awoooi/k8s/monitoring/docker-compose-110.yml

version: '3.8'

services:
  # ---------------------------------------------------------------------------
  # cAdvisor 110 防爆網（2026-04-19 台北凌晨 / Claude Opus 4.7 / Phase 7 盲區治理）
  # Why: 110 cadvisor 目前 0% CPU（已有 flags 降維），但無 mem_limit/cpus 防爆網
  #      加配額作為 L2 永久防爆：萬一未來量爆，會 OOMKill 不會拖垮 110 主機
  # 對映：ADR-090 Layer 2 資源配額強制
  # 注意：此 compose 與 110 live (/home/wooo/monitoring/docker-compose.yml) 有 drift 風險，
  #       目前無 CD workflow 同步 → 列為技術債，下一 session 納入 Git + CD
  # ---------------------------------------------------------------------------
  cadvisor:
    image: gcr.io/cadvisor/cadvisor:latest
    container_name: cadvisor
    restart: unless-stopped
    command:
      - --logtostderr
      - --disable_metrics=disk,diskIO,tcp,udp,percpu,sched,process
      - --housekeeping_interval=30s
      - --max_housekeeping_interval=60s
      - --docker_only=true
    ports:
      - "9180:8080"
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:ro
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
      - /dev/disk/:/dev/disk:ro
      - /etc/localtime:/etc/localtime:ro
    environment:
      - TZ=Asia/Taipei
    privileged: true
    devices:
      - /dev/kmsg
    networks:
      - monitoring
    mem_limit: 512m
    cpus: 1.0

  prometheus:
    image: prom/prometheus:latest
    container_name: prometheus
    restart: unless-stopped
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./alerts.yml:/etc/prometheus/alerts.yml:ro
      - prometheus_data:/prometheus
      - /etc/localtime:/etc/localtime:ro
    environment:
      - TZ=Asia/Taipei
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=30d'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
      - '--web.enable-lifecycle'
    extra_hosts:
      - "host.docker.internal:host-gateway"
    networks:
      - monitoring

  grafana:
    image: grafana/grafana:latest
    container_name: grafana
    restart: unless-stopped
    ports:
      - "3002:3000"
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=WoooTech2026
      - GF_SERVER_ROOT_URL=http://192.168.0.110:3002
      - TZ=Asia/Taipei
    volumes:
      - grafana_data:/var/lib/grafana
      - /etc/localtime:/etc/localtime:ro
    networks:
      - monitoring
    depends_on:
      - prometheus

  blackbox-exporter:
    image: prom/blackbox-exporter:latest
    container_name: blackbox-exporter
    restart: unless-stopped
    ports:
      - "9115:9115"
    volumes:
      - ./blackbox.yml:/etc/blackbox_exporter/config.yml:ro
      - /etc/localtime:/etc/localtime:ro
    environment:
      - TZ=Asia/Taipei
    command:
      - '--config.file=/etc/blackbox_exporter/config.yml'
    networks:
      - monitoring

  alertmanager:
    image: prom/alertmanager:latest
    container_name: alertmanager
    restart: unless-stopped
    ports:
      - "9093:9093"
    volumes:
      - ./alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
      - alertmanager_data:/alertmanager
      - /etc/localtime:/etc/localtime:ro
    environment:
      - TZ=Asia/Taipei
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
    networks:
      - monitoring

  # === Phase 5: GitHub Exporter (OPS.176) ===
  github-exporter:
    image: promhippie/github-exporter:latest
    container_name: github-exporter
    restart: unless-stopped
    ports:
      - '9504:9504'
    environment:
      - GITHUB_EXPORTER_TOKEN=${GITHUB_TOKEN}
      - GITHUB_EXPORTER_REPOS=owenhytsai/wooo-aiops,owenhytsai/clawbot-v5
      - GITHUB_EXPORTER_LOG_LEVEL=info
    networks:
      - monitoring
    labels:
      - 'com.wooo.service=github-exporter'
      - 'com.wooo.phase=phase-5'
    logging:
      driver: json-file
      options:
        max-size: '10m'
        max-file: '3'

networks:
  monitoring:
    driver: bridge

volumes:
  prometheus_data:
  grafana_data:
  alertmanager_data: