observability/prometheus/values.yaml

# ARO-HCP kube-prometheus-stack overrides, review upstream values.yaml for more options.
## Provide a name to substitute for the full names of resources
##
fullnameOverride: "prometheus"
## Install Prometheus Operator CRDs
##
crds:
  enabled: true
  ## The CRD upgrade job mitigates the limitation of helm not being able to upgrade CRDs.
  ## The job will apply the CRDs to the cluster before the operator is deployed, using helm hooks.
  ## It deploy a corresponding clusterrole, clusterrolebinding and serviceaccount to apply the CRDs.
  ## This feature is in preview, off by default and may change in the future.
  upgradeJob:
    enabled: false
    forceConflicts: false
    image:
      busybox:
        registry: docker.io
        repository: busybox
        tag: "latest"
        sha: ""
        pullPolicy: IfNotPresent
      kubectl:
        registry: registry.k8s.io
        repository: kubectl
        tag: "" # defaults to the Kubernetes version
        sha: ""
        pullPolicy: IfNotPresent
global:
  rbac:
    create: true
## Configuration for alertmanager
## ref: https://prometheus.io/docs/alerting/alertmanager/
##
alertmanager:
  enabled: false # Disabled for now.
grafana:
  enabled: false
# Azure Managed Prometheus will scrape or expose these metrics
coreDns:
  enabled: false
kubeDns:
  enabled: false
nodeExporter:
  enabled: false
kubeEtcd:
  enabled: false
kubeScheduler:
  enabled: false
kubeControllerManager:
  enabled: false
kubeProxy:
  enabled: false
kubelet:
  enabled: false
kubeApiServer:
  enabled: false
kubeStateMetrics:
  enabled: false
prometheusOperator:
  enabled: true
  ## Use '{{ template "kube-prometheus-stack.fullname" . }}-operator' by default
  fullnameOverride: ""
  ## Define Log Format
  # Use logfmt (default) or json logging
  # logFormat: logfmt

