KubeZero/charts/kubezero-metrics/values.yaml

kube-prometheus-stack:
  defaultRules:
    create: false

  coreDns:
    enabled: true
  kubeDns:
    enabled: false

  kubeApiServer:
    enabled: true
  kubeStateMetrics:
    enabled: true
  kubeProxy:
    enabled: true

  kubeEtcd:
    enabled: true
    service:
      port: 2381
      targetPort: 2381

  kubeControllerManager:
    enabled: true
    service:
      port: 10257
      targetPort: 10257
    serviceMonitor:
      https: true
      insecureSkipVerify: true

  kubeScheduler:
    enabled: true
    service:
      port: 10259
      targetPort: 10259
    serviceMonitor:
      https: true
      insecureSkipVerify: true

  kubelet:
    enabled: true
    serviceMonitor:
      # removed with 1.18, but still required for all container metrics ??
      cAdvisor: true

  prometheusOperator:
    enabled: true
    logFormat: json

    # Run on controller nodes
    tolerations:
    - key: node-role.kubernetes.io/master
      effect: NoSchedule
    nodeSelector:
      node-role.kubernetes.io/control-plane: ""
    resources:
      requests:
        cpu: 20m
        memory: 32Mi
      limits:
        memory: 64Mi

    admissionWebhooks:
      patch:
        tolerations:
        - key: node-role.kubernetes.io/master
          effect: NoSchedule
        nodeSelector:
          node-role.kubernetes.io/control-plane: ""

  nodeExporter:
    enabled: true

  prometheus-node-exporter:
    hostRootFsMount:
      enabled: false
    prometheus:
      monitor:
        relabelings:
        - sourceLabels: [__meta_kubernetes_pod_node_name]
          separator: ;
          regex: ^(.*)$
          targetLabel: node
          replacement: $1
          action: replace
    resources:
      requests:
        cpu: 20m
        memory: 16Mi

  prometheus:
    enabled: true

    prometheusSpec:
      retention: 8d
      portName: http-prometheus
      logFormat: json
      # externalUrl:

      # gather ALL monitors
      podMonitorSelectorNilUsesHelmValues: false
      serviceMonitorSelectorNilUsesHelmValues: false
      ruleSelectorNilUsesHelmValues: false

      resources:
        requests:
          memory: 512Mi
          cpu: 500m
        limits:
          memory: 3Gi
          # cpu: "1000m"

      walCompression: true
      storageSpec:
        volumeClaimTemplate:
          spec:
            # storageClassName: ebs-sc-gp3-xfs
            accessModes: ["ReadWriteOnce"]
            resources:
              requests:
                storage: 16Gi

  # Custom Grafana tweaks
  grafana:
    enabled: true

    # Disabled as we use the upstream kube-mixin dashboards directly
    defaultDashboardsEnabled: false

    grafana.ini:
      server:
        enable_gzip: true
      analytics:
        check_for_updates: false
      security:
        disable_gravatar: true
        cookie_secure: true
        strict_transport_security: true
      #auth:
      #  disable_login_form: true
      #  disable_signout_menu: true
      auth.anonymous:
        enabled: true
      dashboards:
        min_refresh_interval: "30s"
        default_home_dashboard_path: '/tmp/dashboards/KubeZero/home.json'
      alerting:
        enabled: false
      date_formats:
        default_timezone: UTC

    sidecar:
      dashboards:
        searchNamespace: ALL
        provider:
          foldersFromFilesStructure: true
        script: "/opt/script.sh"
    # For the gunzip script
        extraMounts:
        - name: script-volume
          mountPath: /opt/script.sh
          subPath: script.sh
    extraContainerVolumes:
    - name: script-volume
      configMap:
        name: script-configmap
        defaultMode: 0777

    #persistence:
    #  enabled: true
    #  size: 4Gi
    #  storageClassName: ebs-sc-gp2-xfs
    #deploymentStrategy:
    #  type: Recreate

    plugins:
    - grafana-piechart-panel
    service:
      portName: http-grafana
    initChownData:
      enabled: false
    testFramework:
      enabled: false

  # Assign state metrics to control plane
  kube-state-metrics:
    tolerations:
    - key: node-role.kubernetes.io/master
      effect: NoSchedule
    nodeSelector:
      node-role.kubernetes.io/control-plane: ""

  # Todo
  alertmanager:
    enabled: false
    config:
      global:
        resolve_timeout: 5m
      route:
        group_by: ['severity', 'clusterName']
        group_wait: 30s
        group_interval: 5m
        repeat_interval: 6h
        routes:
        - matchers:
          - alertname = Watchdog
          receiver: 'null'
        - matchers:
          - alertname = InfoInhibitor
          receiver: 'null'
      inhibit_rules:
      - equal:
        - namespace
        - alertname
        source_matchers:
        - severity = critical
        target_matchers:
        - severity =~ warning|info
      - equal:
        - namespace
        - alertname
        source_matchers:
        - severity = warning
        target_matchers:
        - severity = info
      - equal:
        - namespace
        source_matchers:
        - alertname = InfoInhibitor
        target_matchers:
        - severity = info
    alertmanagerSpec:
      # externalUrl:
      logFormat: json

