feat: relase metrics update to fix new apiserver metrics in 1.20 amongst others

This commit is contained in:
Stefan Reimer 2021-07-29 13:50:16 +02:00
parent 99e5c91fc1
commit be2d903c26
54 changed files with 10038 additions and 3207 deletions

View File

@ -1,20 +0,0 @@
apiVersion: v2
name: kubezero-aws-node-termination-handler
description: Umbrella chart for all aws-node-termination-handler
type: application
version: 0.1.2
home: https://kubezero.com
icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
keywords:
- kubezero
- aws-node-termination-handler
maintainers:
- name: Quarky9
dependencies:
- name: kubezero-lib
version: ">= 0.1.3"
repository: https://zero-down-time.github.io/kubezero/
- name: aws-node-termination-handler
version: ">= 0.14.1"
repository: https://aws.github.io/eks-charts
kubeVersion: ">= 1.18.0"

View File

@ -1,48 +0,0 @@
# kubezero-aws-node-termination-handler
![Version: 0.1.2](https://img.shields.io/badge/Version-0.1.2-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square)
Umbrella chart for all aws-node-termination-handler
**Homepage:** <https://kubezero.com>
## Maintainers
| Name | Email | Url |
| ---- | ------ | --- |
| Quarky9 | | |
## Requirements
Kubernetes: `>= 1.18.0`
| Repository | Name | Version |
|------------|------|---------|
| https://aws.github.io/eks-charts | aws-node-termination-handler | >= 0.14.1 |
| https://zero-down-time.github.io/kubezero/ | kubezero-lib | >= 0.1.3 |
## Values
| Key | Type | Default | Description |
|-----|------|---------|-------------|
| aws-node-termination-handler.deleteLocalData | bool | `true` | |
| aws-node-termination-handler.enablePrometheusServer | bool | `false` | |
| aws-node-termination-handler.enableSqsTerminationDraining | bool | `true` | |
| aws-node-termination-handler.jsonLogging | bool | `true` | |
| aws-node-termination-handler.nodeSelector."node-role.kubernetes.io/master" | string | `""` | |
| aws-node-termination-handler.podMonitor.create | bool | `false` | |
| aws-node-termination-handler.podMonitor.labels.release | string | `"metrics"` | |
| aws-node-termination-handler.taintNode | bool | `true` | |
| aws-node-termination-handler.tolerations[0].effect | string | `"NoSchedule"` | |
| aws-node-termination-handler.tolerations[0].key | string | `"node-role.kubernetes.io/master"` | |
## KubeZero default configuration
- enable SQS Mode
- allow draining of localdata
- enable prometheus
## Resources
- https://github.com/aws/aws-node-termination-handler
- https://github.com/aws/eks-charts/tree/master/stable/aws-node-termination-handler

View File

@ -1,27 +0,0 @@
{{ template "chart.header" . }}
{{ template "chart.deprecationWarning" . }}
{{ template "chart.versionBadge" . }}{{ template "chart.typeBadge" . }}{{ template "chart.appVersionBadge" . }}
{{ template "chart.description" . }}
{{ template "chart.homepageLine" . }}
{{ template "chart.maintainersSection" . }}
{{ template "chart.sourcesSection" . }}
{{ template "chart.requirementsSection" . }}
{{ template "chart.valuesSection" . }}
## KubeZero default configuration
- enable SQS Mode
- allow draining of localdata
- enable prometheus
## Resources
- https://github.com/aws/aws-node-termination-handler
- https://github.com/aws/eks-charts/tree/master/stable/aws-node-termination-handler

View File

@ -1,19 +0,0 @@
aws-node-termination-handler:
enableSqsTerminationDraining: true
# queueURL: <SQS queue ARN from kube controller stack>
deleteLocalData: true
taintNode: true
enablePrometheusServer: false
podMonitor:
create: false
labels:
release: metrics
jsonLogging: true
tolerations:
- key: node-role.kubernetes.io/master
effect: NoSchedule
nodeSelector:
node-role.kubernetes.io/master: ""

View File

@ -217,7 +217,8 @@ fluent-bit:
enabled: false
image:
tag: 1.8.1
repository: public.ecr.aws/zero-downtime/fluent-bit
tag: v1.8.2-rc1
serviceMonitor:
enabled: false
@ -268,13 +269,13 @@ fluent-bit:
[INPUT]
Name tail
Path /var/log/containers/*.log
Parser cri-log
#multiline.parser cri
multiline.parser docker,cri
Tag cri.*
Skip_Long_Lines On
DB /var/log/flb_kube.db
DB.Sync Normal
DB.locking true
# Buffer_Max_Size 1M
{{- with .Values.config.input }}
Mem_Buf_Limit {{ default "4MB" .memBufLimit }}
Refresh_Interval {{ default 10 .refreshInterval }}
@ -282,10 +283,10 @@ fluent-bit:
filters: |
[FILTER]
Name lua
Match cri.*
script /fluent-bit/scripts/kubezero.lua
call reassemble_cri_logs
Name parser
Match cri.*
Parser cri-log
Key_Name log
[FILTER]
Name kubernetes
@ -314,7 +315,7 @@ fluent-bit:
Name rewrite_tag
Match cri.*
Emitter_Name kube_tag_rewriter
Rule logtag F kube.$kubernetes['namespace_name'].$kubernetes['container_name'] false
Rule $kubernetes['pod_id'] .* kube.$kubernetes['namespace_name'].$kubernetes['container_name'] false
[FILTER]
Name lua
@ -343,19 +344,6 @@ fluent-bit:
luaScripts:
kubezero.lua: |
local reassemble_state = {}
function reassemble_cri_logs(tag, timestamp, record)
local reassemble_key = tag
if record.logtag == 'P' then
reassemble_state[reassemble_key] = reassemble_state[reassemble_key] or "" .. record.log
return -1, 0, 0
end
record.log = reassemble_state[reassemble_key] or "" .. (record.log or "")
reassemble_state[reassemble_key] = nil
return 1, timestamp, record
end
function nest_k8s_ns(tag, timestamp, record)
if not record['kubernetes']['namespace_name'] then
return 0, 0, 0

View File

@ -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: 0.4.3
version: 0.4.4
home: https://kubezero.com
icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
keywords:
@ -21,7 +21,7 @@ dependencies:
# Switch back to upstream once all alerts are fixed eg. etcd gpcr
# repository: https://prometheus-community.github.io/helm-charts
- name: prometheus-adapter
version: 2.15.0
version: 2.15.2
repository: https://prometheus-community.github.io/helm-charts
condition: prometheus-adapter.enabled
- name: prometheus-pushgateway

View File

@ -6,20 +6,20 @@ annotations:
url: https://github.com/prometheus-operator/kube-prometheus
artifacthub.io/operator: "true"
apiVersion: v2
appVersion: 0.48.1
appVersion: 0.49.0
dependencies:
- condition: kubeStateMetrics.enabled
name: kube-state-metrics
repository: https://prometheus-community.github.io/helm-charts
version: 3.3.*
version: 3.4.*
- condition: nodeExporter.enabled
name: prometheus-node-exporter
repository: https://prometheus-community.github.io/helm-charts
version: 1.18.*
version: 2.0.*
- condition: grafana.enabled
name: grafana
repository: https://grafana.github.io/helm-charts
version: 6.13.*
version: 6.14.*
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
@ -47,4 +47,4 @@ sources:
- https://github.com/prometheus-community/helm-charts
- https://github.com/prometheus-operator/kube-prometheus
type: application
version: 16.13.0
version: 17.0.3

View File

@ -83,6 +83,21 @@ _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 16.x to 17.x
Version 17 upgrades prometheus-operator from 0.48.x to 0.49.x. Helm does not automatically upgrade or install new CRDs on a chart upgrade, so you have to install the CRDs manually before updating:
```console
kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.49.0/example/prometheus-operator-crd/monitoring.coreos.com_alertmanagerconfigs.yaml
kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.49.0/example/prometheus-operator-crd/monitoring.coreos.com_alertmanagers.yaml
kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.49.0/example/prometheus-operator-crd/monitoring.coreos.com_podmonitors.yaml
kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.49.0/example/prometheus-operator-crd/monitoring.coreos.com_probes.yaml
kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.49.0/example/prometheus-operator-crd/monitoring.coreos.com_prometheuses.yaml
kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.49.0/example/prometheus-operator-crd/monitoring.coreos.com_prometheusrules.yaml
kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.49.0/example/prometheus-operator-crd/monitoring.coreos.com_servicemonitors.yaml
kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.49.0/example/prometheus-operator-crd/monitoring.coreos.com_thanosrulers.yaml
```
### From 15.x to 16.x
Version 16 upgrades kube-state-metrics to v2.0.0. This includes changed command-line arguments and removed metrics, see this [blog post](https://kubernetes.io/blog/2021/04/13/kube-state-metrics-v-2-0/). This version also removes Grafana dashboards that supported Kubernetes 1.14 or earlier.