  ## Decrease log verbosity to errors only
  # logLevel: info

  ## Prometheus-operator image
  ##
  image:
    registry: mcr.microsoft.com/oss/v2
    repository: prometheus/prometheus-operator
  ## Prometheus-config-reloader
  ##
  prometheusConfigReloader:
    image:
      registry: mcr.microsoft.com/oss/v2
      repository: prometheus/prometheus-config-reloader
    # resource config for prometheusConfigReloader
    resources: {}
    # requests:
    #   cpu: 200m
    #   memory: 50Mi
    # limits:
    #   cpu: 200m
    #   memory: 50Mi
  affinity:
    nodeAffinity:
      requiredDuringSchedulingIgnoredDuringExecution:
        nodeSelectorTerms:
        - matchExpressions:
          - key: infra
            operator: In
            values:
            - "true"
  tolerations:
  - key: "infra"
    operator: "Equal"
    value: "true"
    effect: "NoSchedule"
## Deploy a Prometheus instance
##
prometheus:
  enabled: true
  ## Service account for Prometheuses to use.
  ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/
  ##
  serviceAccount:
    create: true
    name: "prometheus"
    annotations:
      azure.workload.identity/client-id: ""
    automountServiceAccountToken: true
  ## Configure pod disruption budgets for Prometheus
  ## ref: https://kubernetes.io/docs/tasks/run-application/configure-pdb/#specifying-a-poddisruptionbudget
  ##
  podDisruptionBudget:
    enabled: false
    minAvailable: 1
    maxUnavailable: ""
  serviceMonitor:
    ## If true, create a serviceMonitor for prometheus
    ##
    selfMonitor: true
  ## Settings affecting prometheusSpec
  ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api-reference/api.md#prometheusspec
  ##
  prometheusSpec:
    ## Image of Prometheus.
    ##
    image:
      registry: mcr.microsoft.com/azurelinux/
      repository: prometheus/prometheus
      tag: ""
      sha: ""
    ## If nil, select own namespace. Namespaces to be selected for PrometheusRules discovery.
    ruleNamespaceSelector: {}
    ## If true, a nil or {} value for prometheus.prometheusSpec.ruleSelector will cause the
    ## prometheus resource to be created with selectors based on values in the helm deployment,
    ## which will also match the PrometheusRule resources created
    ##
    ruleSelectorNilUsesHelmValues: false
    ## If true, a nil or {} value for prometheus.prometheusSpec.serviceMonitorSelector will cause the
    ## prometheus resource to be created with selectors based on values in the helm deployment,
    ## which will also match the servicemonitors created
    ##
    serviceMonitorSelectorNilUsesHelmValues: false
    ## ServiceMonitors to be selected for target discovery.
    ## If {}, select all ServiceMonitors
    ##
    serviceMonitorSelector: {}
    ## Namespaces to be selected for ServiceMonitor discovery.
    ##
    serviceMonitorNamespaceSelector: {}
    ## If true, a nil or {} value for prometheus.prometheusSpec.podMonitorSelector will cause the
    ## prometheus resource to be created with selectors based on values in the helm deployment,
    ## which will also match the podmonitors created
    ##
    podMonitorSelectorNilUsesHelmValues: false
    ## PodMonitors to be selected for target discovery.
    ## If {}, select all PodMonitors
    ##
    podMonitorSelector: {}
    ## If nil, select own namespace. Namespaces to be selected for PodMonitor discovery.
    podMonitorNamespaceSelector: {}
    ## How long to retain metrics
    ##
    retention: 1d
    ## Maximum size of metrics
    ##
    retentionSize: "45GiB"
    ## Log level for Prometheus be configured in
    ##
    logLevel: info
    ## Log format for Prometheus be configured in
    ##
    logFormat: logfmt
    ## Standard object's metadata. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#metadata
    ## Metadata Labels and Annotations gets propagated to the prometheus pods.
    ##
    podMetadata:
      labels:
        azure.workload.identity/use: "true"
    ## Pod anti-affinity can prevent the scheduler from placing Prometheus replicas on the same node.
    ## The default value "soft" means that the scheduler should *prefer* to not schedule two replica pods onto the same node but no guarantee is provided.
    ## The value "hard" means that the scheduler is *required* to not schedule two replica pods onto the same node.
    ## The value "" will disable pod anti-affinity so that no anti-affinity rules will be configured.
    podAntiAffinity: ""
    ## If anti-affinity is enabled sets the topologyKey to use for anti-affinity.
    ## This can be changed to, for example, failure-domain.beta.kubernetes.io/zone
    ##
    podAntiAffinityTopologyKey: failure-domain.beta.kubernetes.io/zone
    ## Assign custom affinity rules to the prometheus instance
    ## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/
    ##
    affinity:
      nodeAffinity:
        requiredDuringSchedulingIgnoredDuringExecution:
          nodeSelectorTerms:
          - matchExpressions:
            - key: infra
              operator: In
              values:
              - "true"
    tolerations:
    - key: "infra"
      operator: "Equal"
      value: "true"
      effect: "NoSchedule"
    topologySpreadConstraints:
    - maxSkew: 1
      topologyKey: ""
      whenUnsatisfiable: ScheduleAnyway
      labelSelector:
        matchLabels:
          app: prometheus
    ## The remote_write spec configuration for Prometheus.
    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api-reference/api.md#remotewritespec
    remoteWrite:
    - url: ""
      azureAd:
        cloud: AzurePublic
        sdk: {}
      queueConfig:
        capacity: 2500
        maxShards: 500
        minShards: 1
        maxSamplesPerSend: 2000
        batchSendDeadline: 60s
        minBackoff: 30ms
        maxBackoff: 256s
      metadataConfig:
        send: false
    ## Resource limits & requests
    ##
    resources: {}
    # requests:
    #   memory: 400Mi

    ## Prometheus StorageSpec for persistent data
    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/platform/storage.md
    ##
    storageSpec:
      volumeClaimTemplate:
        spec:
          storageClassName: managed-premium
          accessModes: ["ReadWriteOnce"]
          resources:
            requests:
              storage: 50Gi
## Setting to true produces cleaner resource names, but requires a data migration because the name of the persistent volume changes. Therefore this should only be set once on initial installation.
##
cleanPrometheusOperatorObjectNames: true
## Extra manifests to deploy as an array
extraManifests: []
# - apiVersion: v1
#   kind: ConfigMap
#   metadata:
#   labels:
#     name: prometheus-extra
#   data:
#     extra-data: "value"