warmbly/deploy/worker-cluster/monitoring/values.yaml

# Lightweight kube-prometheus-stack for worker cluster
# No Grafana - use main cluster's Grafana with this Prometheus as data source
#
# Install with:
#   helm install prometheus-stack prometheus-community/kube-prometheus-stack \
#     --namespace monitoring --create-namespace \
#     --values values.yaml

# Disable Grafana - use main cluster's Grafana
grafana:
  enabled: false

# Minimal Prometheus configuration
prometheus:
  enabled: true
  prometheusSpec:
    retention: 7d  # Shorter retention for lightweight setup
    retentionSize: "10GB"

    scrapeInterval: 60s  # Less frequent scraping to reduce load
    evaluationInterval: 60s

    # Minimal resources
    resources:
      requests:
        memory: 256Mi
        cpu: 100m
      limits:
        memory: 512Mi
        cpu: 500m

    # Smaller storage
    storageSpec:
      volumeClaimTemplate:
        spec:
          accessModes: ["ReadWriteOnce"]
          resources:
            requests:
              storage: 15Gi

    # Enable remote-write receiver if you want to receive metrics from other sources
    enableRemoteWriteReceiver: false

    # Monitor all namespaces
    serviceMonitorSelectorNilUsesHelmValues: false
    podMonitorSelectorNilUsesHelmValues: false
    ruleSelectorNilUsesHelmValues: false

  # Expose Prometheus for main cluster's Grafana to connect
  # Option 1: NodePort (simple, use with firewall rules)
  # Option 2: LoadBalancer (if available)
  # Option 3: VPN/private network access
  service:
    type: ClusterIP  # Change to NodePort or LoadBalancer if needed
    port: 9090
    # nodePort: 30090  # Uncomment if using NodePort

# Disable Alertmanager - use main cluster's Alertmanager
alertmanager:
  enabled: false

# Node exporter - runs on every worker node
nodeExporter:
  enabled: true
  resources:
    requests:
      memory: 16Mi
      cpu: 10m
    limits:
      memory: 32Mi
      cpu: 50m

# kube-state-metrics - single instance
kubeStateMetrics:
  enabled: true

kube-state-metrics:
  resources:
    requests:
      memory: 32Mi
      cpu: 10m
    limits:
      memory: 64Mi
      cpu: 50m

# Prometheus Operator - manages Prometheus CRDs
prometheusOperator:
  enabled: true
  resources:
    requests:
      memory: 64Mi
      cpu: 50m
    limits:
      memory: 128Mi
      cpu: 100m

# Disable control plane monitoring (not accessible by default)
kubeApiServer:
  enabled: false

kubeControllerManager:
  enabled: false

kubeScheduler:
  enabled: false

kubeProxy:
  enabled: false

kubeEtcd:
  enabled: false

coreDns:
  enabled: true

# Minimal alerting rules for worker nodes
additionalPrometheusRulesMap:
  worker-node-rules:
    groups:
      - name: worker-node-health
        rules:
          # High worker node CPU
          - alert: WorkerNodeHighCPU
            expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 85
            for: 10m
            labels:
              severity: warning
              cluster: workers
            annotations:
              summary: "Worker node {{ $labels.instance }} CPU > 85%"
              description: "Worker node has sustained high CPU usage."

          # Low worker node memory
          - alert: WorkerNodeLowMemory
            expr: (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100 < 15
            for: 5m
            labels:
              severity: warning
              cluster: workers
            annotations:
              summary: "Worker node {{ $labels.instance }} memory < 15% available"
              description: "Worker node is running low on memory."

          # Worker node disk space
          - alert: WorkerNodeDiskFull
            expr: (node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) * 100 < 15
            for: 5m
            labels:
              severity: warning
              cluster: workers
            annotations:
              summary: "Worker node {{ $labels.instance }} disk < 15% free"
              description: "Worker node root filesystem is running low on space."

          # Node not ready
          - alert: WorkerNodeNotReady
            expr: kube_node_status_condition{condition="Ready",status="true"} == 0
            for: 5m
            labels:
              severity: critical
              cluster: workers
            annotations:
              summary: "Worker node {{ $labels.node }} is not ready"
              description: "Worker node has been in NotReady state for 5 minutes."

      - name: worker-pod-health
        rules:
          # Worker pod not running
          - alert: WorkerPodNotRunning
            expr: kube_pod_status_phase{namespace="warmbly", pod=~"worker.*", phase!="Running"} > 0
            for: 5m
            labels:
              severity: critical
              cluster: workers
            annotations:
              summary: "Worker pod {{ $labels.pod }} is not running"
              description: "Worker pod is in {{ $labels.phase }} state."

          # Worker pod restarting
          - alert: WorkerPodRestarting
            expr: increase(kube_pod_container_status_restarts_total{namespace="warmbly", pod=~"worker.*"}[1h]) > 3
            for: 0m
            labels:
              severity: warning
              cluster: workers
            annotations:
              summary: "Worker pod {{ $labels.pod }} restarting frequently"
              description: "Worker pod has restarted more than 3 times in the last hour."