kube-prometheus-stack-values

values.yaml

# make sure to update your slack hook and apply 

prometheusOperator:
  enabled: true
prometheus:
  enabled: true
  server:
    statefulSet:
      enabled: true
    extraFlags:
    - web.enable-lifecycle
    - storage.tsdb.wal-compression
  prometheusSpec:
    serviceMonitorSelectorNilUsesHelmValues: false #true
    serviceMonitorSelector: {}
    serviceMonitorNamespaceSelector: {}
    storageSpec:
      volumeClaimTemplate:
        spec:
          storageClassName: csi-gce-pd
          accessModes: ["ReadWriteOnce"]
          resources:
            requests:
              storage: 50Gi
    replicas: 1
    retention: 30d
    #additionalScrapeConfigs:
    #  - job_name: mysql
    #    static_configs:
    #      - targets:
    #          - mysql-exporter-prometheus-mysql-exporter:9104


grafana:
  enabled: true
  assertNoLeakedSecrets: false
  defaultDashboardsEditable: true
  defaultDashboardsEnabled: true
  grafana.ini:
    unified_alerting:
      enabled: true
    alerting:
      enabled: false
    server:
      protocol: http
      root_url: '%(protocol)s://%(domain)s'
    force_migration: true
    database:
      host: "10.98.0.3:5432"
      user: grafana
      password: "M8iDvLNSW7Q6PTn2SP8iMNYCkWAzXNCA"
      name: grafana
      type: postgres

  dashboardProviders:
    dashboardproviders.yaml:
      apiVersion: 1
      providers:
        - name: kubernetes
          orgId: 1
          folder:
          type: file
          disableDeletion: true
          editable: true
          options:
            path: /var/lib/grafana/dashboards/default
        - name: imported
          orgId: 1
          folder: imported
          type: file
          disableDeletion: true
          editable: true
          options:
            path: /var/lib/grafana/dashboards/imported

  dashboards:
    imported:
      Logs:
        gnetId: 13639
        revision: 2
        datasource: Loki
      Node-Full-Exporter:
        gnetId: 1860
        revision: 37
        datasource: Prometheus
  sidecar:
    dashboards:
      enabled: true
      label: grafana_dashboard
      labelValue: "1"
      searchNamespace: ALL
      annotations: {}
      multicluster:
        global:
          enabled: false
        etcd:
          enabled: false
      provider:
        allowUiUpdates: false
    datasources:
      enabled: true
      defaultDatasourceEnabled: true
      isDefaultDatasource: true
      uid: prometheus

  additionalDataSources:
    - name: Loki
      type: loki
      isDefault: false
      editable: true
      access: proxy
      url: http://loki:3100
      uid: loki
  serviceMonitor:
    enabled: true
    path: "/metrics"
    labels: {}
    interval: ""
    scheme: http
    tlsConfig: {}
    scrapeTimeout: 30s
  autoscaling:
    enabled: false #true
    minReplicas: 1
    maxReplicas: 5
    targetCPU: "80"
    targetMemory: "80"
    behavior: {}
  rbac:
    extraRoleRules:
      - apiGroups: [""]
        resources: ["endpoints"]
        verbs: ["get", "list", "watch", "create", "update", "patch"]
    extraClusterRoleRules:
      - apiGroups: [""]
        resources: ["persistentvolumes"]
        verbs: ["get", "list", "watch", "create", "delete"]
      - apiGroups: [""]
        resources: ["persistentvolumeclaims"]
        verbs: ["get", "list", "watch", "update"]
      - apiGroups: ["storage.k8s.io"]
        resources: ["storageclasses"]
        verbs: ["get", "list", "watch"]
      - apiGroups: [""]
        resources: ["events"]
        verbs: ["list", "watch", "create", "patch"]
      - apiGroups: ["storage.k8s.io"]
        resources: ["csinodes"]
        verbs: ["get", "list", "watch"]
      - apiGroups: [""]
        resources: ["nodes"]
        verbs: ["get", "list", "watch"]
      - apiGroups: ["coordination.k8s.io"]
        resources: ["leases"]
        verbs: ["get", "watch", "list", "delete", "update", "create"]

  ingress:
    enabled: false

alertmanager:
  config:
    global:
      resolve_timeout: 5m
    route:
      group_by: ['namespace', 'job']
      group_wait: 30s
      group_interval: 5m
      repeat_interval: 12h
      receiver: 'slack-notifications'
      routes:
      - match:
          severity: critical
        receiver: 'slack-notifications'
    receivers:
    - name: 'slack-notifications'
      slack_configs:
      - api_url: '{{your-slack-hook}}'
        channel: '#alerts-dev'
        send_resolved: true

defaultRules:
  create: true
  rules:
    alertmanager: true
    etcd: false #true
    configReloaders: true
    general: false #true
    k8sContainerCpuUsageSecondsTotal: true
    k8sContainerMemoryCache: true
    k8sContainerMemoryRss: true
    k8sContainerMemorySwap: true
    k8sContainerResource: true
    k8sContainerMemoryWorkingSetBytes: true
    k8sPodOwner: true
    kubeApiserverAvailability: true
    kubeApiserverBurnrate: true
    kubeApiserverHistogram: true
    kubeApiserverSlos: true
    kubeControllerManager: false #true
    kubelet: true
    kubeProxy: false #true
    kubePrometheusGeneral: true
    kubePrometheusNodeRecording: true
    kubernetesApps: true
    kubernetesResources: true
    kubernetesStorage: true
    kubernetesSystem: false #true
    kubeSchedulerAlerting: false #true
    kubeSchedulerRecording: false #true
    windows: false