freeleaps-ops/freeleaps/helm-pkg/metrics/values.yaml

global:
  registry: docker.io
  repository: freeleaps
  nodeSelector: {}
logIngest:
  enabled: false
dashboard:
  enabled: false
  name: freeleaps-metrics-dashboard
  title: Freeleaps Metrics Dashboard
metrics:
  replicas: 1
  image:
    registry: docker.io
    repository: null
    name: metrics
    tag: "1.0.0"
    imagePullPolicy: IfNotPresent
  ports:
  - name: http
    containerPort: 8009
    protocol: TCP
  resources:
    requests:
      cpu: '0.1'
      memory: 64Mi
    limits:
      cpu: '0.2'
      memory: 128Mi
  probes: 
    liveness:
      type: httpGet
      config:
        path: /api/_/livez
        port: 8009
        initialDelaySeconds: 30
        periodSeconds: 10
        timeoutSeconds: 10
        successThreshold: 1
        failureThreshold: 5
        terminationGracePeriodSeconds: 30
    readiness:
      type: httpGet
      config:
        path: /api/_/readyz
        port: 8009
        initialDelaySeconds: 30
        periodSeconds: 10
        timeoutSeconds: 10
        successThreshold: 1
        failureThreshold: 5
  services:
  - name: metrics-service
    type: ClusterIP
    port: 8009
    targetPort: 8009
    serviceMonitor:
      enabled: true
      labels:
        release: kube-prometheus-stack
      namespace: freeleaps-monitoring-system
      interval: 30s
      scrapeTimeout: 10s
  configs:
    starrocksHost: ""
    starrocksPort: 8009
    starrocksUser: ""
    starrocksPassword: ""
    starrocksDatabase: ""
    prometheusEndpoint: ""
  vpa:
    minAllowed:
      enabled: false
      cpu: 100m
      memory: 64Mi
    maxAllowed:
      enabled: true
      cpu: 100m
      memory: 128Mi
    controlledResources:
    - cpu
    - memory
  prometheusRule:
    name: freepeals-metrics
    enabled: true
    namespace: "freeleaps-monitoring-system"
    labels:
      release: kube-prometheus-stack
    rules:
      - alert: FreeleapsMetricsServiceDown
        expr: up{job="metrics-service"} == 0
        for: 1m
        labels:
          severity: critical
          service: metrics-service
        annotations:
          summary: "Freeleaps Metrics service is down (instance {{ $labels.instance }})"
          description: "Freeleaps Metrics service has been down for more than 1 minutes."
          runbook_url: "https://netorgft10898514.sharepoint.com/:w:/s/FreeleapsEngineeringTeam/EUlvzumTsPxCpPAzI3gm9OIB0DCLTjQzzYVL6VsHYZFjxg?e=0dxVr7"
      
      - alert: FreeleapsMetricsServiceHighErrorRate
        expr: rate(http_requests_total{job="metrics-service",status=~"5.."}[5m]) > 0.1
        for: 5m
        labels:
          severity: warning
          service: metrics-service
        annotations:
          summary: "High error rate in freeleaps metrics service (instance {{ $labels.instance }})"
          description: "Freeleaps Metrics service error rate is {{ $value }} errors per second."
          runbook_url: "https://netorgft10898514.sharepoint.com/:w:/s/FreeleapsEngineeringTeam/EUlvzumTsPxCpPAzI3gm9OIB0DCLTjQzzYVL6VsHYZFjxg?e=0dxVr7"
      
      # - alert: MetricsServiceHighLatency
      #   expr: histogram_quantile(0.95, rate(http_request_duration_seconds_bucket{job="metrics-service"}[5m])) > 1
      #   for: 5m
      #   labels:
      #     severity: warning
      #     service: metrics-service
      #   annotations:
      #     summary: "High latency in metrics service (instance {{ $labels.instance }})"
      #     description: "95th percentile latency is {{ $value }} seconds."
      
      # - alert: MetricsServiceHighMemoryUsage
      #   expr: (process_resident_memory_bytes{job="metrics-service"} / 1024 / 1024) > 512
      #   for: 5m
      #   labels:
      #     severity: warning
      #     service: metrics
      #   annotations:
      #     summary: "High memory usage in metrics service (instance {{ $labels.instance }})"
      #     description: "Memory usage is {{ $value }} MB."
      
      # - alert: MetricsServiceHighCPUUsage
      #   expr: rate(process_cpu_seconds_total{job="metrics-service"}[5m]) * 100 > 80
      #   for: 5m
      #   labels:
      #     severity: warning
      #     service: metrics
      #   annotations:
      #     summary: "High CPU usage in metrics service (instance {{ $labels.instance }})"
      #     description: "CPU usage is {{ $value }}%."
      
      # - alert: MetricsServiceNoData
      #   expr: absent(up{job="metrics-service"})
      #   for: 5m
      #   labels:
      #     severity: critical
      #     service: metrics
      #   annotations:
      #     summary: "No data from metrics service (instance {{ $labels.instance }})"
      #     description: "No metrics data received from metrics service for more than 5 minutes."