View File

@ -1,5 +1,5 @@
apiVersion: v2
appVersion: 8.0.3
appVersion: 8.0.5
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: 6.13.5
version: 6.14.1

View File

@ -175,6 +175,7 @@ This version requires Helm >= 3.1.0.
| `admin.existingSecret` | The name of an existing secret containing the admin credentials. | `""` |
| `admin.userKey` | The key in the existing admin secret containing the username. | `"admin-user"` |
| `admin.passwordKey` | The key in the existing admin secret containing the password. | `"admin-password"` |
| `serviceAccount.autoMount` | Automount the service account token in the pod| `true` |
| `serviceAccount.annotations` | ServiceAccount annotations | |
| `serviceAccount.create` | Create service account | `true` |
| `serviceAccount.name` | Service account name to use, when empty will be set to created account if `serviceAccount.create` is set else to `default` | `` |

View File

@ -4,6 +4,7 @@
schedulerName: "{{ .Values.schedulerName }}"
{{- end }}
serviceAccountName: {{ template "grafana.serviceAccountName" . }}
automountServiceAccountToken: {{ .Values.serviceAccount.autoMount }}
{{- if .Values.securityContext }}
securityContext:
{{ toYaml .Values.securityContext | indent 2 }}
@ -48,7 +49,7 @@ initContainers:
{{- end }}
imagePullPolicy: {{ .Values.downloadDashboardsImage.pullPolicy }}
command: ["/bin/sh"]
args: [ "-c", "mkdir -p /var/lib/grafana/dashboards/default && /bin/sh /etc/grafana/download_dashboards.sh" ]
args: [ "-c", "mkdir -p /var/lib/grafana/dashboards/default && /bin/sh -x /etc/grafana/download_dashboards.sh" ]
resources:
{{ toYaml .Values.downloadDashboards.resources | indent 6 }}
env:

View File

@ -45,11 +45,11 @@ spec:
{{- end }}
{{- if .Values.imageRenderer.securityContext }}
securityContext:
{{ toYaml .Values.imageRenderer.securityContext | indent 2 }}
{{- toYaml .Values.imageRenderer.securityContext | nindent 8 }}
{{- end }}
{{- if .Values.imageRenderer.hostAliases }}
hostAliases:
{{ toYaml .Values.imageRenderer.hostAliases | indent 2 }}
{{- toYaml .Values.imageRenderer.hostAliases | nindent 8 }}
{{- end }}
{{- if .Values.imageRenderer.priorityClassName }}
priorityClassName: {{ .Values.imageRenderer.priorityClassName }}

View File

@ -3,7 +3,6 @@ apiVersion: policy/v1beta1
kind: PodSecurityPolicy
metadata:
name: {{ template "grafana.fullname" . }}
namespace: {{ template "grafana.namespace" . }}
labels:
{{- include "grafana.labels" . | nindent 4 }}
annotations:

View File

@ -3,7 +3,6 @@ apiVersion: policy/v1beta1
kind: PodSecurityPolicy
metadata:
name: {{ template "grafana.fullname" . }}-test
namespace: {{ template "grafana.namespace" . }}
labels:
{{- include "grafana.labels" . | nindent 4 }}
spec:

View File

@ -19,6 +19,7 @@ serviceAccount:
nameTest:
# annotations:
# eks.amazonaws.com/role-arn: arn:aws:iam::123456789000:role/iam-role-name-here
autoMount: true
replicas: 1
@ -69,7 +70,7 @@ livenessProbe:
image:
repository: grafana/grafana
tag: 8.0.3
tag: 8.0.5
sha: ""
pullPolicy: IfNotPresent
@ -206,7 +207,7 @@ ingress:
# service:
# name: ssl-redirect
# port:
# name: service
# name: use-annotation
tls: []

View File

@ -1,5 +1,5 @@
apiVersion: v2
appVersion: 2.0.0
appVersion: 2.1.0
description: Install kube-state-metrics to generate and expose cluster-level metrics
home: https://github.com/kubernetes/kube-state-metrics/
keywords:
@ -16,4 +16,4 @@ name: kube-state-metrics
sources:
- https://github.com/kubernetes/kube-state-metrics/
type: application
version: 3.3.1
version: 3.4.1

View File

@ -2,7 +2,7 @@
prometheusScrape: true
image:
repository: k8s.gcr.io/kube-state-metrics/kube-state-metrics
tag: v2.0.0
tag: v2.1.0
pullPolicy: IfNotPresent
imagePullSecrets: []
@ -162,8 +162,8 @@ collectors:
- statefulsets
- storageclasses
- validatingwebhookconfigurations
#- verticalpodautoscalers
- volumeattachments
# - verticalpodautoscalers # not a default resource, see also: https://github.com/kubernetes/kube-state-metrics#enabling-verticalpodautoscalers
# Enabling kubeconfig will pass the --kubeconfig argument to the container
kubeconfig:

View File

@ -1,5 +1,5 @@
apiVersion: v1
appVersion: 1.1.2
apiVersion: v2
appVersion: 1.2.0
description: A Helm chart for prometheus node-exporter
home: https://github.com/prometheus/node_exporter/
keywords:
@ -14,4 +14,5 @@ maintainers:
name: prometheus-node-exporter
sources:
- https://github.com/prometheus/node_exporter/
version: 1.18.2
type: application
version: 2.0.1

View File

@ -16,11 +16,7 @@ _See [helm repo](https://helm.sh/docs/helm/helm_repo/) for command documentation
## Install Chart
```console
# Helm 3
$ helm install [RELEASE_NAME] prometheus-community/prometheus-node-exporter
# Helm 2
$ helm install --name [RELEASE_NAME] prometheus-community/prometheus-node-exporter
helm install [RELEASE_NAME] prometheus-community/prometheus-node-exporter
```
_See [configuration](#configuration) below._
@ -30,11 +26,7 @@ _See [helm install](https://helm.sh/docs/helm/helm_install/) for command documen
## Uninstall Chart
```console
# Helm 3
$ helm uninstall [RELEASE_NAME]
# Helm 2
# helm delete --purge [RELEASE_NAME]
helm uninstall [RELEASE_NAME]
```
This removes all the Kubernetes components associated with the chart and deletes the release.
@ -44,8 +36,7 @@ _See [helm uninstall](https://helm.sh/docs/helm/helm_uninstall/) for command doc
## Upgrading Chart
```console
# Helm 3 or 2
$ helm upgrade [RELEASE_NAME] [CHART] --install
helm upgrade [RELEASE_NAME] [CHART] --install
```
_See [helm upgrade](https://helm.sh/docs/helm/helm_upgrade/) for command documentation._
@ -55,9 +46,5 @@ _See [helm upgrade](https://helm.sh/docs/helm/helm_upgrade/) for command documen
See [Customizing the Chart Before Installing](https://helm.sh/docs/intro/using_helm/#customizing-the-chart-before-installing). To see all configurable options with detailed comments, visit the chart's [values.yaml](./values.yaml), or run these configuration commands:
```console
# Helm 2
$ helm inspect values prometheus-community/prometheus-node-exporter
# Helm 3
$ helm show values prometheus-community/prometheus-node-exporter
helm show values prometheus-community/prometheus-node-exporter
```

View File

@ -21,6 +21,7 @@ spec:
{{- toYaml .Values.podAnnotations | nindent 8 }}
{{- end }}
spec:
automountServiceAccountToken: false
serviceAccountName: {{ template "prometheus-node-exporter.serviceAccountName" . }}
{{- if .Values.securityContext }}
securityContext:

View File

@ -3,7 +3,7 @@
# Declare variables to be passed into your templates.
image:
repository: quay.io/prometheus/node-exporter
tag: v1.1.2
tag: v1.2.0
pullPolicy: IfNotPresent
service:

View File

@ -1,4 +1,4 @@
# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.48.1/example/prometheus-operator-crd/monitoring.coreos.com_podmonitors.yaml
# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.49.0/example/prometheus-operator-crd/monitoring.coreos.com_podmonitors.yaml
---
apiVersion: apiextensions.k8s.io/v1
@ -25,24 +25,31 @@ spec:
description: PodMonitor defines monitoring for a set of pods.
properties:
apiVersion:
description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
description: 'APIVersion defines the versioned schema of this representation
of an object. Servers should convert recognized schemas to the latest
internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
type: string
kind:
description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
description: 'Kind is a string value representing the REST resource this
object represents. Servers may infer this from the endpoint the client
submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
type: string
metadata:
type: object
spec:
description: Specification of desired Pod selection for target discovery by Prometheus.
description: Specification of desired Pod selection for target discovery
by Prometheus.
properties:
jobLabel:
description: The label to use to retrieve the job name from.
type: string
namespaceSelector:
description: Selector to select which namespaces the Endpoints objects are discovered from.
description: Selector to select which namespaces the Endpoints objects
are discovered from.
properties:
any:
description: Boolean describing whether all namespaces are selected in contrast to a list restricting them.
description: Boolean describing whether all namespaces are selected
in contrast to a list restricting them.
type: boolean
matchNames:
description: List of namespace names.
@ -53,94 +60,126 @@ spec:
podMetricsEndpoints:
description: A list of endpoints allowed as part of this PodMonitor.
items:
description: PodMetricsEndpoint defines a scrapeable endpoint of a Kubernetes Pod serving Prometheus metrics.
description: PodMetricsEndpoint defines a scrapeable endpoint of
a Kubernetes Pod serving Prometheus metrics.
properties:
basicAuth:
description: 'BasicAuth allow an endpoint to authenticate over basic authentication. More info: https://prometheus.io/docs/operating/configuration/#endpoint'
description: 'BasicAuth allow an endpoint to authenticate over
basic authentication. More info: https://prometheus.io/docs/operating/configuration/#endpoint'
properties:
password:
description: The secret in the service monitor namespace that contains the password for authentication.
description: The secret in the service monitor namespace
that contains the password for authentication.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must
be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
description: Specify whether the Secret or its key must
be defined
type: boolean
required:
- key
type: object
username:
description: The secret in the service monitor namespace that contains the username for authentication.
description: The secret in the service monitor namespace
that contains the username for authentication.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must
be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
description: Specify whether the Secret or its key must
be defined
type: boolean
required:
- key
type: object
type: object
bearerTokenSecret:
description: Secret to mount to read bearer token for scraping targets. The secret needs to be in the same namespace as the pod monitor and accessible by the Prometheus Operator.
description: Secret to mount to read bearer token for scraping
targets. The secret needs to be in the same namespace as the
pod monitor and accessible by the Prometheus Operator.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must
be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
description: Specify whether the Secret or its key must
be defined
type: boolean
required:
- key
type: object
honorLabels:
description: HonorLabels chooses the metric's labels on collisions with target labels.
description: HonorLabels chooses the metric's labels on collisions
with target labels.
type: boolean
honorTimestamps:
description: HonorTimestamps controls whether Prometheus respects the timestamps present in scraped data.
description: HonorTimestamps controls whether Prometheus respects
the timestamps present in scraped data.
type: boolean
interval:
description: Interval at which metrics should be scraped
type: string
metricRelabelings:
description: MetricRelabelConfigs to apply to samples before ingestion.
description: MetricRelabelConfigs to apply to samples before
ingestion.
items:
description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
description: 'RelabelConfig allows dynamic rewriting of the
label set, being applied to samples before ingestion. It
defines `<metric_relabel_configs>`-section of Prometheus
configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
description: Action to perform based on regex matching. Default is 'replace'
description: Action to perform based on regex matching.
Default is 'replace'
type: string
modulus:
description: Modulus to take of the hash of the source label values.
description: Modulus to take of the hash of the source
label values.
format: int64
type: integer
regex:
description: Regular expression against which the extracted value is matched. Default is '(.*)'
description: Regular expression against which the extracted
value is matched. Default is '(.*)'
type: string
replacement:
description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1'
description: Replacement value against which a regex replace
is performed if the regular expression matches. Regex
capture groups are available. Default is '$1'
type: string
separator:
description: Separator placed between concatenated source label values. default is ';'.
description: Separator placed between concatenated source
label values. default is ';'.
type: string
sourceLabels:
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
description: The source labels select values from existing
labels. Their content is concatenated using the configured
separator and matched against the configured regular
expression for the replace, keep, and drop actions.
items:
type: string
type: array
targetLabel:
description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available.
description: Label to which the resulting value is written
in a replace action. It is mandatory for replace actions.
Regex capture groups are available.
type: string
type: object
type: array
@ -155,39 +194,58 @@ spec:
description: HTTP path to scrape for metrics.
type: string
port:
description: Name of the pod port this endpoint refers to. Mutually exclusive with targetPort.
description: Name of the pod port this endpoint refers to. Mutually
exclusive with targetPort.
type: string
proxyUrl:
description: ProxyURL eg http://proxyserver:2195 Directs scrapes to proxy through this endpoint.
description: ProxyURL eg http://proxyserver:2195 Directs scrapes
to proxy through this endpoint.
type: string
relabelings:
description: 'RelabelConfigs to apply to samples before scraping. Prometheus Operator automatically adds relabelings for a few standard Kubernetes fields and replaces original scrape job name with __tmp_prometheus_job_name. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
description: 'RelabelConfigs to apply to samples before scraping.
Prometheus Operator automatically adds relabelings for a few
standard Kubernetes fields and replaces original scrape job
name with __tmp_prometheus_job_name. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
items:
description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
description: 'RelabelConfig allows dynamic rewriting of the
label set, being applied to samples before ingestion. It
defines `<metric_relabel_configs>`-section of Prometheus
configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
description: Action to perform based on regex matching. Default is 'replace'
description: Action to perform based on regex matching.
Default is 'replace'
type: string
modulus:
description: Modulus to take of the hash of the source label values.
description: Modulus to take of the hash of the source
label values.
format: int64
type: integer
regex:
description: Regular expression against which the extracted value is matched. Default is '(.*)'
description: Regular expression against which the extracted
value is matched. Default is '(.*)'
type: string
replacement:
description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1'
description: Replacement value against which a regex replace
is performed if the regular expression matches. Regex
capture groups are available. Default is '$1'
type: string
separator:
description: Separator placed between concatenated source label values. default is ';'.
description: Separator placed between concatenated source
label values. default is ';'.
type: string
sourceLabels:
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
description: The source labels select values from existing
labels. Their content is concatenated using the configured
separator and matched against the configured regular
expression for the replace, keep, and drop actions.
items:
type: string
type: array
targetLabel:
description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available.
description: Label to which the resulting value is written
in a replace action. It is mandatory for replace actions.
Regex capture groups are available.
type: string
type: object
type: array
@ -207,19 +265,24 @@ spec:
description: TLS configuration to use when scraping the endpoint.
properties:
ca:
description: Struct containing the CA cert to use for the targets.
description: Struct containing the CA cert to use for the
targets.
properties:
configMap:
description: ConfigMap containing data to use for the targets.
description: ConfigMap containing data to use for the
targets.
properties:
key:
description: The key to select.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind,
uid?'
type: string
optional:
description: Specify whether the ConfigMap or its key must be defined
description: Specify whether the ConfigMap or its
key must be defined
type: boolean
required:
- key
@ -228,32 +291,41 @@ spec:
description: Secret containing data to use for the targets.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must
be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind,
uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
description: Specify whether the Secret or its key
must be defined
type: boolean
required:
- key
type: object
type: object
cert:
description: Struct containing the client cert file for the targets.
description: Struct containing the client cert file for
the targets.
properties:
configMap:
description: ConfigMap containing data to use for the targets.
description: ConfigMap containing data to use for the
targets.
properties:
key:
description: The key to select.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind,
uid?'
type: string
optional:
description: Specify whether the ConfigMap or its key must be defined
description: Specify whether the ConfigMap or its
key must be defined
type: boolean
required:
- key
@ -262,13 +334,17 @@ spec:
description: Secret containing data to use for the targets.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must
be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind,
uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
description: Specify whether the Secret or its key
must be defined
type: boolean
required:
- key
@ -278,16 +354,20 @@ spec:
description: Disable target certificate validation.
type: boolean
keySecret:
description: Secret containing the client key file for the targets.
description: Secret containing the client key file for the
targets.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must
be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
description: Specify whether the Secret or its key must
be defined
type: boolean
required:
- key
@ -299,30 +379,42 @@ spec:
type: object
type: array
podTargetLabels:
description: PodTargetLabels transfers labels on the Kubernetes Pod onto the target.
description: PodTargetLabels transfers labels on the Kubernetes Pod
onto the target.
items:
type: string
type: array
sampleLimit:
description: SampleLimit defines per-scrape limit on number of scraped samples that will be accepted.
description: SampleLimit defines per-scrape limit on number of scraped
samples that will be accepted.
format: int64
type: integer
selector:
description: Selector to select Pod objects.
properties:
matchExpressions:
description: matchExpressions is a list of label selector requirements. The requirements are ANDed.
description: matchExpressions is a list of label selector requirements.
The requirements are ANDed.
items:
description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values.
description: A label selector requirement is a selector that
contains values, a key, and an operator that relates the key
and values.
properties:
key:
description: key is the label key that the selector applies to.
description: key is the label key that the selector applies
to.
type: string
operator:
description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist.
description: operator represents a key's relationship to
a set of values. Valid operators are In, NotIn, Exists
and DoesNotExist.
type: string
values:
description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch.
description: values is an array of string values. If the
operator is In or NotIn, the values array must be non-empty.
If the operator is Exists or DoesNotExist, the values
array must be empty. This array is replaced during a strategic
merge patch.
items:
type: string
type: array
@ -334,11 +426,16 @@ spec:
matchLabels:
additionalProperties:
type: string
description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed.
description: matchLabels is a map of {key,value} pairs. A single
{key,value} in the matchLabels map is equivalent to an element
of matchExpressions, whose key field is "key", the operator
is "In", and the values array contains only "value". The requirements
are ANDed.
type: object
type: object
targetLimit:
description: TargetLimit defines a limit on the number of scraped targets that will be accepted.
description: TargetLimit defines a limit on the number of scraped
targets that will be accepted.
format: int64
type: integer
required:

View File

@ -1,4 +1,4 @@
# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.48.1/example/prometheus-operator-crd/monitoring.coreos.com_probes.yaml
# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.49.0/example/prometheus-operator-crd/monitoring.coreos.com_probes.yaml
---
apiVersion: apiextensions.k8s.io/v1
@ -25,58 +25,76 @@ spec:
description: Probe defines monitoring for a set of static targets or ingresses.
properties:
apiVersion:
description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
description: 'APIVersion defines the versioned schema of this representation
of an object. Servers should convert recognized schemas to the latest
internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
type: string
kind:
description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
description: 'Kind is a string value representing the REST resource this
object represents. Servers may infer this from the endpoint the client
submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
type: string
metadata:
type: object
spec:
description: Specification of desired Ingress selection for target discovery by Prometheus.
description: Specification of desired Ingress selection for target discovery
by Prometheus.
properties:
basicAuth:
description: 'BasicAuth allow an endpoint to authenticate over basic authentication. More info: https://prometheus.io/docs/operating/configuration/#endpoint'
description: 'BasicAuth allow an endpoint to authenticate over basic
authentication. More info: https://prometheus.io/docs/operating/configuration/#endpoint'
properties:
password:
description: The secret in the service monitor namespace that contains the password for authentication.
description: The secret in the service monitor namespace that
contains the password for authentication.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must be
a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
description: Specify whether the Secret or its key must be
defined
type: boolean
required:
- key
type: object
username:
description: The secret in the service monitor namespace that contains the username for authentication.
description: The secret in the service monitor namespace that
contains the username for authentication.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must be
a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
description: Specify whether the Secret or its key must be
defined
type: boolean
required:
- key
type: object
type: object
bearerTokenSecret:
description: Secret to mount to read bearer token for scraping targets. The secret needs to be in the same namespace as the probe and accessible by the Prometheus Operator.
description: Secret to mount to read bearer token for scraping targets.
The secret needs to be in the same namespace as the probe and accessible
by the Prometheus Operator.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must be a
valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
@ -85,20 +103,28 @@ spec:
- key
type: object
interval:
description: Interval at which targets are probed using the configured prober. If not specified Prometheus' global scrape interval is used.
description: Interval at which targets are probed using the configured
prober. If not specified Prometheus' global scrape interval is used.
type: string
jobName:
description: The job name assigned to scraped metrics by default.
type: string
module:
description: 'The module to use for probing specifying how to probe the target. Example module configuring in the blackbox exporter: https://github.com/prometheus/blackbox_exporter/blob/master/example.yml'
description: 'The module to use for probing specifying how to probe
the target. Example module configuring in the blackbox exporter:
https://github.com/prometheus/blackbox_exporter/blob/master/example.yml'
type: string
prober:
description: Specification for the prober to use for probing targets. The prober.URL parameter is required. Targets cannot be probed if left empty.
description: Specification for the prober to use for probing targets.
The prober.URL parameter is required. Targets cannot be probed if
left empty.
properties:
path:
description: Path to collect metrics from. Defaults to `/probe`.
type: string
proxyUrl:
description: Optional ProxyURL.
type: string
scheme:
description: HTTP scheme to use for scraping. Defaults to `http`.
type: string
@ -112,16 +138,19 @@ spec:
description: Timeout for scraping metrics from the Prometheus exporter.
type: string
targets:
description: Targets defines a set of static and/or dynamically discovered targets to be probed using the prober.
description: Targets defines a set of static and/or dynamically discovered
targets to be probed using the prober.
properties:
ingress:
description: Ingress defines the set of dynamically discovered ingress objects which hosts are considered for probing.
description: Ingress defines the set of dynamically discovered
ingress objects which hosts are considered for probing.
properties:
namespaceSelector:
description: Select Ingress objects by namespace.
properties:
any:
description: Boolean describing whether all namespaces are selected in contrast to a list restricting them.
description: Boolean describing whether all namespaces
are selected in contrast to a list restricting them.
type: boolean
matchNames:
description: List of namespace names.
@ -130,33 +159,48 @@ spec:
type: array
type: object
relabelingConfigs:
description: 'RelabelConfigs to apply to samples before ingestion. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
description: 'RelabelConfigs to apply to samples before ingestion.
More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
items:
description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
description: 'RelabelConfig allows dynamic rewriting of
the label set, being applied to samples before ingestion.
It defines `<metric_relabel_configs>`-section of Prometheus
configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
description: Action to perform based on regex matching. Default is 'replace'
description: Action to perform based on regex matching.
Default is 'replace'
type: string
modulus:
description: Modulus to take of the hash of the source label values.
description: Modulus to take of the hash of the source
label values.
format: int64
type: integer
regex:
description: Regular expression against which the extracted value is matched. Default is '(.*)'
description: Regular expression against which the extracted
value is matched. Default is '(.*)'
type: string
replacement:
description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1'
description: Replacement value against which a regex
replace is performed if the regular expression matches.
Regex capture groups are available. Default is '$1'
type: string
separator:
description: Separator placed between concatenated source label values. default is ';'.
description: Separator placed between concatenated source
label values. default is ';'.
type: string
sourceLabels:
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
description: The source labels select values from existing
labels. Their content is concatenated using the configured
separator and matched against the configured regular
expression for the replace, keep, and drop actions.
items:
type: string
type: array
targetLabel:
description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available.
description: Label to which the resulting value is written
in a replace action. It is mandatory for replace actions.
Regex capture groups are available.
type: string
type: object
type: array
@ -164,18 +208,29 @@ spec:
description: Select Ingress objects by labels.
properties:
matchExpressions:
description: matchExpressions is a list of label selector requirements. The requirements are ANDed.
description: matchExpressions is a list of label selector
requirements. The requirements are ANDed.
items:
description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values.
description: A label selector requirement is a selector
that contains values, a key, and an operator that
relates the key and values.
properties:
key:
description: key is the label key that the selector applies to.
description: key is the label key that the selector
applies to.
type: string
operator:
description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist.
description: operator represents a key's relationship
to a set of values. Valid operators are In, NotIn,
Exists and DoesNotExist.
type: string
values:
description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch.
description: values is an array of string values.
If the operator is In or NotIn, the values array
must be non-empty. If the operator is Exists or
DoesNotExist, the values array must be empty.
This array is replaced during a strategic merge
patch.
items:
type: string
type: array
@ -187,51 +242,73 @@ spec:
matchLabels:
additionalProperties:
type: string
description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed.
description: matchLabels is a map of {key,value} pairs.
A single {key,value} in the matchLabels map is equivalent
to an element of matchExpressions, whose key field is
"key", the operator is "In", and the values array contains
only "value". The requirements are ANDed.
type: object
type: object
type: object
staticConfig:
description: 'StaticConfig defines static targets which are considers for probing. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#static_config.'
description: 'StaticConfig defines static targets which are considers
for probing. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#static_config.'
properties:
labels:
additionalProperties:
type: string
description: Labels assigned to all metrics scraped from the targets.
description: Labels assigned to all metrics scraped from the
targets.
type: object
relabelingConfigs:
description: 'RelabelConfigs to apply to samples before ingestion. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
description: 'RelabelConfigs to apply to samples before ingestion.
More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
items:
description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
description: 'RelabelConfig allows dynamic rewriting of
the label set, being applied to samples before ingestion.
It defines `<metric_relabel_configs>`-section of Prometheus
configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
description: Action to perform based on regex matching. Default is 'replace'
description: Action to perform based on regex matching.
Default is 'replace'
type: string
modulus:
description: Modulus to take of the hash of the source label values.
description: Modulus to take of the hash of the source
label values.
format: int64
type: integer
regex:
description: Regular expression against which the extracted value is matched. Default is '(.*)'
description: Regular expression against which the extracted
value is matched. Default is '(.*)'
type: string
replacement:
description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1'
description: Replacement value against which a regex
replace is performed if the regular expression matches.
Regex capture groups are available. Default is '$1'
type: string
separator:
description: Separator placed between concatenated source label values. default is ';'.
description: Separator placed between concatenated source
label values. default is ';'.
type: string
sourceLabels:
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
description: The source labels select values from existing
labels. Their content is concatenated using the configured
separator and matched against the configured regular
expression for the replace, keep, and drop actions.
items:
type: string
type: array
targetLabel:
description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available.
description: Label to which the resulting value is written
in a replace action. It is mandatory for replace actions.
Regex capture groups are available.
type: string
type: object
type: array
static:
description: Targets is a list of URLs to probe using the configured prober.
description: Targets is a list of URLs to probe using the
configured prober.
items:
type: string
type: array
@ -250,10 +327,12 @@ spec:
description: The key to select.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the ConfigMap or its key must be defined
description: Specify whether the ConfigMap or its key
must be defined
type: boolean
required:
- key
@ -262,13 +341,16 @@ spec:
description: Secret containing data to use for the targets.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must
be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
description: Specify whether the Secret or its key must
be defined
type: boolean
required:
- key
@ -284,10 +366,12 @@ spec:
description: The key to select.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the ConfigMap or its key must be defined
description: Specify whether the ConfigMap or its key
must be defined
type: boolean
required:
- key
@ -296,13 +380,16 @@ spec:
description: Secret containing data to use for the targets.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must
be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
description: Specify whether the Secret or its key must
be defined
type: boolean
required:
- key
@ -315,13 +402,16 @@ spec:
description: Secret containing the client key file for the targets.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must be
a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
description: Specify whether the Secret or its key must be
defined
type: boolean
required:
- key

