KubeZero/charts/kubezero-metrics/values.yaml

kube-prometheus-stack:
  defaultRules:
    create: true

  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/master: ""
    resources:
      requests:
        cpu: 20m
        memory: 32Mi
      limits:
        memory: 64Mi

    namespaces:
      releaseNamespace: true
      additional:
        - kube-system
        - istio-system
        - istio-ingress
        - logging

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

  nodeExporter:
    enabled: true
    serviceMonitor:
      relabelings:
      - sourceLabels: [__meta_kubernetes_pod_node_name]
        separator: ;
        regex: ^(.*)$
        targetLabel: node
        replacement: $1
        action: replace

  prometheus-node-exporter:
    resources:
      requests:
        cpu: 20m
        memory: 16Mi

  prometheus:
    enabled: true

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

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

      storageSpec:
        volumeClaimTemplate:
          spec:
            storageClassName: ebs-sc-gp2-xfs
            accessModes: ["ReadWriteOnce"]
            resources:
              requests:
                storage: 16Gi

  # Custom Grafana tweaks
  # - persistence, plugins, auth
  grafana:
    enabled: true
    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/master: ""

  # Todo
  alertmanager:
    enabled: false
    alertmanagerSpec:
      # externalUrl:
      logFormat: json

# 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/master: ""
  # 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!=""}[3m])) by (<<.GroupBy>>)
        nodeQuery: sum(1 - irate(node_cpu_seconds_total{mode="idle"}[3m]) * 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: 3m

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