kubernetes_monitoring/values.yaml

---

# All values within this helm chart values.yaml file are under namespace `nfc_monitoring`.
# this provides the opportunity to include this helm chart as a dependency without
# variable collision

nfc_monitoring:

  kubernetes:
    cluster_dns_name: cluster.local
    networking: calico


  alert_manager:
    image: 
      name: quay.io/prometheus/alertmanager
      tag: 'v0.26.0'
    namespace: alerting


  grafana:

    admin_user: admin
    admin_password: admin

    image: 
      name: grafana/grafana
      tag: '10.1.2' # '10.0.5'

    namespace: grafana

    replicas: 1

    affinity: 
      nodeAffinity:
        preferredDuringSchedulingIgnoredDuringExecution:
        - preference:
            matchExpressions:
            - key: node-role.kubernetes.io/worker
              operator: Exists
          weight: 100
        - preference:
            matchExpressions:
            - key: node-role.kubernetes.io/storage
              operator: DoesNotExist
          weight: 100
      podAntiAffinity:
        preferredDuringSchedulingIgnoredDuringExecution:
        - podAffinityTerm:
            labelSelector:
              matchExpressions:
              - key: app.kubernetes.io/name
                operator: In
                values:
                - prometheus
            topologyKey: kubernetes.io/hostname
          weight: 10


  grafana_agent:
    image: 
      name: grafana/agent
      tag: 'v0.36.1'
    namespace: monitoring


  loki:

    enabled: true

    image: 
      name: grafana/loki
      tag: 2.7.4

    namespace: logging

    # service name and port are used for the connection to your loki instance
    service_name: loki-gateway
    service_port: 80

    ServiceMonitor:
      selector:
        matchLabels:
          app.kubernetes.io/name: loki
          app.kubernetes.io/component: logging


  kube_monitor_proxy:
    namespace: monitoring


  kube_rbac_proxy:
    # This image is used as part of kube-monitor-proxy.
    image: 
      name: quay.io/brancz/kube-rbac-proxy
      tag: 'v0.14.2'


  kube_state_metrics:
    image: 
      name: registry.k8s.io/kube-state-metrics/kube-state-metrics
      tag: 'v2.8.1'
    namespace: monitoring


  prometheus:

    image:
      name: prom/prometheus
      tag: 'v2.47.0'

    namespace: monitoring

    affinity: 
      nodeAffinity:
        preferredDuringSchedulingIgnoredDuringExecution:
        - preference:
            matchExpressions:
            - key: node-role.kubernetes.io/worker
              operator: Exists
          weight: 100
        - preference:
            matchExpressions:
            - key: node-role.kubernetes.io/storage
              operator: DoesNotExist
          weight: 100
      podAntiAffinity:
        preferredDuringSchedulingIgnoredDuringExecution:
        - podAffinityTerm:
            labelSelector:
              matchExpressions:
              - key: app.kubernetes.io/name
                operator: In
                values:
                - prometheus
            topologyKey: kubernetes.io/hostname
          weight: 10

    # List of namespaces that prometheus is to monitor
    # used to create Roles and RoleBindings
    monitor_namespaces:
      - alerting
      - default
      # - ceph
      - grafana
      - monitoring
      # - kube-dashboard
      # - kube-metrics
      - kube-policy
      - kube-system
      - logging
      # - mariadb
      # - olm
      # - operators

    # Deploy a generate policy for kyverno to create Role and RoleBindings
    # for the prometheus service account so it can monitor
    # new/existing namespaces
    kyverno_role_policy: true

    storage:
      volumeClaimTemplate:
        spec:
          accessModes:
            - ReadWriteOnce
          resources:
            requests:
              storage: 40Gi

    # Additional settings for Prometheus.
    # See: https://prometheus-operator.dev/docs/operator/api/#monitoring.coreos.com/v1.PrometheusSpec
    additional: {}

      # remoteWrite: 
      #   - name: mimir
      #     url: http://mimir-gateway.metrics.svc.cluster.local/api/v1/push


  prometheus_adaptor:

    image:
      name: registry.k8s.io/prometheus-adapter/prometheus-adapter
      tag: 'v0.11.1'

    namespace: monitoring

    affinity: 
      nodeAffinity:
        preferredDuringSchedulingIgnoredDuringExecution:
        - preference:
            matchExpressions:
            - key: node-role.kubernetes.io/worker
              operator: Exists
          weight: 100
        - preference:
            matchExpressions:
            - key: node-role.kubernetes.io/storage
              operator: DoesNotExist
          weight: 100
      podAntiAffinity:
        preferredDuringSchedulingIgnoredDuringExecution:
        - podAffinityTerm:
            labelSelector:
              matchExpressions:
              - key: app.kubernetes.io/name
                operator: In
                values:
                - prometheus
            topologyKey: kubernetes.io/hostname
          weight: 10

  thanos:
    image:
      name: thanosio/thanos
      tag: v0.32.3

    # Prometheus thanos sidecar
    # see: https://thanos.io/tip/components/sidecar.md/
    sidecar:

      enabled: true

      config:
        type: S3
        config:
          bucket: "thanos-metrics"
          endpoint: "rook-ceph-rgw-earth.ceph.svc:80"
          access_key: "7J5NM2MNCDB4T4Y9OKJ5"
          secret_key: "t9r69RzZdWEBL3NCKiUIpDk6j5625xc6HucusiGG"


  additions:

    ceph:

      enabled: true

      namespace: ceph

      PrometheusRules: true

      ServiceMonitor:

        selector:
          matchLabels:
            app: rook-ceph-mgr

    # Add sidecar to grafana pod to load dashboards from configMap
    dashboard_sidecar: 
      
      enabled: true

      image:
        name: ghcr.io/kiwigrid/k8s-sidecar
        tag: '1.24.5'

      label_name: grafana_dashboard
      label_value: "1"


loki_instance:
  image: 
    name: grafana/loki
    tag: 2.7.4
    # tag: 2.9.0
  namespace: loki


oncall_instance:
  image: 
    name: grafana/oncall
    tag: v1.1.40


# oncall:
  
#   # image:
#   #   # Grafana OnCall docker image repository
#   #   repository: grafana/oncall
#   #   tag: v1.1.38
#   #   pullPolicy: Always

#   service:
#     enabled: false
#     type: LoadBalancer
#     port: 8080
#     annotations: {}

#   engine:
#     replicaCount: 1
#     resources:
#       limits:
#         cpu: 100m
#         memory: 128Mi
#       requests:
#         cpu: 100m
#         memory: 128Mi

#   celery:
#     replicaCount: 1
#     resources:
#       limits:
#         cpu: 100m
#         memory: 128Mi
#       requests:
#         cpu: 100m
#         memory: 128Mi
#   database:
#     type: none