View File

@ -1,4 +1,4 @@
# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.48.1/example/prometheus-operator-crd/monitoring.coreos.com_prometheusrules.yaml
# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.49.0/example/prometheus-operator-crd/monitoring.coreos.com_prometheusrules.yaml
---
apiVersion: apiextensions.k8s.io/v1
@ -20,13 +20,18 @@ spec:
- name: v1
schema:
openAPIV3Schema:
description: PrometheusRule defines recording and alerting rules for a Prometheus instance
description: PrometheusRule defines recording and alerting rules for a Prometheus
instance
properties:
apiVersion:
description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
description: 'APIVersion defines the versioned schema of this representation
of an object. Servers should convert recognized schemas to the latest
internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
type: string
kind:
description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
description: 'Kind is a string value representing the REST resource this
object represents. Servers may infer this from the endpoint the client
submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
type: string
metadata:
type: object
@ -36,7 +41,10 @@ spec:
groups:
description: Content of Prometheus rule file
items:
description: 'RuleGroup is a list of sequentially evaluated recording and alerting rules. Note: PartialResponseStrategy is only used by ThanosRuler and will be ignored by Prometheus instances. Valid values for this field are ''warn'' or ''abort''. More info: https://github.com/thanos-io/thanos/blob/master/docs/components/rule.md#partial-response'
description: 'RuleGroup is a list of sequentially evaluated recording
and alerting rules. Note: PartialResponseStrategy is only used
by ThanosRuler and will be ignored by Prometheus instances. Valid
values for this field are ''warn'' or ''abort''. More info: https://github.com/thanos-io/thanos/blob/master/docs/components/rule.md#partial-response'
properties:
interval:
type: string
@ -46,7 +54,10 @@ spec:
type: string
rules:
items:
description: Rule describes an alerting or recording rule.
description: 'Rule describes an alerting or recording rule
See Prometheus documentation: [alerting](https://www.prometheus.io/docs/prometheus/latest/configuration/alerting_rules/)
or [recording](https://www.prometheus.io/docs/prometheus/latest/configuration/recording_rules/#recording-rules)
rule'
properties:
alert:
type: string

