ewoooc/k8s/monitoring/values-prometheus.yaml

# =============================================================================
# WOOO TECH - Momo Pro System
# Kube-Prometheus-Stack Values
# =============================================================================

# Alertmanager 配置
alertmanager:
  enabled: true
  config:
    global:
      resolve_timeout: 5m

    route:
      group_by: ['alertname', 'namespace']
      group_wait: 30s
      group_interval: 5m
      repeat_interval: 4h
      receiver: 'null'  # 預設靜默，只發送明確匹配的告警
      routes:
        # ============================================
        # 靜默規則 (這些告警不發送通知)
        # ============================================
        # 系統內建告警
        - match:
            alertname: InfoInhibitor
          receiver: 'null'
        - match:
            alertname: Watchdog
          receiver: 'null'
        # API 錯誤預算告警 (常見誤報)
        - match:
            alertname: KubeAPIErrorBudgetBurn
          receiver: 'null'
        - match:
            alertname: KubeAPILatencyHigh
          receiver: 'null'
        # info/none 等級告警
        - match:
            severity: none
          receiver: 'null'
        - match:
            severity: info
          receiver: 'null'
        # Rancher 系統告警
        - match:
            namespace: cattle-system
          receiver: 'null'
        - match:
            namespace: cattle-fleet-system
          receiver: 'null'
        # kube-system 系統告警
        - match:
            namespace: kube-system
          receiver: 'null'
        # monitoring namespace 的 CPU 節流告警 (常見)
        - match:
            namespace: monitoring
            alertname: CPUThrottlingHigh
          receiver: 'null'
        # ============================================
        # 發送規則 (只有 momo namespace 的重要告警)
        # ============================================
        - match:
            namespace: momo
            severity: critical
          receiver: 'telegram'
          repeat_interval: 1h
        - match:
            namespace: momo
            severity: warning
          receiver: 'telegram'
          repeat_interval: 4h

    receivers:
      - name: 'null'
      - name: 'telegram'
        telegram_configs:
          - bot_token: '<TELEGRAM_BOT_TOKEN>'
            chat_id: '<TELEGRAM_CHAT_ID>'
            parse_mode: 'HTML'
            message: |
              {{ if eq .Status "firing" }}🚨🔥 <b>告警觸發</b> 🔥🚨{{ else }}✅💚 <b>告警恢復</b> 💚✅{{ end }}

              🏢 <b>環境:</b> 🟦 <code>UAT</code> (mo.wooo.work)
              📋 <b>告警名稱:</b> {{ .CommonLabels.alertname }}
              {{ if eq .CommonLabels.severity "critical" }}🔴{{ else if eq .CommonLabels.severity "warning" }}🟡{{ else }}🔵{{ end }} <b>嚴重程度:</b> {{ .CommonLabels.severity }}
              📦 <b>命名空間:</b> {{ .CommonLabels.namespace }}

              {{ range .Alerts }}
              📝 <b>摘要:</b> {{ .Annotations.summary }}
              💬 <b>詳情:</b> {{ .Annotations.description }}
              ⏰ <i>時間: {{ .StartsAt.Local.Format "2006-01-02 15:04:05" }}</i>
              {{ end }}

              🏷️ <i>MOMO Pro K8s 監控系統 (UAT)</i>

    inhibit_rules:
      - source_match:
          severity: 'critical'
        target_match:
          severity: 'warning'
        equal: ['alertname', 'namespace']

  alertmanagerSpec:
    resources:
      requests:
        memory: 64Mi
        cpu: 10m
      limits:
        memory: 128Mi
        cpu: 100m
    storage:
      volumeClaimTemplate:
        spec:
          storageClassName: local-path
          accessModes: ["ReadWriteOnce"]
          resources:
            requests:
              storage: 1Gi

# Prometheus 配置
prometheus:
  enabled: true
  prometheusSpec:
    retention: 7d
    resources:
      requests:
        memory: 256Mi
        cpu: 100m
      limits:
        memory: 1Gi
        cpu: 500m
    storageSpec:
      volumeClaimTemplate:
        spec:
          storageClassName: local-path
          accessModes: ["ReadWriteOnce"]
          resources:
            requests:
              storage: 10Gi

    # 監控 momo namespace
    serviceMonitorNamespaceSelector: {}
    serviceMonitorSelector: {}
    podMonitorNamespaceSelector: {}
    podMonitorSelector: {}

# Grafana 配置
grafana:
  enabled: true
  adminPassword: "Wooo_Grafana_2026"
  persistence:
    enabled: true
    storageClassName: local-path
    size: 2Gi
  resources:
    requests:
      memory: 128Mi
      cpu: 50m
    limits:
      memory: 256Mi
      cpu: 200m

  # 預設 Dashboard
  defaultDashboardsEnabled: true
  defaultDashboardsTimezone: Asia/Taipei

# Node Exporter
nodeExporter:
  enabled: true
  resources:
    requests:
      memory: 32Mi
      cpu: 10m
    limits:
      memory: 64Mi
      cpu: 100m

# Kube State Metrics
kubeStateMetrics:
  enabled: true
  resources:
    requests:
      memory: 32Mi
      cpu: 10m
    limits:
      memory: 128Mi
      cpu: 100m

# 禁用不需要的組件 (K3s 已內建)
kubeControllerManager:
  enabled: false
kubeScheduler:
  enabled: false
kubeProxy:
  enabled: false
kubeEtcd:
  enabled: false

# Prometheus Operator
prometheusOperator:
  resources:
    requests:
      memory: 64Mi
      cpu: 10m
    limits:
      memory: 256Mi
      cpu: 200m