KubeZero/charts/kubezero-metrics/values.yaml

prometheus-operator:
  alertmanager:
    enabled: false
  coreDns:
    enabled: false
  kubeApiServer:
    enabled: false
  kubeControllerManager:
    enabled: false
  kubeDns:
    enabled: false
  kubeEtcd:
    enabled: false
  kubeProxy:
    enabled: false
  kubeScheduler:
    enabled: false
  kubeStateMetrics:
    enabled: false
  kubelet:
    enabled: false
  grafana:
    enabled: false
  defaultRules:
    create: 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

  prometheus:
    enabled: true
    retention: 10d

    resources:
      requests:
        memory: 512Mi

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

# Metrics adapter
prometheus-adapter:
  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
  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:
          instance:
            resource: node
          namespace:
            resource: namespace
          pod:
            resource: pod
      containerLabel: container
    window: 5m