kube-prometheus-stack_servicecluster

# values-service-cluster.yaml
# kube-prometheus-stack for SERVICE cluster

# ============================================
# PROMETHEUS - optional, for local service cluster metrics
# ============================================
prometheus:
  prometheusSpec:
    externalLabels:
      cluster: "service-cluster"

    # Also push to local Thanos Receive (so all metrics go through same path)
    remoteWrite:
      - url: http://thanos-receive.monitoring.svc:19291/api/v1/receive

    retention: 24h

    resources:
      requests:
        cpu: 200m
        memory: 512Mi
      limits:
        memory: 2Gi

# ============================================
# ALERTMANAGER - central instance
# ============================================
alertmanager:
  enabled: true

  # Expose via MetalLB so site clusters can reach it
  service:
    type: LoadBalancer
    annotations:
      metallb.universe.tf/loadBalancerIPs: 10.x.x.51

  alertmanagerSpec:
    replicas: 2
    retention: 120h
    storage:
      volumeClaimTemplate:
        spec:
          accessModes: ["ReadWriteOnce"]
          resources:
            requests:
              storage: 10Gi
    resources:
      requests:
        cpu: 100m
        memory: 256Mi

  config:
    global:
      resolve_timeout: 5m

    route:
      receiver: 'default'
      group_by: ['alertname', 'cluster']  # Group by cluster!
      group_wait: 30s
      group_interval: 5m
      repeat_interval: 4h
      routes:
        - match:
            severity: critical
          receiver: 'critical'

    receivers:
      - name: 'default'
        # Configure your receivers (Slack, email, etc.)
        # slack_configs:
        #   - channel: '#alerts'
        #     api_url: 'https://hooks.slack.com/...'
      - name: 'critical'
        # pagerduty_configs:
        #   - service_key: '<key>'

# ============================================
# GRAFANA - central with SSO
# ============================================
grafana:
  enabled: true

  replicas: 1

  # Persistence for dashboards
  persistence:
    enabled: true
    size: 5Gi

  # Keycloak OIDC
  grafana.ini:
    server:
      root_url: https://grafana.example.com

    auth:
      disable_login_form: false  # Set true after SSO works

    auth.generic_oauth:
      enabled: true
      name: Keycloak
      allow_sign_up: true
      client_id: grafana
      client_secret: ${GRAFANA_OAUTH_SECRET}
      scopes: openid profile email groups
      auth_url: https://keycloak.example.com/realms/master/protocol/openid-connect/auth
      token_url: https://keycloak.example.com/realms/master/protocol/openid-connect/token
      api_url: https://keycloak.example.com/realms/master/protocol/openid-connect/userinfo
      role_attribute_path: contains(groups[*], 'grafana-admin') && 'Admin' || contains(groups[*], 'grafana-editor') && 'Editor' || 'Viewer'

  envFromSecret: grafana-oauth-secret

  # Thanos Query as datasource (added automatically via additionalDataSources)
  additionalDataSources:
    - name: Thanos
      type: prometheus
      url: http://thanos-query.monitoring.svc:9090
      access: proxy
      isDefault: true

  resources:
    requests:
      cpu: 100m
      memory: 256Mi

# ============================================
# EXPORTERS
# ============================================
nodeExporter:
  enabled: true

kubeStateMetrics:
  enabled: true

# ============================================
# DEFAULT RULES
# ============================================
defaultRules:
  create: true