tokens-reef/deploy/monitoring/docker-compose.monitoring.yml

# =============================================================================
# Sub2API 监控栈 - Prometheus + Grafana + Loki + Jaeger
# =============================================================================
# 使用方法:
#   1. 创建监控目录: mkdir -p monitoring/{prometheus-data,grafana-data,loki-data}
#   2. 启动: docker-compose -f docker-compose.monitoring.yml up -d
#   3. 访问 Grafana: http://localhost:3000 (admin/admin)
# =============================================================================

version: '3.8'

services:
  # ===========================================================================
  # Prometheus - 时序数据库
  # ===========================================================================
  prometheus:
    image: prom/prometheus:v2.50.0
    container_name: sub2api-prometheus
    restart: unless-stopped
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=30d'
      - '--storage.tsdb.retention.size=50GB'
      - '--web.enable-lifecycle'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
    volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./prometheus/rules:/etc/prometheus/rules:ro
      - ./prometheus-data:/prometheus
    ports:
      - "9090:9090"
    networks:
      - monitoring-network
    healthcheck:
      test: ["CMD", "wget", "-q", "-O", "-", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3

  # ===========================================================================
  # Grafana - 可视化平台
  # ===========================================================================
  grafana:
    image: grafana/grafana:10.3.1
    container_name: sub2api-grafana
    restart: unless-stopped
    environment:
      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_SERVER_ROOT_URL=${GRAFANA_ROOT_URL:-http://localhost:3000}
      - GF_INSTALL_PLUGINS=grafana-clock-panel,grafana-simple-json-datasource
    volumes:
      - ./grafana-data:/var/lib/grafana
      - ./grafana/provisioning:/etc/grafana/provisioning:ro
      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
    ports:
      - "3000:3000"
    networks:
      - monitoring-network
    depends_on:
      - prometheus
      - loki
      - jaeger
    healthcheck:
      test: ["CMD", "wget", "-q", "-O", "-", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 10s
      retries: 3

  # ===========================================================================
  # Loki - 日志聚合
  # ===========================================================================
  loki:
    image: grafana/loki:2.9.4
    container_name: sub2api-loki
    restart: unless-stopped
    command: -config.file=/etc/loki/local-config.yaml
    volumes:
      - ./loki/loki-config.yaml:/etc/loki/local-config.yaml:ro
      - ./loki-data:/loki
    ports:
      - "3100:3100"
    networks:
      - monitoring-network
    healthcheck:
      test: ["CMD", "wget", "-q", "-O", "-", "http://localhost:3100/ready"]
      interval: 30s
      timeout: 10s
      retries: 3

  # ===========================================================================
  # Promtail - 日志收集器
  # ===========================================================================
  promtail:
    image: grafana/promtail:2.9.4
    container_name: sub2api-promtail
    restart: unless-stopped
    command: -config.file=/etc/promtail/config.yml
    volumes:
      - ./promtail/promtail-config.yml:/etc/promtail/config.yml:ro
      - /var/log:/var/log:ro
      - /var/lib/docker/containers:/var/lib/docker/containers:ro
    networks:
      - monitoring-network
    depends_on:
      - loki

  # ===========================================================================
  # Jaeger - 分布式追踪
  # ===========================================================================
  jaeger:
    image: jaegertracing/all-in-one:1.54
    container_name: sub2api-jaeger
    restart: unless-stopped
    environment:
      - COLLECTOR_OTLP_ENABLED=true
    ports:
      - "16686:16686"    # UI
      - "4317:4317"      # OTLP gRPC
      - "4318:4318"      # OTLP HTTP
      - "14268:14268"    # Jaeger Thrift
    networks:
      - monitoring-network
    healthcheck:
      test: ["CMD", "wget", "-q", "-O", "-", "http://localhost:16686"]
      interval: 30s
      timeout: 10s
      retries: 3

  # ===========================================================================
  # Node Exporter - 主机指标
  # ===========================================================================
  node-exporter:
    image: prom/node-exporter:v1.7.0
    container_name: sub2api-node-exporter
    restart: unless-stopped
    command:
      - '--path.procfs=/host/proc'
      - '--path.rootfs=/rootfs'
      - '--path.sysfs=/host/sys'
      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    ports:
      - "9100:9100"
    networks:
      - monitoring-network

  # ===========================================================================
  # cAdvisor - 容器指标
  # ===========================================================================
  cadvisor:
    image: gcr.io/cadvisor/cadvisor:v0.47.2
    container_name: sub2api-cadvisor
    restart: unless-stopped
    privileged: true
    devices:
      - /dev/kmsg:/dev/kmsg
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:ro
      - /sys:/sys:ro
      - /var/lib/docker:/var/lib/docker:ro
      - /dev/disk:/dev/disk:ro
    ports:
      - "8081:8080"
    networks:
      - monitoring-network

  # ===========================================================================
  # Alertmanager - 告警管理
  # ===========================================================================
  alertmanager:
    image: prom/alertmanager:v0.27.0
    container_name: sub2api-alertmanager
    restart: unless-stopped
    command:
      - '--config.file=/etc/alertmanager/config.yml'
      - '--storage.path=/alertmanager'
      - '--web.external-url=http://localhost:9093'
    volumes:
      - ./alertmanager/config.yml:/etc/alertmanager/config.yml:ro
      - ./alertmanager-data:/alertmanager
    ports:
      - "9093:9093"
    networks:
      - monitoring-network
    healthcheck:
      test: ["CMD", "wget", "-q", "-O", "-", "http://localhost:9093/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3

networks:
  monitoring-network:
    driver: bridge