      # for none AWS cluster or if SNS AlertHub should NOT be used, remove sns-forwarder by overwriting containers eg.:
      # containers: []

      # Add sns-forwarder to AlertManager pod, see: https://github.com/DataReply/alertmanager-sns-forwarder
      # uses the alertmanager serviceaccount to assume IAM role, requires annotation: kubezero.com/sns_forwarder_arn_prefix to point to SNSAlertHub
      # eg: "arn:aws:sns:eu-central-1:123456789012:"
      containers:
      - name: alertmanager-sns-forwarder
        image: datareply/alertmanager-sns-forwarder:latest
        imagePullPolicy: Always
        env:
        - name: SNS_FORWARDER_ARN_PREFIX
          valueFrom:
            fieldRef:
              fieldPath: metadata.annotations['kubezero.com/sns_forwarder_ARN_PREFIX']
        - name: AWS_ROLE_ARN
          valueFrom:
            fieldRef:
              fieldPath: metadata.annotations['kubezero.com/sns_forwarder_AWS_ROLE_ARN']
        - name: AWS_WEB_IDENTITY_TOKEN_FILE
          value: "/var/run/secrets/sts.amazonaws.com/serviceaccount/token"
        - name: AWS_STS_REGIONAL_ENDPOINTS
          value: regional
        volumeMounts:
        - name: aws-token
          mountPath: "/var/run/secrets/sts.amazonaws.com/serviceaccount/"
          readOnly: true
        resources:
          limits:
            memory: 64Mi
            cpu: 100m
          requests:
            cpu: 25m
            memory: 32Mi
        ports:
        - containerPort: 9087
          name: webhook-port
        livenessProbe:
          httpGet:
            path: /health
            port: webhook-port
          initialDelaySeconds: 30
          timeoutSeconds: 10
        readinessProbe:
          httpGet:
            path: /health
            port: webhook-port
          initialDelaySeconds: 10
          timeoutSeconds: 10
      volumes:
      - name: aws-token
        projected:
          sources:
          - serviceAccountToken:
              path: token
              expirationSeconds: 86400
              audience: "sts.amazonaws.com"

# Metrics adapter
prometheus-adapter:
  enabled: true
  logLevel: 1
  prometheus:
    url: http://metrics-kube-prometheus-st-prometheus
  tolerations:
  - key: node-role.kubernetes.io/master
    effect: NoSchedule
  nodeSelector:
    node-role.kubernetes.io/control-plane: ""
  # Basic rules for HPA to work replacing heaptster, taken from kube-prometheus project
  # https://github.com/coreos/kube-prometheus/blob/master/manifests/prometheus-adapter-configMap.yaml
  rules:
    default: false
    resource:
      cpu:
        containerQuery: sum(irate(container_cpu_usage_seconds_total{<<.LabelMatchers>>,container!="POD",container!="",pod!=""}[5m])) by (<<.GroupBy>>)
        nodeQuery: sum(1 - irate(node_cpu_seconds_total{mode="idle"}[5m]) * on(namespace, pod) group_left(node) node_namespace_pod:kube_pod_info:{<<.LabelMatchers>>}) by (<<.GroupBy>>)
        resources:
          overrides:
            node:
              resource: node
            namespace:
              resource: namespace
            pod:
              resource: pod
        containerLabel: container
      memory:
        containerQuery: sum(container_memory_working_set_bytes{<<.LabelMatchers>>,container!="POD",container!="",pod!=""}) by (<<.GroupBy>>)
        nodeQuery: sum(node_memory_MemTotal_bytes{job="node-exporter",<<.LabelMatchers>>} - node_memory_MemAvailable_bytes{job="node-exporter",<<.LabelMatchers>>}) by (<<.GroupBy>>)
        resources:
          overrides:
            node:
              resource: node
            namespace:
              resource: namespace
            pod:
              resource: pod
        containerLabel: container
      window: 5m

# Pushgateway
prometheus-pushgateway:
  enabled: false

  serviceMonitor:
    enabled: true

istio:
  grafana:
    enabled: false
    ipBlocks: []
    url: ""
    gateway: istio-ingress/ingressgateway
    destination: metrics-grafana

  prometheus:
    enabled: false
    ipBlocks: []
    url: ""
    gateway: istio-ingress/ingressgateway
    destination: metrics-kube-prometheus-st-prometheus

  alertmanager:
    enabled: false
    ipBlocks: []
    url: ""
    gateway: istio-ingress/ingressgateway
    destination: metrics-kube-prometheus-st-alertmanager