KubeZero/charts/kubezero-metrics/values.yaml

grafana:
  istio:
    enabled: false
    url: ""
    gateway: ingressgateway.istio-system.svc.cluster.local

prometheus:
  istio:
    enabled: false
    url: ""
    gateway: ingressgateway.istio-system.svc.cluster.local

prometheus-operator:
  defaultRules:
    create: true
  coreDns:
    enabled: true
  kubeApiServer:
    enabled: true
  kubeStateMetrics:
    enabled: true
  kubeProxy:
    enabled: true

  # Disabled until we figure out how to scrape etcd with ssl client certs, scheduler/proxy/controller require https since 1.17
  kubeControllerManager:
    enabled: false
  kubeDns:
    enabled: false
  kubeEtcd:
    enabled: false
  kubeScheduler:
    enabled: false

  kubelet:
    enabled: true
    serviceMonitor:
      # removed with 1.18 anyways
      cAdvisor: false

  prometheusOperator:
    enabled: true
    #image:
    #  tag: v0.41.0
    #prometheusConfigReloaderImage:
    #  tag: v0.41.0

    # Run on controller nodes
    tolerations:
    - key: node-role.kubernetes.io/master
      effect: NoSchedule
    nodeSelector:
      node-role.kubernetes.io/master: ""

    # Argo takes care of CRDs
    manageCrds: false
    createCustomResource: true

    # Operator has TLS support starting 0.39, but chart does not support CAConfig and operator flags yet
    # see: https://github.com/coreos/prometheus-operator/blob/master/Documentation/user-guides/webhook.md#deploying-the-admission-webhook
    # Until then we disable them as the patching interferes with Argo anyways
    tlsProxy:
      enabled: false
    admissionWebhooks:
      enabled: false

    namespaces:
      releaseNamespace: true
      additional:
        - kube-system

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

  prometheus:
    enabled: true

    prometheusSpec:
      retention: 8d
      portName: http-prometheus

      resources:
        requests:
          memory: 512Mi

      storageSpec:
        volumeClaimTemplate:
          spec:
            storageClassName: ebs-sc-gp2-xfs
            accessModes: ["ReadWriteOnce"]
            resources:
              requests:
                storage: 8Gi

  # Custom Grafana tweaks
  # - persistence, plugins, auth
  grafana:
    enabled: true
    persistence:
      enabled: true
      size: 4Gi
      storageClassName: ebs-sc-gp2-xfs
    plugins:
    - grafana-piechart-panel
    service:
      portName: http-grafana
    initChownData:
      enabled: false
    testFramework:
      enabled: false

  # Todo
  alertmanager:
    enabled: false

# Metrics adapter
prometheus-adapter:
  prometheus:
    url: http://metrics-prometheus-operato-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!=""}[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