water-management-system/deploy/production/monitoring/docker-compose.monitoring.yml

# ============================================================
# 监控栈 Docker Compose 编排
# 
# 使用方式:
#   docker compose -f deploy/production/monitoring/docker-compose.monitoring.yml up -d
#
# 包含组件:
#   - Prometheus (指标收集与告警)
#   - Grafana (可视化仪表盘)
#   - Node Exporter (主机指标)
#   - cAdvisor (容器指标)
#   - AlertManager (告警管理)
# ============================================================

services:
  # ==================== Prometheus ====================
  prometheus:
    image: prom/prometheus:v2.51.0
    container_name: wm-prometheus
    restart: always
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=30d'
      - '--storage.tsdb.retention.size=10GB'
      - '--web.console.libraries=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--web.enable-lifecycle'
      - '--web.enable-admin-api'
    ports:
      - "127.0.0.1:9090:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./alert_rules.yml:/etc/prometheus/alert_rules.yml:ro
      - prometheus_data:/prometheus
    networks:
      - wm-network
      - monitoring
    deploy:
      resources:
        limits:
          cpus: '1.0'
          memory: 2G
        reservations:
          cpus: '0.25'
          memory: 512M
    logging:
      driver: json-file
      options:
        max-size: "50m"
        max-file: "3"
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3

  # ==================== Grafana ====================
  grafana:
    image: grafana/grafana:10.4.0
    container_name: wm-grafana
    restart: always
    ports:
      - "127.0.0.1:3000:3000"
    environment:
      GF_SECURITY_ADMIN_USER: ${GRAFANA_ADMIN_USER:-admin}
      GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD:-admin}
      GF_SERVER_ROOT_URL: ${GRAFANA_ROOT_URL:-http://localhost:3000}
      GF_INSTALL_PLUGINS: grafana-clock-panel,grafana-simple-json-datasource
      GF_USERS_ALLOW_SIGN_UP: "false"
      GF_AUTH_ANONYMOUS_ENABLED: "false"
      GF_SECURITY_COOKIE_SECURE: "true"
      GF_SECURITY_STRICT_TRANSPORT_SECURITY: "true"
    volumes:
      - ./grafana/provisioning/datasources.yml:/etc/grafana/provisioning/datasources/datasources.yml:ro
      - grafana_data:/var/lib/grafana
    networks:
      - monitoring
      - wm-network
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 512M
        reservations:
          cpus: '0.1'
          memory: 128M
    logging:
      driver: json-file
      options:
        max-size: "30m"
        max-file: "3"
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 10s
      retries: 3

  # ==================== Node Exporter ====================
  node-exporter:
    image: prom/node-exporter:v1.7.0
    container_name: wm-node-exporter
    restart: always
    command:
      - '--path.rootfs=/host'
      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
    ports:
      - "127.0.0.1:9100:9100"
    volumes:
      - /:/host:ro,rslave
    pid: host
    networks:
      - monitoring
    deploy:
      resources:
        limits:
          cpus: '0.2'
          memory: 128M
        reservations:
          cpus: '0.05'
          memory: 32M
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

  # ==================== cAdvisor ====================
  cadvisor:
    image: gcr.io/cadvisor/cadvisor:v0.49.1
    container_name: wm-cadvisor
    restart: always
    ports:
      - "127.0.0.1:8880:8080"
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:ro
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
      - /dev/disk/:/dev/disk:ro
    privileged: true
    devices:
      - /dev/kmsg:/dev/kmsg
    networks:
      - monitoring
    deploy:
      resources:
        limits:
          cpus: '0.3'
          memory: 256M
        reservations:
          cpus: '0.1'
          memory: 64M
    logging:
      driver: json-file
      options:
        max-size: "20m"
        max-file: "3"

  # ==================== AlertManager ====================
  alertmanager:
    image: prom/alertmanager:v0.27.0
    container_name: wm-alertmanager
    restart: always
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
    ports:
      - "127.0.0.1:9093:9093"
    volumes:
      - ./alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
      - alertmanager_data:/alertmanager
    networks:
      - monitoring
    deploy:
      resources:
        limits:
          cpus: '0.2'
          memory: 256M
        reservations:
          cpus: '0.05'
          memory: 64M
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

  # ==================== PostgreSQL Exporter ====================
  postgres-exporter:
    image: prometheuscommunity/postgres-exporter:v0.15.0
    container_name: wm-postgres-exporter
    restart: always
    environment:
      DATA_SOURCE_NAME: "postgresql://${POSTGRES_USER:-water}:${POSTGRES_PASSWORD:-water123}@postgres:5432/${POSTGRES_DB:-water_management}?sslmode=disable"
    ports:
      - "127.0.0.1:9187:9187"
    depends_on:
      - postgres
    networks:
      - monitoring
      - wm-network
    deploy:
      resources:
        limits:
          cpus: '0.2'
          memory: 128M
        reservations:
          cpus: '0.05'
          memory: 32M
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

  # ==================== Redis Exporter ====================
  redis-exporter:
    image: oliver006/redis_exporter:v1.58.0
    container_name: wm-redis-exporter
    restart: always
    environment:
      REDIS_ADDR: redis://redis:6379
      REDIS_PASSWORD: ${REDIS_PASSWORD:-water123}
    ports:
      - "127.0.0.1:9121:9121"
    depends_on:
      - redis
    networks:
      - monitoring
      - wm-network
    deploy:
      resources:
        limits:
          cpus: '0.1'
          memory: 64M
        reservations:
          cpus: '0.02'
          memory: 16M
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

# ==================== 数据卷 ====================
volumes:
  prometheus_data:
  grafana_data:
  alertmanager_data:

# ==================== 网络 ====================
networks:
  monitoring:
    driver: bridge
    name: wm-monitoring
  wm-network:
    external: true
    name: wm-network