View File

@ -1,4 +1,4 @@
# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.48.1/example/prometheus-operator-crd/monitoring.coreos.com_servicemonitors.yaml
# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.49.0/example/prometheus-operator-crd/monitoring.coreos.com_servicemonitors.yaml
---
apiVersion: apiextensions.k8s.io/v1
@ -25,50 +25,65 @@ spec:
description: ServiceMonitor defines monitoring for a set of services.
properties:
apiVersion:
description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
description: 'APIVersion defines the versioned schema of this representation
of an object. Servers should convert recognized schemas to the latest
internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
type: string
kind:
description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
description: 'Kind is a string value representing the REST resource this
object represents. Servers may infer this from the endpoint the client
submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
type: string
metadata:
type: object
spec:
description: Specification of desired Service selection for target discovery by Prometheus.
description: Specification of desired Service selection for target discovery
by Prometheus.
properties:
endpoints:
description: A list of endpoints allowed as part of this ServiceMonitor.
items:
description: Endpoint defines a scrapeable endpoint serving Prometheus metrics.
description: Endpoint defines a scrapeable endpoint serving Prometheus
metrics.
properties:
basicAuth:
description: 'BasicAuth allow an endpoint to authenticate over basic authentication More info: https://prometheus.io/docs/operating/configuration/#endpoints'
description: 'BasicAuth allow an endpoint to authenticate over
basic authentication More info: https://prometheus.io/docs/operating/configuration/#endpoints'
properties:
password:
description: The secret in the service monitor namespace that contains the password for authentication.
description: The secret in the service monitor namespace
that contains the password for authentication.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must
be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
description: Specify whether the Secret or its key must
be defined
type: boolean
required:
- key
type: object
username:
description: The secret in the service monitor namespace that contains the username for authentication.
description: The secret in the service monitor namespace
that contains the username for authentication.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must
be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
description: Specify whether the Secret or its key must
be defined
type: boolean
required:
- key
@ -78,57 +93,79 @@ spec:
description: File to read bearer token for scraping targets.
type: string
bearerTokenSecret:
description: Secret to mount to read bearer token for scraping targets. The secret needs to be in the same namespace as the service monitor and accessible by the Prometheus Operator.
description: Secret to mount to read bearer token for scraping
targets. The secret needs to be in the same namespace as the
service monitor and accessible by the Prometheus Operator.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must
be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
description: Specify whether the Secret or its key must
be defined
type: boolean
required:
- key
type: object
honorLabels:
description: HonorLabels chooses the metric's labels on collisions with target labels.
description: HonorLabels chooses the metric's labels on collisions
with target labels.
type: boolean
honorTimestamps:
description: HonorTimestamps controls whether Prometheus respects the timestamps present in scraped data.
description: HonorTimestamps controls whether Prometheus respects
the timestamps present in scraped data.
type: boolean
interval:
description: Interval at which metrics should be scraped
type: string
metricRelabelings:
description: MetricRelabelConfigs to apply to samples before ingestion.
description: MetricRelabelConfigs to apply to samples before
ingestion.
items:
description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
description: 'RelabelConfig allows dynamic rewriting of the
label set, being applied to samples before ingestion. It
defines `<metric_relabel_configs>`-section of Prometheus
configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
description: Action to perform based on regex matching. Default is 'replace'
description: Action to perform based on regex matching.
Default is 'replace'
type: string
modulus:
description: Modulus to take of the hash of the source label values.
description: Modulus to take of the hash of the source
label values.
format: int64
type: integer
regex:
description: Regular expression against which the extracted value is matched. Default is '(.*)'
description: Regular expression against which the extracted
value is matched. Default is '(.*)'
type: string
replacement:
description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1'
description: Replacement value against which a regex replace
is performed if the regular expression matches. Regex
capture groups are available. Default is '$1'
type: string
separator:
description: Separator placed between concatenated source label values. default is ';'.
description: Separator placed between concatenated source
label values. default is ';'.
type: string
sourceLabels:
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
description: The source labels select values from existing
labels. Their content is concatenated using the configured
separator and matched against the configured regular
expression for the replace, keep, and drop actions.
items:
type: string
type: array
targetLabel:
description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available.
description: Label to which the resulting value is written
in a replace action. It is mandatory for replace actions.
Regex capture groups are available.
type: string
type: object
type: array
@ -143,39 +180,58 @@ spec:
description: HTTP path to scrape for metrics.
type: string
port:
description: Name of the service port this endpoint refers to. Mutually exclusive with targetPort.
description: Name of the service port this endpoint refers to.
Mutually exclusive with targetPort.
type: string
proxyUrl:
description: ProxyURL eg http://proxyserver:2195 Directs scrapes to proxy through this endpoint.
description: ProxyURL eg http://proxyserver:2195 Directs scrapes
to proxy through this endpoint.
type: string
relabelings:
description: 'RelabelConfigs to apply to samples before scraping. Prometheus Operator automatically adds relabelings for a few standard Kubernetes fields and replaces original scrape job name with __tmp_prometheus_job_name. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
description: 'RelabelConfigs to apply to samples before scraping.
Prometheus Operator automatically adds relabelings for a few
standard Kubernetes fields and replaces original scrape job
name with __tmp_prometheus_job_name. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
items:
description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
description: 'RelabelConfig allows dynamic rewriting of the
label set, being applied to samples before ingestion. It
defines `<metric_relabel_configs>`-section of Prometheus
configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
description: Action to perform based on regex matching. Default is 'replace'
description: Action to perform based on regex matching.
Default is 'replace'
type: string
modulus:
description: Modulus to take of the hash of the source label values.
description: Modulus to take of the hash of the source
label values.
format: int64
type: integer
regex:
description: Regular expression against which the extracted value is matched. Default is '(.*)'
description: Regular expression against which the extracted
value is matched. Default is '(.*)'
type: string
replacement:
description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1'
description: Replacement value against which a regex replace
is performed if the regular expression matches. Regex
capture groups are available. Default is '$1'
type: string
separator:
description: Separator placed between concatenated source label values. default is ';'.
description: Separator placed between concatenated source
label values. default is ';'.
type: string
sourceLabels:
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
description: The source labels select values from existing
labels. Their content is concatenated using the configured
separator and matched against the configured regular
expression for the replace, keep, and drop actions.
items:
type: string
type: array
targetLabel:
description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available.
description: Label to which the resulting value is written
in a replace action. It is mandatory for replace actions.
Regex capture groups are available.
type: string
type: object
type: array
@ -189,25 +245,32 @@ spec:
anyOf:
- type: integer
- type: string
description: Name or number of the target port of the Pod behind the Service, the port must be specified with container port property. Mutually exclusive with port.
description: Name or number of the target port of the Pod behind
the Service, the port must be specified with container port
property. Mutually exclusive with port.
x-kubernetes-int-or-string: true
tlsConfig:
description: TLS configuration to use when scraping the endpoint
properties:
ca:
description: Struct containing the CA cert to use for the targets.
description: Struct containing the CA cert to use for the
targets.
properties:
configMap:
description: ConfigMap containing data to use for the targets.
description: ConfigMap containing data to use for the
targets.
properties:
key:
description: The key to select.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind,
uid?'
type: string
optional:
description: Specify whether the ConfigMap or its key must be defined
description: Specify whether the ConfigMap or its
key must be defined
type: boolean
required:
- key
@ -216,35 +279,45 @@ spec:
description: Secret containing data to use for the targets.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must
be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind,
uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
description: Specify whether the Secret or its key
must be defined
type: boolean
required:
- key
type: object
type: object
caFile:
description: Path to the CA cert in the Prometheus container to use for the targets.
description: Path to the CA cert in the Prometheus container
to use for the targets.
type: string
cert:
description: Struct containing the client cert file for the targets.
description: Struct containing the client cert file for
the targets.
properties:
configMap:
description: ConfigMap containing data to use for the targets.
description: ConfigMap containing data to use for the
targets.
properties:
key:
description: The key to select.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind,
uid?'
type: string
optional:
description: Specify whether the ConfigMap or its key must be defined
description: Specify whether the ConfigMap or its
key must be defined
type: boolean
required:
- key
@ -253,38 +326,48 @@ spec:
description: Secret containing data to use for the targets.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must
be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind,
uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
description: Specify whether the Secret or its key
must be defined
type: boolean
required:
- key
type: object
type: object
certFile:
description: Path to the client cert file in the Prometheus container for the targets.
description: Path to the client cert file in the Prometheus
container for the targets.
type: string
insecureSkipVerify:
description: Disable target certificate validation.
type: boolean
keyFile:
description: Path to the client key file in the Prometheus container for the targets.
description: Path to the client key file in the Prometheus
container for the targets.
type: string
keySecret:
description: Secret containing the client key file for the targets.
description: Secret containing the client key file for the
targets.
properties:
key:
description: The key of the secret to select from. Must be a valid secret key.
description: The key of the secret to select from. Must
be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must be defined
description: Specify whether the Secret or its key must
be defined
type: boolean
required:
- key
@ -296,13 +379,18 @@ spec:
type: object
type: array
jobLabel:
description: The label to use to retrieve the job name from.
description: "Chooses the label of the Kubernetes `Endpoints`. Its
value will be used for the `job`-label's value of the created metrics.
\n Default & fallback value: the name of the respective Kubernetes
`Endpoint`."
type: string
namespaceSelector:
description: Selector to select which namespaces the Endpoints objects are discovered from.
description: Selector to select which namespaces the Kubernetes Endpoints
objects are discovered from.
properties:
any:
description: Boolean describing whether all namespaces are selected in contrast to a list restricting them.
description: Boolean describing whether all namespaces are selected
in contrast to a list restricting them.
type: boolean
matchNames:
description: List of namespace names.
@ -311,30 +399,42 @@ spec:
type: array
type: object
podTargetLabels:
description: PodTargetLabels transfers labels on the Kubernetes Pod onto the target.
description: PodTargetLabels transfers labels on the Kubernetes `Pod`
onto the created metrics.
items:
type: string
type: array
sampleLimit:
description: SampleLimit defines per-scrape limit on number of scraped samples that will be accepted.
description: SampleLimit defines per-scrape limit on number of scraped
samples that will be accepted.
format: int64
type: integer
selector:
description: Selector to select Endpoints objects.
properties:
matchExpressions:
description: matchExpressions is a list of label selector requirements. The requirements are ANDed.
description: matchExpressions is a list of label selector requirements.
The requirements are ANDed.
items:
description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values.
description: A label selector requirement is a selector that
contains values, a key, and an operator that relates the key
and values.
properties:
key:
description: key is the label key that the selector applies to.
description: key is the label key that the selector applies
to.
type: string
operator:
description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist.
description: operator represents a key's relationship to
a set of values. Valid operators are In, NotIn, Exists
and DoesNotExist.
type: string
values:
description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch.
description: values is an array of string values. If the
operator is In or NotIn, the values array must be non-empty.
If the operator is Exists or DoesNotExist, the values
array must be empty. This array is replaced during a strategic
merge patch.
items:
type: string
type: array
@ -346,16 +446,23 @@ spec:
matchLabels:
additionalProperties:
type: string
description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed.
description: matchLabels is a map of {key,value} pairs. A single
{key,value} in the matchLabels map is equivalent to an element
of matchExpressions, whose key field is "key", the operator
is "In", and the values array contains only "value". The requirements
are ANDed.
type: object
type: object
targetLabels:
description: TargetLabels transfers labels on the Kubernetes Service onto the target.
description: TargetLabels transfers labels from the Kubernetes `Service`
onto the created metrics. All labels set in `selector.matchLabels`
are automatically transferred.
items:
type: string
type: array
targetLimit:
description: TargetLimit defines a limit on the number of scraped targets that will be accepted.
description: TargetLimit defines a limit on the number of scraped
targets that will be accepted.
format: int64
type: integer
required:

