fullnameOverride: stack
victoria-metrics-operator:
  env:
    - name: VM_VMALERTDEFAULT_CONFIGRELOADERCPU
      value: 0
    - name: VM_VMAGENTDEFAULT_CONFIGRELOADERCPU
      value: 0
    - name: VM_VMALERTMANAGER_CONFIGRELOADERCPU
      value: 0
  operator:
    enable_converter_ownership: true # Required to allow VM to remove VM rules it imports if a prometheus rule is deleted
defaultDashboards:
  enabled: true
defaultRules:
  rules:
    groups:
      etcd:
        create: false
      kubernetesSystemControllerManager:
        create: false
      kubernetesSystemScheduler:
        create: false
vmsingle:
  spec:
    retentionPeriod: "1y"
    replicaCount: 1
    extraArgs:
      maxLabelsPerTimeseries: "50"
    storage:
      accessModes:
        - ReadWriteOnce
      resources:
        requests:
          storage: 100Gi
    resources:
      limits:
        memory: 6Gi
      requests:
        cpu: 500m
        memory: 2Gi
alertmanager:
  enabled: true
  spec:
    externalURL: https://alertmanager.${cluster_internal_domain}
  useManagedConfig: true
  config:
    route:
      group_by: ["alertname", "job"]
      group_interval: 10m
      group_wait: 1m
      receiver: discord
      repeat_interval: 12h
      routes:
        - receiver: "blackhole"
          matchers:
            - alertname=~"InfoInhibitor|Watchdog"
        - receiver: discord
          group_interval: 5m
          group_wait: 30s
          repeat_interval: 12h
          matchers:
            - severity=~"warning|critical"
    inhibit_rules:
      - source_matchers:
          - severity = "critical"
        target_matchers:
          - severity = "warning"
        equal: ["alertname", "namespace"]
    receivers:
      - name: "blackhole"
      - name: discord
        discord_configs:
          - webhook_url_secret:
              name: alertmanager-env-vars
              key: DISCORD_WEBHOOK_URL
vmalert:
  enabled: true
  spec:
    selectAllByDefault: false # Skip vmalerts for vmlog rules
    ruleSelector:
      matchExpressions:
        - key: vmalert-logs.io/enabled
          operator: NotIn
          values: ["true"]
    ruleNamespaceSelector:
      matchExpressions:
        - key: somekey
          operator: NotIn
          values: ["never-used-value"]
    extraArgs:
      external.url: https://vm.${cluster_internal_domain}
vmagent:
  spec:
    extraArgs:
      promscrape.maxScrapeSize: 50MiB
      promscrape.streamParse: "true"
      promscrape.dropOriginalLabels: "true"
    resources:
      limits:
        memory: 1Gi
      requests:
        cpu: 50m
        memory: 500Mi
grafana:
  enabled: false
prometheus-node-exporter:
  vmScrape:
    spec:
      endpoints:
        - port: metrics
          relabelConfigs:
            - source_labels:
                - __meta_kubernetes_endpoint_node_name
              target_label: node
kubelet:
  vmScrape:
    spec:
      # drop high cardinality label and useless metrics for cadvisor and kubelet
      metricRelabelConfigs:
        # Drop less useful container CPU metrics.
        - sourceLabels: [__name__]
          action: drop
          regex: "container_cpu_(cfs_throttled_seconds_total|load_average_10s|system_seconds_total|user_seconds_total)"
        # Drop less useful / always zero container memory metrics.
        - sourceLabels: [__name__]
          action: drop
          regex: "container_memory_(failures_total|mapped_file|swap)"
        # Drop less useful container process metrics.
        - sourceLabels: [__name__]
          action: drop
          # regex: 'container_(file_descriptors|tasks_state|threads_max)'
          regex: "container_(tasks_state|threads_max)"
        # Drop less useful container filesystem metrics.
        - sourceLabels: [__name__]
          action: drop
          regex: "container_fs_(io_current|io_time_seconds_total|io_time_weighted_seconds_total|reads_merged_total|sector_reads_total|sector_writes_total|writes_merged_total)"
        # Drop less useful container blkio metrics.
        - sourceLabels: [__name__]
          action: drop
          regex: "container_blkio_device_usage_total"
        # Drop container spec metrics that overlap with kube-state-metrics.
        - sourceLabels: [__name__]
          action: drop
          regex: "container_spec.*"
        # Drop cgroup metrics with no pod.
        - sourceLabels: [id, pod]
          action: drop
          regex: ".+;"
        - action: drop
          sourceLabels: [__name__]
          regex: prober_probe_duration_seconds_bucket
        # Drop high-cardinality labels.
        - action: labeldrop
          regex: (uid|id|pod_uid|interface)
        - action: drop
          sourceLabels: [__name__]
          regex: (rest_client_request_duration_seconds_bucket|rest_client_request_duration_seconds_sum|rest_client_request_duration_seconds_count)
kubeControllerManager:
  enabled: false
kubeEtcd:
  enabled: false
kubeScheduler:
  enabled: false
kubeProxy:
  enabled: false
additionalVictoriaMetricsMap:
  dockerhub-rules:
    create: true
    groups:
      - name: dockerhub
        rules:
          - alert: DockerhubRateLimitRisk
            annotations:
              summary: Kubernetes cluster Dockerhub rate limit risk
            expr: count(time() - container_last_seen{image=~"(docker.io).*",container!=""} < 30) > 100
            labels:
              severity: critical
  oom-rules:
    create: true
    groups:
      - name: oom
        rules:
          - alert: OomKilled
            annotations:
              summary: Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has been OOMKilled {{ $value }} times in the last 10 minutes.
            expr: (kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total offset 10m >= 1) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason="OOMKilled"}[10m]) == 1
            labels:
              severity: critical