRenderer.affinity }} affinity: -{{ tpl (toYaml .) $root | indent 8 }} + {{- tpl (toYaml .) $root | nindent 8 }} {{- end }} {{- with .Values.imageRenderer.tolerations }} tolerations: -{{ toYaml . | indent 8 }} + {{- toYaml . | nindent 8 }} {{- end }} volumes: - name: image-renderer-tmpfs 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 index 0d9bdfe4..fb694451 100644 --- 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 @@ -1,18 +1,18 @@ -{{- if and (.Values.imageRenderer.enabled) (.Values.imageRenderer.networkPolicy.limitIngress) }} +{{- 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" . }} + name: {{ include "grafana.fullname" . }}-image-renderer-ingress + namespace: {{ include "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 }} + {{- with .Values.imageRenderer.podLabels }} + {{- toYaml . | nindent 6 }} {{- end }} policyTypes: @@ -24,30 +24,30 @@ spec: from: - namespaceSelector: matchLabels: - name: {{ template "grafana.namespace" . }} - podSelector: + name: {{ include "grafana.namespace" . }} + - podSelector: matchLabels: {{- include "grafana.selectorLabels" . | nindent 14 }} - {{- if .Values.podLabels }} - {{ toYaml .Values.podLabels | nindent 14 }} + {{- with .Values.podLabels }} + {{- toYaml . | nindent 14 }} {{- end }} -{{ end }} +{{- end }} -{{- if and (.Values.imageRenderer.enabled) (.Values.imageRenderer.networkPolicy.limitEgress) }} +{{- 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" . }} + name: {{ include "grafana.fullname" . }}-image-renderer-egress + namespace: {{ include "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 }} + {{- with .Values.imageRenderer.podLabels }} + {{- toYaml . | nindent 6 }} {{- end }} policyTypes: @@ -67,7 +67,7 @@ spec: - podSelector: matchLabels: {{- include "grafana.selectorLabels" . | nindent 14 }} - {{- if .Values.podLabels }} - {{ toYaml .Values.podLabels | nindent 14 }} + {{- with .Values.podLabels }} + {{- toYaml . | nindent 14 }} {{- end }} -{{ 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 index fcf707a3..f8da127c 100644 --- 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 @@ -1,33 +1,31 @@ -{{ if .Values.imageRenderer.enabled }} -{{ if .Values.imageRenderer.service.enabled }} +{{- if and .Values.imageRenderer.enabled .Values.imageRenderer.service.enabled }} apiVersion: v1 kind: Service metadata: - name: {{ template "grafana.fullname" . }}-image-renderer - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.fullname" . }}-image-renderer + namespace: {{ include "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 }} + {{- with .Values.imageRenderer.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.imageRenderer.service.annotations }} annotations: -{{ toYaml . | indent 4 }} -{{- end }} + {{- toYaml . | nindent 4 }} + {{- end }} spec: type: ClusterIP - {{- if .Values.imageRenderer.service.clusterIP }} - clusterIP: {{ .Values.imageRenderer.service.clusterIP }} - {{end}} + {{- with .Values.imageRenderer.service.clusterIP }} + clusterIP: {{ . }} + {{- end }} ports: - name: {{ .Values.imageRenderer.service.portName }} port: {{ .Values.imageRenderer.service.port }} protocol: TCP targetPort: {{ .Values.imageRenderer.service.targetPort }} - {{- if .Values.imageRenderer.appProtocol }} - appProtocol: {{ .Values.imageRenderer.appProtocol }} + {{- with .Values.imageRenderer.appProtocol }} + appProtocol: {{ . }} {{- end }} selector: {{- include "grafana.imageRenderer.selectorLabels" . | nindent 4 }} -{{ end }} -{{ end }} +{{- 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 index 7699ceca..063cdfaa 100644 --- 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 @@ -11,15 +11,15 @@ apiVersion: {{ include "grafana.ingress.apiVersion" . }} kind: Ingress metadata: name: {{ $fullName }} - namespace: {{ template "grafana.namespace" . }} + namespace: {{ include "grafana.namespace" . }} labels: {{- include "grafana.labels" . | nindent 4 }} -{{- if .Values.ingress.labels }} -{{ toYaml .Values.ingress.labels | indent 4 }} -{{- end }} - {{- if .Values.ingress.annotations }} + {{- with .Values.ingress.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.ingress.annotations }} annotations: - {{- range $key, $value := .Values.ingress.annotations }} + {{- range $key, $value := . }} {{ $key }}: {{ tpl $value $ | quote }} {{- end }} {{- end }} @@ -27,19 +27,19 @@ spec: {{- if and $ingressSupportsIngressClassName .Values.ingress.ingressClassName }} ingressClassName: {{ .Values.ingress.ingressClassName }} {{- end -}} -{{- if .Values.ingress.tls }} + {{- with .Values.ingress.tls }} tls: -{{ tpl (toYaml .Values.ingress.tls) $ | indent 4 }} -{{- end }} + {{- tpl (toYaml .) $ | nindent 4 }} + {{- end }} rules: {{- if .Values.ingress.hosts }} {{- range .Values.ingress.hosts }} - - host: {{ tpl . $}} + - host: {{ tpl . $ }} http: paths: -{{- if $extraPaths }} -{{ toYaml $extraPaths | indent 10 }} -{{- end }} + {{- with $extraPaths }} + {{- toYaml . | nindent 10 }} + {{- end }} - path: {{ $ingressPath }} {{- if $ingressSupportsPathType }} pathType: {{ $ingressPathType }} @@ -68,8 +68,8 @@ spec: serviceName: {{ $fullName }} servicePort: {{ $servicePort }} {{- end }} - {{- if $ingressPath }} - path: {{ $ingressPath }} + {{- with $ingressPath }} + path: {{ . }} {{- end }} {{- if $ingressSupportsPathType }} pathType: {{ $ingressPathType }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/networkpolicy.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/networkpolicy.yaml index b751d943..ea4578be 100644 --- a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/networkpolicy.yaml +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/networkpolicy.yaml @@ -2,12 +2,12 @@ apiVersion: networking.k8s.io/v1 kind: NetworkPolicy metadata: - name: {{ template "grafana.fullname" . }} - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} labels: {{- include "grafana.labels" . | nindent 4 }} {{- with .Values.labels }} - {{ toYaml . | nindent 4 }} + {{- toYaml . | nindent 4 }} {{- end }} {{- with .Values.annotations }} annotations: @@ -23,7 +23,7 @@ spec: {{- end }} podSelector: matchLabels: - {{- include "grafana.selectorLabels" . | nindent 6 }} + {{- include "grafana.selectorLabels" . | nindent 6 }} {{- if .Values.networkPolicy.egress.enabled }} egress: @@ -38,7 +38,7 @@ spec: from: - podSelector: matchLabels: - {{ template "grafana.fullname" . }}-client: "true" + {{ include "grafana.fullname" . }}-client: "true" {{- with .Values.networkPolicy.explicitNamespacesSelector }} - namespaceSelector: {{- toYaml . | nindent 12 }} 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 index 70901b70..05251214 100644 --- 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 @@ -2,20 +2,20 @@ apiVersion: {{ include "grafana.podDisruptionBudget.apiVersion" . }} kind: PodDisruptionBudget metadata: - name: {{ template "grafana.fullname" . }} - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} labels: {{- include "grafana.labels" . | nindent 4 }} -{{- if .Values.labels }} -{{ toYaml .Values.labels | indent 4 }} -{{- end }} + {{- with .Values.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} spec: -{{- if .Values.podDisruptionBudget.minAvailable }} - minAvailable: {{ .Values.podDisruptionBudget.minAvailable }} -{{- end }} -{{- if .Values.podDisruptionBudget.maxUnavailable }} - maxUnavailable: {{ .Values.podDisruptionBudget.maxUnavailable }} -{{- end }} + {{- with .Values.podDisruptionBudget.minAvailable }} + minAvailable: {{ . }} + {{- end }} + {{- with .Values.podDisruptionBudget.maxUnavailable }} + maxUnavailable: {{ . }} + {{- end }} selector: matchLabels: {{- include "grafana.selectorLabels" . | nindent 6 }} 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 index d9905c62..eed7af95 100644 --- 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 @@ -1,9 +1,8 @@ -{{- if .Values.rbac.pspEnabled }} -{{- if .Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy" }} +{{- if and .Values.rbac.pspEnabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} apiVersion: policy/v1beta1 kind: PodSecurityPolicy metadata: - name: {{ template "grafana.fullname" . }} + name: {{ include "grafana.fullname" . }} labels: {{- include "grafana.labels" . | nindent 4 }} annotations: @@ -48,4 +47,3 @@ spec: max: 65535 readOnlyRootFilesystem: false {{- end }} -{{- 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 index 8d93f5c2..eb8f87f0 100644 --- 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 @@ -2,17 +2,20 @@ apiVersion: v1 kind: PersistentVolumeClaim metadata: - name: {{ template "grafana.fullname" . }} - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} labels: {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.persistence.extraPvcLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} {{- with .Values.persistence.annotations }} annotations: -{{ toYaml . | indent 4 }} + {{- toYaml . | nindent 4 }} {{- end }} {{- with .Values.persistence.finalizers }} finalizers: -{{ toYaml . | indent 4 }} + {{- toYaml . | nindent 4 }} {{- end }} spec: accessModes: @@ -22,12 +25,12 @@ spec: resources: requests: storage: {{ .Values.persistence.size | quote }} - {{- if .Values.persistence.storageClassName }} - storageClassName: {{ .Values.persistence.storageClassName }} - {{- end -}} + {{- with .Values.persistence.storageClassName }} + storageClassName: {{ . }} + {{- end }} {{- with .Values.persistence.selectorLabels }} selector: matchLabels: -{{ toYaml . | indent 6 }} + {{- toYaml . | nindent 6 }} {{- end }} -{{- 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 index ff2160f4..ffdb16f6 100644 --- 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 @@ -1,31 +1,31 @@ {{- if and .Values.rbac.create (not .Values.rbac.useExistingRole) -}} -apiVersion: {{ template "grafana.rbac.apiVersion" . }} +apiVersion: {{ include "grafana.rbac.apiVersion" . }} kind: Role metadata: - name: {{ template "grafana.fullname" . }} - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} labels: {{- include "grafana.labels" . | nindent 4 }} -{{- with .Values.annotations }} + {{- 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 (or .Values.sidecar.plugins.enabled .Values.rbac.extraRoleRules)))) }} + {{- toYaml . | nindent 4 }} + {{- end }} +{{- if or .Values.rbac.pspEnabled (and .Values.rbac.namespaced (or .Values.sidecar.dashboards.enabled .Values.sidecar.datasources.enabled .Values.sidecar.plugins.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 (or .Values.sidecar.datasources.enabled .Values.sidecar.plugins.enabled)) }} -- apiGroups: [""] # "" indicates the core API group - resources: ["configmaps", "secrets"] - verbs: ["get", "watch", "list"] -{{- end }} -{{- with .Values.rbac.extraRoleRules }} -{{ toYaml . | indent 0 }} -{{- end}} + {{- if .Values.rbac.pspEnabled }} + - apiGroups: ['extensions'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: [{{ include "grafana.fullname" . }}] + {{- end }} + {{- if and .Values.rbac.namespaced (or .Values.sidecar.dashboards.enabled .Values.sidecar.datasources.enabled .Values.sidecar.plugins.enabled) }} + - apiGroups: [""] # "" indicates the core API group + resources: ["configmaps", "secrets"] + verbs: ["get", "watch", "list"] + {{- end }} + {{- with .Values.rbac.extraRoleRules }} + {{- toYaml . | nindent 2 }} + {{- end}} {{- else }} rules: [] {{- 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 index e0107255..cc07bd9a 100644 --- 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 @@ -1,25 +1,25 @@ -{{- if .Values.rbac.create -}} -apiVersion: {{ template "grafana.rbac.apiVersion" . }} +{{- if .Values.rbac.create }} +apiVersion: {{ include "grafana.rbac.apiVersion" . }} kind: RoleBinding metadata: - name: {{ template "grafana.fullname" . }} - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} labels: {{- include "grafana.labels" . | nindent 4 }} -{{- with .Values.annotations }} + {{- with .Values.annotations }} annotations: -{{ toYaml . | indent 4 }} -{{- end }} + {{- toYaml . | nindent 4 }} + {{- end }} roleRef: apiGroup: rbac.authorization.k8s.io kind: Role -{{- if (not .Values.rbac.useExistingRole) }} - name: {{ template "grafana.fullname" . }} -{{- else }} + {{- if .Values.rbac.useExistingRole }} name: {{ .Values.rbac.useExistingRole }} -{{- end }} + {{- else }} + name: {{ include "grafana.fullname" . }} + {{- end }} subjects: - kind: ServiceAccount - name: {{ template "grafana.serviceAccountName" . }} - namespace: {{ template "grafana.namespace" . }} -{{- end -}} + name: {{ include "grafana.serviceAccountName" . }} + namespace: {{ include "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 index 5c09313e..c7655671 100644 --- 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 @@ -2,13 +2,13 @@ apiVersion: v1 kind: Secret metadata: - name: {{ template "grafana.fullname" . }}-env - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.fullname" . }}-env + namespace: {{ include "grafana.namespace" . }} labels: {{- include "grafana.labels" . | nindent 4 }} type: Opaque data: {{- range $key, $val := .Values.envRenderSecret }} {{ $key }}: {{ $val | b64enc | quote }} -{{- end -}} +{{- 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 index c8aa750a..5cbd5274 100644 --- 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 @@ -2,14 +2,14 @@ apiVersion: v1 kind: Secret metadata: - name: {{ template "grafana.fullname" . }} - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} labels: {{- include "grafana.labels" . | nindent 4 }} -{{- with .Values.annotations }} + {{- with .Values.annotations }} annotations: -{{ toYaml . | indent 4 }} -{{- end }} + {{- toYaml . | nindent 4 }} + {{- end }} type: Opaque data: {{- if and (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) (not .Values.admin.existingSecret) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) }} @@ -17,7 +17,7 @@ data: {{- if .Values.adminPassword }} admin-password: {{ .Values.adminPassword | b64enc | quote }} {{- else }} - admin-password: {{ template "grafana.password" . }} + admin-password: {{ include "grafana.password" . }} {{- end }} {{- end }} {{- if not .Values.ldap.existingSecret }} 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 index d0a1756c..43d360b5 100644 --- 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 @@ -1,55 +1,55 @@ -{{ if .Values.service.enabled }} +{{- if .Values.service.enabled }} +{{- $root := . }} apiVersion: v1 kind: Service metadata: - name: {{ template "grafana.fullname" . }} - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} labels: {{- include "grafana.labels" . | nindent 4 }} -{{- if .Values.service.labels }} -{{ toYaml .Values.service.labels | indent 4 }} -{{- end }} -{{- $root := . }} -{{- with .Values.service.annotations }} + {{- with .Values.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.service.annotations }} annotations: -{{ tpl (toYaml . | indent 4) $root }} -{{- 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 }} + {{- tpl (toYaml . | nindent 4) $root }} {{- end }} - {{- if .Values.service.loadBalancerSourceRanges }} - loadBalancerSourceRanges: -{{ toYaml .Values.service.loadBalancerSourceRanges | indent 4 }} - {{- end -}} -{{- else }} +spec: + {{- if (or (eq .Values.service.type "ClusterIP") (empty .Values.service.type)) }} + type: ClusterIP + {{- with .Values.service.clusterIP }} + clusterIP: {{ . }} + {{- end }} + {{- else if eq .Values.service.type "LoadBalancer" }} type: {{ .Values.service.type }} -{{- end }} -{{- if .Values.service.externalIPs }} + {{- with .Values.service.loadBalancerIP }} + loadBalancerIP: {{ . }} + {{- end }} + {{- with .Values.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- else }} + type: {{ .Values.service.type }} + {{- end }} + {{- with .Values.service.externalIPs }} externalIPs: -{{ toYaml .Values.service.externalIPs | indent 4 }} -{{- end }} + {{- toYaml . | nindent 4 }} + {{- end }} ports: - name: {{ .Values.service.portName }} port: {{ .Values.service.port }} protocol: TCP targetPort: {{ .Values.service.targetPort }} - {{- if .Values.service.appProtocol }} - appProtocol: {{ .Values.service.appProtocol }} + {{- with .Values.service.appProtocol }} + appProtocol: {{ . }} {{- end }} {{- if (and (eq .Values.service.type "NodePort") (not (empty .Values.service.nodePort))) }} - nodePort: {{.Values.service.nodePort}} - {{ end }} - {{- if .Values.extraExposePorts }} - {{- tpl (toYaml .Values.extraExposePorts) . | nindent 4 }} + nodePort: {{ .Values.service.nodePort }} + {{- end }} + {{- with .Values.extraExposePorts }} + {{- tpl (toYaml . | nindent 4) $root }} {{- end }} selector: {{- include "grafana.selectorLabels" . | nindent 4 }} -{{ end }} +{{- end }} 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 index 4ccee15e..784e71ba 100644 --- 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 @@ -1,14 +1,17 @@ {{- if .Values.serviceAccount.create }} +{{- $root := . -}} apiVersion: v1 kind: ServiceAccount metadata: labels: {{- include "grafana.labels" . | nindent 4 }} -{{- $root := . }} -{{- with .Values.serviceAccount.annotations }} + {{- with .Values.serviceAccount.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.serviceAccount.annotations }} annotations: -{{ tpl (toYaml . | indent 4) $root }} -{{- end }} - name: {{ template "grafana.serviceAccountName" . }} - namespace: {{ template "grafana.namespace" . }} + {{- tpl (toYaml . | nindent 4) $root }} + {{- end }} + name: {{ include "grafana.serviceAccountName" . }} + namespace: {{ include "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 index 0876a637..6575fb9a 100644 --- 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 @@ -3,16 +3,16 @@ apiVersion: monitoring.coreos.com/v1 kind: ServiceMonitor metadata: - name: {{ template "grafana.fullname" . }} + name: {{ include "grafana.fullname" . }} {{- if .Values.serviceMonitor.namespace }} namespace: {{ tpl .Values.serviceMonitor.namespace . }} {{- else }} - namespace: {{ template "grafana.namespace" . }} + namespace: {{ include "grafana.namespace" . }} {{- end }} labels: {{- include "grafana.labels" . | nindent 4 }} - {{- if .Values.serviceMonitor.labels }} - {{- toYaml .Values.serviceMonitor.labels | nindent 4 }} + {{- with .Values.serviceMonitor.labels }} + {{- toYaml . | nindent 4 }} {{- end }} spec: endpoints: @@ -26,19 +26,19 @@ spec: honorLabels: true path: {{ .Values.serviceMonitor.path }} scheme: {{ .Values.serviceMonitor.scheme }} - {{- if .Values.serviceMonitor.tlsConfig }} + {{- with .Values.serviceMonitor.tlsConfig }} tlsConfig: - {{- toYaml .Values.serviceMonitor.tlsConfig | nindent 6 }} + {{- toYaml . | nindent 6 }} {{- end }} - {{- if .Values.serviceMonitor.relabelings }} + {{- with .Values.serviceMonitor.relabelings }} relabelings: - {{- toYaml .Values.serviceMonitor.relabelings | nindent 4 }} + {{- toYaml . | nindent 6 }} {{- end }} jobLabel: "{{ .Release.Name }}" selector: matchLabels: - {{- include "grafana.selectorLabels" . | nindent 8 }} + {{- include "grafana.selectorLabels" . | nindent 6 }} namespaceSelector: matchNames: - - {{ template "grafana.namespace" . }} + - {{ include "grafana.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 index b308dec4..4cde0eb2 100644 --- 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 @@ -1,38 +1,39 @@ -{{- if (or (.Values.useStatefulSet) (and .Values.persistence.enabled (not .Values.persistence.existingClaim) (eq .Values.persistence.type "statefulset")))}} +{{- $sts := list "sts" "StatefulSet" -}} +{{- if (or (.Values.useStatefulSet) (and .Values.persistence.enabled (not .Values.persistence.existingClaim) (has .Values.persistence.type $sts)))}} apiVersion: apps/v1 kind: StatefulSet metadata: - name: {{ template "grafana.fullname" . }} - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} labels: {{- include "grafana.labels" . | nindent 4 }} -{{- with .Values.annotations }} + {{- with .Values.annotations }} annotations: -{{ toYaml . | indent 4 }} -{{- end }} + {{- toYaml . | nindent 4 }} + {{- end }} spec: replicas: {{ .Values.replicas }} selector: matchLabels: {{- include "grafana.selectorLabels" . | nindent 6 }} - serviceName: {{ template "grafana.fullname" . }}-headless + serviceName: {{ include "grafana.fullname" . }}-headless template: metadata: labels: {{- include "grafana.selectorLabels" . | nindent 8 }} -{{- with .Values.podLabels }} -{{ toYaml . | indent 8 }} -{{- end }} + {{- with .Values.podLabels }} + {{- toYaml . | nindent 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 and (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))) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + {{- if and (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))) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} checksum/secret: {{ include (print $.Template.BasePath "/secret.yaml") . | sha256sum }} -{{- end }} -{{- with .Values.podAnnotations }} -{{ toYaml . | indent 8 }} -{{- end }} + {{- end }} + {{- with .Values.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} spec: {{- include "grafana.pod" . | nindent 6 }} {{- if .Values.persistence.enabled}} @@ -48,7 +49,7 @@ spec: {{- with .Values.persistence.selectorLabels }} selector: matchLabels: -{{ toYaml . | indent 10 }} + {{- toYaml . | nindent 10 }} {{- end }} {{- end }} {{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-configmap.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-configmap.yaml index 772ecbbe..01c96c92 100644 --- a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-configmap.yaml +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/tests/test-configmap.yaml @@ -2,14 +2,17 @@ apiVersion: v1 kind: ConfigMap metadata: - name: {{ template "grafana.fullname" . }}-test - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.fullname" . }}-test + namespace: {{ include "grafana.namespace" . }} + annotations: + "helm.sh/hook": test-success + "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" labels: {{- include "grafana.labels" . | nindent 4 }} data: run.sh: |- @test "Test Health" { - url="http://{{ template "grafana.fullname" . }}/api/health" + url="http://{{ include "grafana.fullname" . }}/api/health" code=$(wget --server-response --spider --timeout 90 --tries 10 ${url} 2>&1 | awk '/^ HTTP/{print $2}') [ "$code" == "200" ] 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 index 6ccc7a70..6fae3923 100644 --- 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 @@ -1,9 +1,11 @@ -{{- if and .Values.testFramework.enabled .Values.rbac.pspEnabled }} -{{- if .Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy" }} +{{- if and .Values.testFramework.enabled .Values.rbac.pspEnabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} apiVersion: policy/v1beta1 kind: PodSecurityPolicy metadata: - name: {{ template "grafana.fullname" . }}-test + name: {{ include "grafana.fullname" . }}-test + annotations: + "helm.sh/hook": test-success + "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" labels: {{- include "grafana.labels" . | nindent 4 }} spec: @@ -21,11 +23,10 @@ spec: runAsUser: rule: RunAsAny volumes: - - configMap - - downwardAPI - - emptyDir - - projected - - csi - - secret -{{- end }} + - configMap + - downwardAPI + - emptyDir + - projected + - csi + - 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 index 6b10677a..cdace2c1 100644 --- 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 @@ -1,14 +1,17 @@ -{{- if and .Values.testFramework.enabled .Values.rbac.pspEnabled -}} +{{- 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" . }} + name: {{ include "grafana.fullname" . }}-test + namespace: {{ include "grafana.namespace" . }} + annotations: + "helm.sh/hook": test-success + "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" labels: {{- include "grafana.labels" . | nindent 4 }} rules: -- apiGroups: ['policy'] - resources: ['podsecuritypolicies'] - verbs: ['use'] - resourceNames: [{{ template "grafana.fullname" . }}-test] + - apiGroups: ['policy'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: [{{ include "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 index 58fa5e78..91d45242 100644 --- 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 @@ -1,17 +1,20 @@ -{{- if and .Values.testFramework.enabled .Values.rbac.pspEnabled -}} +{{- 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" . }} + name: {{ include "grafana.fullname" . }}-test + namespace: {{ include "grafana.namespace" . }} + annotations: + "helm.sh/hook": test-success + "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" labels: {{- include "grafana.labels" . | nindent 4 }} roleRef: apiGroup: rbac.authorization.k8s.io kind: Role - name: {{ template "grafana.fullname" . }}-test + name: {{ include "grafana.fullname" . }}-test subjects: -- kind: ServiceAccount - name: {{ template "grafana.serviceAccountNameTest" . }} - namespace: {{ template "grafana.namespace" . }} + - kind: ServiceAccount + name: {{ include "grafana.serviceAccountNameTest" . }} + namespace: {{ include "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 index 5c335073..38fba359 100644 --- 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 @@ -4,6 +4,9 @@ kind: ServiceAccount metadata: labels: {{- include "grafana.labels" . | nindent 4 }} - name: {{ template "grafana.serviceAccountNameTest" . }} - namespace: {{ template "grafana.namespace" . }} + name: {{ include "grafana.serviceAccountNameTest" . }} + namespace: {{ include "grafana.namespace" . }} + annotations: + "helm.sh/hook": test-success + "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" {{- 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 index ef43d80d..9fb88426 100644 --- 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 @@ -1,38 +1,36 @@ {{- if .Values.testFramework.enabled }} +{{- $root := . }} apiVersion: v1 kind: Pod metadata: - name: {{ template "grafana.fullname" . }}-test + name: {{ include "grafana.fullname" . }}-test labels: {{- include "grafana.labels" . | nindent 4 }} annotations: "helm.sh/hook": test-success "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" - namespace: {{ template "grafana.namespace" . }} + namespace: {{ include "grafana.namespace" . }} spec: - serviceAccountName: {{ template "grafana.serviceAccountNameTest" . }} - {{- if .Values.testFramework.securityContext }} - securityContext: {{ toYaml .Values.testFramework.securityContext | nindent 4 }} + serviceAccountName: {{ include "grafana.serviceAccountNameTest" . }} + {{- with .Values.testFramework.securityContext }} + securityContext: + {{- toYaml . | nindent 4 }} {{- end }} - {{- $root := . }} - {{- if .Values.image.pullSecrets }} + {{- if or .Values.image.pullSecrets .Values.global.imagePullSecrets }} imagePullSecrets: - {{- range .Values.image.pullSecrets }} - - name: {{ tpl . $root }} - {{- end}} + {{- include "grafana.imagePullSecrets" (dict "root" $root "imagePullSecrets" .Values.image.pullSecrets) | nindent 4 }} {{- end }} {{- with .Values.nodeSelector }} nodeSelector: -{{ toYaml . | indent 4 }} + {{- toYaml . | nindent 4 }} {{- end }} - {{- $root := . }} {{- with .Values.affinity }} affinity: -{{ tpl (toYaml .) $root | indent 4 }} + {{- tpl (toYaml .) $root | nindent 4 }} {{- end }} {{- with .Values.tolerations }} tolerations: -{{ toYaml . | indent 4 }} + {{- toYaml . | nindent 4 }} {{- end }} containers: - name: {{ .Release.Name }}-test @@ -44,8 +42,8 @@ spec: name: tests readOnly: true volumes: - - name: tests - configMap: - name: {{ template "grafana.fullname" . }}-test + - name: tests + configMap: + name: {{ include "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 index adcbbca3..527cd420 100644 --- a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/values.yaml +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/values.yaml @@ -1,3 +1,18 @@ +global: + # To help compatibility with other charts which use global.imagePullSecrets. + # Allow either an array of {name: pullSecret} maps (k8s-style), or an array of strings (more common helm-style). + # Can be tempalted. + # global: + # imagePullSecrets: + # - name: pullSecret1 + # - name: pullSecret2 + # or + # global: + # imagePullSecrets: + # - pullSecret1 + # - pullSecret2 + imagePullSecrets: [] + rbac: create: true ## Use an existing ClusterRole/Role (depending on rbac.namespaced false/true) @@ -17,6 +32,8 @@ serviceAccount: create: true name: nameTest: + ## ServiceAccount labels. + labels: {} ## Service account annotations. Can be templated. # annotations: # eks.amazonaws.com/role-arn: arn:aws:iam::123456789000:role/iam-role-name-here @@ -99,8 +116,7 @@ securityContext: runAsGroup: 472 fsGroup: 472 -containerSecurityContext: - {} +containerSecurityContext: {} # Enable creating the grafana configmap createConfigmap: true @@ -137,6 +153,11 @@ downloadDashboards: envFromSecret: "" resources: {} securityContext: {} + envValueFrom: {} + # ENV_NAME: + # configMapKeyRef: + # name: configmap-name + # key: value_key ## Pod Annotations # podAnnotations: {} @@ -307,6 +328,8 @@ persistence: # subPath: "" ## Name of an existing PVC. Can be templated. # existingClaim: + ## Extra labels to apply to a PVC. + extraPvcLabels: {} ## If persistence is not enabled, this allows to mount the ## local storage in-memory to improve performance @@ -321,7 +344,7 @@ persistence: initChownData: ## If false, data ownership will not be reset at startup - ## This allows the prometheus-server to be run with an arbitrary user + ## This allows the grafana-server to be run with an arbitrary user ## enabled: true @@ -343,6 +366,9 @@ initChownData: # requests: # cpu: 100m # memory: 128Mi + securityContext: + runAsNonRoot: false + runAsUser: 0 # Administrator credentials when not using an existing secret (see below) @@ -363,11 +389,6 @@ admin: # - "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: @@ -581,7 +602,7 @@ alerting: {} # component: Grafana # group: app-stack # summary: | - # {{ `{{ template "default.message" . }}` }} + # {{ `{{ include "default.message" . }}` }} ## Configure notifiers ## ref: http://docs.grafana.org/administration/provisioning/#alert-notification-channels @@ -987,6 +1008,7 @@ revisionHistoryLimit: 10 ## Add a seperate remote image renderer deployment/service imageRenderer: + deploymentStrategy: {} # Enable the image-renderer deployment & service enabled: false replicas: 1 @@ -1009,6 +1031,12 @@ imageRenderer: serviceAccountName: "" # image-renderer deployment securityContext securityContext: {} + # image-renderer deployment container securityContext + containerSecurityContext: + capabilities: + drop: ['ALL'] + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true # image-renderer deployment Host Aliases hostAliases: [] # image-renderer deployment priority class @@ -1058,6 +1086,11 @@ imageRenderer: ## affinity: {} + ## Use an alternate scheduler, e.g. "stork". + ## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/ + ## + # schedulerName: "default-scheduler" + networkPolicy: ## @param networkPolicy.enabled Enable creation of NetworkPolicy resources. Only Ingress traffic is filtered for now. ## 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 index 6ff3e2e4..29d6acc3 100644 --- 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 @@ -1,5 +1,5 @@ apiVersion: v2 -appVersion: 2.6.0 +appVersion: 2.7.0 description: Install kube-state-metrics to generate and expose cluster-level metrics home: https://github.com/kubernetes/kube-state-metrics/ keywords: @@ -12,10 +12,10 @@ maintainers: name: tariq1890 - email: manuel@rueg.eu name: mrueg -- email: davidcalvertfr@gmail.com +- email: david@0xdc.me name: dotdc name: kube-state-metrics sources: - https://github.com/kubernetes/kube-state-metrics/ type: application -version: 4.20.2 +version: 4.24.0 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 index 976b2733..0d193fbc 100644 --- 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 @@ -80,3 +80,22 @@ Selector labels app.kubernetes.io/name: {{ include "kube-state-metrics.name" . }} app.kubernetes.io/instance: {{ .Release.Name }} {{- end }} + +{{/* Sets default scrape limits for servicemonitor */}} +{{- define "servicemonitor.scrapeLimits" -}} +{{- with .sampleLimit }} +sampleLimit: {{ . }} +{{- end }} +{{- with .targetLimit }} +targetLimit: {{ . }} +{{- end }} +{{- with .labelLimit }} +labelLimit: {{ . }} +{{- end }} +{{- with .labelNameLengthLimit }} +labelNameLengthLimit: {{ . }} +{{- end }} +{{- with .labelValueLengthLimit }} +labelValueLengthLimit: {{ . }} +{{- end }} +{{- end -}} 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 index 3299056a..8905e113 100644 --- 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 @@ -1,4 +1,4 @@ -{{- if .Values.podSecurityPolicy.enabled }} +{{- if and .Values.podSecurityPolicy.enabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} apiVersion: policy/v1beta1 kind: PodSecurityPolicy metadata: 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 index 69047d4f..654e4a3d 100644 --- 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 @@ -1,4 +1,4 @@ -{{- if and .Values.podSecurityPolicy.enabled .Values.rbac.create -}} +{{- if and .Values.podSecurityPolicy.enabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole metadata: 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 index 03c56d57..5b62a18b 100644 --- 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 @@ -1,4 +1,4 @@ -{{- if and .Values.podSecurityPolicy.enabled .Values.rbac.create -}} +{{- if and .Values.podSecurityPolicy.enabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRoleBinding metadata: diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/role.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/role.yaml index e3275140..6474914f 100644 --- a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/role.yaml +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/role.yaml @@ -69,6 +69,12 @@ rules: - jobs verbs: ["list", "watch"] {{ end -}} +{{ if has "leases" $.Values.collectors }} +- apiGroups: ["coordination.k8s.io"] + resources: + - leases + verbs: ["list", "watch"] +{{ end -}} {{ if has "limitranges" $.Values.collectors }} - apiGroups: [""] resources: 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 index 92c6d4fc..6c486a66 100644 --- 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 @@ -34,7 +34,15 @@ spec: {{- if .Values.service.loadBalancerIP }} loadBalancerIP: "{{ .Values.service.loadBalancerIP }}" {{- end }} -{{- if .Values.service.clusterIP }} +{{- if .Values.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: + {{- range $cidr := .Values.service.loadBalancerSourceRanges }} + - {{ $cidr }} + {{- end }} +{{- end }} +{{- if .Values.autosharding.enabled }} + clusterIP: None +{{- else if .Values.service.clusterIP }} clusterIP: "{{ .Values.service.clusterIP }}" {{- end }} selector: 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 index 4deac955..e93df4c4 100644 --- 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 @@ -11,11 +11,12 @@ metadata: {{- end }} spec: jobLabel: {{ default "app.kubernetes.io/name" .Values.prometheus.monitor.jobLabel }} + {{- include "servicemonitor.scrapeLimits" .Values.prometheus.monitor | indent 2 }} selector: matchLabels: - {{- if .Values.prometheus.monitor.selectorOverride -}} - {{ toYaml .Values.prometheus.monitor.selectorOverride | nindent 6 }} - {{ else }} + {{- with .Values.prometheus.monitor.selectorOverride }} + {{- toYaml . | nindent 6 }} + {{- else }} {{- include "kube-state-metrics.selectorLabels" . | indent 6 }} {{- end }} endpoints: 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 index fb35dd72..d32b1232 100644 --- 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 @@ -2,7 +2,7 @@ prometheusScrape: true image: repository: registry.k8s.io/kube-state-metrics/kube-state-metrics - tag: v2.6.0 + tag: v2.7.0 sha: "" pullPolicy: IfNotPresent @@ -29,6 +29,8 @@ service: type: ClusterIP nodePort: 0 loadBalancerIP: "" + # Only allow access to the loadBalancerIP from these IPs + loadBalancerSourceRanges: [] clusterIP: "" annotations: {} @@ -79,6 +81,25 @@ prometheus: namespace: "" jobLabel: "" interval: "" + ## SampleLimit defines per-scrape limit on number of scraped samples that will be accepted. + ## + sampleLimit: 0 + + ## TargetLimit defines a limit on the number of scraped targets that will be accepted. + ## + targetLimit: 0 + + ## Per-scrape limit on number of labels that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + ## + labelLimit: 0 + + ## Per-scrape limit on length of labels name that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + ## + labelNameLengthLimit: 0 + + ## Per-scrape limit on length of labels value that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + ## + labelValueLengthLimit: 0 scrapeTimeout: "" proxyUrl: "" selectorOverride: {} @@ -184,6 +205,7 @@ collectors: - horizontalpodautoscalers - ingresses - jobs + - leases - limitranges - mutatingwebhookconfigurations - namespaces 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 index abcba280..5b50a123 100644 --- 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 @@ -1,5 +1,5 @@ apiVersion: v2 -appVersion: 1.3.1 +appVersion: 1.5.0 description: A Helm chart for prometheus node-exporter home: https://github.com/prometheus/node_exporter/ keywords: @@ -15,4 +15,4 @@ name: prometheus-node-exporter sources: - https://github.com/prometheus/node_exporter/ type: application -version: 4.3.0 +version: 4.8.0 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 index 21030894..f5e2603e 100644 --- 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 @@ -3,8 +3,8 @@ Expand the name of the chart. */}} {{- define "prometheus-node-exporter.name" -}} -{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}} -{{- end -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }} +{{- end }} {{/* Create a default fully qualified app name. @@ -12,30 +12,39 @@ We truncate at 63 chars because some Kubernetes name fields are limited to this 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 -}} +{{- 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" }} -helm.sh/chart: {{ template "prometheus-node-exporter.chart" . }} +{{/* +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 }} + +{{/* +Common labels +*/}} +{{- define "prometheus-node-exporter.labels" -}} +helm.sh/chart: {{ include "prometheus-node-exporter.chart" . }} app.kubernetes.io/managed-by: {{ .Release.Service }} app.kubernetes.io/component: metrics -app.kubernetes.io/part-of: {{ template "prometheus-node-exporter.name" . }} -{{- include "prometheus-node-exporter.selectorLabels" . }} -{{- if .Chart.AppVersion }} -app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} +app.kubernetes.io/part-of: {{ include "prometheus-node-exporter.name" . }} +{{ include "prometheus-node-exporter.selectorLabels" . }} +{{- with .Chart.AppVersion }} +app.kubernetes.io/version: {{ . | quote }} {{- end }} -{{- if .Values.podLabels}} -{{ toYaml .Values.podLabels }} +{{- with .Values.podLabels }} +{{ toYaml . }} {{- end }} {{- if .Values.releaseLabel }} release: {{ .Release.Name }} @@ -45,37 +54,30 @@ release: {{ .Release.Name }} {{/* Selector labels */}} -{{- define "prometheus-node-exporter.selectorLabels" }} +{{- define "prometheus-node-exporter.selectorLabels" -}} +app.kubernetes.io/name: {{ include "prometheus-node-exporter.name" . }} app.kubernetes.io/instance: {{ .Release.Name }} -app.kubernetes.io/name: {{ template "prometheus-node-exporter.name" . }} {{- 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 -}} +{{- if .Values.serviceAccount.create }} +{{- default (include "prometheus-node-exporter.fullname" .) .Values.serviceAccount.name }} +{{- else }} +{{- default "default" .Values.serviceAccount.name }} +{{- end }} +{{- end }} {{/* The image to use */}} {{- define "prometheus-node-exporter.image" -}} -{{- if .Values.image.sha -}} +{{- if .Values.image.sha }} {{- printf "%s:%s@%s" .Values.image.repository (default (printf "v%s" .Chart.AppVersion) .Values.image.tag) .Values.image.sha }} -{{- else -}} +{{- else }} {{- printf "%s:%s" .Values.image.repository (default (printf "v%s" .Chart.AppVersion) .Values.image.tag) }} {{- end }} {{- end }} @@ -84,24 +86,43 @@ The image to use 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 -}} +{{- if .Values.namespaceOverride }} +{{- .Values.namespaceOverride }} +{{- else }} +{{- .Release.Namespace }} +{{- end }} +{{- end }} {{/* Create the namespace name of the service monitor */}} {{- define "prometheus-node-exporter.monitor-namespace" -}} - {{- if .Values.namespaceOverride -}} - {{- .Values.namespaceOverride -}} - {{- else -}} - {{- if .Values.prometheus.monitor.namespace -}} - {{- .Values.prometheus.monitor.namespace -}} - {{- else -}} - {{- .Release.Namespace -}} - {{- end -}} - {{- end -}} -{{- end -}} +{{- if .Values.namespaceOverride }} +{{- .Values.namespaceOverride }} +{{- else }} +{{- if .Values.prometheus.monitor.namespace }} +{{- .Values.prometheus.monitor.namespace }} +{{- else }} +{{- .Release.Namespace }} +{{- end }} +{{- end }} +{{- end }} + +{{/* Sets default scrape limits for servicemonitor */}} +{{- define "servicemonitor.scrapeLimits" -}} +{{- with .sampleLimit }} +sampleLimit: {{ . }} +{{- end }} +{{- with .targetLimit }} +targetLimit: {{ . }} +{{- end }} +{{- with .labelLimit }} +labelLimit: {{ . }} +{{- end }} +{{- with .labelNameLengthLimit }} +labelNameLengthLimit: {{ . }} +{{- end }} +{{- with .labelValueLengthLimit }} +labelValueLengthLimit: {{ . }} +{{- 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 index a742f24c..189b2d0b 100644 --- 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 @@ -1,38 +1,44 @@ 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 }} + name: {{ include "prometheus-node-exporter.fullname" . }} + namespace: {{ include "prometheus-node-exporter.namespace" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} + {{- with .Values.daemonsetAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} spec: selector: matchLabels: - {{- include "prometheus-node-exporter.selectorLabels" . | indent 6 }} - {{- if .Values.updateStrategy }} + {{- include "prometheus-node-exporter.selectorLabels" . | nindent 6 }} + {{- with .Values.updateStrategy }} updateStrategy: -{{ toYaml .Values.updateStrategy | indent 4 }} + {{- toYaml . | nindent 4 }} {{- end }} template: metadata: - labels: {{ include "prometheus-node-exporter.labels" . | indent 8 }} - {{- if .Values.podAnnotations }} + {{- with .Values.podAnnotations }} annotations: - {{- toYaml .Values.podAnnotations | nindent 8 }} + {{- toYaml . | nindent 8 }} {{- end }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 8 }} spec: automountServiceAccountToken: {{ .Values.serviceAccount.automountServiceAccountToken }} - serviceAccountName: {{ template "prometheus-node-exporter.serviceAccountName" . }} -{{- if .Values.securityContext }} + {{- with .Values.securityContext }} securityContext: -{{ toYaml .Values.securityContext | indent 8 }} -{{- end }} -{{- if .Values.priorityClassName }} - priorityClassName: {{ .Values.priorityClassName }} -{{- end }} - {{- if .Values.extraInitContainers }} - initContainers: - {{ toYaml .Values.extraInitContainers | nindent 6 }} + {{- toYaml . | nindent 8 }} {{- end }} + {{- with .Values.priorityClassName }} + priorityClassName: {{ . }} + {{- end }} + {{- with .Values.extraInitContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + serviceAccountName: {{ include "prometheus-node-exporter.serviceAccountName" . }} containers: - name: node-exporter image: {{ include "prometheus-node-exporter.image" . }} @@ -44,26 +50,27 @@ spec: - --path.rootfs=/host/root {{- end }} - --web.listen-address=[$(HOST_IP)]:{{ .Values.service.port }} -{{- if .Values.extraArgs }} -{{ toYaml .Values.extraArgs | indent 12 }} -{{- end }} + {{- with .Values.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} {{- with .Values.containerSecurityContext }} - securityContext: {{ toYaml . | nindent 12 }} + securityContext: + {{- toYaml . | nindent 12 }} {{- end }} env: - - name: HOST_IP - {{- if .Values.service.listenOnAllInterfaces }} - value: 0.0.0.0 - {{- else }} - valueFrom: - fieldRef: - apiVersion: v1 - fieldPath: status.hostIP + - name: HOST_IP + {{- if .Values.service.listenOnAllInterfaces }} + value: 0.0.0.0 + {{- else }} + valueFrom: + fieldRef: + apiVersion: v1 + fieldPath: status.hostIP + {{- end }} + {{- range $key, $value := .Values.env }} + - name: {{ $key }} + value: {{ $value | quote }} {{- end }} - {{- range $key, $value := .Values.env }} - - name: {{ $key }} - value: {{ $value | quote }} - {{- end }} ports: - name: {{ .Values.service.portName }} containerPort: {{ .Values.service.port }} @@ -98,8 +105,10 @@ spec: periodSeconds: {{ .Values.readinessProbe.periodSeconds }} successThreshold: {{ .Values.readinessProbe.successThreshold }} timeoutSeconds: {{ .Values.readinessProbe.timeoutSeconds }} + {{- with .Values.resources }} resources: -{{ toYaml .Values.resources | indent 12 }} + {{- toYaml . | nindent 12 }} + {{- end }} volumeMounts: - name: proc mountPath: /host/proc @@ -115,37 +124,29 @@ spec: {{- end }} readOnly: true {{- end }} - {{- if .Values.extraHostVolumeMounts }} {{- range $_, $mount := .Values.extraHostVolumeMounts }} - name: {{ $mount.name }} mountPath: {{ $mount.mountPath }} readOnly: {{ $mount.readOnly }} - {{- if $mount.mountPropagation }} - mountPropagation: {{ $mount.mountPropagation }} + {{- with $mount.mountPropagation }} + mountPropagation: {{ . }} + {{- end }} {{- 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 }} - {{- if .Values.secrets }} {{- range $_, $mount := .Values.secrets }} - name: {{ .name }} mountPath: {{ .mountPath }} {{- end }} - {{- end }} - {{- end }} -{{- if .Values.sidecars }} -{{ toYaml .Values.sidecars | indent 8 }} + {{- with .Values.sidecars }} + {{- toYaml . | nindent 8 }} {{- if or .Values.sidecarVolumeMount .Values.sidecarHostVolumeMounts }} volumeMounts: {{- range $_, $mount := .Values.sidecarVolumeMount }} @@ -162,29 +163,29 @@ spec: {{- end }} {{- end }} {{- end }} -{{- end }} -{{- if .Values.imagePullSecrets }} + {{- end }} + {{- with .Values.imagePullSecrets }} imagePullSecrets: -{{ toYaml .Values.imagePullSecrets | indent 8 }} + {{ toYaml . | nindent 8 }} {{- end }} hostNetwork: {{ .Values.hostNetwork }} hostPID: {{ .Values.hostPID }} -{{- if .Values.affinity }} + {{- with .Values.affinity }} affinity: -{{ toYaml .Values.affinity | indent 8 }} -{{- end }} -{{- with .Values.dnsConfig }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.dnsConfig }} dnsConfig: -{{ toYaml . | indent 8 }} -{{- end }} -{{- if .Values.nodeSelector }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.nodeSelector }} nodeSelector: -{{ toYaml .Values.nodeSelector | indent 8 }} -{{- end }} - {{- with .Values.tolerations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.tolerations }} tolerations: -{{ toYaml . | indent 8 }} - {{- end }} + {{- toYaml . | nindent 8 }} + {{- end }} volumes: - name: proc hostPath: @@ -197,38 +198,28 @@ spec: hostPath: path: / {{- end }} - {{- 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.sidecarHostVolumeMounts }} {{- range $_, $mount := .Values.sidecarHostVolumeMounts }} - name: {{ $mount.name }} hostPath: path: {{ $mount.hostPath }} {{- end }} - {{- end }} - {{- if .Values.configmaps }} {{- range $_, $mount := .Values.configmaps }} - name: {{ $mount.name }} configMap: name: {{ $mount.name }} {{- end }} - {{- end }} - {{- if .Values.secrets }} {{- range $_, $mount := .Values.secrets }} - name: {{ $mount.name }} secret: secretName: {{ $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 index ef3e270b..45eeb8d9 100644 --- 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 @@ -2,9 +2,10 @@ 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 }} + name: {{ include "prometheus-node-exporter.fullname" . }} + namespace: {{ include "prometheus-node-exporter.namespace" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} subsets: - addresses: {{- range .Values.endpoints }} 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 index cb433369..89573172 100644 --- 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 @@ -1,15 +1,14 @@ -{{- if .Values.rbac.create }} -{{- if .Values.rbac.pspEnabled }} +{{- if and .Values.rbac.create .Values.rbac.pspEnabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} kind: ClusterRole apiVersion: rbac.authorization.k8s.io/v1 metadata: - name: psp-{{ template "prometheus-node-exporter.fullname" . }} - labels: {{ include "prometheus-node-exporter.labels" . | indent 4 }} + name: psp-{{ include "prometheus-node-exporter.fullname" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} rules: - apiGroups: ['extensions'] resources: ['podsecuritypolicies'] verbs: ['use'] resourceNames: - - {{ template "prometheus-node-exporter.fullname" . }} -{{- end }} + - {{ include "prometheus-node-exporter.fullname" . }} {{- 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 index d36d93ec..33337017 100644 --- 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 @@ -1,17 +1,16 @@ -{{- if .Values.rbac.create }} -{{- if .Values.rbac.pspEnabled }} +{{- if and .Values.rbac.create .Values.rbac.pspEnabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRoleBinding metadata: - name: psp-{{ template "prometheus-node-exporter.fullname" . }} - labels: {{ include "prometheus-node-exporter.labels" . | indent 4 }} + name: psp-{{ include "prometheus-node-exporter.fullname" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} roleRef: apiGroup: rbac.authorization.k8s.io kind: ClusterRole - name: psp-{{ template "prometheus-node-exporter.fullname" . }} + name: psp-{{ include "prometheus-node-exporter.fullname" . }} subjects: - kind: ServiceAccount - name: {{ template "prometheus-node-exporter.fullname" . }} - namespace: {{ template "prometheus-node-exporter.namespace" . }} -{{- end }} + name: {{ include "prometheus-node-exporter.fullname" . }} + namespace: {{ include "prometheus-node-exporter.namespace" . }} {{- 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 index ea8bcba3..4896c84d 100644 --- 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 @@ -1,15 +1,15 @@ -{{- if .Values.rbac.create }} -{{- if .Values.rbac.pspEnabled }} +{{- if and .Values.rbac.create .Values.rbac.pspEnabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} 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 }} -{{- if .Values.rbac.pspAnnotations }} + name: {{ include "prometheus-node-exporter.fullname" . }} + namespace: {{ include "prometheus-node-exporter.namespace" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} + {{- with .Values.rbac.pspAnnotations }} annotations: -{{ toYaml .Values.rbac.pspAnnotations | indent 4 }} -{{- end}} + {{- toYaml . | nindent 4 }} + {{- end }} spec: privileged: false # Allow core volume types. @@ -47,4 +47,3 @@ spec: 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 index fbed05ca..c0129dbd 100644 --- 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 @@ -1,22 +1,23 @@ apiVersion: v1 kind: Service metadata: - name: {{ template "prometheus-node-exporter.fullname" . }} - namespace: {{ template "prometheus-node-exporter.namespace" . }} - labels: {{ include "prometheus-node-exporter.labels" . | indent 4 }} -{{- if .Values.service.annotations }} + name: {{ include "prometheus-node-exporter.fullname" . }} + namespace: {{ include "prometheus-node-exporter.namespace" . }} + labels: + {{- include "prometheus-node-exporter.labels" $ | nindent 4 }} + {{- with .Values.service.annotations }} annotations: -{{ toYaml .Values.service.annotations | indent 4 }} -{{- end }} + {{- toYaml . | nindent 4 }} + {{- end }} spec: type: {{ .Values.service.type }} ports: - port: {{ .Values.service.port }} - {{- if ( and (eq .Values.service.type "NodePort" ) (not (empty .Values.service.nodePort)) ) }} + {{- if ( and (eq .Values.service.type "NodePort" ) (not (empty .Values.service.nodePort)) ) }} nodePort: {{ .Values.service.nodePort }} - {{- end }} + {{- end }} targetPort: {{ .Values.service.targetPort }} protocol: TCP name: {{ .Values.service.portName }} selector: - {{- include "prometheus-node-exporter.selectorLabels" . | indent 4 }} + {{- include "prometheus-node-exporter.selectorLabels" . | nindent 4 }} 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 index dc3fee6a..b82630ca 100644 --- 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 @@ -1,14 +1,17 @@ -{{- if .Values.rbac.create -}} -{{- if .Values.serviceAccount.create -}} +{{- if and .Values.rbac.create .Values.serviceAccount.create -}} apiVersion: v1 kind: ServiceAccount metadata: - name: {{ template "prometheus-node-exporter.serviceAccountName" . }} - namespace: {{ template "prometheus-node-exporter.namespace" . }} - labels: {{ include "prometheus-node-exporter.labels" . | indent 4 }} + name: {{ include "prometheus-node-exporter.serviceAccountName" . }} + namespace: {{ include "prometheus-node-exporter.namespace" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} + {{- with .Values.serviceAccount.annotations }} annotations: -{{ toYaml .Values.serviceAccount.annotations | indent 4 }} + {{- toYaml . | nindent 4 }} + {{- end }} +{{- with .Values.serviceAccount.imagePullSecrets }} imagePullSecrets: -{{ toYaml .Values.serviceAccount.imagePullSecrets | indent 2 }} -{{- end -}} + {{- toYaml . | nindent 2 }} +{{- end }} {{- end -}} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/servicemonitor.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/servicemonitor.yaml index 3408c67d..073ce57a 100644 --- a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/servicemonitor.yaml +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/servicemonitor.yaml @@ -2,50 +2,52 @@ apiVersion: {{ .Values.prometheus.monitor.apiVersion | default "monitoring.coreos.com/v1" }} kind: ServiceMonitor metadata: - name: {{ template "prometheus-node-exporter.fullname" . }} - namespace: {{ template "prometheus-node-exporter.monitor-namespace" . }} - labels: {{ include "prometheus-node-exporter.labels" . | indent 4 }} - {{- if .Values.prometheus.monitor.additionalLabels }} - {{- toYaml .Values.prometheus.monitor.additionalLabels | nindent 4 }} - {{- end }} + name: {{ include "prometheus-node-exporter.fullname" . }} + namespace: {{ include "prometheus-node-exporter.monitor-namespace" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} + {{- with .Values.prometheus.monitor.additionalLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} spec: jobLabel: {{ default "app.kubernetes.io/name" .Values.prometheus.monitor.jobLabel }} + {{- include "servicemonitor.scrapeLimits" .Values.prometheus.monitor | nindent 2 }} selector: matchLabels: - {{- if .Values.prometheus.monitor.selectorOverride }} - {{ toYaml .Values.prometheus.monitor.selectorOverride | indent 6 }} - {{ else }} - {{ include "prometheus-node-exporter.selectorLabels" . | indent 6 }} + {{- with .Values.prometheus.monitor.selectorOverride }} + {{- toYaml . | nindent 6 }} + {{- else }} + {{- include "prometheus-node-exporter.selectorLabels" . | nindent 6 }} {{- end }} endpoints: - port: {{ .Values.service.portName }} scheme: {{ .Values.prometheus.monitor.scheme }} - {{- with .Values.prometheus.monitor.basicAuth }} + {{- with .Values.prometheus.monitor.basicAuth }} basicAuth: {{- toYaml . | nindent 8 }} - {{- end }} - {{- with .Values.prometheus.monitor.bearerTokenFile }} + {{- end }} + {{- with .Values.prometheus.monitor.bearerTokenFile }} bearerTokenFile: {{ . }} - {{- end }} - {{- with .Values.prometheus.monitor.tlsConfig }} + {{- end }} + {{- with .Values.prometheus.monitor.tlsConfig }} tlsConfig: {{- toYaml . | nindent 8 }} - {{- end }} - {{- with .Values.prometheus.monitor.proxyUrl }} + {{- end }} + {{- with .Values.prometheus.monitor.proxyUrl }} proxyUrl: {{ . }} - {{- end }} - {{- with .Values.prometheus.monitor.interval }} + {{- end }} + {{- with .Values.prometheus.monitor.interval }} interval: {{ . }} - {{- end }} - {{- with .Values.prometheus.monitor.scrapeTimeout }} + {{- end }} + {{- with .Values.prometheus.monitor.scrapeTimeout }} scrapeTimeout: {{ . }} - {{- end }} - {{- with .Values.prometheus.monitor.relabelings }} + {{- end }} + {{- with .Values.prometheus.monitor.relabelings }} relabelings: {{- toYaml . | nindent 8 }} - {{- end }} - {{- with .Values.prometheus.monitor.metricRelabelings }} + {{- end }} + {{- with .Values.prometheus.monitor.metricRelabelings }} metricRelabelings: {{- toYaml . | nindent 8 }} - {{- end }} + {{- end }} {{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/verticalpodautoscaler.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/verticalpodautoscaler.yaml new file mode 100644 index 00000000..ae8295d9 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/verticalpodautoscaler.yaml @@ -0,0 +1,34 @@ +{{- if and (.Capabilities.APIVersions.Has "autoscaling.k8s.io/v1") (.Values.verticalPodAutoscaler.enabled) }} +apiVersion: autoscaling.k8s.io/v1 +kind: VerticalPodAutoscaler +metadata: + name: {{ include "prometheus-node-exporter.fullname" . }} + namespace: {{ include "prometheus-node-exporter.namespace" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} +spec: + resourcePolicy: + containerPolicies: + - containerName: {{ include "prometheus-node-exporter.name" . }} + {{- with .Values.verticalPodAutoscaler.controlledResources }} + controlledResources: {{ . }} + {{- end }} + {{- with .Values.verticalPodAutoscaler.maxAllowed }} + maxAllowed: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.verticalPodAutoscaler.minAllowed }} + minAllowed: + {{- toYaml . | nindent 8 }} + {{- end }} + targetRef: + apiVersion: apps/v1 + kind: DaemonSet + name: {{ include "prometheus-node-exporter.fullname" . }} + {{- if .Values.verticalPodAutoscaler.updatePolicy }} + updatePolicy: + {{- with .Values.verticalPodAutoscaler.updatePolicy.updateMode }} + updateMode: {{ . }} + {{- end }} + {{- 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 index a00ae4d3..f491bdfa 100644 --- 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 @@ -54,6 +54,26 @@ prometheus: ## prometheus.monitor.apiVersion ApiVersion for the serviceMonitor Resource(defaults to "monitoring.coreos.com/v1") apiVersion: "" + ## SampleLimit defines per-scrape limit on number of scraped samples that will be accepted. + ## + sampleLimit: 0 + + ## TargetLimit defines a limit on the number of scraped targets that will be accepted. + ## + targetLimit: 0 + + ## Per-scrape limit on number of labels that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + ## + labelLimit: 0 + + ## Per-scrape limit on length of labels name that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + ## + labelNameLengthLimit: 0 + + ## Per-scrape limit on length of labels value that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + ## + labelValueLengthLimit: 0 + ## Customize the updateStrategy if set updateStrategy: type: RollingUpdate @@ -142,6 +162,9 @@ podAnnotations: # Extra labels to be added to node exporter pods podLabels: {} +# Annotations to be added to node exporter daemonset +daemonsetAnnotations: {} + ## set to true to add the release label so scraping of the servicemonitor with kube-prometheus-stack works out of the box releaseLabel: false @@ -246,3 +269,23 @@ readinessProbe: periodSeconds: 10 successThreshold: 1 timeoutSeconds: 1 + +# Enable vertical pod autoscaler support for prometheus-node-exporter +verticalPodAutoscaler: + enabled: false + # List of resources that the vertical pod autoscaler can control. Defaults to cpu and memory + controlledResources: [] + + # Define the max allowed resources for the pod + maxAllowed: {} + # cpu: 200m + # memory: 100Mi + # Define the min allowed resources for the pod + minAllowed: {} + # cpu: 200m + # memory: 100Mi + + # updatePolicy: + # Specifies whether recommended updates are applied when a Pod is started and whether recommended updates + # are applied during the life of a Pod. Possible values are "Off", "Initial", "Recreate", and "Auto". + # updateMode: Auto diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/_helpers.tpl b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/_helpers.tpl index 25eb226a..b01fe6dd 100644 --- a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/_helpers.tpl +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/_helpers.tpl @@ -38,6 +38,11 @@ The longest name that gets created adds and extra 37 characters, so truncation s {{- end }} {{- end }} +{{/* Prometheus apiVersion for networkpolicy */}} +{{- define "kube-prometheus-stack.prometheus.networkPolicy.apiVersion" -}} +{{- print "networking.k8s.io/v1" -}} +{{- end }} + {{/* Alertmanager custom resource instance name */}} {{- define "kube-prometheus-stack.alertmanager.crname" -}} {{- if .Values.cleanPrometheusOperatorObjectNames }} 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 index a1e4749d..986f0353 100644 --- a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/alertmanager.yaml +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/alertmanager.yaml @@ -13,14 +13,15 @@ metadata: {{- end }} spec: {{- if .Values.alertmanager.alertmanagerSpec.image }} + {{- $registry := .Values.global.imageRegistry | default .Values.alertmanager.alertmanagerSpec.image.registry -}} {{- if and .Values.alertmanager.alertmanagerSpec.image.tag .Values.alertmanager.alertmanagerSpec.image.sha }} - image: "{{ .Values.alertmanager.alertmanagerSpec.image.repository }}:{{ .Values.alertmanager.alertmanagerSpec.image.tag }}@sha256:{{ .Values.alertmanager.alertmanagerSpec.image.sha }}" + image: "{{ $registry }}/{{ .Values.alertmanager.alertmanagerSpec.image.repository }}:{{ .Values.alertmanager.alertmanagerSpec.image.tag }}@sha256:{{ .Values.alertmanager.alertmanagerSpec.image.sha }}" {{- else if .Values.alertmanager.alertmanagerSpec.image.sha }} - image: "{{ .Values.alertmanager.alertmanagerSpec.image.repository }}@sha256:{{ .Values.alertmanager.alertmanagerSpec.image.sha }}" + image: "{{ $registry }}/{{ .Values.alertmanager.alertmanagerSpec.image.repository }}@sha256:{{ .Values.alertmanager.alertmanagerSpec.image.sha }}" {{- else if .Values.alertmanager.alertmanagerSpec.image.tag }} - image: "{{ .Values.alertmanager.alertmanagerSpec.image.repository }}:{{ .Values.alertmanager.alertmanagerSpec.image.tag }}" + image: "{{ $registry }}/{{ .Values.alertmanager.alertmanagerSpec.image.repository }}:{{ .Values.alertmanager.alertmanagerSpec.image.tag }}" {{- else }} - image: "{{ .Values.alertmanager.alertmanagerSpec.image.repository }}" + image: "{{ $registry }}/{{ .Values.alertmanager.alertmanagerSpec.image.repository }}" {{- end }} version: {{ .Values.alertmanager.alertmanagerSpec.image.tag }} {{- if .Values.alertmanager.alertmanagerSpec.image.sha }} 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 index b96aa1dd..350ebe88 100644 --- a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/servicemonitor.yaml +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/servicemonitor.yaml @@ -18,6 +18,7 @@ spec: - {{ printf "%s" (include "kube-prometheus-stack.namespace" .) | quote }} endpoints: - port: {{ .Values.alertmanager.alertmanagerSpec.portName }} + enableHttp2: {{ .Values.alertmanager.serviceMonitor.enableHttp2 }} {{- if .Values.alertmanager.serviceMonitor.interval }} interval: {{ .Values.alertmanager.serviceMonitor.interval }} {{- end }} @@ -27,9 +28,6 @@ spec: {{- if .Values.alertmanager.serviceMonitor.scheme }} scheme: {{ .Values.alertmanager.serviceMonitor.scheme }} {{- end }} - {{- if .Values.alertmanager.serviceMonitor.enableHttp2 }} - enableHttp2: {{ .Values.alertmanager.serviceMonitor.enableHttp2 }} - {{- end }} {{- if .Values.alertmanager.serviceMonitor.bearerTokenFile }} bearerTokenFile: {{ .Values.alertmanager.serviceMonitor.bearerTokenFile }} {{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/alertmanager-overview.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/alertmanager-overview.yaml new file mode 100644 index 00000000..7236239b --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/alertmanager-overview.yaml @@ -0,0 +1,614 @@ +{{- /* +Generated from 'alertmanager-overview' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "alertmanager-overview" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + alertmanager-overview.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "30s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "current set of alerts stored in the Alertmanager", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(alertmanager_alerts{namespace=~\"$namespace\",service=~\"$service\"}) by (namespace,service,instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Alerts", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "rate of successful and invalid alerts received by the Alertmanager", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "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": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(alertmanager_alerts_received_total{namespace=~\"$namespace\",service=~\"$service\"}[$__rate_interval])) by (namespace,service,instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Received", + "refId": "A" + }, + { + "expr": "sum(rate(alertmanager_alerts_invalid_total{namespace=~\"$namespace\",service=~\"$service\"}[$__rate_interval])) by (namespace,service,instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Invalid", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Alerts receive rate", + "tooltip": { + "shared": true, + "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": true, + "title": "Alerts", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "rate of successful and invalid notifications sent by the Alertmanager", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": "integration", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(alertmanager_notifications_total{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (integration,namespace,service,instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Total", + "refId": "A" + }, + { + "expr": "sum(rate(alertmanager_notifications_failed_total{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (integration,namespace,service,instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Failed", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "$integration: Notifications Send Rate", + "tooltip": { + "shared": true, + "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": "$datasource", + "description": "latency of notifications sent by the Alertmanager", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 5, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": "integration", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99,\n sum(rate(alertmanager_notification_latency_seconds_bucket{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (le,namespace,service,instance)\n) \n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} 99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50,\n sum(rate(alertmanager_notification_latency_seconds_bucket{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (le,namespace,service,instance)\n) \n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Median", + "refId": "B" + }, + { + "expr": "sum(rate(alertmanager_notification_latency_seconds_sum{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (namespace,service,instance)\n/\nsum(rate(alertmanager_notification_latency_seconds_count{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (namespace,service,instance)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Average", + "refId": "C" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "$integration: Notification Duration", + "tooltip": { + "shared": true, + "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": true, + "title": "Notifications", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "alertmanager-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "Prometheus" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(alertmanager_alerts, namespace)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "service", + "multi": false, + "name": "service", + "options": [ + + ], + "query": "label_values(alertmanager_alerts, service)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "all", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": true, + "label": null, + "multi": false, + "name": "integration", + "options": [ + + ], + "query": "label_values(alertmanager_notifications_total{integration=~\".*\"}, integration)", + "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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "title": "Alertmanager / Overview", + "uid": "alertmanager-overview", + "version": 0 + } +{{- end }} \ No newline at end of file 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..4b9fe4b8 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/apiserver.yaml @@ -0,0 +1,1772 @@ +{{- /* +Generated from 'apiserver' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled .Values.kubeApiServer.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "$datasource", + "decimals": 3, + "description": "How many percent of requests (both read and write) in 30 days have been answered successfully and fast enough?", + "format": "percentunit", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "rightSide": true + }, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 4, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "apiserver_request:availability30d{verb=\"all\", cluster=\"$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": "$datasource", + "decimals": 3, + "description": "How much error budget is left looking at our 0.990% availability guarantees?", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 8, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "100 * (apiserver_request:availability30d{verb=\"all\", cluster=\"$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": "$datasource", + "decimals": 3, + "description": "How many percent of read requests (LIST,GET) in 30 days have been answered successfully and fast enough?", + "format": "percentunit", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "rightSide": true + }, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "apiserver_request:availability30d{verb=\"read\", cluster=\"$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": "$datasource", + "description": "How many read requests (LIST,GET) per second do the apiservers get by code?", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/2../i", + "color": "#56A64B" + }, + { + "alias": "/3../i", + "color": "#F2CC0C" + }, + { + "alias": "/4../i", + "color": "#3274D9" + }, + { + "alias": "/5../i", + "color": "#E02F44" + } + ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (code) (code_resource:apiserver_request_total:rate5m{verb=\"read\", cluster=\"$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": "$datasource", + "description": "How many percent of read requests (LIST,GET) per second are returned with errors (5xx)?", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"read\",code=~\"5..\", cluster=\"$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, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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_slo_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": "1m", + "legend": { + "alignAsTable": true, + "rightSide": 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 + }, + "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, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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": "$datasource", + "description": "How many seconds is the 99th percentile for writing (POST|PUT|PATCH|DELETE) a given resource?", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 12, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "cluster_quantile:apiserver_request_slo_duration_seconds:histogram_quantile{verb=\"write\", cluster=\"$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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 13, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(workqueue_adds_total{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) 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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 14, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(workqueue_depth{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) 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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 15, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) 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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 16, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "process_resident_memory_bytes{job=\"apiserver\",instance=~\"$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, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 18, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"apiserver\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(up{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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..16c18727 --- /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/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)", + "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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..5d687e87 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/controller-manager.yaml @@ -0,0 +1,1190 @@ +{{- /* +Generated from 'controller-manager' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled .Values.kubeControllerManager.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "rightSide": true + }, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(up{cluster=\"$cluster\", job=\"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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(workqueue_adds_total{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(workqueue_depth{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "2xx", + "refId": "A" + }, + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "3xx", + "refId": "B" + }, + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "4xx", + "refId": "C" + }, + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "5xx", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Kube API Request Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}verb{{`}}`}} {{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Post Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "interval": "1m", + "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=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}verb{{`}}`}} {{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Get Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}[$__rate_interval])", + "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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 11, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "go_goroutines{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Goroutines", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kube-controller-manager\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(up{cluster=\"$cluster\", 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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..aeda5331 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/etcd.yaml @@ -0,0 +1,1227 @@ +{{- /* +Generated from 'etcd' from https://raw.githubusercontent.com/etcd-io/etcd/main/contrib/mixin/mixin.libsonnet +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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled .Values.kubeEtcd.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "RPC Rate", + "metric": "grpc_server_started_total", + "refId": "A", + "step": 2 + }, + { + "expr": "sum(rate(grpc_server_handled_total{job=\"$cluster\",grpc_type=\"unary\",grpc_code=~\"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "RPC Failed Rate", + "metric": "grpc_server_handled_total", + "refId": "B", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "RPC Rate", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$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\"}[$__rate_interval])) by (instance, le))", + "hide": false, + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} WAL fsync", + "metric": "etcd_disk_wal_fsync_duration_seconds_bucket", + "refId": "A", + "step": 4 + }, + { + "expr": "histogram_quantile(0.99, sum(rate(etcd_disk_backend_commit_duration_seconds_bucket{job=\"$cluster\"}[$__rate_interval])) by (instance, le))", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} DB fsync", + "metric": "etcd_disk_backend_commit_duration_seconds_bucket", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Disk Sync Duration", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "s", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$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=\"$cluster\"}[$__rate_interval])", + "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\"}[$__rate_interval])", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Client Traffic Out", + "metric": "etcd_network_client_grpc_sent_bytes_total", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Client Traffic Out", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$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=\"$cluster\"}[$__rate_interval])) 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\"}[$__rate_interval])) by (instance)", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Peer Traffic Out", + "metric": "etcd_network_peer_sent_bytes_total", + "refId": "A", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Peer Traffic Out", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "title": "New row" + }, + { + "collapse": false, + "editable": true, + "height": "250px", + "panels": [ + { + "aliasColors": {}, + "bars": false, + "datasource": "$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=\"$cluster\"}[$__rate_interval]))", + "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\"}[$__rate_interval]))", + "intervalFactor": 2, + "legendFormat": "Proposal Commit Rate", + "metric": "etcd_server_proposals_committed_total", + "refId": "C", + "step": 2 + }, + { + "expr": "sum(rate(etcd_server_proposals_applied_total{job=\"$cluster\"}[$__rate_interval]))", + "intervalFactor": 2, + "legendFormat": "Proposal Apply Rate", + "refId": "D", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Raft Proposals", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": "", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "datasource": "$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=\"$cluster\"}[1d])", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Total Leader Elections Per Day", + "metric": "etcd_server_leader_changes_seen_total", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Total Leader Elections Per Day", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "decimals": 0, + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {} + }, + "overrides": [] + }, + "fill": 0, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 28 + }, + "hiddenSeries": false, + "id": 42, + "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", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.4.3", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (instance, le) (rate(etcd_network_peer_round_trip_time_seconds_bucket{job=\"$cluster\"}[$__rate_interval])))", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Peer round trip time", + "metric": "etcd_network_peer_round_trip_time_seconds_bucket", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Peer round trip time", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "$$hashKey": "object:925", + "decimals": null, + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:926", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "title": "New row" + } + ], + "schemaVersion": 13, + "sharedCrosshair": false, + "style": "dark", + "tags": [ + "etcd-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "Prometheus" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": {{ if (or .Values.grafana.sidecar.dashboards.multicluster.global.enabled .Values.grafana.sidecar.dashboards.multicluster.etcd.enabled) }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [], + "query": "label_values(etcd_server_has_leader, job)", + "refresh": 2, + "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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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/grafana-overview.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/grafana-overview.yaml new file mode 100644 index 00000000..decbf0b1 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/grafana-overview.yaml @@ -0,0 +1,636 @@ +{{- /* +Generated from 'grafana-overview' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "grafana-overview" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + grafana-overview.json: |- + { + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "target": { + "limit": 100, + "matchAny": false, + "tags": [ + + ], + "type": "dashboard" + }, + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "id": 3085, + "iteration": 1631554945276, + "links": [ + + ], + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "mappings": [ + + ], + "noValue": "0", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [ + + ] + }, + "gridPos": { + "h": 5, + "w": 6, + "x": 0, + "y": 0 + }, + "id": 6, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "mean" + ], + "fields": "", + "values": false + }, + "text": { + + }, + "textMode": "auto" + }, + "pluginVersion": "8.1.3", + "targets": [ + { + "expr": "grafana_alerting_result_total{job=~\"$job\", instance=~\"$instance\", state=\"alerting\"}", + "instant": true, + "interval": "", + "legendFormat": "", + "refId": "A" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Firing Alerts", + "type": "stat" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "mappings": [ + + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [ + + ] + }, + "gridPos": { + "h": 5, + "w": 6, + "x": 6, + "y": 0 + }, + "id": 8, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "mean" + ], + "fields": "", + "values": false + }, + "text": { + + }, + "textMode": "auto" + }, + "pluginVersion": "8.1.3", + "targets": [ + { + "expr": "sum(grafana_stat_totals_dashboard{job=~\"$job\", instance=~\"$instance\"})", + "interval": "", + "legendFormat": "", + "refId": "A" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Dashboards", + "type": "stat" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "align": null, + "displayMode": "auto" + }, + "mappings": [ + + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [ + + ] + }, + "gridPos": { + "h": 5, + "w": 12, + "x": 12, + "y": 0 + }, + "id": 10, + "options": { + "showHeader": true + }, + "pluginVersion": "8.1.3", + "targets": [ + { + "expr": "grafana_build_info{job=~\"$job\", instance=~\"$instance\"}", + "instant": true, + "interval": "", + "legendFormat": "", + "refId": "A" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Build Info", + "transformations": [ + { + "id": "labelsToFields", + "options": { + + } + }, + { + "id": "organize", + "options": { + "excludeByName": { + "Time": true, + "Value": true, + "branch": true, + "container": true, + "goversion": true, + "namespace": true, + "pod": true, + "revision": true + }, + "indexByName": { + "Time": 7, + "Value": 11, + "branch": 4, + "container": 8, + "edition": 2, + "goversion": 6, + "instance": 1, + "job": 0, + "namespace": 9, + "pod": 10, + "revision": 5, + "version": 3 + }, + "renameByName": { + + } + } + } + ], + "type": "table" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "links": [ + + ] + }, + "overrides": [ + + ] + }, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 5 + }, + "hiddenSeries": false, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "nullPointMode": "null", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "8.1.3", + "pointradius": 2, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status_code) (irate(grafana_http_request_duration_seconds_count{job=~\"$job\", instance=~\"$instance\"}[1m])) ", + "interval": "", + "legendFormat": "{{`{{`}}status_code{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeRegions": [ + + ], + "timeShift": null, + "title": "RPS", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "$$hashKey": "object:157", + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:158", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "links": [ + + ] + }, + "overrides": [ + + ] + }, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 5 + }, + "hiddenSeries": false, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "nullPointMode": "null", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "8.1.3", + "pointradius": 2, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum(irate(grafana_http_request_duration_seconds_bucket{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval])) by (le)) * 1", + "interval": "", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "exemplar": true, + "expr": "histogram_quantile(0.50, sum(irate(grafana_http_request_duration_seconds_bucket{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval])) by (le)) * 1", + "interval": "", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "exemplar": true, + "expr": "sum(irate(grafana_http_request_duration_seconds_sum{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval])) * 1 / sum(irate(grafana_http_request_duration_seconds_count{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval]))", + "interval": "", + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeRegions": [ + + ], + "timeShift": null, + "title": "Request Latency", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "$$hashKey": "object:210", + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:211", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "schemaVersion": 30, + "style": "dark", + "tags": [ + + ], + "templating": { + "list": [ + { + "current": { + "selected": true, + "text": "dev-cortex", + "value": "dev-cortex" + }, + "description": null, + "error": null, + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "queryValue": "", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "selected": false, + "text": [ + "default/grafana" + ], + "value": [ + "default/grafana" + ] + }, + "datasource": "$datasource", + "definition": "label_values(grafana_build_info, job)", + "description": null, + "error": null, + "hide": 0, + "includeAll": true, + "label": null, + "multi": true, + "name": "job", + "options": [ + + ], + "query": { + "query": "label_values(grafana_build_info, job)", + "refId": "Billing Admin-job-Variable-Query" + }, + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".*", + "current": { + "selected": false, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "definition": "label_values(grafana_build_info, instance)", + "description": null, + "error": null, + "hide": 0, + "includeAll": true, + "label": null, + "multi": true, + "name": "instance", + "options": [ + + ], + "query": { + "query": "label_values(grafana_build_info, instance)", + "refId": "Billing Admin-instance-Variable-Query" + }, + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-6h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ] + }, + "timezone": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "title": "Grafana Overview", + "uid": "6be0s85Mk", + "version": 2 + } +{{- 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..4a1846c8 --- /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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled .Values.coreDns.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 0 + }, + "hiddenSeries": false, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "total", + "yaxis": 2 + } + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(coredns_dns_request_count_total{job=\"coredns\",instance=~\"$instance\"}[5m])) by (proto) or\nsum(rate(coredns_dns_requests_total{job=\"coredns\",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{job=\"coredns\",instance=~\"$instance\"}[5m])) by (type) or \nsum(rate(coredns_dns_requests_total{job=\"coredns\",instance=~\"$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": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 8, + "x": 16, + "y": 0 + }, + "hiddenSeries": false, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "total", + "yaxis": 2 + } + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(coredns_dns_request_count_total{job=\"coredns\",instance=~\"$instance\"}[5m])) by (zone) or\nsum(rate(coredns_dns_requests_total{job=\"coredns\",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{job=\"coredns\",instance=~\"$instance\"}[5m])) or\nsum(rate(coredns_dns_do_requests_total{job=\"coredns\",instance=~\"$instance\"}[5m]))", + "interval": "", + "intervalFactor": 2, + "legendFormat": "DO", + "refId": "A", + "step": 40 + }, + { + "expr": "sum(rate(coredns_dns_request_count_total{job=\"coredns\",instance=~\"$instance\"}[5m])) or\nsum(rate(coredns_dns_requests_total{job=\"coredns\",instance=~\"$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": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 6, + "x": 12, + "y": 7 + }, + "hiddenSeries": false, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "tcp:90", + "yaxis": 2 + }, + { + "alias": "tcp:99 ", + "yaxis": 2 + }, + { + "alias": "tcp:50", + "yaxis": 2 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(coredns_dns_request_size_bytes_bucket{job=\"coredns\",instance=~\"$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{job=\"coredns\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto))", + "intervalFactor": 2, + "legendFormat": "{{"{{proto}}"}}:90", + "refId": "B", + "step": 60 + }, + { + "expr": "histogram_quantile(0.50, sum(rate(coredns_dns_request_size_bytes_bucket{job=\"coredns\",instance=~\"$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": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 6, + "x": 18, + "y": 7 + }, + "hiddenSeries": false, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "tcp:90", + "yaxis": 1 + }, + { + "alias": "tcp:99 ", + "yaxis": 1 + }, + { + "alias": "tcp:50", + "yaxis": 1 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(coredns_dns_request_size_bytes_bucket{job=\"coredns\",instance=~\"$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{job=\"coredns\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto))", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{"{{proto}}"}}:90", + "refId": "B", + "step": 60 + }, + { + "expr": "histogram_quantile(0.50, sum(rate(coredns_dns_request_size_bytes_bucket{job=\"coredns\",instance=~\"$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": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 14 + }, + "hiddenSeries": false, + "id": 14, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(coredns_dns_response_rcode_count_total{job=\"coredns\",instance=~\"$instance\"}[5m])) by (rcode) or\nsum(rate(coredns_dns_responses_total{job=\"coredns\",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{job=\"coredns\",instance=~\"$instance\"}[5m])) by (le, job))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99%", + "refId": "A", + "step": 40 + }, + { + "expr": "histogram_quantile(0.90, sum(rate(coredns_dns_request_duration_seconds_bucket{job=\"coredns\",instance=~\"$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{job=\"coredns\",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{job=\"coredns\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto)) ", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{"{{proto}}"}}:99%", + "refId": "A", + "step": 40 + }, + { + "expr": "histogram_quantile(0.90, sum(rate(coredns_dns_response_size_bytes_bucket{job=\"coredns\",instance=~\"$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{job=\"coredns\",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{job=\"coredns\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto)) ", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{"{{proto}}"}}:99%", + "refId": "A", + "step": 40 + }, + { + "expr": "histogram_quantile(0.90, sum(rate(coredns_dns_response_size_bytes_bucket{job=\"coredns\",instance=~\"$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{job=\"coredns\",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{job=\"coredns\",instance=~\"$instance\"}) by (type) or\nsum(coredns_cache_entries{job=\"coredns\",instance=~\"$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": "$datasource", + "editable": true, + "error": false, + "fieldConfig": { + "defaults": { + "custom": {}, + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 28 + }, + "hiddenSeries": false, + "id": 24, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "7.2.0", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "misses", + "yaxis": 2 + } + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(coredns_cache_hits_total{job=\"coredns\",instance=~\"$instance\"}[5m])) by (type)", + "hide": false, + "intervalFactor": 2, + "legendFormat": "hits:{{"{{type}}"}}", + "refId": "A", + "step": 40 + }, + { + "expr": "sum(rate(coredns_cache_misses_total{job=\"coredns\",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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..b6b3e1d4 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-cluster.yaml @@ -0,0 +1,3088 @@ +{{- /* +Generated from 'k8s-resources-cluster' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 1, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "cluster:node_cpu:ratio_rate5m{cluster=\"$cluster\"}", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation", + "tooltip": { + "shared": false, + "sort": 2, + "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": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\",cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Requests Commitment", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\",cluster=\"$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": 2, + "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": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "1 - sum(:node_memory_MemAvailable_bytes:sum{cluster=\"$cluster\"}) / sum(node_memory_MemTotal_bytes{job=\"node-exporter\",cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilisation", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"memory\",cluster=\"$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": 2, + "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": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"memory\",cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Limits Commitment", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Headlines", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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_irate{cluster=\"$cluster\"}) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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=$__cell", + "pattern": "namespace", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(kube_pod_owner{job=\"kube-state-metrics\", cluster=\"$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=\"$cluster\"}) by (workload, namespace)) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$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_irate{cluster=\"$cluster\"}) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$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": 2, + "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": "$datasource", + "fill": 10, + "id": 9, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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": 2, + "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": "$datasource", + "fill": 1, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Pods", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$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{job=\"kube-state-metrics\", 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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Requests by Namespace", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Requests", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 11, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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=$__cell", + "pattern": "namespace", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Network Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Network Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 12, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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": 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": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 14, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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": "avg(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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": 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": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 15, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Namespace: Transmitted", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Average Container Bandwidth by Namespace", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 16, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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": 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": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 17, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 18, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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": 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": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 19, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets Dropped", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "decimals": -1, + "fill": 10, + "id": 20, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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": "ceil(sum by(namespace) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "IOPS(Reads+Writes)", + "tooltip": { + "shared": false, + "sort": 2, + "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": "$datasource", + "fill": 10, + "id": 21, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}namespace{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "ThroughPut(Read+Write)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Storage IO", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 22, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "sort": { + "col": 4, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "IOPS(Reads)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "IOPS(Writes)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "IOPS(Reads + Writes)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Throughput(Read)", + "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": "Bps" + }, + { + "alias": "Throughput(Write)", + "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": "Bps" + }, + { + "alias": "Throughput(Read + Write)", + "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": "Bps" + }, + { + "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=$__cell", + "pattern": "namespace", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum by(namespace) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum by(namespace) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum by(namespace) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum by(namespace) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Storage IO", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Storage IO - Distribution", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, 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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..9151a288 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-namespace.yaml @@ -0,0 +1,2797 @@ +{{- /* +Generated from 'k8s-resources-namespace' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 1, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation (from requests)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})", + "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": 2, + "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": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilisation (from requests)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})", + "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": 2, + "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": "$datasource", + "fill": 10, + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "quota - requests", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + }, + { + "alias": "quota - limits", + "color": "#FF9830", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$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=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - limits", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{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_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{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_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{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": 2, + "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": "$datasource", + "fill": 10, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "quota - requests", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + }, + { + "alias": "quota - limits", + "color": "#FF9830", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - limits", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage (w/o cache)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(container_memory_cache{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + }, + { + "expr": "sum(container_memory_swap{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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": 2, + "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": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Network Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Network Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 12, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 14, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 15, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets Dropped", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "decimals": -1, + "fill": 10, + "id": 16, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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": "ceil(sum by(pod) (rate(container_fs_reads_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "IOPS(Reads+Writes)", + "tooltip": { + "shared": false, + "sort": 2, + "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": "$datasource", + "fill": 10, + "id": 17, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "ThroughPut(Read+Write)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Storage IO", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 18, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "sort": { + "col": 4, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "IOPS(Reads)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "IOPS(Writes)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "IOPS(Reads + Writes)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Throughput(Read)", + "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": "Bps" + }, + { + "alias": "Throughput(Write)", + "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": "Bps" + }, + { + "alias": "Throughput(Read + Write)", + "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": "Bps" + }, + { + "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 by(pod) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum by(pod) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum by(pod) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum by(pod) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Storage IO", + "tooltip": { + "shared": false, + "sort": 2, + "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": "Storage IO - Distribution", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)", + "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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..93668129 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-node.yaml @@ -0,0 +1,1026 @@ +{{- /* +Generated from 'k8s-resources-node' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "$datasource", + "fill": 10, + "id": 1, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "max capacity", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(kube_node_status_capacity{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "max capacity", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{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_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{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_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{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": 2, + "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": "$datasource", + "fill": 10, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "max capacity", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(kube_node_status_capacity{cluster=\"$cluster\", node=~\"$node\", resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "max capacity", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\", container!=\"\"}) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage (w/o cache)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{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(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{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(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$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": 2, + "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": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": true, + "name": "node", + "options": [ + + ], + "query": "label_values(kube_node_info{cluster=\"$cluster\"}, node)", + "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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..4efba703 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-pod.yaml @@ -0,0 +1,2469 @@ +{{- /* +Generated from 'k8s-resources-pod' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "$datasource", + "fill": 10, + "id": 1, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "requests", + "color": "#F2495C", + "fill": 0, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + }, + { + "alias": "limits", + "color": "#FF9830", + "fill": 0, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}) by (container)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}container{{`}}`}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "requests", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limits", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 2, + "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": "$datasource", + "fill": 10, + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": true, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(increase(container_cpu_cfs_throttled_periods_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container) /sum(increase(container_cpu_cfs_periods_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}container{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + { + "colorMode": "critical", + "fill": true, + "line": true, + "op": "gt", + "value": 0.25, + "yaxis": "left" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Throttling", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Throttling", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$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_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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": true, + "linewidth": 2, + "stack": false + }, + { + "alias": "limits", + "color": "#FF9830", + "dashes": true, + "fill": 0, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}container{{`}}`}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "requests", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limits", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage (WSS)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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 (WSS)", + "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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + }, + { + "expr": "sum(container_memory_swap{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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": 2, + "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": "$datasource", + "fill": 10, + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$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": 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": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$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": 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": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$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": 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": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets Dropped", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "decimals": -1, + "fill": 10, + "id": 12, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "ceil(sum by(pod) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Reads", + "legendLink": null, + "step": 10 + }, + { + "expr": "ceil(sum by(pod) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Writes", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "IOPS", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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 by(pod) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Reads", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum by(pod) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Writes", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "ThroughPut", + "tooltip": { + "shared": false, + "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": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Storage IO - Distribution(Pod - Read & Writes)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "decimals": -1, + "fill": 10, + "id": 14, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "ceil(sum by(container) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}container{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "IOPS(Reads+Writes)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 15, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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 by(container) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}container{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "ThroughPut(Read+Write)", + "tooltip": { + "shared": false, + "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": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Storage IO - Distribution(Containers)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 16, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "sort": { + "col": 4, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "IOPS(Reads)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "IOPS(Writes)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "IOPS(Reads + Writes)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Throughput(Read)", + "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": "Bps" + }, + { + "alias": "Throughput(Write)", + "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": "Bps" + }, + { + "alias": "Throughput(Read + Write)", + "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": "Bps" + }, + { + "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 by(container) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum by(container) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\",device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum by(container) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum by(container) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Storage IO", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Storage IO - Distribution", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "pod", + "options": [ + + ], + "query": "label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..2a30eac7 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-workload.yaml @@ -0,0 +1,2024 @@ +{{- /* +Generated from 'k8s-resources-workload' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "$datasource", + "fill": 10, + "id": 1, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$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=\"$type\"}\n) by (pod)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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_irate{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{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\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_irate{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{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\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{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\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_irate{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{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\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": 2, + "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": "$datasource", + "fill": 10, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$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=\"$type\"}\n) by (pod)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\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{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\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{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\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{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\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": 2, + "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": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Network Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Network Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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": "(avg(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Pod: Received", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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": "(avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Pod: Transmitted", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Average Container Bandwidth by Pod", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 12, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets Dropped", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)", + "refresh": 2, + "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=\"$namespace\"}, workload_type)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$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_type=\"$type\"}, workload)", + "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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..13559657 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-workloads-namespace.yaml @@ -0,0 +1,2189 @@ +{{- /* +Generated from 'k8s-resources-workloads-namespace' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "$datasource", + "fill": 10, + "id": 1, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "quota - requests", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + }, + { + "alias": "quota - limits", + "color": "#FF9830", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$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": 2, + "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, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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=\"$type\"}) by (workload, workload_type)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$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{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$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{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$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_irate{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=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$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": 2, + "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": "$datasource", + "fill": 10, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "quota - requests", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + }, + { + "alias": "quota - limits", + "color": "#FF9830", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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": 2, + "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, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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=\"$type\"}) by (workload, workload_type)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$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": 2, + "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": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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": 2, + "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": "Current Network Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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": 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": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(avg(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Workload: Received", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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": "(avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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": 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": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Average Container Bandwidth by Workload", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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": 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": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 12, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}workload{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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": 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": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets Dropped", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "deployment", + "value": "deployment" + }, + "datasource": "$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": 2, + "regex": "", + "skipUrlSync": false, + "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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..6335d523 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/kubelet.yaml @@ -0,0 +1,2254 @@ +{{- /* +Generated from 'kubelet' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled .Values.kubelet.