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

# Sub2API 单机监控栈 (2核4G优化版)
# 资源限制: Prometheus 128MB, Grafana 128MB, Node Exporter 32MB
# 总内存占用: ~300MB

version: '3.8'

services:
  prometheus:
    image: prom/prometheus:v2.50.0
    container_name: sub2api-prometheus
    restart: unless-stopped
    mem_limit: 128m
    cpus: '0.2'
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.retention.time=15d'
      - '--storage.tsdb.retention.size=2GB'
      - '--storage.tsdb.wal-compression'
      - '--storage.tsdb.min-block-duration=2h'
      - '--storage.tsdb.max-block-duration=2h'
      - '--query.max-samples=50000000'
      - '--query.timeout=2m'
      - '--web.enable-lifecycle'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
    volumes:
      - ./prometheus/prometheus-single.yml:/etc/prometheus/prometheus.yml:ro
      - ./prometheus/rules:/etc/prometheus/rules:ro
      - prometheus-data:/prometheus
    ports:
      - "9090:9090"
    networks:
      - monitoring
    healthcheck:
      test: ["CMD", "wget", "-q", "--spider", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3

  grafana:
    image: grafana/grafana:10.3.0
    container_name: sub2api-grafana
    restart: unless-stopped
    mem_limit: 128m
    cpus: '0.1'
    environment:
      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
      - GF_INSTALL_PLUGINS=grafana-clock-panel
      - GF_ANALYTICS_REPORTING_ENABLED=false
      - GF_ANALYTICS_CHECK_FOR_UPDATES=false
      - GF_LOG_LEVEL=warn
      - GF_LOG_MODE=console
      - GF_DATABASE_TYPE=sqlite3
      - GF_DATABASE_PATH=/var/lib/grafana/grafana.db
      - GF_SESSION_PROVIDER=memory
      - GF_METRICS_ENABLED=false
      - GF_TRACING_ENABLED=false
    volumes:
      - ./grafana/grafana-single.ini:/etc/grafana/grafana.ini:ro
      - ./grafana/provisioning:/etc/grafana/provisioning:ro
      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
      - grafana-data:/var/lib/grafana
    ports:
      - "3000:3000"
    networks:
      - monitoring
    depends_on:
      - prometheus
    healthcheck:
      test: ["CMD", "wget", "-q", "--spider", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 10s
      retries: 3

  node-exporter:
    image: prom/node-exporter:v1.7.0
    container_name: sub2api-node-exporter
    restart: unless-stopped
    mem_limit: 32m
    cpus: '0.05'
    command:
      - '--path.procfs=/host/proc'
      - '--path.rootfs=/rootfs'
      - '--path.sysfs=/host/sys'
      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
      - '--collector.cpu.info'
      - '--collector.meminfo'
      - '--no-collector.wifi'
      - '--no-collector.hwmon'
      - '--no-collector.btrfs'
      # 暴露 textfile_collector 目录，供备份脚本写入心跳指标
      - '--collector.textfile.directory=/var/lib/node_exporter/textfile_collector'
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
      - /var/lib/node_exporter:/var/lib/node_exporter:ro
    networks:
      - monitoring
    healthcheck:
      test: ["CMD", "wget", "-q", "--spider", "http://localhost:9100/metrics"]
      interval: 30s
      timeout: 10s
      retries: 3

  # Blackbox Exporter - HTTP/TLS 探测 & 证书过期检查
  # 内存占用 ~16MB，可放心加入单机部署
  blackbox-exporter:
    image: prom/blackbox-exporter:v0.24.0
    container_name: sub2api-blackbox
    restart: unless-stopped
    mem_limit: 32m
    cpus: '0.05'
    command:
      - '--config.file=/etc/blackbox_exporter/config.yml'
    volumes:
      - ./blackbox/config.yml:/etc/blackbox_exporter/config.yml:ro
    networks:
      - monitoring
    healthcheck:
      test: ["CMD", "wget", "-q", "--spider", "http://localhost:9115/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3

volumes:
  prometheus-data:
    driver: local
  grafana-data:
    driver: local

networks:
  monitoring:
    driver: bridge