View File

@ -2149,7 +2149,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -2235,7 +2235,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -2333,7 +2333,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -2419,7 +2419,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,

View File

@ -706,7 +706,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
"expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -715,7 +715,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
"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,
@ -724,7 +724,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
"expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -733,7 +733,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
"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,
@ -1171,7 +1171,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
"expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -1180,7 +1180,7 @@ data:
"step": 10
},
{
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
"expr": "sum(container_memory_working_set_bytes{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,
@ -1189,7 +1189,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
"expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -1198,7 +1198,7 @@ data:
"step": 10
},
{
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}) by (pod)",
"expr": "sum(container_memory_working_set_bytes{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,
@ -1842,7 +1842,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -1928,7 +1928,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -2026,7 +2026,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -2112,7 +2112,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,

View File

@ -321,7 +321,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"}) by (pod)",
"expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -330,7 +330,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"}) by (pod)",
"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,
@ -339,7 +339,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"}) by (pod)",
"expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -348,7 +348,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"}) by (pod)",
"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,
@ -749,7 +749,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\", resource=\"memory\"}) by (pod)",
"expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -758,7 +758,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\", resource=\"memory\"}) by (pod)",
"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,
@ -767,7 +767,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\", resource=\"memory\"}) by (pod)",
"expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -776,7 +776,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\", resource=\"memory\"}) by (pod)",
"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,

View File

@ -459,7 +459,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}) by (container)",
"expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -468,7 +468,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}) by (container)",
"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,
@ -477,7 +477,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}) by (container)",
"expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -486,7 +486,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}) by (container)",
"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,
@ -922,7 +922,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}) by (container)",
"expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -931,7 +931,7 @@ data:
"step": 10
},
{
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", image!=\"\"}) by (container) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}) by (container)",
"expr": "sum(container_memory_working_set_bytes{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,
@ -940,7 +940,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}) by (container)",
"expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -949,7 +949,7 @@ data:
"step": 10
},
{
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}) by (container)",
"expr": "sum(container_memory_working_set_bytes{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,
@ -1294,7 +1294,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -1381,7 +1381,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -1480,7 +1480,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -1567,7 +1567,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,

View File

@ -1520,7 +1520,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -1606,7 +1606,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -1704,7 +1704,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -1790,7 +1790,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,

View File

@ -1707,7 +1707,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -1793,7 +1793,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -1891,7 +1891,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -1977,7 +1977,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,

View File

@ -573,6 +573,14 @@ data:
"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",

View File

@ -55,6 +55,12 @@ spec:
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) (
(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) (
@ -66,6 +72,12 @@ spec:
)
)
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) (
(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) (
@ -77,6 +89,12 @@ spec:
)
)
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) (
(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) (
@ -88,6 +106,12 @@ spec:
)
)
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) (
(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) (

View File

@ -25,6 +25,16 @@ spec:
- 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: |-
1 - (
(
@ -39,14 +49,14 @@ spec:
-
(
(
sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope=~"resource|",le="0.1"}[30d]))
sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope=~"resource|",le="1"}[30d]))
or
vector(0)
)
+
sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope="namespace",le="0.5"}[30d]))
sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope="namespace",le="5"}[30d]))
+
sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope="cluster",le="5"}[30d]))
sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope="cluster",le="40"}[30d]))
)
) +
# errors
@ -64,14 +74,14 @@ spec:
(
# too slow
(
sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[30d]))
sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="1"}[30d]))
or
vector(0)
)
+
sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[30d]))
sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="5"}[30d]))
+
sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[30d]))
sum by (cluster) (increase(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="40"}[30d]))
)
+
# errors
@ -99,62 +109,20 @@ spec:
labels:
verb: write
record: apiserver_request:availability30d
- 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, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"2.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"2.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"2.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"2.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"2.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="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",code=~"3.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"3.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"3.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"3.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"3.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="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",code=~"4.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"4.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"4.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"4.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"4.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="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",code=~"5.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"5.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"5.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"5.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"5.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"5.."}[1h]))
record: code_verb:apiserver_request_total:increase1h
- expr: sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~"LIST|GET"})
- expr: sum by (cluster,code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m]))
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"})
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:apiserver_request_total:increase30d
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 }}

View File

@ -0,0 +1,328 @@
{{- /*
Generated from 'kube-apiserver-burnrate.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-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 }}
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_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[1d]))
-
(
(
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="1"}[1d]))
or
vector(0)
)
+
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="5"}[1d]))
+
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="40"}[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_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[1h]))
-
(
(
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="1"}[1h]))
or
vector(0)
)
+
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="5"}[1h]))
+
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="40"}[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_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[2h]))
-
(
(
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="1"}[2h]))
or
vector(0)
)
+
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="5"}[2h]))
+
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="40"}[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_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[30m]))
-
(
(
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="1"}[30m]))
or
vector(0)
)
+
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="5"}[30m]))
+
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="40"}[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_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[3d]))
-
(
(
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="1"}[3d]))
or
vector(0)
)
+
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="5"}[3d]))
+
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="40"}[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_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[5m]))
-
(
(
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="1"}[5m]))
or
vector(0)
)
+
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="5"}[5m]))
+
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="40"}[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_duration_seconds_count{job="apiserver",verb=~"LIST|GET"}[6h]))
-
(
(
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope=~"resource|",le="1"}[6h]))
or
vector(0)
)
+
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="namespace",le="5"}[6h]))
+
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",scope="cluster",le="40"}[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_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d]))
-
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",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_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h]))
-
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",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_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h]))
-
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",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_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m]))
-
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",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_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d]))
-
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",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_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
-
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",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_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h]))
-
sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",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 }}

View File

@ -0,0 +1,49 @@
{{- /*
Generated from 'kube-apiserver-histogram.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-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 }}
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_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET"}[5m]))) > 0
labels:
quantile: '0.99'
verb: read
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
- expr: histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))) > 0
labels:
quantile: '0.99'
verb: write
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
- expr: histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod))
labels:
quantile: '0.99'
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
- expr: histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod))
labels:
quantile: '0.9'
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
- expr: histogram_quantile(0.5, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod))
labels:
quantile: '0.5'
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
{{- end }}

View File

@ -33,7 +33,7 @@ spec:
expr: |-
increase(kube_pod_container_status_restarts_total{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}[10m]) > 0
and
sum without (phase) (kube_pod_status_phase{phase!="Running",job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} == 1)
kube_pod_container_status_waiting{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"} == 1
for: 15m
labels:
severity: warning