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": [ + + ], + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "links": [ + + ], + "mappings": [ + + ], + "thresholds": { + "mode": "absolute", + "steps": [ + + ] + }, + "unit": "none" + } + }, + "gridPos": { + "h": 7, + "w": 4, + "x": 0, + "y": 0 + }, + "id": 2, + "links": [ + + ], + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "textMode": "auto" + }, + "pluginVersion": "7", + "targets": [ + { + "expr": "sum(kubelet_node_name{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "title": "Running Kubelets", + "transparent": false, + "type": "stat" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "links": [ + + ], + "mappings": [ + + ], + "thresholds": { + "mode": "absolute", + "steps": [ + + ] + }, + "unit": "none" + } + }, + "gridPos": { + "h": 7, + "w": 4, + "x": 4, + "y": 0 + }, + "id": 3, + "links": [ + + ], + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "textMode": "auto" + }, + "pluginVersion": "7", + "targets": [ + { + "expr": "sum(kubelet_running_pods{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}) OR sum(kubelet_running_pod_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "title": "Running Pods", + "transparent": false, + "type": "stat" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "links": [ + + ], + "mappings": [ + + ], + "thresholds": { + "mode": "absolute", + "steps": [ + + ] + }, + "unit": "none" + } + }, + "gridPos": { + "h": 7, + "w": 4, + "x": 8, + "y": 0 + }, + "id": 4, + "links": [ + + ], + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "textMode": "auto" + }, + "pluginVersion": "7", + "targets": [ + { + "expr": "sum(kubelet_running_containers{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}) OR sum(kubelet_running_container_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "title": "Running Containers", + "transparent": false, + "type": "stat" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "links": [ + + ], + "mappings": [ + + ], + "thresholds": { + "mode": "absolute", + "steps": [ + + ] + }, + "unit": "none" + } + }, + "gridPos": { + "h": 7, + "w": 4, + "x": 12, + "y": 0 + }, + "id": 5, + "links": [ + + ], + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "textMode": "auto" + }, + "pluginVersion": "7", + "targets": [ + { + "expr": "sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\", state=\"actual_state_of_world\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "title": "Actual Volume Count", + "transparent": false, + "type": "stat" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "links": [ + + ], + "mappings": [ + + ], + "thresholds": { + "mode": "absolute", + "steps": [ + + ] + }, + "unit": "none" + } + }, + "gridPos": { + "h": 7, + "w": 4, + "x": 16, + "y": 0 + }, + "id": 6, + "links": [ + + ], + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "textMode": "auto" + }, + "pluginVersion": "7", + "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" + } + ], + "title": "Desired Volume Count", + "transparent": false, + "type": "stat" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "links": [ + + ], + "mappings": [ + + ], + "thresholds": { + "mode": "absolute", + "steps": [ + + ] + }, + "unit": "none" + } + }, + "gridPos": { + "h": 7, + "w": 4, + "x": 20, + "y": 0 + }, + "id": 7, + "links": [ + + ], + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "textMode": "auto" + }, + "pluginVersion": "7", + "targets": [ + { + "expr": "sum(rate(kubelet_node_config_error{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "title": "Config Error Count", + "transparent": false, + "type": "stat" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 7 + }, + "id": 8, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubelet_runtime_operations_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) 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": true, + "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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 7 + }, + "id": 9, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubelet_runtime_operations_errors_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) 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": true, + "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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 14 + }, + "id": 10, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_runtime_operations_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) 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": true, + "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 + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 21 + }, + "id": 11, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) 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\"}[$__rate_interval])) by (instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} worker", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Pod Start Rate", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 21 + }, + "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, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_start_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} pod", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} worker", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Pod Start Duration", + "tooltip": { + "shared": true, + "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 + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 28 + }, + "id": 13, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(storage_operation_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) 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": true, + "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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 28 + }, + "id": 14, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(storage_operation_errors_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) 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": true, + "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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 35 + }, + "id": 15, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(storage_operation_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) 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": true, + "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 + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 42 + }, + "id": 16, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubelet_cgroup_manager_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) 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": true, + "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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 42 + }, + "id": 17, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_cgroup_manager_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) 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": true, + "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 + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Pod lifecycle event generator", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 49 + }, + "id": 18, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubelet_pleg_relist_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "PLEG relist rate", + "tooltip": { + "shared": true, + "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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 49 + }, + "id": 19, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_interval_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "PLEG relist interval", + "tooltip": { + "shared": true, + "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 + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 56 + }, + "id": 20, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "PLEG relist duration", + "tooltip": { + "shared": true, + "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 + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 63 + }, + "id": 21, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))", + "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..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "3xx", + "refId": "B" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))", + "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..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "5xx", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "RPC Rate", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 70 + }, + "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, + "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\"}[$__rate_interval])) by (instance, verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}verb{{`}}`}} {{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Request duration 99th quantile", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 77 + }, + "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, + "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": true, + "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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 8, + "x": 8, + "y": 77 + }, + "id": 24, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU usage", + "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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 8, + "x": 16, + "y": 77 + }, + "id": 25, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "go_goroutines{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Goroutines", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "refresh": "10s", + "rows": [ + + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "instance", + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics\",cluster=\"$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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..1e8e61b2 --- /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/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}pod{{`}}`}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Errors", + "titleSize": "h6", + "type": "row" + } + ], + "refresh": "10s", + "rows": [ + + ], + "schemaVersion": 18, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)", + "refresh": 2, + "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=\"$cluster\"}, namespace)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..c4fc4bb2 --- /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/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "kube-system", + "value": "kube-system" + }, + "datasource": "$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": 2, + "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=\"$namespace\", workload=~\".+\"}, workload_type)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..a0bdbb75 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/node-cluster-rsrc-use.yaml @@ -0,0 +1,1063 @@ +{{- /* +Generated from 'node-cluster-rsrc-use' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled .Values.nodeExporter.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + node-cluster-rsrc-use.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "30s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "((\n instance:node_cpu_utilisation:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}\n *\n instance:node_num_cpu:sum{job=\"node-exporter\", cluster=\"$cluster\"}\n) != 0 )\n/ scalar(sum(instance:node_num_cpu:sum{job=\"node-exporter\", cluster=\"$cluster\"}))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}} instance {{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation", + "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": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n instance:node_load1_per_cpu:ratio{job=\"node-exporter\", cluster=\"$cluster\"}\n / scalar(count(instance:node_load1_per_cpu:ratio{job=\"node-exporter\", cluster=\"$cluster\"}))\n) != 0\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Saturation (Load1 per CPU)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "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": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n instance:node_memory_utilisation:ratio{job=\"node-exporter\", cluster=\"$cluster\"}\n / scalar(count(instance:node_memory_utilisation:ratio{job=\"node-exporter\", cluster=\"$cluster\"}))\n) != 0\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilisation", + "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": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 5, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_vmstat_pgmajfault:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Saturation (Major Page Faults)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "rds", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "rds", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/Receive/", + "stack": "A" + }, + { + "alias": "/Transmit/", + "stack": "B", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_network_receive_bytes_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Receive", + "refId": "A" + }, + { + "expr": "instance:node_network_transmit_bytes_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Transmit", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Utilisation (Bytes Receive/Transmit)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "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": [ + { + "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:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Receive", + "refId": "A" + }, + { + "expr": "instance:node_network_transmit_drop_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} Transmit", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Saturation (Drops Receive/Transmit)", + "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": null, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}\n / scalar(count(instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}))\n) != 0\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}device{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk IO Utilisation", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "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": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}\n / scalar(count(instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}))\n) != 0\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}device{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk IO Saturation", + "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": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk IO", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum without (device) (\n max without (fstype, mountpoint) ((\n node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", cluster=\"$cluster\"}\n -\n node_filesystem_avail_bytes{job=\"node-exporter\", fstype!=\"\", cluster=\"$cluster\"}\n ) != 0)\n)\n/ scalar(sum(max without (fstype, mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", cluster=\"$cluster\"})))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk Space Utilisation", + "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": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk Space", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "node-exporter-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(node_time_seconds, 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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "title": "Node Exporter / USE Method / Cluster", + "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..6ed320d0 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/node-rsrc-use.yaml @@ -0,0 +1,1089 @@ +{{- /* +Generated from 'node-rsrc-use' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled .Values.nodeExporter.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + node-rsrc-use.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "30s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_cpu_utilisation:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Utilisation", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "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": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_load1_per_cpu:ratio{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Saturation", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Saturation (Load1 per CPU)", + "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": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_memory_utilisation:ratio{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Utilisation", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilisation", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 5, + "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": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_vmstat_pgmajfault:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Major page Faults", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Saturation (Major Page Faults)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "rds", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "rds", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/Receive/", + "stack": "A" + }, + { + "alias": "/Transmit/", + "stack": "B", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_network_receive_bytes_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Receive", + "refId": "A" + }, + { + "expr": "instance:node_network_transmit_bytes_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Transmit", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Utilisation (Bytes Receive/Transmit)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "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": [ + { + "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:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Receive", + "refId": "A" + }, + { + "expr": "instance:node_network_transmit_drop_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Transmit", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Saturation (Drops Receive/Transmit)", + "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": null, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}device{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk IO Utilisation", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "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": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}device{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk IO Saturation", + "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": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk IO", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(1 -\n (\n max without (mountpoint, fstype) (node_filesystem_avail_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\", cluster=\"$cluster\"})\n /\n max without (mountpoint, fstype) (node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\", cluster=\"$cluster\"})\n ) != 0\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}device{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk Space Utilisation", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk Space", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "node-exporter-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(node_time_seconds, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(node_exporter_build_info{job=\"node-exporter\", cluster=\"$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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "title": "Node Exporter / USE Method / Node", + "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-darwin.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/nodes-darwin.yaml new file mode 100644 index 00000000..3a706b84 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/nodes-darwin.yaml @@ -0,0 +1,1073 @@ +{{- /* +Generated from 'nodes-darwin' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.namespace" . }} + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "nodes-darwin" | trunc 63 | trimSuffix "-" }} + annotations: +{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }} + labels: + {{- if $.Values.grafana.sidecar.dashboards.label }} + {{ $.Values.grafana.sidecar.dashboards.label }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- end }} + app: {{ template "kube-prometheus-stack.name" $ }}-grafana +{{ include "kube-prometheus-stack.labels" $ | indent 4 }} +data: + nodes-darwin.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "30s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n (1 - sum without (mode) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode=~\"idle|iowait|steal\", instance=\"$instance\"}[$__rate_interval])))\n/ ignoring(cpu) group_left\n count without (cpu, mode) (node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\"})\n)\n", + "format": "time_series", + "intervalFactor": 5, + "legendFormat": "{{`{{`}}cpu{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": true, + "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=\"$instance\", mode=\"idle\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "logical cores", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Load Average", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$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": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_total_bytes{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Physical Memory", + "refId": "A" + }, + { + "expr": "(\n node_memory_internal_bytes{job=\"node-exporter\", instance=\"$instance\"} -\n node_memory_purgeable_bytes{job=\"node-exporter\", instance=\"$instance\"} +\n node_memory_wired_bytes{job=\"node-exporter\", instance=\"$instance\"} +\n node_memory_compressed_bytes{job=\"node-exporter\", instance=\"$instance\"}\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Memory Used", + "refId": "B" + }, + { + "expr": "(\n node_memory_internal_bytes{job=\"node-exporter\", instance=\"$instance\"} -\n node_memory_purgeable_bytes{job=\"node-exporter\", instance=\"$instance\"}\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "App Memory", + "refId": "C" + }, + { + "expr": "node_memory_wired_bytes{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Wired Memory", + "refId": "D" + }, + { + "expr": "node_memory_compressed_bytes{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Compressed", + "refId": "E" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 100, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "rgba(50, 172, 45, 0.97)" + }, + { + "color": "rgba(237, 129, 40, 0.89)", + "value": 80 + }, + { + "color": "rgba(245, 54, 54, 0.9)", + "value": 90 + } + ] + }, + "unit": "percent" + } + }, + "gridPos": { + + }, + "id": 5, + "span": 3, + "targets": [ + { + "expr": "(\n (\n avg(node_memory_internal_bytes{job=\"node-exporter\", instance=\"$instance\"}) -\n avg(node_memory_purgeable_bytes{job=\"node-exporter\", instance=\"$instance\"}) +\n avg(node_memory_wired_bytes{job=\"node-exporter\", instance=\"$instance\"}) +\n avg(node_memory_compressed_bytes{job=\"node-exporter\", instance=\"$instance\"})\n ) /\n avg(node_memory_total_bytes{job=\"node-exporter\", instance=\"$instance\"})\n)\n*\n100\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "" + } + ], + "title": "Memory Usage", + "transparent": false, + "type": "gauge" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$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=\"$instance\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}device{{`}}`}} read", + "refId": "A" + }, + { + "expr": "rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}device{{`}}`}} written", + "refId": "B" + }, + { + "expr": "rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}device{{`}}`}} io time", + "refId": "C" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk I/O", + "tooltip": { + "shared": true, + "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": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "yellow", + "value": 0.8 + }, + { + "color": "red", + "value": 0.9 + } + ] + }, + "unit": "decbytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Mounted on" + }, + "properties": [ + { + "id": "custom.width", + "value": 260 + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Size" + }, + "properties": [ + { + "id": "custom.width", + "value": 93 + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Used" + }, + "properties": [ + { + "id": "custom.width", + "value": 72 + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Available" + }, + "properties": [ + { + "id": "custom.width", + "value": 88 + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Used, %" + }, + "properties": [ + { + "id": "unit", + "value": "percentunit" + }, + { + "id": "custom.displayMode", + "value": "gradient-gauge" + }, + { + "id": "max", + "value": 1 + }, + { + "id": "min", + "value": 0 + } + ] + } + ] + }, + "gridPos": { + + }, + "id": 7, + "span": 6, + "targets": [ + { + "expr": "max by (mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\"})\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "" + }, + { + "expr": "max by (mountpoint) (node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\"})\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "" + } + ], + "title": "Disk Space Usage", + "transformations": [ + { + "id": "groupBy", + "options": { + "fields": { + "Value #A": { + "aggregations": [ + "lastNotNull" + ], + "operation": "aggregate" + }, + "Value #B": { + "aggregations": [ + "lastNotNull" + ], + "operation": "aggregate" + }, + "mountpoint": { + "aggregations": [ + + ], + "operation": "groupby" + } + } + } + }, + { + "id": "merge", + "options": { + + } + }, + { + "id": "calculateField", + "options": { + "alias": "Used", + "binary": { + "left": "Value #A (lastNotNull)", + "operator": "-", + "reducer": "sum", + "right": "Value #B (lastNotNull)" + }, + "mode": "binary", + "reduce": { + "reducer": "sum" + } + } + }, + { + "id": "calculateField", + "options": { + "alias": "Used, %", + "binary": { + "left": "Used", + "operator": "/", + "reducer": "sum", + "right": "Value #A (lastNotNull)" + }, + "mode": "binary", + "reduce": { + "reducer": "sum" + } + } + }, + { + "id": "organize", + "options": { + "excludeByName": { + + }, + "indexByName": { + + }, + "renameByName": { + "Value #A (lastNotNull)": "Size", + "Value #B (lastNotNull)": "Available", + "mountpoint": "Mounted on" + } + } + }, + { + "id": "sortBy", + "options": { + "fields": { + + }, + "sort": [ + { + "field": "Mounted on" + } + ] + } + } + ], + "transparent": false, + "type": "table" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Network received (bits/s)", + "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=\"$instance\", device!=\"lo\"}[$__rate_interval]) * 8", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}device{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Received", + "tooltip": { + "shared": true, + "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": "bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Network transmitted (bits/s)", + "fill": 0, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__rate_interval]) * 8", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}device{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Transmitted", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "node-exporter-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "Instance", + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(node_uname_info{job=\"node-exporter\", sysname=\"Darwin\"}, 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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "title": "Node Exporter / MacOS", + "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..d575e048 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/nodes.yaml @@ -0,0 +1,1066 @@ +{{- /* +Generated from 'nodes' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled .Values.nodeExporter.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": 1, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "30s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n (1 - sum without (mode) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode=~\"idle|iowait|steal\", instance=\"$instance\"}[$__rate_interval])))\n/ ignoring(cpu) group_left\n count without (cpu, mode) (node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\"})\n)\n", + "format": "time_series", + "intervalFactor": 5, + "legendFormat": "{{`{{`}}cpu{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": true, + "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=\"$instance\", mode=\"idle\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "logical cores", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Load Average", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$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=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "memory free", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 100, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "rgba(50, 172, 45, 0.97)" + }, + { + "color": "rgba(237, 129, 40, 0.89)", + "value": 80 + }, + { + "color": "rgba(245, 54, 54, 0.9)", + "value": 90 + } + ] + }, + "unit": "percent" + } + }, + "gridPos": { + + }, + "id": 5, + "span": 3, + "targets": [ + { + "expr": "100 -\n(\n avg(node_memory_MemAvailable_bytes{job=\"node-exporter\", instance=\"$instance\"}) /\n avg(node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"})\n* 100\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "" + } + ], + "title": "Memory Usage", + "transparent": false, + "type": "gauge" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory", + "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=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}device{{`}}`}} read", + "refId": "A" + }, + { + "expr": "rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}device{{`}}`}} written", + "refId": "B" + }, + { + "expr": "rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}device{{`}}`}} io time", + "refId": "C" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk I/O", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "yellow", + "value": 0.8 + }, + { + "color": "red", + "value": 0.9 + } + ] + }, + "unit": "decbytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Mounted on" + }, + "properties": [ + { + "id": "custom.width", + "value": 260 + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Size" + }, + "properties": [ + { + "id": "custom.width", + "value": 93 + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Used" + }, + "properties": [ + { + "id": "custom.width", + "value": 72 + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Available" + }, + "properties": [ + { + "id": "custom.width", + "value": 88 + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Used, %" + }, + "properties": [ + { + "id": "unit", + "value": "percentunit" + }, + { + "id": "custom.displayMode", + "value": "gradient-gauge" + }, + { + "id": "max", + "value": 1 + }, + { + "id": "min", + "value": 0 + } + ] + } + ] + }, + "gridPos": { + + }, + "id": 7, + "span": 6, + "targets": [ + { + "expr": "max by (mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\"})\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "" + }, + { + "expr": "max by (mountpoint) (node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\"})\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "" + } + ], + "title": "Disk Space Usage", + "transformations": [ + { + "id": "groupBy", + "options": { + "fields": { + "Value #A": { + "aggregations": [ + "lastNotNull" + ], + "operation": "aggregate" + }, + "Value #B": { + "aggregations": [ + "lastNotNull" + ], + "operation": "aggregate" + }, + "mountpoint": { + "aggregations": [ + + ], + "operation": "groupby" + } + } + } + }, + { + "id": "merge", + "options": { + + } + }, + { + "id": "calculateField", + "options": { + "alias": "Used", + "binary": { + "left": "Value #A (lastNotNull)", + "operator": "-", + "reducer": "sum", + "right": "Value #B (lastNotNull)" + }, + "mode": "binary", + "reduce": { + "reducer": "sum" + } + } + }, + { + "id": "calculateField", + "options": { + "alias": "Used, %", + "binary": { + "left": "Used", + "operator": "/", + "reducer": "sum", + "right": "Value #A (lastNotNull)" + }, + "mode": "binary", + "reduce": { + "reducer": "sum" + } + } + }, + { + "id": "organize", + "options": { + "excludeByName": { + + }, + "indexByName": { + + }, + "renameByName": { + "Value #A (lastNotNull)": "Size", + "Value #B (lastNotNull)": "Available", + "mountpoint": "Mounted on" + } + } + }, + { + "id": "sortBy", + "options": { + "fields": { + + }, + "sort": [ + { + "field": "Mounted on" + } + ] + } + } + ], + "transparent": false, + "type": "table" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Network received (bits/s)", + "fill": 0, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__rate_interval]) * 8", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}device{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Received", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Network transmitted (bits/s)", + "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=\"$instance\", device!=\"lo\"}[$__rate_interval]) * 8", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{`{{`}}device{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Transmitted", + "tooltip": { + "shared": true, + "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": "bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "node-exporter-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "Instance", + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(node_uname_info{job=\"node-exporter\", sysname!=\"Darwin\"}, 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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "title": "Node Exporter / Nodes", + "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..3fc290dc --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/persistentvolumesusage.yaml @@ -0,0 +1,587 @@ +{{- /* +Generated from 'persistentvolumesusage' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 9, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n sum without(instance, node) (topk(1, (kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n -\n sum without(instance, node) (topk(1, (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Used Space", + "refId": "A" + }, + { + "expr": "sum without(instance, node) (topk(1, (kubelet_volume_stats_available_bytes{cluster=\"$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": "$datasource", + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "rightSide": true + }, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "max without(instance,node) (\n(\n topk(1, kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n -\n topk(1, kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n)\n/\ntopk(1, kubelet_volume_stats_capacity_bytes{cluster=\"$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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 9, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes_used{cluster=\"$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) (topk(1, (kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n -\n sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes_used{cluster=\"$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": "$datasource", + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "rightSide": true + }, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "max without(instance,node) (\ntopk(1, kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n/\ntopk(1, kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n* 100)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "80, 90", + "title": "Volume inodes Usage", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kubelet_volume_stats_capacity_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}, 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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..ff50c49c --- /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/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "kube-system", + "value": "kube-system" + }, + "datasource": "$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": 2, + "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=~\"$namespace\"}, pod)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..f8ffafc4 --- /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/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled .Values.prometheus.prometheusSpec.remoteWriteDashboards }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "60s", + "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=~\"$instance\"} != 0)\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}}:{{`{{`}}instance{{`}}`}} {{`{{`}}remote_name{{`}}`}}:{{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Highest Timestamp In vs. Highest Timestamp Sent", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$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": "clamp_min(\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, 0)\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=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]))\n- \n (rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_dropped_total{cluster=~\"$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=~\"$instance\"} or prometheus_remote_storage_samples_pending{cluster=~\"$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]) or rate(prometheus_remote_storage_samples_dropped_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=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{cluster=~\"$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]) or rate(prometheus_remote_storage_samples_retried_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=~\"$instance\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}}:{{`{{`}}instance{{`}}`}} {{`{{`}}remote_name{{`}}`}}:{{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Enqueue Retries", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Misc. Rates", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "prometheus-mixin" + ], + "templating": { + "list": [ + { + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "value": { + "selected": true, + "text": "All", + "value": "$__all" + } + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}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": { + "text": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "value": { + "selected": true, + "text": "All", + "value": "$__all" + } + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(prometheus_build_info{cluster=~\"$cluster\"}, instance)", + "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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..124ee371 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/prometheus.yaml @@ -0,0 +1,1235 @@ +{{- /* +Generated from 'prometheus' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "60s", + "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=~\"$instance\"})", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Prometheus Stats", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Prometheus Stats", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$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": 2, + "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=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Targets", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Targets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Discovery", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$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": 2, + "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_body_size_limit_total[1m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "exceeded body size limit: {{`{{`}}job{{`}}`}}", + "legendLink": null, + "step": 10 + }, + { + "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": 2, + "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": 2, + "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=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}job{{`}}`}} {{`{{`}}instance{{`}}`}} head series", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Head Series", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$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": 2, + "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=~\"$instance\",slice=\"inner_eval\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}job{{`}}`}} {{`{{`}}instance{{`}}`}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Query Rate", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$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": 2, + "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": [ + "prometheus-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "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=\"prometheus-k8s\",namespace=\"monitoring\"}, job)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "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{job=~\"$job\"}, 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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..53a077c1 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/proxy.yaml @@ -0,0 +1,1271 @@ +{{- /* +Generated from 'proxy' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled .Values.kubeProxy.