View File

@ -57,6 +57,7 @@ spec:
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- if semverCompare ">=1.18.0-0" $kubeTargetVersion }}
- alert: AggregatedAPIDown
annotations:
description: An aggregated API {{`{{`}} $labels.name {{`}}`}}/{{`{{`}} $labels.namespace {{`}}`}} has been only {{`{{`}} $value | humanize {{`}}`}}% available over the last 10m.
@ -69,6 +70,7 @@ spec:
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if .Values.kubeApiServer.enabled }}
- alert: KubeAPIDown
annotations:

View File

@ -274,5 +274,35 @@ spec:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
- alert: NodeFileDescriptorLimit
annotations:
description: File descriptors limit at {{`{{`}} $labels.instance {{`}}`}} is currently at {{`{{`}} printf "%.2f" $value {{`}}`}}%.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-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 }}
- alert: NodeFileDescriptorLimit
annotations:
description: File descriptors limit at {{`{{`}} $labels.instance {{`}}`}} is currently at {{`{{`}} printf "%.2f" $value {{`}}`}}%.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-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 }}

View File

@ -26,8 +26,9 @@ spec:
rules:
- alert: NodeNetworkInterfaceFlapping
annotations:
message: Network interface "{{`{{`}} $labels.device {{`}}`}}" changing it's up status often on node-exporter {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}}
description: Network interface "{{`{{`}} $labels.device {{`}}`}}" changing it's up status often on node-exporter {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}}
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodenetworkinterfaceflapping
summary: Network interface is often changin it's status
expr: changes(node_network_up{job="node-exporter",device!~"veth.+"}[2m]) > 2
for: 2m
labels:

View File

@ -15,6 +15,15 @@ metadata:
{{- end }}
spec:
type: {{ .Values.prometheus.thanosServiceExternal.type }}
{{- if .Values.prometheus.thanosServiceExternal.loadBalancerIP }}
loadBalancerIP: {{ .Values.prometheus.thanosServiceExternal.loadBalancerIP }}
{{- end }}
{{- if .Values.prometheus.thanosServiceExternal.loadBalancerSourceRanges }}
loadBalancerSourceRanges:
{{- range $cidr := .Values.prometheus.thanosServiceExternal.loadBalancerSourceRanges }}
- {{ $cidr }}
{{- end }}
{{- end }}
ports:
- name: {{ .Values.prometheus.thanosServiceExternal.portName }}
port: {{ .Values.prometheus.thanosServiceExternal.port }}

View File

@ -1562,7 +1562,7 @@ prometheusOperator:
##
image:
repository: quay.io/prometheus-operator/prometheus-operator
tag: v0.48.1
tag: v0.49.0
sha: ""
pullPolicy: IfNotPresent
@ -1578,7 +1578,7 @@ prometheusOperator:
##
prometheusConfigReloaderImage:
repository: quay.io/prometheus-operator/prometheus-config-reloader
tag: v0.48.1
tag: v0.49.0
sha: ""
## Set the prometheus config reloader side-car CPU limit
@ -1649,6 +1649,8 @@ prometheus:
portName: grpc
port: 10901
targetPort: "grpc"
loadBalancerIP: ""
loadBalancerSourceRanges: []
## Service type
##
@ -1928,7 +1930,7 @@ prometheus:
##
image:
repository: quay.io/prometheus/prometheus
tag: v2.27.1
tag: v2.28.1
sha: ""
## Tolerations for use with node taints

View File

@ -18,7 +18,7 @@
"subdir": "grafana-builder"
}
},
"version": "2a6bdb7df17539b27869bab8b04eab0cc69a7abb",
"version": "8df6a4ff1623781260c3236761c2ebe837958b3f",
"sum": "GRf2GvwEU4jhXV+JOonXSZ4wdDv8mnHBPCQ6TUVd+g8="
},
{
@ -28,8 +28,8 @@
"subdir": ""
}
},
"version": "50dddcc2aecf074c7f7fab92caa87a806e5040fa",
"sum": "H4TcGWDVaNF51ZaGpJwm9rVympjpTtSjl4UCYI8q1LU="
"version": "25b5047a57352345e478b215370dfcd1fecee27d",
"sum": "z+ksn3PAtR/fYtxgsrrG4euIriyiefZsTUcJaVXdG1Q="
}
],
"legacyImports": false

View File

@ -1,6 +1,6 @@
#!/bin/bash
VERSION=16.13.0
VERSION=17.0.3
PG_VER=1.10.1
rm -rf charts/kube-prometheus-stack

View File

@ -18,18 +18,6 @@ diff -tubr charts/kube-prometheus-stack/charts/grafana/templates/_pod.tpl charts
{{- end}}
- name: {{ .Chart.Name }}
{{- if .Values.image.sha }}
diff -tubr charts/kube-prometheus-stack/charts/kube-state-metrics/values.yaml charts/kube-prometheus-stack.zdt/charts/kube-state-metrics/values.yaml
--- charts/kube-prometheus-stack/charts/kube-state-metrics/values.yaml 2021-06-26 19:54:57.000000000 +0200
+++ charts/kube-prometheus-stack.zdt/charts/kube-state-metrics/values.yaml 2021-07-01 13:33:01.713947294 +0200
@@ -162,7 +162,7 @@
- statefulsets
- storageclasses
- validatingwebhookconfigurations
- - verticalpodautoscalers
+ #- verticalpodautoscalers
- volumeattachments
# Enabling kubeconfig will pass the --kubeconfig argument to the container
diff -tubr charts/kube-prometheus-stack/templates/prometheus/rules-1.14/etcd.yaml charts/kube-prometheus-stack.zdt/templates/prometheus/rules-1.14/etcd.yaml
--- charts/kube-prometheus-stack/templates/prometheus/rules-1.14/etcd.yaml 2021-06-26 19:54:57.000000000 +0200
+++ charts/kube-prometheus-stack.zdt/templates/prometheus/rules-1.14/etcd.yaml 2021-07-01 13:31:20.750609396 +0200

View File

@ -1,5 +1,5 @@
{{- if .Values.rabbitmq.auth.tls.enabled }}
apiVersion: cert-manager.io/v1alpha2
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: rabbitmq-server-certificate

View File

@ -2,7 +2,7 @@ apiVersion: v2
name: kubezero-redis
description: KubeZero Umbrella Chart for Redis HA
type: application
version: 0.2.2
version: 0.3.0
home: https://kubezero.com
icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
keywords:
@ -19,7 +19,7 @@ dependencies:
repository: https://charts.bitnami.com/bitnami
condition: redis.enabled
- name: redis-cluster
version: 4.1.0
version: 6.2.7
repository: https://charts.bitnami.com/bitnami
condition: redis-cluster.enabled

View File

@ -20,8 +20,6 @@ redis:
enabled: false
serviceMonitor:
enabled: false
selector:
release: metrics
# extraArgs:
# redis.addr: "redis://localhost:6379"
@ -40,8 +38,6 @@ redis-cluster:
enabled: false
serviceMonitor:
enabled: false
selector:
release: metrics
persistence:
enabled: false

View File

@ -1,5 +1,5 @@
#!/bin/bash
set -eu
set -eux
CHARTS=${1:-'.*'}
FORCE=${2:-''}

21
scripts/upgrade_cert-manager.sh Executable file
View File

@ -0,0 +1,21 @@
#!/bin/bash
kubectl get -o yaml \
--all-namespaces \
issuer,clusterissuer,certificates,certificaterequests > cert-manager-backup.yaml
kubectl cert-manager convert --output-version cert-manager.io/v1 -f cert-manager-backup.yaml > cert-manager-v1.yaml
./bootstrap.sh delete cert-manager $1
kubectl delete crd certificaterequests.cert-manager.io
kubectl delete crd certificates.cert-manager.io
kubectl delete crd challenges.acme.cert-manager.io
kubectl delete crd clusterissuers.cert-manager.io
kubectl delete crd issuers.cert-manager.io
kubectl delete crd orders.acme.cert-manager.io
./bootstrap.sh crds cert-manager $1
./bootstrap.sh deploy cert-manager $1
kubectl apply -f cert-manager-v1.yaml