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "rightSide": true + }, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(up{cluster=\"$cluster\", job=\"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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 5, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubeproxy_sync_proxy_rules_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))", + "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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 5, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99,rate(kubeproxy_sync_proxy_rules_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))", + "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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubeproxy_network_programming_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))", + "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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubeproxy_network_programming_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval])) 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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "2xx", + "refId": "A" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "3xx", + "refId": "B" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "4xx", + "refId": "C" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "5xx", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Kube API Request Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[$__rate_interval])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}verb{{`}}`}} {{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Post Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "interval": "1m", + "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=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}verb{{`}}`}} {{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Get Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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=\"$cluster\", job=\"kube-proxy\",instance=~\"$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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 11, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}[$__rate_interval])", + "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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 12, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "go_goroutines{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Goroutines", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kube-proxy\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(up{job=\"kube-proxy\", cluster=\"$cluster\", 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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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..c7ac2072 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/scheduler.yaml @@ -0,0 +1,1112 @@ +{{- /* +Generated from 'scheduler' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled .Values.kubeScheduler.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "rightSide": true + }, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(up{cluster=\"$cluster\", job=\"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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 5, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(scheduler_e2e_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} e2e", + "refId": "A" + }, + { + "expr": "sum(rate(scheduler_binding_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} binding", + "refId": "B" + }, + { + "expr": "sum(rate(scheduler_scheduling_algorithm_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} scheduling algorithm", + "refId": "C" + }, + { + "expr": "sum(rate(scheduler_volume_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} volume", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Scheduling Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "interval": "1m", + "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{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} e2e", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} binding", + "refId": "B" + }, + { + "expr": "histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} scheduling algorithm", + "refId": "C" + }, + { + "expr": "histogram_quantile(0.99, sum(rate(scheduler_volume_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "2xx", + "refId": "A" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "3xx", + "refId": "B" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "4xx", + "refId": "C" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "5xx", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Kube API Request Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}verb{{`}}`}} {{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Post Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "interval": "1m", + "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=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}verb{{`}}`}} {{`{{`}}url{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Get Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "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=\"$cluster\", job=\"kube-scheduler\", instance=~\"$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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])", + "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": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "go_goroutines{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{`{{`}}instance{{`}}`}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Goroutines", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kube-scheduler\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(up{job=\"kube-scheduler\", cluster=\"$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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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/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..35ca442b --- /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/main/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 (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: {{ template "kube-prometheus-stack-grafana.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 }}: {{ ternary $.Values.grafana.sidecar.dashboards.labelValue "1" (not (empty $.Values.grafana.sidecar.dashboards.labelValue)) | quote }} + {{- 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": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 1 + }, + "id": 3, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 11 + }, + "id": 6, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 12 + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 22 + }, + "id": 12, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 23 + }, + "id": 15, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$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{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", 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": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": {{ if .Values.grafana.sidecar.dashboards.multicluster.global.enabled }}0{{ else }}2{{ end }}, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_info{job=\"kube-state-metrics\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "kube-system", + "value": "kube-system" + }, + "datasource": "$datasource", + "definition": "label_values(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\"}, namespace)", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\"}, namespace)", + "refresh": 2, + "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=~\"$namespace\"}, workload)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "deployment", + "value": "deployment" + }, + "datasource": "$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": 2, + "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": "{{ .Values.grafana.defaultDashboardsTimezone }}", + "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/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 index 6c91ee00..cf2787b5 100644 --- 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 @@ -18,7 +18,7 @@ rules: verbs: - get - update -{{- if .Values.global.rbac.pspEnabled }} +{{- if and (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") .Values.global.rbac.pspEnabled }} {{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} {{- if semverCompare "> 1.15.0-0" $kubeTargetVersion }} - apiGroups: ['policy'] 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 index 6a9db3e2..1bb9b02f 100644 --- 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 @@ -34,10 +34,11 @@ spec: {{- end }} containers: - name: create + {{- $registry := .Values.global.imageRegistry | default .Values.prometheusOperator.admissionWebhooks.patch.image.registry -}} {{- 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 }} + image: {{ $registry }}/{{ .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 }} + image: {{ $registry }}/{{ .Values.prometheusOperator.admissionWebhooks.patch.image.repository }}:{{ .Values.prometheusOperator.admissionWebhooks.patch.image.tag }} {{- end }} imagePullPolicy: {{ .Values.prometheusOperator.admissionWebhooks.patch.image.pullPolicy }} args: 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 index 1ac7ceb3..350669af 100644 --- 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 @@ -34,10 +34,11 @@ spec: {{- end }} containers: - name: patch + {{- $registry := .Values.global.imageRegistry | default .Values.prometheusOperator.admissionWebhooks.patch.image.registry -}} {{- 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 }} + image: {{ $registry }}/{{ .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 }} + image: {{ $registry }}/{{ .Values.prometheusOperator.admissionWebhooks.patch.image.repository }}:{{ .Values.prometheusOperator.admissionWebhooks.patch.image.tag }} {{- end }} imagePullPolicy: {{ .Values.prometheusOperator.admissionWebhooks.patch.image.pullPolicy }} args: diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/networkpolicy-createSecret.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/networkpolicy-createSecret.yaml new file mode 100644 index 00000000..270bf854 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/networkpolicy-createSecret.yaml @@ -0,0 +1,29 @@ +{{- if .Values.prometheusOperator.networkPolicy.enabled }} +{{- if and .Values.prometheusOperator.enabled .Values.prometheusOperator.admissionWebhooks.enabled .Values.prometheusOperator.admissionWebhooks.patch.enabled (not .Values.prometheusOperator.admissionWebhooks.certManager.enabled) }} +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +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 + ## Ensure this is run before the job + "helm.sh/hook-weight": "-5" +{{- with .Values.prometheusOperator.admissionWebhooks.annotations }} +{{ toYaml . | indent 4 }} +{{- end }} + labels: + app: {{ template "kube-prometheus-stack.name" $ }}-admission-create +{{- include "kube-prometheus-stack.labels" $ | indent 4 }} +spec: + podSelector: + matchLabels: + app: {{ template "kube-prometheus-stack.name" $ }}-admission-create +{{- include "kube-prometheus-stack.labels" $ | indent 6 }} + egress: + - {} + policyTypes: + - Egress +{{- end }} +{{- end }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/networkpolicy-patchWebhook.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/networkpolicy-patchWebhook.yaml new file mode 100644 index 00000000..170c651b --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/networkpolicy-patchWebhook.yaml @@ -0,0 +1,29 @@ +{{- if .Values.prometheusOperator.networkPolicy.enabled }} +{{- if and .Values.prometheusOperator.enabled .Values.prometheusOperator.admissionWebhooks.enabled .Values.prometheusOperator.admissionWebhooks.patch.enabled (not .Values.prometheusOperator.admissionWebhooks.certManager.enabled) }} +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +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 + ## Ensure this is run before the job + "helm.sh/hook-weight": "-5" +{{- with .Values.prometheusOperator.admissionWebhooks.patch.annotations }} +{{ toYaml . | indent 4 }} +{{- end }} + labels: + app: {{ template "kube-prometheus-stack.name" $ }}-admission-patch +{{- include "kube-prometheus-stack.labels" $ | indent 4 }} +spec: + podSelector: + matchLabels: + app: {{ template "kube-prometheus-stack.name" $ }}-admission-patch +{{- include "kube-prometheus-stack.labels" $ | indent 6 }} + egress: + - {} + policyTypes: + - Egress +{{- end }} +{{- 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 index 9feff52d..5a8c19a2 100644 --- 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 @@ -1,4 +1,4 @@ -{{- if and .Values.prometheusOperator.enabled .Values.prometheusOperator.admissionWebhooks.enabled .Values.prometheusOperator.admissionWebhooks.patch.enabled .Values.global.rbac.create .Values.global.rbac.pspEnabled (not .Values.prometheusOperator.admissionWebhooks.certManager.enabled) }} +{{- if and (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") .Values.prometheusOperator.enabled .Values.prometheusOperator.admissionWebhooks.enabled .Values.prometheusOperator.admissionWebhooks.patch.enabled .Values.global.rbac.create .Values.global.rbac.pspEnabled (not .Values.prometheusOperator.admissionWebhooks.certManager.enabled) }} apiVersion: policy/v1beta1 kind: PodSecurityPolicy metadata: 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 index 92426594..8d4e7d3c 100644 --- 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 @@ -36,6 +36,7 @@ webhooks: {{- if and .Values.prometheusOperator.admissionWebhooks.caBundle (not .Values.prometheusOperator.admissionWebhooks.patch.enabled) (not .Values.prometheusOperator.admissionWebhooks.certManager.enabled) }} caBundle: {{ .Values.prometheusOperator.admissionWebhooks.caBundle }} {{- end }} + timeoutSeconds: {{ .Values.prometheusOperator.admissionWebhooks.timeoutSeconds }} admissionReviewVersions: ["v1", "v1beta1"] sideEffects: None {{- 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 index c3888b95..97a78cda 100644 --- 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 @@ -40,10 +40,11 @@ spec: {{- end }} containers: - name: {{ template "kube-prometheus-stack.name" . }} + {{- $registry := .Values.global.imageRegistry | default .Values.prometheusOperator.image.registry -}} {{- if .Values.prometheusOperator.image.sha }} - image: "{{ .Values.prometheusOperator.image.repository }}:{{ .Values.prometheusOperator.image.tag }}@sha256:{{ .Values.prometheusOperator.image.sha }}" + image: "{{ $registry }}/{{ .Values.prometheusOperator.image.repository }}:{{ .Values.prometheusOperator.image.tag }}@sha256:{{ .Values.prometheusOperator.image.sha }}" {{- else }} - image: "{{ .Values.prometheusOperator.image.repository }}:{{ .Values.prometheusOperator.image.tag }}" + image: "{{ $registry }}/{{ .Values.prometheusOperator.image.repository }}:{{ .Values.prometheusOperator.image.tag }}" {{- end }} imagePullPolicy: "{{ .Values.prometheusOperator.image.pullPolicy }}" args: @@ -73,15 +74,15 @@ spec: {{- end }} - --localhost=127.0.0.1 {{- if .Values.prometheusOperator.prometheusDefaultBaseImage }} - - --prometheus-default-base-image={{ .Values.prometheusOperator.prometheusDefaultBaseImage }} + - --prometheus-default-base-image={{ .Values.global.imageRegistry | default .Values.prometheusOperator.prometheusDefaultBaseImageRegistry }}/{{ .Values.prometheusOperator.prometheusDefaultBaseImage }} {{- end }} {{- if .Values.prometheusOperator.alertmanagerDefaultBaseImage }} - - --alertmanager-default-base-image={{ .Values.prometheusOperator.alertmanagerDefaultBaseImage }} + - --alertmanager-default-base-image={{ .Values.global.imageRegistry | default .Values.prometheusOperator.alertmanagerDefaultBaseImageRegistry }}/{{ .Values.prometheusOperator.alertmanagerDefaultBaseImage }} {{- end }} {{- if .Values.prometheusOperator.prometheusConfigReloader.image.sha }} - - --prometheus-config-reloader={{ .Values.prometheusOperator.prometheusConfigReloader.image.repository }}:{{ .Values.prometheusOperator.prometheusConfigReloader.image.tag }}@sha256:{{ .Values.prometheusOperator.prometheusConfigReloader.image.sha }} + - --prometheus-config-reloader={{ $registry }}/{{ .Values.prometheusOperator.prometheusConfigReloader.image.repository }}:{{ .Values.prometheusOperator.prometheusConfigReloader.image.tag }}@sha256:{{ .Values.prometheusOperator.prometheusConfigReloader.image.sha }} {{- else }} - - --prometheus-config-reloader={{ .Values.prometheusOperator.prometheusConfigReloader.image.repository }}:{{ .Values.prometheusOperator.prometheusConfigReloader.image.tag }} + - --prometheus-config-reloader={{ $registry }}/{{ .Values.prometheusOperator.prometheusConfigReloader.image.repository }}:{{ .Values.prometheusOperator.prometheusConfigReloader.image.tag }} {{- end }} - --config-reloader-cpu-request={{ .Values.prometheusOperator.prometheusConfigReloader.resources.requests.cpu }} - --config-reloader-cpu-limit={{ .Values.prometheusOperator.prometheusConfigReloader.resources.limits.cpu }} @@ -97,9 +98,9 @@ spec: - --prometheus-instance-namespaces={{ .Values.prometheusOperator.prometheusInstanceNamespaces | join "," }} {{- end }} {{- if .Values.prometheusOperator.thanosImage.sha }} - - --thanos-default-base-image={{ .Values.prometheusOperator.thanosImage.repository }}:{{ .Values.prometheusOperator.thanosImage.tag }}@sha256:{{ .Values.prometheusOperator.thanosImage.sha }} + - --thanos-default-base-image={{ $registry }}/{{ .Values.prometheusOperator.thanosImage.repository }}:{{ .Values.prometheusOperator.thanosImage.tag }}@sha256:{{ .Values.prometheusOperator.thanosImage.sha }} {{- else }} - - --thanos-default-base-image={{ .Values.prometheusOperator.thanosImage.repository }}:{{ .Values.prometheusOperator.thanosImage.tag }} + - --thanos-default-base-image={{ $registry }}/{{ .Values.prometheusOperator.thanosImage.repository }}:{{ .Values.prometheusOperator.thanosImage.tag }} {{- end }} {{- if .Values.prometheusOperator.thanosRulerInstanceNamespaces }} - --thanos-ruler-instance-namespaces={{ .Values.prometheusOperator.thanosRulerInstanceNamespaces | join "," }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/networkpolicy.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/networkpolicy.yaml new file mode 100644 index 00000000..ebffa9c8 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/networkpolicy.yaml @@ -0,0 +1,26 @@ +{{- if .Values.prometheusOperator.networkPolicy.enabled }} +apiVersion: {{ template "kube-prometheus-stack.prometheus.networkPolicy.apiVersion" . }} +kind: NetworkPolicy +metadata: + name: {{ template "kube-prometheus-stack.fullname" . }}-operator + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }}-operator +spec: + egress: + - {} + ingress: + - ports: + {{- if .Values.prometheusOperator.tls.enabled }} + - port: {{ .Values.prometheusOperator.tls.internalPort }} + {{- else }} + - port: 8080 + {{- end }} + policyTypes: + - Egress + - Ingress + podSelector: + matchLabels: + app: {{ template "kube-prometheus-stack.name" . }}-operator + release: {{ $.Release.Name | quote }} +{{- 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 index b7bd952b..987b0ec6 100644 --- 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 @@ -7,6 +7,9 @@ metadata: labels: app: {{ template "kube-prometheus-stack.name" . }}-operator {{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- with .Values.prometheusOperator.serviceMonitor.additionalLabels }} +{{ toYaml . | indent 4 }} +{{- end }} spec: endpoints: {{- if .Values.prometheusOperator.tls.enabled }} 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 index 71915e80..82f8f647 100644 --- a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/prometheus.yaml +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/prometheus.yaml @@ -12,6 +12,7 @@ metadata: {{ toYaml .Values.prometheus.annotations | indent 4 }} {{- end }} spec: +{{- if or .Values.prometheus.prometheusSpec.alertingEndpoints .Values.alertmanager.enabled }} alerting: alertmanagers: {{- if .Values.prometheus.prometheusSpec.alertingEndpoints }} @@ -24,22 +25,22 @@ spec: pathPrefix: "{{ .Values.alertmanager.alertmanagerSpec.routePrefix }}" {{- end }} apiVersion: {{ .Values.alertmanager.apiVersion }} -{{- else }} - [] +{{- end }} {{- end }} {{- if .Values.prometheus.prometheusSpec.apiserverConfig }} apiserverConfig: {{ toYaml .Values.prometheus.prometheusSpec.apiserverConfig | indent 4}} {{- end }} {{- if .Values.prometheus.prometheusSpec.image }} + {{- $registry := .Values.global.imageRegistry | default .Values.prometheus.prometheusSpec.image.registry -}} {{- if and .Values.prometheus.prometheusSpec.image.tag .Values.prometheus.prometheusSpec.image.sha }} - image: "{{ .Values.prometheus.prometheusSpec.image.repository }}:{{ .Values.prometheus.prometheusSpec.image.tag }}@sha256:{{ .Values.prometheus.prometheusSpec.image.sha }}" + image: "{{ $registry }}/{{ .Values.prometheus.prometheusSpec.image.repository }}:{{ .Values.prometheus.prometheusSpec.image.tag }}@sha256:{{ .Values.prometheus.prometheusSpec.image.sha }}" {{- else if .Values.prometheus.prometheusSpec.image.sha }} - image: "{{ .Values.prometheus.prometheusSpec.image.repository }}@sha256:{{ .Values.prometheus.prometheusSpec.image.sha }}" + image: "{{ $registry }}/{{ .Values.prometheus.prometheusSpec.image.repository }}@sha256:{{ .Values.prometheus.prometheusSpec.image.sha }}" {{- else if .Values.prometheus.prometheusSpec.image.tag }} - image: "{{ .Values.prometheus.prometheusSpec.image.repository }}:{{ .Values.prometheus.prometheusSpec.image.tag }}" + image: "{{ $registry }}/{{ .Values.prometheus.prometheusSpec.image.repository }}:{{ .Values.prometheus.prometheusSpec.image.tag }}" {{- else }} - image: "{{ .Values.prometheus.prometheusSpec.image.repository }}" + image: "{{ $registry }}/{{ .Values.prometheus.prometheusSpec.image.repository }}" {{- end }} version: {{ .Values.prometheus.prometheusSpec.image.tag }} {{- if .Values.prometheus.prometheusSpec.image.sha }} @@ -387,4 +388,5 @@ spec: {{- if .Values.prometheus.prometheusSpec.minReadySeconds }} minReadySeconds: {{ .Values.prometheus.prometheusSpec.minReadySeconds }} {{- end }} + hostNetwork: {{ .Values.prometheus.prometheusSpec.hostNetwork }} {{- 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..f2fcc1ca --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/alertmanager.rules.yaml @@ -0,0 +1,215 @@ +{{- /* +Generated from 'alertmanager.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/alertmanager-prometheusRule.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: +{{- if not (.Values.defaultRules.disabled.AlertmanagerFailedReload | default false) }} + - alert: AlertmanagerFailedReload + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Configuration has failed to load for {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod{{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/alertmanager/alertmanagerfailedreload + summary: Reloading an Alertmanager configuration has failed. + 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(alertmanager_config_last_reload_successful{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m]) == 0 + for: 10m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.AlertmanagerMembersInconsistent | default false) }} + - alert: AlertmanagerMembersInconsistent + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Alertmanager {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod{{`}}`}} has only found {{`{{`}} $value {{`}}`}} members of the {{`{{`}}$labels.job{{`}}`}} cluster. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/alertmanager/alertmanagermembersinconsistent + summary: A member of an Alertmanager cluster has not found all other cluster members. + 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(alertmanager_cluster_members{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m]) + < on (namespace,service) group_left + count by (namespace,service) (max_over_time(alertmanager_cluster_members{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m])) + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.AlertmanagerFailedToSendAlerts | default false) }} + - alert: AlertmanagerFailedToSendAlerts + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Alertmanager {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod{{`}}`}} failed to send {{`{{`}} $value | humanizePercentage {{`}}`}} of notifications to {{`{{`}} $labels.integration {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/alertmanager/alertmanagerfailedtosendalerts + summary: An Alertmanager instance failed to send notifications. + expr: |- + ( + rate(alertmanager_notifications_failed_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m]) + / + rate(alertmanager_notifications_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m]) + ) + > 0.01 + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.AlertmanagerClusterFailedToSendAlerts | default false) }} + - alert: AlertmanagerClusterFailedToSendAlerts + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: The minimum notification failure rate to {{`{{`}} $labels.integration {{`}}`}} sent from any instance in the {{`{{`}}$labels.job{{`}}`}} cluster is {{`{{`}} $value | humanizePercentage {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/alertmanager/alertmanagerclusterfailedtosendalerts + summary: All Alertmanager instances in a cluster failed to send notifications to a critical integration. + expr: |- + min by (namespace,service, integration) ( + rate(alertmanager_notifications_failed_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration=~`.*`}[5m]) + / + rate(alertmanager_notifications_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration=~`.*`}[5m]) + ) + > 0.01 + for: 5m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.AlertmanagerClusterFailedToSendAlerts | default false) }} + - alert: AlertmanagerClusterFailedToSendAlerts + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: The minimum notification failure rate to {{`{{`}} $labels.integration {{`}}`}} sent from any instance in the {{`{{`}}$labels.job{{`}}`}} cluster is {{`{{`}} $value | humanizePercentage {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/alertmanager/alertmanagerclusterfailedtosendalerts + summary: All Alertmanager instances in a cluster failed to send notifications to a non-critical integration. + expr: |- + min by (namespace,service, integration) ( + rate(alertmanager_notifications_failed_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration!~`.*`}[5m]) + / + rate(alertmanager_notifications_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration!~`.*`}[5m]) + ) + > 0.01 + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.AlertmanagerConfigInconsistent | default false) }} + - alert: AlertmanagerConfigInconsistent + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Alertmanager instances within the {{`{{`}}$labels.job{{`}}`}} cluster have different configurations. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/alertmanager/alertmanagerconfiginconsistent + summary: Alertmanager instances within the same cluster have different configurations. + expr: |- + count by (namespace,service) ( + count_values by (namespace,service) ("config_hash", alertmanager_config_hash{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}) + ) + != 1 + for: 20m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.AlertmanagerClusterDown | default false) }} + - alert: AlertmanagerClusterDown + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: '{{`{{`}} $value | humanizePercentage {{`}}`}} of Alertmanager instances within the {{`{{`}}$labels.job{{`}}`}} cluster have been up for less than half of the last 5m.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/alertmanager/alertmanagerclusterdown + summary: Half or more of the Alertmanager instances within the same cluster are down. + expr: |- + ( + count by (namespace,service) ( + avg_over_time(up{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m]) < 0.5 + ) + / + count by (namespace,service) ( + up{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"} + ) + ) + >= 0.5 + for: 5m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.AlertmanagerClusterCrashlooping | default false) }} + - alert: AlertmanagerClusterCrashlooping + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: '{{`{{`}} $value | humanizePercentage {{`}}`}} of Alertmanager instances within the {{`{{`}}$labels.job{{`}}`}} cluster have restarted at least 5 times in the last 10m.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/alertmanager/alertmanagerclustercrashlooping + summary: Half or more of the Alertmanager instances within the same cluster are crashlooping. + expr: |- + ( + count by (namespace,service) ( + changes(process_start_time_seconds{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[10m]) > 4 + ) + / + count by (namespace,service) ( + up{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"} + ) + ) + >= 0.5 + for: 5m + 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/config-reloaders.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/config-reloaders.yaml new file mode 100644 index 00000000..37109eb0 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/config-reloaders.yaml @@ -0,0 +1,46 @@ +{{- /* +Generated from 'config-reloaders' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/prometheusOperator-prometheusRule.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" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.configReloaders }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "config-reloaders" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: config-reloaders + rules: +{{- if not (.Values.defaultRules.disabled.ConfigReloaderSidecarErrors | default false) }} + - alert: ConfigReloaderSidecarErrors + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 'Errors encountered while the {{`{{`}}$labels.pod{{`}}`}} config-reloader sidecar attempts to sync config in {{`{{`}}$labels.namespace{{`}}`}} namespace. + + As a result, configuration for service running in {{`{{`}}$labels.pod{{`}}`}} may be stale and cannot be updated anymore.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus-operator/configreloadersidecarerrors + summary: config-reloader sidecar has not had a successful reload for 10m + expr: max_over_time(reloader_last_reload_successful{namespace=~".+"}[5m]) == 0 + for: 10m + labels: + severity: warning +{{- 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/etcd.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/etcd.yaml new file mode 100644 index 00000000..a0af3582 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/etcd.yaml @@ -0,0 +1,294 @@ +{{- /* +Generated from 'etcd' group from https://raw.githubusercontent.com/etcd-io/etcd/main/contrib/mixin/mixin.libsonnet +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: +{{- if not (.Values.defaultRules.disabled.etcdMembersDown | default false) }} + - alert: etcdMembersDown + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": members are down ({{`{{`}} $value {{`}}`}}).' + summary: etcd cluster members are down. + expr: |- + max without (endpoint) ( + sum without (instance) (up{job=~".*etcd.*"} == bool 0) + or + count without (To) ( + sum without (instance) (rate(etcd_network_peer_sent_failures_total{job=~".*etcd.*"}[120s])) > 0.01 + ) + ) + > 0 + for: 10m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.etcdInsufficientMembers | default false) }} + - alert: etcdInsufficientMembers + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": insufficient members ({{`{{`}} $value {{`}}`}}).' + summary: etcd cluster has insufficient number of members. + expr: sum(up{job=~".*etcd.*"} == bool 1) without (instance) < ((count(up{job=~".*etcd.*"}) without (instance) + 1) / 2) + for: 3m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.etcdNoLeader | default false) }} + - alert: etcdNoLeader + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": member {{`{{`}} $labels.instance {{`}}`}} has no leader.' + summary: etcd cluster 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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.etcdHighNumberOfLeaderChanges | default false) }} + - alert: etcdHighNumberOfLeaderChanges + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: '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.' + summary: etcd cluster has high number of leader changes. + expr: increase((max without (instance) (etcd_server_leader_changes_seen_total{job=~".*etcd.*"}) or 0*absent(etcd_server_leader_changes_seen_total{job=~".*etcd.*"}))[15m:1m]) >= 4 + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.etcdHighNumberOfFailedGRPCRequests | default false) }} + - alert: etcdHighNumberOfFailedGRPCRequests + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": {{`{{`}} $value {{`}}`}}% of requests for {{`{{`}} $labels.grpc_method {{`}}`}} failed on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + summary: etcd cluster has high number of failed grpc requests. + expr: |- + 100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code) + / + sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code) + > 1 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.etcdHighNumberOfFailedGRPCRequests | default false) }} + - alert: etcdHighNumberOfFailedGRPCRequests + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": {{`{{`}} $value {{`}}`}}% of requests for {{`{{`}} $labels.grpc_method {{`}}`}} failed on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + summary: etcd cluster has high number of failed grpc requests. + expr: |- + 100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code) + / + sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code) + > 5 + for: 5m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.etcdGRPCRequestsSlow | default false) }} + - alert: etcdGRPCRequestsSlow + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": 99th percentile of gRPC requests is {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}} for {{`{{`}} $labels.grpc_method {{`}}`}} method.' + summary: etcd grpc requests are slow + expr: |- + histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_method!="Defragment", grpc_type="unary"}[5m])) without(grpc_type)) + > 0.15 + for: 10m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.etcdMemberCommunicationSlow | default false) }} + - alert: etcdMemberCommunicationSlow + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": member communication with {{`{{`}} $labels.To {{`}}`}} is taking {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + summary: etcd cluster member communication is slow. + 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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.etcdHighNumberOfFailedProposals | default false) }} + - alert: etcdHighNumberOfFailedProposals + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": {{`{{`}} $value {{`}}`}} proposal failures within the last 30 minutes on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + summary: etcd cluster has high number of proposal failures. + 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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.etcdHighFsyncDurations | default false) }} + - alert: etcdHighFsyncDurations + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": 99th percentile fsync durations are {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + summary: etcd cluster 99th percentile fsync durations are too high. + 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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.etcdHighFsyncDurations | default false) }} + - alert: etcdHighFsyncDurations + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": 99th percentile fsync durations are {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + summary: etcd cluster 99th percentile fsync durations are too high. + expr: |- + histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~".*etcd.*"}[5m])) + > 1 + for: 10m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.etcdHighCommitDurations | default false) }} + - alert: etcdHighCommitDurations + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": 99th percentile commit durations {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' + summary: etcd cluster 99th percentile commit durations are too high. + 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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.etcdDatabaseQuotaLowSpace | default false) }} + - alert: etcdDatabaseQuotaLowSpace + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": database size exceeds the defined quota on etcd instance {{`{{`}} $labels.instance {{`}}`}}, please defrag or increase the quota as the writes to etcd will be disabled when it is full.' + summary: etcd cluster database is running full. + expr: (last_over_time(etcd_mvcc_db_total_size_in_bytes[5m]) / last_over_time(etcd_server_quota_backend_bytes[5m]))*100 > 95 + for: 10m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.etcdExcessiveDatabaseGrowth | default false) }} + - alert: etcdExcessiveDatabaseGrowth + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": Predicting running out of disk space in the next four hours, based on write observations within the past four hours on etcd instance {{`{{`}} $labels.instance {{`}}`}}, please check as it might be disruptive.' + summary: etcd cluster database growing very fast. + expr: predict_linear(etcd_mvcc_db_total_size_in_bytes[4h], 4*60*60) > etcd_server_quota_backend_bytes + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.etcdDatabaseHighFragmentationRatio | default false) }} + - alert: etcdDatabaseHighFragmentationRatio + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": database size in use on instance {{`{{`}} $labels.instance {{`}}`}} is {{`{{`}} $value | humanizePercentage {{`}}`}} of the actual allocated disk space, please run defragmentation (e.g. etcdctl defrag) to retrieve the unused fragmented disk space.' + runbook_url: https://etcd.io/docs/v3.5/op-guide/maintenance/#defragmentation + summary: etcd database size in use is less than 50% of the actual allocated storage. + expr: (last_over_time(etcd_mvcc_db_total_size_in_use_in_bytes[5m]) / last_over_time(etcd_mvcc_db_total_size_in_bytes[5m])) < 0.5 + for: 10m + labels: + severity: warning +{{- 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/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..7ab648bc --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/general.rules.yaml @@ -0,0 +1,98 @@ +{{- /* +Generated from 'general.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubePrometheus-prometheusRule.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: +{{- if not (.Values.defaultRules.disabled.TargetDown | default false) }} + - alert: TargetDown + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: '{{`{{`}} printf "%.4g" $value {{`}}`}}% of the {{`{{`}} $labels.job {{`}}`}}/{{`{{`}} $labels.service {{`}}`}} targets in {{`{{`}} $labels.namespace {{`}}`}} namespace are down.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/general/targetdown + summary: One or more targets are unreachable. + 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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.Watchdog | default false) }} + - alert: Watchdog + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: '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. + + ' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/general/watchdog + summary: An alert that should always be firing to certify that Alertmanager is working properly. + expr: vector(1) + labels: + severity: none +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.InfoInhibitor | default false) }} + - alert: InfoInhibitor + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 'This is an alert that is used to inhibit info alerts. + + By themselves, the info-level alerts are sometimes very noisy, but they are relevant when combined with + + other alerts. + + This alert fires whenever there''s a severity="info" alert, and stops firing when another alert with a + + severity of ''warning'' or ''critical'' starts firing on the same namespace. + + This alert should be routed to a null receiver and configured to inhibit alerts with severity="info". + + ' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/general/infoinhibitor + summary: Info-level alert inhibition. + expr: ALERTS{severity = "info"} == 1 unless on(namespace) ALERTS{alertname != "InfoInhibitor", severity =~ "warning|critical", alertstate="firing"} == 1 + labels: + severity: none +{{- 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/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..b88b9b28 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.yaml @@ -0,0 +1,173 @@ +{{- /* +Generated from 'k8s.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetesControlPlane-prometheusRule.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 by (cluster, namespace, pod, container) ( + irate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}[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_irate + - 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: |- + kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"} * on (namespace, pod, cluster) + group_left() max by (namespace, pod, cluster) ( + (kube_pod_status_phase{phase=~"Pending|Running"} == 1) + ) + record: cluster:namespace:pod_memory:active:kube_pod_container_resource_requests + - expr: |- + sum by (namespace, cluster) ( + sum by (namespace, pod, cluster) ( + max by (namespace, pod, container, cluster) ( + kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"} + ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace_memory:kube_pod_container_resource_requests:sum + - expr: |- + kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"} * on (namespace, pod, cluster) + group_left() max by (namespace, pod, cluster) ( + (kube_pod_status_phase{phase=~"Pending|Running"} == 1) + ) + record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests + - expr: |- + sum by (namespace, cluster) ( + sum by (namespace, pod, cluster) ( + max by (namespace, pod, container, cluster) ( + kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"} + ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace_cpu:kube_pod_container_resource_requests:sum + - expr: |- + kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"} * on (namespace, pod, cluster) + group_left() max by (namespace, pod, cluster) ( + (kube_pod_status_phase{phase=~"Pending|Running"} == 1) + ) + record: cluster:namespace:pod_memory:active:kube_pod_container_resource_limits + - expr: |- + sum by (namespace, cluster) ( + sum by (namespace, pod, cluster) ( + max by (namespace, pod, container, cluster) ( + kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"} + ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace_memory:kube_pod_container_resource_limits:sum + - expr: |- + kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"} * on (namespace, pod, cluster) + group_left() max by (namespace, pod, cluster) ( + (kube_pod_status_phase{phase=~"Pending|Running"} == 1) + ) + record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits + - expr: |- + sum by (namespace, cluster) ( + sum by (namespace, pod, cluster) ( + max by (namespace, pod, container, cluster) ( + kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"} + ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace_cpu:kube_pod_container_resource_limits: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 + - expr: |- + max by (cluster, namespace, workload, pod) ( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="Job"}, + "workload", "$1", "owner_name", "(.*)" + ) + ) + labels: + workload_type: job + 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..bae96b90 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-availability.rules.yaml @@ -0,0 +1,136 @@ +{{- /* +Generated from 'kube-apiserver-availability.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetesControlPlane-prometheusRule.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: avg_over_time(code_verb:apiserver_request_total:increase1h[30d]) * 24 * 30 + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~"LIST|GET"}) + labels: + verb: read + record: code:apiserver_request_total:increase30d + - expr: sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~"POST|PUT|PATCH|DELETE"}) + labels: + verb: write + record: code:apiserver_request_total:increase30d + - expr: sum by (cluster, verb, scope) (increase(apiserver_request_slo_duration_seconds_count[1h])) + record: cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase1h + - expr: sum by (cluster, verb, scope) (avg_over_time(cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase1h[30d]) * 24 * 30) + record: cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d + - expr: sum by (cluster, verb, scope, le) (increase(apiserver_request_slo_duration_seconds_bucket[1h])) + record: cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase1h + - expr: sum by (cluster, verb, scope, le) (avg_over_time(cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase1h[30d]) * 24 * 30) + record: cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d + - expr: |- + 1 - ( + ( + # write too slow + sum by (cluster) (cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d{verb=~"POST|PUT|PATCH|DELETE"}) + - + sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le="1"}) + ) + + ( + # read too slow + sum by (cluster) (cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d{verb=~"LIST|GET"}) + - + ( + ( + sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le="1"}) + or + vector(0) + ) + + + sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le="5"}) + + + sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le="30"}) + ) + ) + + # errors + sum by (cluster) (code:apiserver_request_total:increase30d{code=~"5.."} or vector(0)) + ) + / + sum by (cluster) (code:apiserver_request_total:increase30d) + labels: + verb: all + record: apiserver_request:availability30d + - expr: |- + 1 - ( + sum by (cluster) (cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d{verb=~"LIST|GET"}) + - + ( + # too slow + ( + sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le="1"}) + or + vector(0) + ) + + + sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le="5"}) + + + sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le="30"}) + ) + + + # errors + sum by (cluster) (code:apiserver_request_total:increase30d{verb="read",code=~"5.."} or vector(0)) + ) + / + sum by (cluster) (code:apiserver_request_total:increase30d{verb="read"}) + labels: + verb: read + record: apiserver_request:availability30d + - expr: |- + 1 - ( + ( + # too slow + sum by (cluster) (cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d{verb=~"POST|PUT|PATCH|DELETE"}) + - + sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le="1"}) + ) + + + # errors + sum by (cluster) (code:apiserver_request_total:increase30d{verb="write",code=~"5.."} or vector(0)) + ) + / + sum by (cluster) (code:apiserver_request_total:increase30d{verb="write"}) + labels: + verb: write + record: apiserver_request:availability30d + - expr: sum by (cluster,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 (cluster,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: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"2.."}[1h])) + record: code_verb:apiserver_request_total:increase1h + - expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"3.."}[1h])) + record: code_verb:apiserver_request_total:increase1h + - expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"4.."}[1h])) + record: code_verb:apiserver_request_total:increase1h + - expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"5.."}[1h])) + record: code_verb:apiserver_request_total:increase1h +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-burnrate.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-burnrate.rules.yaml new file mode 100644 index 00000000..6774fc35 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-burnrate.rules.yaml @@ -0,0 +1,328 @@ +{{- /* +Generated from 'kube-apiserver-burnrate.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetesControlPlane-prometheusRule.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.kubeApiserverBurnrate }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kube-apiserver-burnrate.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-burnrate.rules + rules: + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[1d])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[1d])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[1d])) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[1d])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1d])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1d])) + labels: + verb: read + record: apiserver_request:burnrate1d + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[1h])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[1h])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[1h])) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[1h])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1h])) + labels: + verb: read + record: apiserver_request:burnrate1h + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[2h])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[2h])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[2h])) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[2h])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[2h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[2h])) + labels: + verb: read + record: apiserver_request:burnrate2h + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[30m])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[30m])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[30m])) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[30m])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[30m])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[30m])) + labels: + verb: read + record: apiserver_request:burnrate30m + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[3d])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[3d])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[3d])) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[3d])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[3d])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[3d])) + labels: + verb: read + record: apiserver_request:burnrate3d + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[5m])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[5m])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[5m])) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[5m])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[5m])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m])) + labels: + verb: read + record: apiserver_request:burnrate5m + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[6h])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[6h])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[6h])) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[6h])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[6h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[6h])) + labels: + verb: read + record: apiserver_request:burnrate6h + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[1d])) + - + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[1d])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1d])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d])) + labels: + verb: write + record: apiserver_request:burnrate1d + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[1h])) + - + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[1h])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h])) + labels: + verb: write + record: apiserver_request:burnrate1h + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[2h])) + - + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[2h])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[2h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h])) + labels: + verb: write + record: apiserver_request:burnrate2h + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[30m])) + - + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[30m])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[30m])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m])) + labels: + verb: write + record: apiserver_request:burnrate30m + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[3d])) + - + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[3d])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[3d])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d])) + labels: + verb: write + record: apiserver_request:burnrate3d + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[5m])) + - + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[5m])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[5m])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m])) + labels: + verb: write + record: apiserver_request:burnrate5m + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[6h])) + - + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[6h])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[6h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h])) + labels: + verb: write + record: apiserver_request:burnrate6h +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-histogram.rules.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-histogram.rules.yaml new file mode 100644 index 00000000..762bcc6d --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-histogram.rules.yaml @@ -0,0 +1,37 @@ +{{- /* +Generated from 'kube-apiserver-histogram.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetesControlPlane-prometheusRule.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.kubeApiserverHistogram }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kube-apiserver-histogram.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-histogram.rules + rules: + - expr: histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[5m]))) > 0 + labels: + quantile: '0.99' + verb: read + record: cluster_quantile:apiserver_request_slo_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[5m]))) > 0 + labels: + quantile: '0.99' + verb: write + record: cluster_quantile:apiserver_request_slo_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-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..867fe20d --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-slos.yaml @@ -0,0 +1,115 @@ +{{- /* +Generated from 'kube-apiserver-slos' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetesControlPlane-prometheusRule.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: +{{- if not (.Values.defaultRules.disabled.KubeAPIErrorBudgetBurn | default false) }} + - alert: KubeAPIErrorBudgetBurn + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: The API server is burning too much error budget. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeAPIErrorBudgetBurn | default false) }} + - alert: KubeAPIErrorBudgetBurn + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: The API server is burning too much error budget. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeAPIErrorBudgetBurn | default false) }} + - alert: KubeAPIErrorBudgetBurn + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: The API server is burning too much error budget. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeAPIErrorBudgetBurn | default false) }} + - alert: KubeAPIErrorBudgetBurn + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: The API server is burning too much error budget. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- 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..78a3db1c --- /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/main/manifests/kubePrometheus-prometheusRule.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..0cd0ba5b --- /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/main/manifests/kubePrometheus-prometheusRule.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:sum_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..355575d8 --- /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/main/manifests/kubernetesControlPlane-prometheusRule.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.kubeSchedulerRecording }} +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..7547436a --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-state-metrics.yaml @@ -0,0 +1,107 @@ +{{- /* +Generated from 'kube-state-metrics' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubeStateMetrics-prometheusRule.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: +{{- if not (.Values.defaultRules.disabled.KubeStateMetricsListErrors | default false) }} + - alert: KubeStateMetricsListErrors + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + 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 }}/kube-state-metrics/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeStateMetricsWatchErrors | default false) }} + - alert: KubeStateMetricsWatchErrors + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + 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 }}/kube-state-metrics/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 }} +{{- if not (.Values.defaultRules.disabled.KubeStateMetricsShardingMismatch | default false) }} + - alert: KubeStateMetricsShardingMismatch + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: kube-state-metrics pods are running with different --total-shards configuration, some Kubernetes objects may be exposed multiple times or not exposed at all. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kube-state-metrics/kubestatemetricsshardingmismatch + summary: kube-state-metrics sharding is misconfigured. + expr: stdvar (kube_state_metrics_total_shards{job="kube-state-metrics"}) != 0 + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeStateMetricsShardsMissing | default false) }} + - alert: KubeStateMetricsShardsMissing + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: kube-state-metrics shards are missing, some Kubernetes objects are not being exposed. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kube-state-metrics/kubestatemetricsshardsmissing + summary: kube-state-metrics shards are missing. + expr: |- + 2^max(kube_state_metrics_total_shards{job="kube-state-metrics"}) - 1 + - + sum( 2 ^ max by (shard_ordinal) (kube_state_metrics_shard_ordinal{job="kube-state-metrics"}) ) + != 0 + 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/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..9176cd02 --- /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/main/manifests/kubernetesControlPlane-prometheusRule.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 (cluster, instance, le) * on(cluster, 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 (cluster, instance, le) * on(cluster, 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 (cluster, instance, le) * on(cluster, 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..78ce26f9 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-apps.yaml @@ -0,0 +1,375 @@ +{{- /* +Generated from 'kubernetes-apps' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetesControlPlane-prometheusRule.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: +{{- if not (.Values.defaultRules.disabled.KubePodCrashLooping | default false) }} + - alert: KubePodCrashLooping + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 'Pod {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} ({{`{{`}} $labels.container {{`}}`}}) is in waiting state (reason: "CrashLoopBackOff").' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubepodcrashlooping + summary: Pod is crash looping. + expr: max_over_time(kube_pod_container_status_waiting_reason{reason="CrashLoopBackOff", job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}[5m]) >= 1 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubePodNotReady | default false) }} + - alert: KubePodNotReady + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Pod {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} has been in a non-ready state for longer than 15 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubepodnotready + summary: Pod has been in a non-ready state for more than 15 minutes. + expr: |- + sum by (namespace, pod, cluster) ( + max by(namespace, pod, cluster) ( + kube_pod_status_phase{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}", phase=~"Pending|Unknown|Failed"} + ) * on(namespace, pod, cluster) group_left(owner_kind) topk by(namespace, pod, cluster) ( + 1, max by(namespace, pod, owner_kind, cluster) (kube_pod_owner{owner_kind!="Job"}) + ) + ) > 0 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeDeploymentGenerationMismatch | default false) }} + - alert: KubeDeploymentGenerationMismatch + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + 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 }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeDeploymentReplicasMismatch | default false) }} + - alert: KubeDeploymentReplicasMismatch + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Deployment {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.deployment {{`}}`}} has not matched the expected number of replicas for longer than 15 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }}"}[10m]) + == + 0 + ) + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeStatefulSetReplicasMismatch | default false) }} + - alert: KubeStatefulSetReplicasMismatch + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: StatefulSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.statefulset {{`}}`}} has not matched the expected number of replicas for longer than 15 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }}"}[10m]) + == + 0 + ) + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeStatefulSetGenerationMismatch | default false) }} + - alert: KubeStatefulSetGenerationMismatch + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + 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 }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeStatefulSetUpdateNotRolledOut | default false) }} + - alert: KubeStatefulSetUpdateNotRolledOut + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: StatefulSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.statefulset {{`}}`}} update has not been rolled out. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeDaemonSetRolloutStuck | default false) }} + - alert: KubeDaemonSetRolloutStuck + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} has not finished or progressed for at least 15 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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_status_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_status_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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeContainerWaiting | default false) }} + - alert: KubeContainerWaiting + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: pod/{{`{{`}} $labels.pod {{`}}`}} in namespace {{`{{`}} $labels.namespace {{`}}`}} on container {{`{{`}} $labels.container{{`}}`}} has been in waiting state for longer than 1 hour. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubecontainerwaiting + summary: Pod container waiting longer than 1 hour + expr: sum by (namespace, pod, container, cluster) (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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeDaemonSetNotScheduled | default false) }} + - alert: KubeDaemonSetNotScheduled + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: '{{`{{`}} $value {{`}}`}} Pods of DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} are not scheduled.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeDaemonSetMisScheduled | default false) }} + - alert: KubeDaemonSetMisScheduled + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: '{{`{{`}} $value {{`}}`}} Pods of DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} are running where they are not supposed to run.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeJobNotCompleted | default false) }} + - alert: KubeJobNotCompleted + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Job {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.job_name {{`}}`}} is taking more than {{`{{`}} "43200" | humanizeDuration {{`}}`}} to complete. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubejobnotcompleted + summary: Job did not complete in time + expr: |- + time() - max by(namespace, job_name, cluster) (kube_job_status_start_time{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + and + kube_job_status_active{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} > 0) > 43200 + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeJobFailed | default false) }} + - alert: KubeJobFailed + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Job {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.job_name {{`}}`}} failed to complete. Removing failed job after investigation should clear this alert. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeHpaReplicasMismatch | default false) }} + - alert: KubeHpaReplicasMismatch + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: HPA {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.horizontalpodautoscaler {{`}}`}} has not matched the desired number of replicas for longer than 15 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubehpareplicasmismatch + summary: HPA has not matched desired number of replicas. + expr: |- + (kube_horizontalpodautoscaler_status_desired_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + != + kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}) + and + (kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + > + kube_horizontalpodautoscaler_spec_min_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}) + and + (kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + < + kube_horizontalpodautoscaler_spec_max_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}) + and + changes(kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}[15m]) == 0 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeHpaMaxedOut | default false) }} + - alert: KubeHpaMaxedOut + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: HPA {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.horizontalpodautoscaler {{`}}`}} has been running at max replicas for longer than 15 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubehpamaxedout + summary: HPA is running at max replicas + expr: |- + kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} + == + kube_horizontalpodautoscaler_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 }} +{{- 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..5fab8d7a --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-resources.yaml @@ -0,0 +1,193 @@ +{{- /* +Generated from 'kubernetes-resources' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetesControlPlane-prometheusRule.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: +{{- if not (.Values.defaultRules.disabled.KubeCPUOvercommit | default false) }} + - alert: KubeCPUOvercommit + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Cluster has overcommitted CPU resource requests for Pods by {{`{{`}} $value {{`}}`}} CPU shares and cannot tolerate node failure. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubecpuovercommit + summary: Cluster has overcommitted CPU resource requests. + expr: |- + sum(namespace_cpu:kube_pod_container_resource_requests:sum{}) - (sum(kube_node_status_allocatable{resource="cpu"}) - max(kube_node_status_allocatable{resource="cpu"})) > 0 + and + (sum(kube_node_status_allocatable{resource="cpu"}) - max(kube_node_status_allocatable{resource="cpu"})) > 0 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeMemoryOvercommit | default false) }} + - alert: KubeMemoryOvercommit + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Cluster has overcommitted memory resource requests for Pods by {{`{{`}} $value | humanize {{`}}`}} bytes and cannot tolerate node failure. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubememoryovercommit + summary: Cluster has overcommitted memory resource requests. + expr: |- + sum(namespace_memory:kube_pod_container_resource_requests:sum{}) - (sum(kube_node_status_allocatable{resource="memory"}) - max(kube_node_status_allocatable{resource="memory"})) > 0 + and + (sum(kube_node_status_allocatable{resource="memory"}) - max(kube_node_status_allocatable{resource="memory"})) > 0 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeCPUQuotaOvercommit | default false) }} + - alert: KubeCPUQuotaOvercommit + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Cluster has overcommitted CPU resource requests for Namespaces. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubecpuquotaovercommit + summary: Cluster has overcommitted CPU resource requests. + expr: |- + sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(cpu|requests.cpu)"})) + / + sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"}) + > 1.5 + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeMemoryQuotaOvercommit | default false) }} + - alert: KubeMemoryQuotaOvercommit + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Cluster has overcommitted memory resource requests for Namespaces. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubememoryquotaovercommit + summary: Cluster has overcommitted memory resource requests. + expr: |- + sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(memory|requests.memory)"})) + / + sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) + > 1.5 + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeQuotaAlmostFull | default false) }} + - alert: KubeQuotaAlmostFull + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeQuotaFullyUsed | default false) }} + - alert: KubeQuotaFullyUsed + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeQuotaExceeded | default false) }} + - alert: KubeQuotaExceeded + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.CPUThrottlingHigh | default false) }} + - alert: CPUThrottlingHigh + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: '{{`{{`}} $value | humanizePercentage {{`}}`}} throttling of CPU in namespace {{`{{`}} $labels.namespace {{`}}`}} for container {{`{{`}} $labels.container {{`}}`}} in pod {{`{{`}} $labels.pod {{`}}`}}.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- 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..fd193398 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-storage.yaml @@ -0,0 +1,161 @@ +{{- /* +Generated from 'kubernetes-storage' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetesControlPlane-prometheusRule.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: +{{- if not (.Values.defaultRules.disabled.KubePersistentVolumeFillingUp | default false) }} + - alert: KubePersistentVolumeFillingUp + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: The PersistentVolume claimed by {{`{{`}} $labels.persistentvolumeclaim {{`}}`}} in Namespace {{`{{`}} $labels.namespace {{`}}`}} is only {{`{{`}} $value | humanizePercentage {{`}}`}} free. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 + and + kubelet_volume_stats_used_bytes{job="kubelet", namespace=~"{{ $targetNamespace }}", metrics_path="/metrics"} > 0 + unless on(namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1 + unless on(namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1 + for: 1m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubePersistentVolumeFillingUp | default false) }} + - alert: KubePersistentVolumeFillingUp + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + 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 }}/kubernetes/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 + kubelet_volume_stats_used_bytes{job="kubelet", namespace=~"{{ $targetNamespace }}", metrics_path="/metrics"} > 0 + and + predict_linear(kubelet_volume_stats_available_bytes{job="kubelet", namespace=~"{{ $targetNamespace }}", metrics_path="/metrics"}[6h], 4 * 24 * 3600) < 0 + unless on(namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1 + unless on(namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1 + for: 1h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubePersistentVolumeInodesFillingUp | default false) }} + - alert: KubePersistentVolumeInodesFillingUp + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: The PersistentVolume claimed by {{`{{`}} $labels.persistentvolumeclaim {{`}}`}} in Namespace {{`{{`}} $labels.namespace {{`}}`}} only has {{`{{`}} $value | humanizePercentage {{`}}`}} free inodes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubepersistentvolumeinodesfillingup + summary: PersistentVolumeInodes are filling up. + expr: |- + ( + kubelet_volume_stats_inodes_free{job="kubelet", namespace=~"{{ $targetNamespace }}", metrics_path="/metrics"} + / + kubelet_volume_stats_inodes{job="kubelet", namespace=~"{{ $targetNamespace }}", metrics_path="/metrics"} + ) < 0.03 + and + kubelet_volume_stats_inodes_used{job="kubelet", namespace=~"{{ $targetNamespace }}", metrics_path="/metrics"} > 0 + unless on(namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1 + unless on(namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1 + for: 1m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubePersistentVolumeInodesFillingUp | default false) }} + - alert: KubePersistentVolumeInodesFillingUp + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Based on recent sampling, the PersistentVolume claimed by {{`{{`}} $labels.persistentvolumeclaim {{`}}`}} in Namespace {{`{{`}} $labels.namespace {{`}}`}} is expected to run out of inodes within four days. Currently {{`{{`}} $value | humanizePercentage {{`}}`}} of its inodes are free. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubepersistentvolumeinodesfillingup + summary: PersistentVolumeInodes are filling up. + expr: |- + ( + kubelet_volume_stats_inodes_free{job="kubelet", namespace=~"{{ $targetNamespace }}", metrics_path="/metrics"} + / + kubelet_volume_stats_inodes{job="kubelet", namespace=~"{{ $targetNamespace }}", metrics_path="/metrics"} + ) < 0.15 + and + kubelet_volume_stats_inodes_used{job="kubelet", namespace=~"{{ $targetNamespace }}", metrics_path="/metrics"} > 0 + and + predict_linear(kubelet_volume_stats_inodes_free{job="kubelet", namespace=~"{{ $targetNamespace }}", metrics_path="/metrics"}[6h], 4 * 24 * 3600) < 0 + unless on(namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1 + unless on(namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1 + for: 1h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubePersistentVolumeErrors | default false) }} + - alert: KubePersistentVolumeErrors + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: The persistent volume {{`{{`}} $labels.persistentvolume {{`}}`}} has status {{`{{`}} $labels.phase {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- 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..fcb5298e --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-apiserver.yaml @@ -0,0 +1,130 @@ +{{- /* +Generated from 'kubernetes-system-apiserver' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetesControlPlane-prometheusRule.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: +{{- if not (.Values.defaultRules.disabled.KubeClientCertificateExpiration | default false) }} + - alert: KubeClientCertificateExpiration + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: A client certificate used to authenticate to kubernetes apiserver is expiring in less than 7.0 days. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeClientCertificateExpiration | default false) }} + - alert: KubeClientCertificateExpiration + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: A client certificate used to authenticate to kubernetes apiserver is expiring in less than 24.0 hours. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 + for: 5m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeAggregatedAPIErrors | default false) }} + - alert: KubeAggregatedAPIErrors + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Kubernetes aggregated API {{`{{`}} $labels.name {{`}}`}}/{{`{{`}} $labels.namespace {{`}}`}} has reported errors. It has appeared unavailable {{`{{`}} $value | humanize {{`}}`}} times averaged over the past 10m. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubeaggregatedapierrors + summary: Kubernetes aggregated API has reported errors. + expr: sum by(name, namespace, cluster)(increase(aggregator_unavailable_apiservice_total[10m])) > 4 + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeAggregatedAPIDown | default false) }} + - alert: KubeAggregatedAPIDown + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Kubernetes aggregated API {{`{{`}} $labels.name {{`}}`}}/{{`{{`}} $labels.namespace {{`}}`}} has been only {{`{{`}} $value | humanize {{`}}`}}% available over the last 10m. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubeaggregatedapidown + summary: Kubernetes aggregated API is down. + expr: (1 - max by(name, namespace, cluster)(avg_over_time(aggregator_unavailable_apiservice[10m]))) * 100 < 85 + for: 5m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if .Values.kubeApiServer.enabled }} +{{- if not (.Values.defaultRules.disabled.KubeAPIDown | default false) }} + - alert: KubeAPIDown + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: KubeAPI has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- if not (.Values.defaultRules.disabled.KubeAPITerminatedRequests | default false) }} + - alert: KubeAPITerminatedRequests + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: The kubernetes apiserver has terminated {{`{{`}} $value | humanizePercentage {{`}}`}} of its incoming requests. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubeapiterminatedrequests + summary: The kubernetes apiserver has terminated {{`{{`}} $value | humanizePercentage {{`}}`}} of its incoming requests. + expr: sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m])) / ( sum(rate(apiserver_request_total{job="apiserver"}[10m])) + sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m])) ) > 0.20 + for: 5m + labels: + severity: warning +{{- 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-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..c423fb81 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-controller-manager.yaml @@ -0,0 +1,46 @@ +{{- /* +Generated from 'kubernetes-system-controller-manager' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetesControlPlane-prometheusRule.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 .Values.defaultRules.rules.kubeControllerManager }} +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 }} +{{- if not (.Values.defaultRules.disabled.KubeControllerManagerDown | default false) }} + - alert: KubeControllerManagerDown + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: KubeControllerManager has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-kube-proxy.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-kube-proxy.yaml new file mode 100644 index 00000000..8082fdc0 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-kube-proxy.yaml @@ -0,0 +1,44 @@ +{{- /* +Generated from 'kubernetes-system-kube-proxy' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetesControlPlane-prometheusRule.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.kubeProxy.enabled .Values.defaultRules.rules.kubeProxy }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubernetes-system-kube-proxy" | 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-kube-proxy + rules: +{{- if not (.Values.defaultRules.disabled.KubeProxyDown | default false) }} + - alert: KubeProxyDown + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: KubeProxy has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubeproxydown + summary: Target disappeared from Prometheus target discovery. + expr: absent(up{job="kube-proxy"} == 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-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..fe558cf2 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-kubelet.yaml @@ -0,0 +1,253 @@ +{{- /* +Generated from 'kubernetes-system-kubelet' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetesControlPlane-prometheusRule.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: +{{- if not (.Values.defaultRules.disabled.KubeNodeNotReady | default false) }} + - alert: KubeNodeNotReady + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: '{{`{{`}} $labels.node {{`}}`}} has been unready for more than 15 minutes.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeNodeUnreachable | default false) }} + - alert: KubeNodeUnreachable + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: '{{`{{`}} $labels.node {{`}}`}} is unreachable and some workloads may be rescheduled.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeletTooManyPods | default false) }} + - alert: KubeletTooManyPods + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Kubelet '{{`{{`}} $labels.node {{`}}`}}' is running at {{`{{`}} $value | humanizePercentage {{`}}`}} of its Pod capacity. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubelettoomanypods + summary: Kubelet is running at capacity. + expr: |- + count by(cluster, 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(cluster, node) ( + kube_node_status_capacity{job="kube-state-metrics",resource="pods"} != 1 + ) > 0.95 + for: 15m + labels: + severity: info +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeNodeReadinessFlapping | default false) }} + - alert: KubeNodeReadinessFlapping + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: The readiness status of node {{`{{`}} $labels.node {{`}}`}} has changed {{`{{`}} $value {{`}}`}} times in the last 15 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubenodereadinessflapping + summary: Node readiness status is flapping. + expr: sum(changes(kube_node_status_condition{status="true",condition="Ready"}[15m])) by (cluster, node) > 2 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeletPlegDurationHigh | default false) }} + - alert: KubeletPlegDurationHigh + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{`{{`}} $value {{`}}`}} seconds on node {{`{{`}} $labels.node {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeletPodStartUpLatencyHigh | default false) }} + - alert: KubeletPodStartUpLatencyHigh + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Kubelet Pod startup 99th percentile latency is {{`{{`}} $value {{`}}`}} seconds on node {{`{{`}} $labels.node {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 (cluster, instance, le)) * on(cluster, 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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeletClientCertificateExpiration | default false) }} + - alert: KubeletClientCertificateExpiration + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Client certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeletClientCertificateExpiration | default false) }} + - alert: KubeletClientCertificateExpiration + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Client certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeletServerCertificateExpiration | default false) }} + - alert: KubeletServerCertificateExpiration + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Server certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeletServerCertificateExpiration | default false) }} + - alert: KubeletServerCertificateExpiration + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Server certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeletClientCertificateRenewalErrors | default false) }} + - alert: KubeletClientCertificateRenewalErrors + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + 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 }}/kubernetes/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeletServerCertificateRenewalErrors | default false) }} + - alert: KubeletServerCertificateRenewalErrors + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + 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 }}/kubernetes/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 }} +{{- end }} +{{- if .Values.prometheusOperator.kubeletService.enabled }} +{{- if not (.Values.defaultRules.disabled.KubeletDown | default false) }} + - alert: KubeletDown + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Kubelet has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- 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..19c974dd --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-scheduler.yaml @@ -0,0 +1,46 @@ +{{- /* +Generated from 'kubernetes-system-scheduler' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetesControlPlane-prometheusRule.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.kubeSchedulerAlerting }} +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 }} +{{- if not (.Values.defaultRules.disabled.KubeSchedulerDown | default false) }} + - alert: KubeSchedulerDown + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: KubeScheduler has disappeared from Prometheus target discovery. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/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 }} +{{- 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..32605926 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system.yaml @@ -0,0 +1,65 @@ +{{- /* +Generated from 'kubernetes-system' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetesControlPlane-prometheusRule.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: +{{- if not (.Values.defaultRules.disabled.KubeVersionMismatch | default false) }} + - alert: KubeVersionMismatch + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: There are {{`{{`}} $value {{`}}`}} different semantic versions of Kubernetes components running. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubeversionmismatch + summary: Different semantic versions of Kubernetes components running. + expr: count by (cluster) (count by (git_version, cluster) (label_replace(kubernetes_build_info{job!~"kube-dns|coredns"},"git_version","$1","git_version","(v[0-9]*.[0-9]*).*"))) > 1 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.KubeClientErrors | default false) }} + - alert: KubeClientErrors + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Kubernetes API server client '{{`{{`}} $labels.job {{`}}`}}/{{`{{`}} $labels.instance {{`}}`}}' is experiencing {{`{{`}} $value | humanizePercentage {{`}}`}} errors.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubeclienterrors + summary: Kubernetes API server client is experiencing errors. + expr: |- + (sum(rate(rest_client_requests_total{code=~"5.."}[5m])) by (cluster, instance, job, namespace) + / + sum(rate(rest_client_requests_total[5m])) by (cluster, instance, job, namespace)) + > 0.01 + for: 15m + labels: + severity: warning +{{- 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/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..c3cfe36c --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.rules.yaml @@ -0,0 +1,89 @@ +{{- /* +Generated from 'node-exporter.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/nodeExporter-prometheusRule.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.nodeExporterRecording }} +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, mode) ( + node_cpu_seconds_total{job="node-exporter",mode="idle"} + ) + record: instance:node_num_cpu:sum + - expr: |- + 1 - avg without (cpu) ( + sum without (mode) (rate(node_cpu_seconds_total{job="node-exporter", mode=~"idle|iowait|steal"}[5m])) + ) + record: instance:node_cpu_utilisation:rate5m + - 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"} + 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"} + ) + ) + / + node_memory_MemTotal_bytes{job="node-exporter"} + ) + record: instance:node_memory_utilisation:ratio + - expr: rate(node_vmstat_pgmajfault{job="node-exporter"}[5m]) + record: instance:node_vmstat_pgmajfault:rate5m + - expr: rate(node_disk_io_time_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)"}[5m]) + record: instance_device:node_disk_io_time_seconds:rate5m + - expr: rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)"}[5m]) + record: instance_device:node_disk_io_time_weighted_seconds:rate5m + - expr: |- + sum without (device) ( + rate(node_network_receive_bytes_total{job="node-exporter", device!="lo"}[5m]) + ) + record: instance:node_network_receive_bytes_excluding_lo:rate5m + - expr: |- + sum without (device) ( + rate(node_network_transmit_bytes_total{job="node-exporter", device!="lo"}[5m]) + ) + record: instance:node_network_transmit_bytes_excluding_lo:rate5m + - expr: |- + sum without (device) ( + rate(node_network_receive_drop_total{job="node-exporter", device!="lo"}[5m]) + ) + record: instance:node_network_receive_drop_excluding_lo:rate5m + - expr: |- + sum without (device) ( + rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[5m]) + ) + record: instance:node_network_transmit_drop_excluding_lo:rate5m +{{- 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..2fa7e28d --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.yaml @@ -0,0 +1,398 @@ +{{- /* +Generated from 'node-exporter' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/nodeExporter-prometheusRule.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.nodeExporterAlerting }} +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: +{{- if not (.Values.defaultRules.disabled.NodeFilesystemSpaceFillingUp | default false) }} + - alert: NodeFilesystemSpaceFillingUp + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + 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 }}/node/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 < 15 + 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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.NodeFilesystemSpaceFillingUp | default false) }} + - alert: NodeFilesystemSpaceFillingUp + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + 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 }}/node/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 < 10 + 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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.NodeFilesystemAlmostOutOfSpace | default false) }} + - alert: NodeFilesystemAlmostOutOfSpace + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/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: 30m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.NodeFilesystemAlmostOutOfSpace | default false) }} + - alert: NodeFilesystemAlmostOutOfSpace + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/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: 30m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.NodeFilesystemFilesFillingUp | default false) }} + - alert: NodeFilesystemFilesFillingUp + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + 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 }}/node/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.NodeFilesystemFilesFillingUp | default false) }} + - alert: NodeFilesystemFilesFillingUp + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + 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 }}/node/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.NodeFilesystemAlmostOutOfFiles | default false) }} + - alert: NodeFilesystemAlmostOutOfFiles + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.NodeFilesystemAlmostOutOfFiles | default false) }} + - alert: NodeFilesystemAlmostOutOfFiles + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.NodeNetworkReceiveErrs | default false) }} + - alert: NodeNetworkReceiveErrs + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: '{{`{{`}} $labels.instance {{`}}`}} interface {{`{{`}} $labels.device {{`}}`}} has encountered {{`{{`}} printf "%.0f" $value {{`}}`}} receive errors in the last two minutes.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.NodeNetworkTransmitErrs | default false) }} + - alert: NodeNetworkTransmitErrs + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: '{{`{{`}} $labels.instance {{`}}`}} interface {{`{{`}} $labels.device {{`}}`}} has encountered {{`{{`}} printf "%.0f" $value {{`}}`}} transmit errors in the last two minutes.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.NodeHighNumberConntrackEntriesUsed | default false) }} + - alert: NodeHighNumberConntrackEntriesUsed + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: '{{`{{`}} $value | humanizePercentage {{`}}`}} of conntrack entries are used.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.NodeTextFileCollectorScrapeError | default false) }} + - alert: NodeTextFileCollectorScrapeError + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Node Exporter text file collector failed to scrape. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.NodeClockSkewDetected | default false) }} + - alert: NodeClockSkewDetected + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: 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 }}/node/nodeclockskewdetected + summary: Clock skew detected. + expr: |- + ( + node_timex_offset_seconds{job="node-exporter"} > 0.05 + and + deriv(node_timex_offset_seconds{job="node-exporter"}[5m]) >= 0 + ) + or + ( + node_timex_offset_seconds{job="node-exporter"} < -0.05 + and + deriv(node_timex_offset_seconds{job="node-exporter"}[5m]) <= 0 + ) + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.NodeClockNotSynchronising | default false) }} + - alert: NodeClockNotSynchronising + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Clock on {{`{{`}} $labels.instance {{`}}`}} is not synchronising. Ensure NTP is configured on this host. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/nodeclocknotsynchronising + summary: Clock not synchronising. + expr: |- + min_over_time(node_timex_sync_status{job="node-exporter"}[5m]) == 0 + and + node_timex_maxerror_seconds{job="node-exporter"} >= 16 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.NodeRAIDDegraded | default false) }} + - alert: NodeRAIDDegraded + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + 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 }}/node/noderaiddegraded + summary: RAID Array is degraded + expr: node_md_disks_required{job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)"} - ignoring (state) (node_md_disks{state="active",job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)"}) > 0 + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.NodeRAIDDiskFailure | default false) }} + - alert: NodeRAIDDiskFailure + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + 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 }}/node/noderaiddiskfailure + summary: Failed device in RAID array + expr: node_md_disks{state="failed",job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)"} > 0 + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.NodeFileDescriptorLimit | default false) }} + - alert: NodeFileDescriptorLimit + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: File descriptors limit at {{`{{`}} $labels.instance {{`}}`}} is currently at {{`{{`}} printf "%.2f" $value {{`}}`}}%. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/nodefiledescriptorlimit + summary: Kernel is predicted to exhaust file descriptors limit soon. + expr: |- + ( + node_filefd_allocated{job="node-exporter"} * 100 / node_filefd_maximum{job="node-exporter"} > 70 + ) + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.NodeFileDescriptorLimit | default false) }} + - alert: NodeFileDescriptorLimit + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: File descriptors limit at {{`{{`}} $labels.instance {{`}}`}} is currently at {{`{{`}} printf "%.2f" $value {{`}}`}}%. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/nodefiledescriptorlimit + summary: Kernel is predicted to exhaust file descriptors limit soon. + expr: |- + ( + node_filefd_allocated{job="node-exporter"} * 100 / node_filefd_maximum{job="node-exporter"} > 90 + ) + 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/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..93209734 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-network.yaml @@ -0,0 +1,44 @@ +{{- /* +Generated from 'node-network' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubePrometheus-prometheusRule.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: +{{- if not (.Values.defaultRules.disabled.NodeNetworkInterfaceFlapping | default false) }} + - alert: NodeNetworkInterfaceFlapping + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Network interface "{{`{{`}} $labels.device {{`}}`}}" changing its up status often on node-exporter {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} + runbook_url: {{ .Values.defaultRules.runbookUrl }}/general/nodenetworkinterfaceflapping + summary: Network interface is often changing its status + 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 }} +{{- 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..4f8da294 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node.rules.yaml @@ -0,0 +1,55 @@ +{{- /* +Generated from 'node.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetesControlPlane-prometheusRule.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: |- + topk by(cluster, namespace, pod) (1, + max by (cluster, 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) + topk by(namespace, pod) (1, 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 + - expr: |- + sum(rate(node_cpu_seconds_total{job="node-exporter",mode!="idle",mode!="iowait",mode!="steal"}[5m])) / + count(sum(node_cpu_seconds_total{job="node-exporter"}) by (cluster, instance, cpu)) + record: cluster:node_cpu:ratio_rate5m +{{- 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..1c6b5c5d --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/prometheus-operator.yaml @@ -0,0 +1,148 @@ +{{- /* +Generated from 'prometheus-operator' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/prometheusOperator-prometheusRule.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" }} +{{- $namespace := printf "%s" (include "kube-prometheus-stack.namespace" .) }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "prometheus-operator" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: prometheus-operator + rules: +{{- if not (.Values.defaultRules.disabled.PrometheusOperatorListErrors | default false) }} + - alert: PrometheusOperatorListErrors + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Errors while performing List operations in controller {{`{{`}}$labels.controller{{`}}`}} in {{`{{`}}$labels.namespace{{`}}`}} namespace. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus-operator/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="{{ $namespace }}"}[10m]))) > 0.4 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusOperatorWatchErrors | default false) }} + - alert: PrometheusOperatorWatchErrors + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Errors while performing watch operations in controller {{`{{`}}$labels.controller{{`}}`}} in {{`{{`}}$labels.namespace{{`}}`}} namespace. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus-operator/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 }}"}[5m])) / sum by (controller,namespace) (rate(prometheus_operator_watch_operations_total{job="{{ $operatorJob }}",namespace="{{ $namespace }}"}[5m]))) > 0.4 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusOperatorSyncFailed | default false) }} + - alert: PrometheusOperatorSyncFailed + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Controller {{`{{`}} $labels.controller {{`}}`}} in {{`{{`}} $labels.namespace {{`}}`}} namespace fails to reconcile {{`{{`}} $value {{`}}`}} objects. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus-operator/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusOperatorReconcileErrors | default false) }} + - alert: PrometheusOperatorReconcileErrors + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: '{{`{{`}} $value | humanizePercentage {{`}}`}} of reconciling operations failed for {{`{{`}} $labels.controller {{`}}`}} controller in {{`{{`}} $labels.namespace {{`}}`}} namespace.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus-operator/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusOperatorNodeLookupErrors | default false) }} + - alert: PrometheusOperatorNodeLookupErrors + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Errors while reconciling Prometheus in {{`{{`}} $labels.namespace {{`}}`}} Namespace. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus-operator/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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusOperatorNotReady | default false) }} + - alert: PrometheusOperatorNotReady + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus operator in {{`{{`}} $labels.namespace {{`}}`}} namespace isn't ready to reconcile {{`{{`}} $labels.controller {{`}}`}} resources. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus-operator/prometheusoperatornotready + summary: Prometheus operator not ready + expr: min by (controller,namespace) (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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusOperatorRejectedResources | default false) }} + - alert: PrometheusOperatorRejectedResources + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus operator in {{`{{`}} $labels.namespace {{`}}`}} namespace rejected {{`{{`}} printf "%0.0f" $value {{`}}`}} {{`{{`}} $labels.controller {{`}}`}}/{{`{{`}} $labels.resource {{`}}`}} resources. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus-operator/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 }} +{{- 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..358ca7a4 --- /dev/null +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/prometheus.yaml @@ -0,0 +1,448 @@ +{{- /* +Generated from 'prometheus' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/prometheus-prometheusRule.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" }} +{{- $namespace := printf "%s" (include "kube-prometheus-stack.namespace" .) }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "prometheus" | trunc 63 | trimSuffix "-" }} + namespace: {{ template "kube-prometheus-stack.namespace" . }} + labels: + app: {{ template "kube-prometheus-stack.name" . }} +{{ include "kube-prometheus-stack.labels" . | indent 4 }} +{{- if .Values.defaultRules.labels }} +{{ toYaml .Values.defaultRules.labels | indent 4 }} +{{- end }} +{{- if .Values.defaultRules.annotations }} + annotations: +{{ toYaml .Values.defaultRules.annotations | indent 4 }} +{{- end }} +spec: + groups: + - name: prometheus + rules: +{{- if not (.Values.defaultRules.disabled.PrometheusBadConfig | default false) }} + - alert: PrometheusBadConfig + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has failed to reload its configuration. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusbadconfig + 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="{{ $namespace }}"}[5m]) == 0 + for: 10m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusNotificationQueueRunningFull | default false) }} + - alert: PrometheusNotificationQueueRunningFull + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Alert notification queue of Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is running full. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusnotificationqueuerunningfull + 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 }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusErrorSendingAlertsToSomeAlertmanagers | default false) }} + - alert: PrometheusErrorSendingAlertsToSomeAlertmanagers + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: '{{`{{`}} printf "%.1f" $value {{`}}`}}% errors while sending alerts from Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} to Alertmanager {{`{{`}}$labels.alertmanager{{`}}`}}.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheuserrorsendingalertstosomealertmanagers + 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="{{ $namespace }}"}[5m]) + ) + * 100 + > 1 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusNotConnectedToAlertmanagers | default false) }} + - alert: PrometheusNotConnectedToAlertmanagers + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is not connected to any Alertmanagers. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusnotconnectedtoalertmanagers + 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="{{ $namespace }}"}[5m]) < 1 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusTSDBReloadsFailing | default false) }} + - alert: PrometheusTSDBReloadsFailing + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has detected {{`{{`}}$value | humanize{{`}}`}} reload failures over the last 3h. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheustsdbreloadsfailing + summary: Prometheus has issues reloading blocks from disk. + expr: increase(prometheus_tsdb_reloads_failures_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[3h]) > 0 + for: 4h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusTSDBCompactionsFailing | default false) }} + - alert: PrometheusTSDBCompactionsFailing + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has detected {{`{{`}}$value | humanize{{`}}`}} compaction failures over the last 3h. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheustsdbcompactionsfailing + summary: Prometheus has issues compacting blocks. + expr: increase(prometheus_tsdb_compactions_failed_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[3h]) > 0 + for: 4h + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusNotIngestingSamples | default false) }} + - alert: PrometheusNotIngestingSamples + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is not ingesting samples. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusnotingestingsamples + summary: Prometheus is not ingesting samples. + expr: |- + ( + rate(prometheus_tsdb_head_samples_appended_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) <= 0 + and + ( + sum without(scrape_job) (prometheus_target_metadata_cache_entries{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}) > 0 + or + sum without(rule_group) (prometheus_rule_group_rules{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}) > 0 + ) + ) + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusDuplicateTimestamps | default false) }} + - alert: PrometheusDuplicateTimestamps + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is dropping {{`{{`}} printf "%.4g" $value {{`}}`}} samples/s with different values but duplicated timestamp. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusduplicatetimestamps + summary: Prometheus is dropping samples with duplicate timestamps. + expr: rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusOutOfOrderTimestamps | default false) }} + - alert: PrometheusOutOfOrderTimestamps + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is dropping {{`{{`}} printf "%.4g" $value {{`}}`}} samples/s with timestamps arriving out of order. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusoutofordertimestamps + summary: Prometheus drops samples with out-of-order timestamps. + expr: rate(prometheus_target_scrapes_sample_out_of_order_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0 + for: 10m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusRemoteStorageFailures | default false) }} + - alert: PrometheusRemoteStorageFailures + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} failed to send {{`{{`}} printf "%.1f" $value {{`}}`}}% of the samples to {{`{{`}} $labels.remote_name{{`}}`}}:{{`{{`}} $labels.url {{`}}`}} + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusremotestoragefailures + summary: Prometheus fails to send samples to remote storage. + expr: |- + ( + (rate(prometheus_remote_storage_failed_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m])) + / + ( + (rate(prometheus_remote_storage_failed_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m])) + + + (rate(prometheus_remote_storage_succeeded_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) or rate(prometheus_remote_storage_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m])) + ) + ) + * 100 + > 1 + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusRemoteWriteBehind | default false) }} + - alert: PrometheusRemoteWriteBehind + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} remote write is {{`{{`}} printf "%.1f" $value {{`}}`}}s behind for {{`{{`}} $labels.remote_name{{`}}`}}:{{`{{`}} $labels.url {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusremotewritebehind + 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]) + - ignoring(remote_name, url) group_right + max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) + ) + > 120 + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusRemoteWriteDesiredShards | default false) }} + - alert: PrometheusRemoteWriteDesiredShards + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus {{`{{`}}$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 {{`}}`}}. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusremotewritedesiredshards + 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="{{ $namespace }}"}[5m]) + ) + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusRuleFailures | default false) }} + - alert: PrometheusRuleFailures + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has failed to evaluate {{`{{`}} printf "%.0f" $value {{`}}`}} rules in the last 5m. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusrulefailures + summary: Prometheus is failing rule evaluations. + expr: increase(prometheus_rule_evaluation_failures_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0 + for: 15m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusMissingRuleEvaluations | default false) }} + - alert: PrometheusMissingRuleEvaluations + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has missed {{`{{`}} printf "%.0f" $value {{`}}`}} rule group evaluations in the last 5m. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusmissingruleevaluations + summary: Prometheus is missing rule evaluations due to slow rule group evaluation. + expr: increase(prometheus_rule_group_iterations_missed_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusTargetLimitHit | default false) }} + - alert: PrometheusTargetLimitHit + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has dropped {{`{{`}} printf "%.0f" $value {{`}}`}} targets because the number of targets exceeded the configured target_limit. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheustargetlimithit + 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="{{ $namespace }}"}[5m]) > 0 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusLabelLimitHit | default false) }} + - alert: PrometheusLabelLimitHit + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has dropped {{`{{`}} printf "%.0f" $value {{`}}`}} targets because some samples exceeded the configured label_limit, label_name_length_limit or label_value_length_limit. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheuslabellimithit + summary: Prometheus has dropped targets because some scrape configs have exceeded the labels limit. + expr: increase(prometheus_target_scrape_pool_exceeded_label_limits_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusScrapeBodySizeLimitHit | default false) }} + - alert: PrometheusScrapeBodySizeLimitHit + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has failed {{`{{`}} printf "%.0f" $value {{`}}`}} scrapes in the last 5m because some targets exceeded the configured body_size_limit. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusscrapebodysizelimithit + summary: Prometheus has dropped some targets that exceeded body size limit. + expr: increase(prometheus_target_scrapes_exceeded_body_size_limit_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusScrapeSampleLimitHit | default false) }} + - alert: PrometheusScrapeSampleLimitHit + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has failed {{`{{`}} printf "%.0f" $value {{`}}`}} scrapes in the last 5m because some targets exceeded the configured sample_limit. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusscrapesamplelimithit + summary: Prometheus has failed scrapes that have exceeded the configured sample limit. + expr: increase(prometheus_target_scrapes_exceeded_sample_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 }} +{{- if not (.Values.defaultRules.disabled.PrometheusTargetSyncFailure | default false) }} + - alert: PrometheusTargetSyncFailure + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: '{{`{{`}} printf "%.0f" $value {{`}}`}} targets in Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} have failed to sync because invalid configuration was supplied.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheustargetsyncfailure + summary: Prometheus has failed to sync targets. + expr: increase(prometheus_target_sync_failed_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[30m]) > 0 + for: 5m + labels: + severity: critical +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusHighQueryLoad | default false) }} + - alert: PrometheusHighQueryLoad + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} query API has less than 20% available capacity in its query engine for the last 15 minutes. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheushighqueryload + summary: Prometheus is reaching its maximum capacity serving concurrent requests. + expr: avg_over_time(prometheus_engine_queries{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) / max_over_time(prometheus_engine_queries_concurrent_max{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0.8 + for: 15m + labels: + severity: warning +{{- if .Values.defaultRules.additionalRuleLabels }} +{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} +{{- end }} +{{- end }} +{{- if not (.Values.defaultRules.disabled.PrometheusErrorSendingAlertsToAnyAlertmanager | default false) }} + - alert: PrometheusErrorSendingAlertsToAnyAlertmanager + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} + description: '{{`{{`}} printf "%.1f" $value {{`}}`}}% minimum errors while sending alerts from Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} to any Alertmanager.' + runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheuserrorsendingalertstoanyalertmanager + 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 }}",alertmanager!~``}[5m]) + / + rate(prometheus_notifications_sent_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}",alertmanager!~``}[5m]) + ) + * 100 + > 3 + 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/thanos-ruler/ruler.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/thanos-ruler/ruler.yaml index 73d5a7d6..ebca08c4 100644 --- a/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/thanos-ruler/ruler.yaml +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/thanos-ruler/ruler.yaml @@ -13,14 +13,15 @@ metadata: {{- end }} spec: {{- if .Values.thanosRuler.thanosRulerSpec.image }} + {{- $registry := .Values.global.imageRegistry | default .Values.thanosRuler.thanosRulerSpec.image.registry -}} {{- if and .Values.thanosRuler.thanosRulerSpec.image.tag .Values.thanosRuler.thanosRulerSpec.image.sha }} - image: "{{ .Values.thanosRuler.thanosRulerSpec.image.repository }}:{{ .Values.thanosRuler.thanosRulerSpec.image.tag }}@sha256:{{ .Values.thanosRuler.thanosRulerSpec.image.sha }}" + image: "{{ $registry }}/{{ .Values.thanosRuler.thanosRulerSpec.image.repository }}:{{ .Values.thanosRuler.thanosRulerSpec.image.tag }}@sha256:{{ .Values.thanosRuler.thanosRulerSpec.image.sha }}" {{- else if .Values.thanosRuler.thanosRulerSpec.image.sha }} - image: "{{ .Values.thanosRuler.thanosRulerSpec.image.repository }}@sha256:{{ .Values.thanosRuler.thanosRulerSpec.image.sha }}" + image: "{{ $registry }}/{{ .Values.thanosRuler.thanosRulerSpec.image.repository }}@sha256:{{ .Values.thanosRuler.thanosRulerSpec.image.sha }}" {{- else if .Values.thanosRuler.thanosRulerSpec.image.tag }} - image: "{{ .Values.thanosRuler.thanosRulerSpec.image.repository }}:{{ .Values.thanosRuler.thanosRulerSpec.image.tag }}" + image: "{{ $registry }}/{{ .Values.thanosRuler.thanosRulerSpec.image.repository }}:{{ .Values.thanosRuler.thanosRulerSpec.image.tag }}" {{- else }} - image: "{{ .Values.thanosRuler.thanosRulerSpec.image.repository }}" + image: "{{ $registry }}/{{ .Values.thanosRuler.thanosRulerSpec.image.repository }}" {{- end }} {{- if .Values.thanosRuler.thanosRulerSpec.image.sha }} sha: {{ .Values.thanosRuler.thanosRulerSpec.image.sha }} diff --git a/charts/kubezero-metrics/charts/kube-prometheus-stack/values.yaml b/charts/kubezero-metrics/charts/kube-prometheus-stack/values.yaml index 00983e25..e5d805cd 100644 --- a/charts/kubezero-metrics/charts/kube-prometheus-stack/values.yaml +++ b/charts/kubezero-metrics/charts/kube-prometheus-stack/values.yaml @@ -122,6 +122,10 @@ global: # seccomp.security.alpha.kubernetes.io/defaultProfileName: 'docker/default' # apparmor.security.beta.kubernetes.io/defaultProfileName: 'runtime/default' + ## Global image registry to use if it needs to be overriden for some specific use cases (e.g local registries, custom images, ...) + ## + imageRegistry: "" + ## 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/ ## @@ -418,7 +422,7 @@ alertmanager: ## enableHttp2: Whether to enable HTTP2. ## See https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#endpoint - enableHttp2: false + enableHttp2: true ## tlsConfig: TLS configuration to use when scraping the endpoint. For example if using istio mTLS. ## Of type: https://github.com/coreos/prometheus-operator/blob/main/Documentation/api.md#tlsconfig @@ -457,7 +461,8 @@ alertmanager: ## Image of Alertmanager ## image: - repository: quay.io/prometheus/alertmanager + registry: quay.io + repository: prometheus/alertmanager tag: v0.24.0 sha: "" @@ -1032,7 +1037,8 @@ kubelet: ## ## metrics_path is required to match upstream rules and charts cAdvisorRelabelings: - - sourceLabels: [__metrics_path__] + - action: replace + sourceLabels: [__metrics_path__] targetLabel: metrics_path # - sourceLabels: [__meta_kubernetes_pod_node_name] # separator: ; @@ -1045,7 +1051,8 @@ kubelet: ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#relabelconfig ## probesRelabelings: - - sourceLabels: [__metrics_path__] + - action: replace + sourceLabels: [__metrics_path__] targetLabel: metrics_path # - sourceLabels: [__meta_kubernetes_pod_node_name] # separator: ; @@ -1058,7 +1065,8 @@ kubelet: ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#relabelconfig ## resourceRelabelings: - - sourceLabels: [__metrics_path__] + - action: replace + sourceLabels: [__metrics_path__] targetLabel: metrics_path # - sourceLabels: [__meta_kubernetes_pod_node_name] # separator: ; @@ -1087,7 +1095,8 @@ kubelet: ## ## metrics_path is required to match upstream rules and charts relabelings: - - sourceLabels: [__metrics_path__] + - action: replace + sourceLabels: [__metrics_path__] targetLabel: metrics_path # - sourceLabels: [__meta_kubernetes_pod_node_name] # separator: ; @@ -1622,7 +1631,8 @@ prometheusOperator: patch: enabled: true image: - repository: k8s.gcr.io/ingress-nginx/kube-webhook-certgen + registry: k8s.gcr.io + repository: ingress-nginx/kube-webhook-certgen tag: v1.3.0 sha: "" pullPolicy: IfNotPresent @@ -1692,6 +1702,11 @@ prometheusOperator: ## # clusterDomain: "cluster.local" + networkPolicy: + ## Enable creation of NetworkPolicy resources. + ## + enabled: false + ## Service account for Alertmanager to use. ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/ ## @@ -1776,6 +1791,9 @@ prometheusOperator: ## Create a servicemonitor for the operator ## serviceMonitor: + ## Labels for ServiceMonitor + additionalLabels: {} + ## Scrape interval. If not set, the Prometheus default scrape interval is used. ## interval: "" @@ -1888,24 +1906,34 @@ prometheusOperator: ## Prometheus-operator image ## image: - repository: quay.io/prometheus-operator/prometheus-operator + registry: quay.io + repository: prometheus-operator/prometheus-operator tag: v0.60.1 sha: "" pullPolicy: IfNotPresent ## Prometheus image to use for prometheuses managed by the operator ## - # prometheusDefaultBaseImage: quay.io/prometheus/prometheus + # prometheusDefaultBaseImage: prometheus/prometheus + + ## Prometheus image registry to use for prometheuses managed by the operator + ## + # prometheusDefaultBaseImageRegistry: quay.io ## Alertmanager image to use for alertmanagers managed by the operator ## - # alertmanagerDefaultBaseImage: quay.io/prometheus/alertmanager + # alertmanagerDefaultBaseImage: prometheus/alertmanager + + ## Alertmanager image registry to use for alertmanagers managed by the operator + ## + # alertmanagerDefaultBaseImageRegistry: quay.io ## Prometheus-config-reloader ## prometheusConfigReloader: image: - repository: quay.io/prometheus-operator/prometheus-config-reloader + registry: quay.io + repository: prometheus-operator/prometheus-config-reloader tag: v0.60.1 sha: "" @@ -1921,7 +1949,8 @@ prometheusOperator: ## Thanos side-car image when configured ## thanosImage: - repository: quay.io/thanos/thanos + registry: quay.io + repository: thanos/thanos tag: v0.28.1 sha: "" @@ -2358,7 +2387,8 @@ prometheus: ## Image of Prometheus. ## image: - repository: quay.io/prometheus/prometheus + registry: quay.io + repository: prometheus/prometheus tag: v2.39.1 sha: "" @@ -2903,6 +2933,12 @@ prometheus: ## be considered available. Defaults to 0 (pod will be considered available as soon as it is ready). minReadySeconds: 0 + # 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 + # Use the host's network namespace if true. Make sure to understand the security implications if you want to enable it. + # When hostNetwork is enabled, this will set dnsPolicy to ClusterFirstWithHostNet automatically. + hostNetwork: false + additionalRulesForClusterRole: [] # - apiGroups: [ "" ] # resources: @@ -3193,7 +3229,8 @@ thanosRuler: ## Image of ThanosRuler ## image: - repository: quay.io/thanos/thanos + registry: quay.io + repository: thanos/thanos tag: v0.28.1 sha: "" diff --git a/charts/kubezero-metrics/charts/prometheus-pushgateway/.helmignore b/charts/kubezero-metrics/charts/prometheus-pushgateway/.helmignore deleted file mode 100644 index e90c9f6d..00000000 --- a/charts/kubezero-metrics/charts/prometheus-pushgateway/.helmignore +++ /dev/null @@ -1,24 +0,0 @@ -# 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 - -# OWNERS file for Kubernetes -OWNERS \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/prometheus-pushgateway/Chart.yaml b/charts/kubezero-metrics/charts/prometheus-pushgateway/Chart.yaml deleted file mode 100644 index 5f3b4b9e..00000000 --- a/charts/kubezero-metrics/charts/prometheus-pushgateway/Chart.yaml +++ /dev/null @@ -1,16 +0,0 @@ -apiVersion: v1 -appVersion: 1.4.2 -description: A Helm chart for prometheus pushgateway -home: https://github.com/prometheus/pushgateway -keywords: -- pushgateway -- prometheus -maintainers: -- email: gianrubio@gmail.com - name: gianrubio -- email: christian.staude@staffbase.com - name: cstaud -name: prometheus-pushgateway -sources: -- https://github.com/prometheus/pushgateway -version: 1.20.0 diff --git a/charts/kubezero-metrics/charts/prometheus-pushgateway/README.md b/charts/kubezero-metrics/charts/prometheus-pushgateway/README.md deleted file mode 100644 index 9f0ac5e8..00000000 --- a/charts/kubezero-metrics/charts/prometheus-pushgateway/README.md +++ /dev/null @@ -1,63 +0,0 @@ -# Prometheus Pushgateway - -This chart bootstraps a prometheus [pushgateway](http://github.com/prometheus/pushgateway) deployment on a [Kubernetes](http://kubernetes.io) cluster using the [Helm](https://helm.sh) package manager. - -An optional prometheus `ServiceMonitor` can be enabled, should you wish to use this gateway with a [Prometheus Operator](https://github.com/coreos/prometheus-operator). - -## 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-pushgateway - -# Helm 2 -$ helm install --name [RELEASE_NAME] prometheus-community/prometheus-pushgateway -``` - -_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._ - -## 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, visit the chart's [values.yaml](./values.yaml), or run these configuration commands: - -```console -# Helm 2 -$ helm inspect values prometheus-community/prometheus-pushgateway - -# Helm 3 -$ helm show values prometheus-community/prometheus-pushgateway -``` diff --git a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/NOTES.txt b/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/NOTES.txt deleted file mode 100644 index 0196e2b3..00000000 --- a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/NOTES.txt +++ /dev/null @@ -1,19 +0,0 @@ -1. Get the application URL by running these commands: -{{- if .Values.ingress.enabled }} -{{- range .Values.ingress.hosts }} - http{{ if $.Values.ingress.tls }}s{{ end }}://{{ . }}{{ $.Values.ingress.path }} -{{- end }} -{{- else if contains "NodePort" .Values.service.type }} - export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ template "prometheus-pushgateway.fullname" . }}) - export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}") - echo http://$NODE_IP:$NODE_PORT -{{- else if contains "LoadBalancer" .Values.service.type }} - NOTE: It may take a few minutes for the LoadBalancer IP to be available. - You can watch the status of by running 'kubectl get svc -w {{ template "prometheus-pushgateway.fullname" . }}' - export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ template "prometheus-pushgateway.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 {{ .Release.Namespace }} -l "app={{ template "prometheus-pushgateway.name" . }},release={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}") - echo "Visit http://127.0.0.1:9091 to use your application" - kubectl port-forward $POD_NAME 9091 -{{- end }} diff --git a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/_helpers.tpl b/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/_helpers.tpl deleted file mode 100644 index c8332781..00000000 --- a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/_helpers.tpl +++ /dev/null @@ -1,161 +0,0 @@ -{{/* vim: set filetype=mustache: */}} -{{/* -Expand the name of the chart. -*/}} -{{- define "prometheus-pushgateway.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-pushgateway.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 "prometheus-pushgateway.chart" -}} -{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}} -{{- end -}} - - -{{/* -Create the name of the service account to use -*/}} -{{- define "prometheus-pushgateway.serviceAccountName" -}} -{{- if .Values.serviceAccount.create -}} - {{ default (include "prometheus-pushgateway.fullname" .) .Values.serviceAccount.name }} -{{- else -}} - {{ default "default" .Values.serviceAccount.name }} -{{- end -}} -{{- end -}} - -{{/* -Create default labels -*/}} -{{- define "prometheus-pushgateway.defaultLabels" -}} -{{- $labelChart := include "prometheus-pushgateway.chart" $ -}} -{{- $labelApp := include "prometheus-pushgateway.name" $ -}} -{{- $labels := dict "app" $labelApp "chart" $labelChart "release" .Release.Name "heritage" .Release.Service -}} -{{- $indent := .indent | default 4 -}} -{{ merge .extraLabels $labels | toYaml | indent $indent }} -{{- end -}} - -{{/* -Return the appropriate apiVersion for networkpolicy. -*/}} -{{- define "prometheus-pushgateway.networkPolicy.apiVersion" -}} -{{- if semverCompare ">=1.4-0, <1.7-0" .Capabilities.KubeVersion.GitVersion -}} -{{- print "extensions/v1beta1" -}} -{{- else if semverCompare "^1.7-0" .Capabilities.KubeVersion.GitVersion -}} -{{- print "networking.k8s.io/v1" -}} -{{- end -}} -{{- end -}} - -{{/* -Returns pod spec -*/}} -{{- define "prometheus-pushgateway.podSpec" -}} - serviceAccountName: {{ template "prometheus-pushgateway.serviceAccountName" . }} - {{- if .Values.priorityClassName }} - priorityClassName: {{ .Values.priorityClassName | quote }} - {{- end }} - {{- if .Values.imagePullSecrets }} - imagePullSecrets: -{{ toYaml .Values.imagePullSecrets | indent 8 }} - {{- end }} - {{- if .Values.extraInitContainers }} - initContainers: - {{ toYaml .Values.extraInitContainers | nindent 8 }} - {{- end }} - containers: - {{- if .Values.extraContainers }} -{{ toYaml .Values.extraContainers | indent 8 }} - {{- end }} - - name: pushgateway - image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}" - imagePullPolicy: {{ .Values.image.pullPolicy }} - {{- if .Values.extraVars }} - env: -{{ toYaml .Values.extraVars | indent 12 }} - {{- end }} - {{- if .Values.extraArgs }} - args: -{{ toYaml .Values.extraArgs | indent 12 }} - {{- end }} - ports: - - name: metrics - containerPort: 9091 - protocol: TCP -{{- if .Values.liveness.enabled }} - livenessProbe: -{{ toYaml .Values.liveness.probe | indent 12 }} - {{- end }} -{{- if .Values.readiness.enabled }} - readinessProbe: -{{ toYaml .Values.readiness.probe | indent 12 }} - {{- end }} - resources: -{{ toYaml .Values.resources | indent 12 }} - {{- if .Values.containerSecurityContext }} - securityContext: -{{ toYaml .Values.containerSecurityContext | indent 12 }} - {{- end }} - volumeMounts: - - name: storage-volume - mountPath: "{{ .Values.persistentVolume.mountPath }}" - subPath: "{{ .Values.persistentVolume.subPath }}" - {{- if .Values.extraVolumeMounts }} -{{ toYaml .Values.extraVolumeMounts | indent 12 }} - {{- end }} - {{- if .Values.nodeSelector }} - nodeSelector: -{{ toYaml .Values.nodeSelector | indent 8 }} - {{- end }} - {{- if .Values.tolerations }} - tolerations: -{{ toYaml .Values.tolerations | indent 8 }} - {{- end }} - {{- if .Values.affinity }} - affinity: -{{ toYaml .Values.affinity | indent 8 }} - {{- end }} - {{- if .Values.topologySpreadConstraints }} - topologySpreadConstraints: -{{ toYaml .Values.topologySpreadConstraints | indent 8 }} - {{- end }} - {{- if .Values.securityContext }} - securityContext: -{{ toYaml .Values.securityContext | indent 8 }} - {{- end }} - volumes: - {{- $storageVolumeAsPVCTemplate := and .Values.runAsStatefulSet .Values.persistentVolume.enabled -}} - {{- if not $storageVolumeAsPVCTemplate }} - - name: storage-volume - {{- if .Values.persistentVolume.enabled }} - persistentVolumeClaim: - claimName: {{ if .Values.persistentVolume.existingClaim }}{{ .Values.persistentVolume.existingClaim }}{{- else }}{{ template "prometheus-pushgateway.fullname" . }}{{- end }} - {{- else }} - emptyDir: {} - {{- end -}} - {{- end -}} - {{- if .Values.extraVolumes }} -{{ toYaml .Values.extraVolumes | indent 8 }} - {{- else if $storageVolumeAsPVCTemplate }} - [] - {{- end }} - -{{- end }} diff --git a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/deployment.yaml b/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/deployment.yaml deleted file mode 100644 index 8355fa06..00000000 --- a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/deployment.yaml +++ /dev/null @@ -1,27 +0,0 @@ -{{- if not .Values.runAsStatefulSet }} -apiVersion: apps/v1 -kind: Deployment -metadata: - name: {{ template "prometheus-pushgateway.fullname" . }} - namespace: {{ .Release.Namespace }} - labels: -{{ template "prometheus-pushgateway.defaultLabels" merge (dict "extraLabels" .Values.podLabels) . }} -spec: - replicas: {{ .Values.replicaCount }} - {{- if .Values.strategy }} - strategy: -{{ toYaml .Values.strategy | indent 4 }} - {{- end }} - selector: - matchLabels: - app: {{ template "prometheus-pushgateway.name" . }} - release: {{ .Release.Name }} - template: - metadata: - labels: -{{ template "prometheus-pushgateway.defaultLabels" merge (dict "extraLabels" .Values.podLabels "indent" 8) . }} - annotations: -{{ toYaml .Values.podAnnotations | indent 8 }} - spec: - {{ include "prometheus-pushgateway.podSpec" . }} -{{- end -}} diff --git a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/ingress.yaml b/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/ingress.yaml deleted file mode 100644 index 1a6bad3b..00000000 --- a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/ingress.yaml +++ /dev/null @@ -1,52 +0,0 @@ -{{- if .Values.ingress.enabled -}} -{{- $serviceName := include "prometheus-pushgateway.fullname" . }} -{{- $servicePort := .Values.service.port -}} -{{- $ingressPath := .Values.ingress.path -}} -{{- $ingressClassName := .Values.ingress.className -}} -{{- $ingressPathType := .Values.ingress.pathType -}} -{{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion -}} -apiVersion: networking.k8s.io/v1 -{{- else if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}} -apiVersion: networking.k8s.io/v1beta1 -{{- else -}} -apiVersion: extensions/v1beta1 -{{- end }} -kind: Ingress -metadata: -{{- if .Values.ingress.annotations }} - annotations: -{{ toYaml .Values.ingress.annotations | indent 4}} -{{- end }} - labels: -{{ template "prometheus-pushgateway.defaultLabels" merge (dict "extraLabels" dict) . }} - name: {{ template "prometheus-pushgateway.fullname" . }} - namespace: {{ .Release.Namespace }} -spec: - {{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion }} - ingressClassName: {{ $ingressClassName }} - {{- end }} - rules: - {{- range $host := .Values.ingress.hosts }} - - host: {{ $host }} - http: - paths: - - path: {{ $ingressPath }} - {{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion }} - pathType: {{ $ingressPathType }} - {{- end }} - backend: - {{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion }} - service: - name: {{ $serviceName }} - port: - number: {{ $servicePort }} - {{- else }} - serviceName: {{ $serviceName }} - servicePort: {{ $servicePort }} - {{- end }} - {{- end -}} -{{- if .Values.ingress.tls }} - tls: -{{ toYaml .Values.ingress.tls | indent 4 }} - {{- end -}} -{{- end -}} diff --git a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/networkpolicy.yaml b/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/networkpolicy.yaml deleted file mode 100644 index aa490585..00000000 --- a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/networkpolicy.yaml +++ /dev/null @@ -1,26 +0,0 @@ -{{ if .Values.networkPolicy }} -apiVersion: {{ template "prometheus-pushgateway.networkPolicy.apiVersion" . }} -kind: NetworkPolicy -metadata: -{{- if .Values.networkPolicy.customSelectors }} - name: ingress-allow-customselector-{{ template "prometheus-pushgateway.name" . }} -{{- else if .Values.networkPolicy.allowAll }} - name: ingress-allow-all-{{ template "prometheus-pushgateway.name" . }} -{{- else -}} -{{- fail "One of `allowAll` or `customSelectors` must be specified." }} -{{- end }} - labels: -{{ template "prometheus-pushgateway.defaultLabels" merge (dict "extraLabels" .Values.podLabels) . }} -spec: - podSelector: - matchLabels: - app: {{ template "prometheus-pushgateway.name" .}} - release: {{ .Release.Name }} - ingress: - - ports: - - port: {{ .Values.service.targetPort }} -{{- if .Values.networkPolicy.customSelectors }} - from: -{{ toYaml .Values.networkPolicy.customSelectors | indent 8 }} -{{- end -}} -{{- end -}} diff --git a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/pdb.yaml b/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/pdb.yaml deleted file mode 100644 index f316d7ca..00000000 --- a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/pdb.yaml +++ /dev/null @@ -1,18 +0,0 @@ -{{- if .Values.podDisruptionBudget -}} -{{ if $.Capabilities.APIVersions.Has "policy/v1/PodDisruptionBudget" -}} -apiVersion: policy/v1 -{{- else -}} -apiVersion: policy/v1beta1 -{{- end }} -kind: PodDisruptionBudget -metadata: - name: {{ template "prometheus-pushgateway.fullname" . }} - namespace: {{ .Release.Namespace }} - labels: -{{ template "prometheus-pushgateway.defaultLabels" merge (dict "extraLabels" .Values.podLabels) . }} -spec: - selector: - matchLabels: - app: {{ template "prometheus-pushgateway.name" . }} -{{ toYaml .Values.podDisruptionBudget | indent 2 }} -{{- end -}} \ No newline at end of file diff --git a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/pushgateway-pvc.yaml b/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/pushgateway-pvc.yaml deleted file mode 100644 index 0640bdd1..00000000 --- a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/pushgateway-pvc.yaml +++ /dev/null @@ -1,30 +0,0 @@ -{{- if not .Values.runAsStatefulSet -}} -{{- if .Values.persistentVolume.enabled -}} -{{- if not .Values.persistentVolume.existingClaim -}} -apiVersion: v1 -kind: PersistentVolumeClaim -metadata: - {{- if .Values.persistentVolume.annotations }} - annotations: -{{ toYaml .Values.persistentVolume.annotations | indent 4 }} - {{- end }} - labels: -{{ template "prometheus-pushgateway.defaultLabels" merge (dict "extraLabels" .Values.persistentVolumeLabels) . }} - name: {{ template "prometheus-pushgateway.fullname" . }} - namespace: {{ .Release.Namespace }} -spec: - accessModes: -{{ toYaml .Values.persistentVolume.accessModes | indent 4 }} -{{- if .Values.persistentVolume.storageClass }} -{{- if (eq "-" .Values.persistentVolume.storageClass) }} - storageClassName: "" -{{- else }} - storageClassName: "{{ .Values.persistentVolume.storageClass }}" -{{- end }} -{{- end }} - resources: - requests: - storage: "{{ .Values.persistentVolume.size }}" -{{- end -}} -{{- end -}} -{{- end -}} diff --git a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/service.yaml b/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/service.yaml deleted file mode 100644 index a8ab0c76..00000000 --- a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/service.yaml +++ /dev/null @@ -1,36 +0,0 @@ -apiVersion: v1 -kind: Service -metadata: - name: {{ template "prometheus-pushgateway.fullname" . }} - namespace: {{ .Release.Namespace }} - annotations: -{{ .Values.serviceAnnotations | toYaml | indent 4 }} - labels: -{{ template "prometheus-pushgateway.defaultLabels" merge (dict "extraLabels" .Values.serviceLabels) . }} -spec: -{{- if .Values.service.clusterIP }} - clusterIP: {{ .Values.service.clusterIP }} -{{ else if .Values.runAsStatefulSet }} - clusterIP: None # Headless service -{{- end }} - type: {{ .Values.service.type }} -{{- if .Values.service.loadBalancerIP }} - loadBalancerIP: {{ .Values.service.loadBalancerIP }} -{{- end }} -{{- if .Values.service.loadBalancerSourceRanges }} - loadBalancerSourceRanges: - {{- range $cidr := .Values.service.loadBalancerSourceRanges }} - - {{ $cidr }} - {{- end }} -{{- end }} - ports: - - port: {{ .Values.service.port }} - targetPort: {{ .Values.service.targetPort }} - {{- if and (eq .Values.service.type "NodePort") .Values.service.nodePort }} - nodePort: {{ .Values.service.nodePort }} - {{- end }} - protocol: TCP - name: http - selector: - app: {{ template "prometheus-pushgateway.name" . }} - release: {{ .Release.Name }} diff --git a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/serviceaccount.yaml b/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/serviceaccount.yaml deleted file mode 100644 index 7ccd0ddc..00000000 --- a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/serviceaccount.yaml +++ /dev/null @@ -1,13 +0,0 @@ -{{- if .Values.serviceAccount.create -}} -apiVersion: v1 -kind: ServiceAccount -metadata: - name: {{ template "prometheus-pushgateway.serviceAccountName" . }} - namespace: {{ .Release.Namespace }} - labels: -{{ template "prometheus-pushgateway.defaultLabels" merge (dict "extraLabels" .Values.serviceAccountLabels) . }} -{{- if .Values.serviceAccount.annotations }} - annotations: -{{ toYaml .Values.serviceAccount.annotations | indent 4 }} -{{- end }} -{{- end -}} diff --git a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/servicemonitor.yaml b/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/servicemonitor.yaml deleted file mode 100644 index 28e810ca..00000000 --- a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/servicemonitor.yaml +++ /dev/null @@ -1,46 +0,0 @@ -{{- if .Values.serviceMonitor.enabled }} -apiVersion: monitoring.coreos.com/v1 -kind: ServiceMonitor -metadata: - name: {{ template "prometheus-pushgateway.fullname" . }} - {{- if .Values.serviceMonitor.namespace }} - namespace: {{ .Values.serviceMonitor.namespace }} - {{- end }} - labels: -{{ template "prometheus-pushgateway.defaultLabels" merge (dict "extraLabels" .Values.serviceMonitor.additionalLabels) . }} -spec: - endpoints: - - port: http - {{- if .Values.serviceMonitor.interval }} - interval: {{ .Values.serviceMonitor.interval }} - {{- end }} - {{- if .Values.serviceMonitor.scheme }} - scheme: {{ .Values.serviceMonitor.scheme }} - {{- end }} - {{- if .Values.serviceMonitor.bearerTokenFile }} - bearerTokenFile: {{ .Values.serviceMonitor.bearerTokenFile }} - {{- end }} - {{- if .Values.serviceMonitor.tlsConfig }} - tlsConfig: {{ toYaml .Values.serviceMonitor.tlsConfig | nindent 6 }} - {{- end }} - {{- if .Values.serviceMonitor.scrapeTimeout }} - scrapeTimeout: {{ .Values.serviceMonitor.scrapeTimeout }} - {{- end }} - path: /metrics - honorLabels: {{ .Values.serviceMonitor.honorLabels }} - {{- if .Values.serviceMonitor.metricRelabelings }} - metricRelabelings: - {{- tpl (toYaml .Values.serviceMonitor.metricRelabelings | nindent 4) . }} - {{- end }} - {{- if .Values.serviceMonitor.relabelings }} - relabelings: - {{ toYaml .Values.serviceMonitor.relabelings | nindent 4 }} - {{- end }} - namespaceSelector: - matchNames: - - {{ .Release.Namespace }} - selector: - matchLabels: - app: {{ template "prometheus-pushgateway.name" . }} - release: {{ .Release.Name }} -{{- end -}} diff --git a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/statefulset.yaml b/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/statefulset.yaml deleted file mode 100644 index 9cffb5a9..00000000 --- a/charts/kubezero-metrics/charts/prometheus-pushgateway/templates/statefulset.yaml +++ /dev/null @@ -1,47 +0,0 @@ -{{- if .Values.runAsStatefulSet }} -apiVersion: apps/v1 -kind: StatefulSet -metadata: - name: {{ template "prometheus-pushgateway.fullname" . }} - labels: -{{ template "prometheus-pushgateway.defaultLabels" merge (dict "extraLabels" .Values.podLabels) . }} -spec: - replicas: {{ .Values.replicaCount }} - serviceName: {{ template "prometheus-pushgateway.fullname" . }} - selector: - matchLabels: - app: {{ template "prometheus-pushgateway.name" . }} - release: {{ .Release.Name }} - template: - metadata: - labels: -{{ template "prometheus-pushgateway.defaultLabels" merge (dict "extraLabels" .Values.podLabels "indent" 8) . }} - annotations: -{{ toYaml .Values.podAnnotations | indent 8 }} - spec: - {{ include "prometheus-pushgateway.podSpec" . }} - {{- if .Values.persistentVolume.enabled }} - volumeClaimTemplates: - - metadata: - {{- if .Values.persistentVolume.annotations }} - annotations: - {{ toYaml .Values.persistentVolume.annotations | indent 10 }} - {{- end }} - labels: -{{ template "prometheus-pushgateway.defaultLabels" merge (dict "extraLabels" .Values.persistentVolumeLabels "indent" 10) . }} - name: storage-volume - spec: - accessModes: - {{ toYaml .Values.persistentVolume.accessModes }} - {{- if .Values.persistentVolume.storageClass }} - {{- if (eq "-" .Values.persistentVolume.storageClass) }} - storageClassName: "" - {{- else }} - storageClassName: "{{ .Values.persistentVolume.storageClass }}" - {{- end }} - {{- end }} - resources: - requests: - storage: "{{ .Values.persistentVolume.size }}" - {{- end }} -{{- end -}} diff --git a/charts/kubezero-metrics/charts/prometheus-pushgateway/values.yaml b/charts/kubezero-metrics/charts/prometheus-pushgateway/values.yaml deleted file mode 100644 index aed41a8f..00000000 --- a/charts/kubezero-metrics/charts/prometheus-pushgateway/values.yaml +++ /dev/null @@ -1,313 +0,0 @@ -# Default values for prometheus-pushgateway. -# This is a YAML-formatted file. -# Declare variables to be passed into your templates. - -# Provide a name in place of prometheus-pushgateway for `app:` labels -nameOverride: "" - -# Provide a name to substitute for the full names of resources -fullnameOverride: "" - -image: - repository: prom/pushgateway - tag: v1.4.2 - pullPolicy: IfNotPresent - -# Optional pod imagePullSecrets -imagePullSecrets: [] - -service: - type: ClusterIP - port: 9091 - targetPort: 9091 - - # Optional - Can be used for headless if value is "None" - clusterIP: "" - - loadBalancerIP: "" - loadBalancerSourceRanges: [] - -# Optional pod annotations -podAnnotations: {} - -# Optional pod labels -podLabels: {} - -# Optional service annotations -serviceAnnotations: {} - -# Optional service labels -serviceLabels: {} - -# Optional serviceAccount labels -serviceAccountLabels: {} - -# Optional persistentVolume labels -persistentVolumeLabels: {} - -# Optional additional environment variables -extraVars: [] - -## Additional pushgateway container arguments -## -## example: -## extraArgs: -## - --persistence.file=/data/pushgateway.data -## - --persistence.interval=5m -extraArgs: [] - -## Additional InitContainers to initialize the pod -## -extraInitContainers: [] - -# Optional additional containers (sidecar) -extraContainers: [] - # - name: oAuth2-proxy - # args: - # - -https-address=:9092 - # - -upstream=http://localhost:9091 - # - -skip-auth-regex=^/metrics - # - -openshift-delegate-urls={"/":{"group":"monitoring.coreos.com","resource":"prometheuses","verb":"get"}} - # image: openshift/oauth-proxy:v1.1.0 - # ports: - # - containerPort: 9092 - # name: proxy - # resources: - # limits: - # memory: 16Mi - # requests: - # memory: 4Mi - # cpu: 20m - # volumeMounts: - # - mountPath: /etc/prometheus/secrets/pushgateway-tls - # name: secret-pushgateway-tls - -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 - -liveness: - enabled: true - probe: - httpGet: - path: /-/ready - port: 9091 - initialDelaySeconds: 10 - timeoutSeconds: 10 - -readiness: - enabled: true - probe: - httpGet: - path: /-/ready - port: 9091 - initialDelaySeconds: 10 - timeoutSeconds: 10 - -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: - -## Configure ingress resource that allow you to access the -## pushgateway installation. Set up the URL -## ref: http://kubernetes.io/docs/user-guide/ingress/ -## -ingress: - ## Enable Ingress. - ## - enabled: false - # AWS ALB requires path of /* - className: "" - path: / - pathType: ImplementationSpecific - - ## Annotations. - ## - # annotations: - # kubernetes.io/ingress.class: nginx - # kubernetes.io/tls-acme: 'true' - - ## Hostnames. - ## Must be provided if Ingress is enabled. - ## - # hosts: - # - pushgateway.domain.com - - ## TLS configuration. - ## Secrets must be manually created in the namespace. - ## - # tls: - # - secretName: pushgateway-tls - # hosts: - # - pushgateway.domain.com - -tolerations: {} - # - effect: NoSchedule - # operator: Exists - -## Node labels for pushgateway pod assignment -## Ref: https://kubernetes.io/docs/user-guide/node-selection/ -## -nodeSelector: {} - -replicaCount: 1 - -## When running more than one replica alongside with persistence, different volumes are needed -## per replica, since sharing a `persistence.file` across replicas does not keep metrics synced. -## For this purpose, you can enable the `runAsStatefulSet` to deploy the pushgateway as a -## StatefulSet instead of as a Deployment. -runAsStatefulSet: false - -## Security context to be added to push-gateway pods -## -securityContext: - fsGroup: 65534 - runAsUser: 65534 - runAsNonRoot: true - -## Security context to be added to push-gateway containers -## Having a separate variable as securityContext differs for pods and containers. -containerSecurityContext: {} -# allowPrivilegeEscalation: false -# readOnlyRootFilesystem: true -# runAsUser: 65534 -# runAsNonRoot: true - -## Affinity for pod assignment -## Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity -affinity: {} - -## Topology spread constraints for pods -## Ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-topology-spread-constraints/ -topologySpreadConstraints: [] - -# Enable this if you're using https://github.com/coreos/prometheus-operator -serviceMonitor: - enabled: false - namespace: monitoring - - # Fallback to the prometheus default unless specified - # interval: 10s - - ## 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: - # Fallback to the prometheus default unless specified - # scrapeTimeout: 30s - - ## Used to pass Labels that are used by the Prometheus installed in your cluster to select Service Monitors to work with - ## ref: https://github.com/coreos/prometheus-operator/blob/master/Documentation/api.md#prometheusspec - additionalLabels: {} - - # Retain the job and instance labels of the metrics pushed to the Pushgateway - # [Scraping Pushgateway](https://github.com/prometheus/pushgateway#configure-the-pushgateway-as-a-target-to-scrape) - honorLabels: true - - ## Metric relabel configs to apply to samples before ingestion. - ## [Metric Relabeling](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs) - metricRelabelings: [] - # - action: keep - # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+' - # sourceLabels: [__name__] - - ## Relabel configs to apply to samples before ingestion. - ## [Relabeling](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config) - relabelings: [] - # - sourceLabels: [__meta_kubernetes_pod_node_name] - # separator: ; - # regex: ^(.*)$ - # targetLabel: nodename - # replacement: $1 - # action: replace - -# The values to set in the PodDisruptionBudget spec (minAvailable/maxUnavailable) -# If not set then a PodDisruptionBudget will not be created -podDisruptionBudget: {} - -priorityClassName: - -# Deployment Strategy type -strategy: - type: Recreate - -persistentVolume: - ## If true, pushgateway will create/use a Persistent Volume Claim - ## If false, use emptyDir - ## - enabled: false - - ## pushgateway data Persistent Volume access modes - ## Must match those of existing PV or dynamic provisioner - ## Ref: http://kubernetes.io/docs/user-guide/persistent-volumes/ - ## - accessModes: - - ReadWriteOnce - - ## pushgateway data Persistent Volume Claim annotations - ## - annotations: {} - - ## pushgateway data Persistent Volume existing claim name - ## Requires pushgateway.persistentVolume.enabled: true - ## If defined, PVC must be created manually before volume will be bound - existingClaim: "" - - ## pushgateway data Persistent Volume mount root path - ## - mountPath: /data - - ## pushgateway data Persistent Volume size - ## - size: 2Gi - - ## pushgateway data Persistent Volume Storage Class - ## If defined, storageClassName: - ## If set to "-", storageClassName: "", which disables dynamic provisioning - ## If undefined (the default) or set to null, no storageClassName spec is - ## set, choosing the default provisioner. (gp2 on AWS, standard on - ## GKE, AWS & OpenStack) - ## - # storageClass: "-" - - ## Subdirectory of pushgateway data Persistent Volume to mount - ## Useful if the volume's root directory is not empty - ## - subPath: "" - -extraVolumes: [] - # - name: extra - # emptyDir: {} -extraVolumeMounts: [] - # - name: extra - # mountPath: /usr/share/extras - # readOnly: true - -# Configuration for clusters with restrictive network policies in place: -# - allowAll allows access to the PushGateway from any namespace -# - customSelector is a list of pod/namespaceSelectors to allow access from -# These options are mutually exclusive and the latter will take precedence. -networkPolicy: {} - # allowAll: true - # customSelectors: - # - namespaceSelector: - # matchLabels: - # type: admin - # - podSelector: - # matchLabels: - # app: myapp diff --git a/charts/kubezero-metrics/jsonnet/jsonnetfile.lock.json b/charts/kubezero-metrics/jsonnet/jsonnetfile.lock.json index 0a4814b8..02d6d125 100644 --- a/charts/kubezero-metrics/jsonnet/jsonnetfile.lock.json +++ b/charts/kubezero-metrics/jsonnet/jsonnetfile.lock.json @@ -18,7 +18,7 @@ "subdir": "contrib/mixin" } }, - "version": "62169d12ebf61cc58e8d781eb201d9416487e4a0", + "version": "127e9c05b0c1405d0ab395b899939430226e76ff", "sum": "W/Azptf1PoqjyMwJON96UY69MFugDA4IAYiKURscryc=" }, { @@ -48,7 +48,7 @@ "subdir": "grafana-builder" } }, - "version": "d73aff453c9784cd6922119f3ce33d8d355a79e1", + "version": "e6a0083d9cc0f0ec79507397ce0e156d558f6efb", "sum": "tDR6yT2GVfw0wTU12iZH+m01HrbIr6g/xN+/8nzNkU0=" }, { @@ -68,7 +68,7 @@ "subdir": "lib/promgrafonnet" } }, - "version": "05a58f765eda05902d4f7dd22098a2b870f7ca1e", + "version": "3c386687c1f8ceb6b79ff887c4a934e9cee1b90a", "sum": "zv7hXGui6BfHzE9wPatHI/AGZa4A2WKo6pq7ZdqBsps=" }, { diff --git a/charts/kubezero-metrics/update.sh b/charts/kubezero-metrics/update.sh index 674a8aad..d8455dc8 100755 --- a/charts/kubezero-metrics/update.sh +++ b/charts/kubezero-metrics/update.sh @@ -1,21 +1,21 @@ #!/bin/bash set -ex -PG_VER=$(yq eval '.dependencies[] | select(.name=="prometheus-pushgateway") | .version' Chart.yaml) +#PG_VER=$(yq eval '.dependencies[] | select(.name=="prometheus-pushgateway") | .version' Chart.yaml) -helm repo update +helm dep update VERSION=$(yq eval '.dependencies[] | select(.name=="kube-prometheus-stack") | .version' Chart.yaml) rm -rf charts/kube-prometheus-stack helm pull prometheus-community/kube-prometheus-stack --untar --untardir charts --version $VERSION -rm -rf charts/prometheus-pushgateway -helm pull prometheus-community/prometheus-pushgateway --untar --untardir charts --version $PG_VER +#rm -rf charts/prometheus-pushgateway +#helm pull prometheus-community/prometheus-pushgateway --untar --untardir charts --version $PG_VER # workaround for https://github.com/prometheus-community/helm-charts/issues/1500 patch -p0 -i zdt.patch --no-backup-if-mismatch -patch -p0 -i zdt-pushgateway.patch --no-backup-if-mismatch +#patch -p0 -i zdt-pushgateway.patch --no-backup-if-mismatch # Create ZDT dashboard, alerts etc configmaps cd jsonnet && make diff --git a/charts/kubezero/values.yaml b/charts/kubezero/values.yaml index bb31830e..330955a5 100644 --- a/charts/kubezero/values.yaml +++ b/charts/kubezero/values.yaml @@ -66,7 +66,7 @@ istio-private-ingress: metrics: enabled: false namespace: monitoring - targetRevision: 0.8.7 + targetRevision: 0.8.8 istio: grafana: {} prometheus: {}