rwadurian/backend/infrastructure/docker-compose.yml

# =============================================================================
# RWA Infrastructure - 可观测性与服务治理基础设施
# =============================================================================
#
# 模块化设计，可按需启用：
#   - consul:     服务发现与配置中心
#   - jaeger:     分布式链路追踪
#   - loki:       日志聚合
#   - grafana:    统一可视化仪表盘
#
# 使用方法:
#   ./deploy.sh up                    # 启动所有组件
#   ./deploy.sh up consul             # 只启动 Consul
#   ./deploy.sh up jaeger loki        # 启动指定组件
#   ./deploy.sh down                  # 停止所有组件
#
# =============================================================================

services:
  # ===========================================================================
  # Consul - 服务发现与配置中心
  # ===========================================================================
  # 功能：
  #   - 服务注册与发现
  #   - 健康检查
  #   - KV 配置存储
  #   - 多数据中心支持
  # ===========================================================================
  consul:
    image: docker.io/hashicorp/consul:1.18
    container_name: rwa-consul
    command: agent -server -bootstrap-expect=1 -ui -client=0.0.0.0 -datacenter=rwa-dc1
    environment:
      TZ: Asia/Shanghai
      CONSUL_BIND_INTERFACE: eth0
    ports:
      - "${CONSUL_HTTP_PORT:-8500}:8500"     # HTTP API + UI
      - "${CONSUL_DNS_PORT:-8600}:8600/udp"  # DNS
      - "8301:8301"                           # Serf LAN
      - "8302:8302"                           # Serf WAN
    volumes:
      - consul_data:/consul/data
      - ./consul/config:/consul/config:ro
    healthcheck:
      test: ["CMD", "consul", "members"]
      interval: 10s
      timeout: 5s
      retries: 5
    restart: unless-stopped
    networks:
      - rwa-infra
    profiles:
      - consul
      - full

  # ===========================================================================
  # Jaeger - 分布式链路追踪
  # ===========================================================================
  # 功能：
  #   - 请求链路追踪
  #   - 性能瓶颈分析
  #   - 服务依赖可视化
  #   - 错误定位
  # ===========================================================================
  jaeger:
    image: docker.io/jaegertracing/all-in-one:1.54
    container_name: rwa-jaeger
    environment:
      TZ: Asia/Shanghai
      COLLECTOR_ZIPKIN_HOST_PORT: :9411
      COLLECTOR_OTLP_ENABLED: true
      SPAN_STORAGE_TYPE: badger
      BADGER_EPHEMERAL: false
      BADGER_DIRECTORY_VALUE: /badger/data
      BADGER_DIRECTORY_KEY: /badger/key
    ports:
      - "${JAEGER_UI_PORT:-16686}:16686"     # UI
      - "6831:6831/udp"                       # Thrift compact (agent)
      - "6832:6832/udp"                       # Thrift binary (agent)
      - "4317:4317"                           # OTLP gRPC
      - "4318:4318"                           # OTLP HTTP
      - "14250:14250"                         # gRPC (collector)
      - "14268:14268"                         # HTTP (collector)
      - "9411:9411"                           # Zipkin compatible
    volumes:
      - jaeger_data:/badger
    healthcheck:
      test: ["CMD-SHELL", "wget -q --spider http://localhost:16686 || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 5
    restart: unless-stopped
    networks:
      - rwa-infra
    profiles:
      - jaeger
      - tracing
      - full

  # ===========================================================================
  # Loki - 日志聚合系统
  # ===========================================================================
  # 功能：
  #   - 日志收集与存储
  #   - 日志查询 (LogQL)
  #   - 与 Grafana 深度集成
  #   - 低资源占用
  # ===========================================================================
  loki:
    image: docker.io/grafana/loki:2.9.4
    container_name: rwa-loki
    command: -config.file=/etc/loki/loki-config.yml
    ports:
      - "${LOKI_PORT:-3100}:3100"
    volumes:
      - ./loki/loki-config.yml:/etc/loki/loki-config.yml:ro
      - loki_data:/loki
    healthcheck:
      test: ["CMD-SHELL", "wget -q --spider http://localhost:3100/ready || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 5
    restart: unless-stopped
    networks:
      - rwa-infra
    profiles:
      - loki
      - logging
      - full

  # ===========================================================================
  # Promtail - 日志收集代理
  # ===========================================================================
  # 功能：
  #   - 收集 Docker 容器日志
  #   - 日志标签化
  #   - 推送到 Loki
  # ===========================================================================
  promtail:
    image: docker.io/grafana/promtail:2.9.4
    container_name: rwa-promtail
    command: -config.file=/etc/promtail/promtail-config.yml
    volumes:
      - ./loki/promtail-config.yml:/etc/promtail/promtail-config.yml:ro
      - /var/lib/docker/containers:/var/lib/docker/containers:ro
      - /var/run/docker.sock:/var/run/docker.sock:ro
      - promtail_positions:/tmp
    depends_on:
      loki:
        condition: service_healthy
    restart: unless-stopped
    networks:
      - rwa-infra
    profiles:
      - loki
      - logging
      - full

  # ===========================================================================
  # Grafana - 统一可视化平台
  # ===========================================================================
  # 功能：
  #   - 多数据源集成 (Prometheus, Loki, Jaeger)
  #   - 自定义仪表盘
  #   - 告警管理
  #   - 团队协作
  # ===========================================================================
  grafana:
    image: docker.io/grafana/grafana:10.3.1
    container_name: rwa-grafana
    environment:
      - TZ=Asia/Shanghai
      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin123}
      - GF_USERS_ALLOW_SIGN_UP=false
      # 服务器配置
      - GF_SERVER_ROOT_URL=${GRAFANA_ROOT_URL:-http://localhost:3030}
      - GF_SERVER_SERVE_FROM_SUB_PATH=false
      # 安全配置
      - GF_SECURITY_ALLOW_EMBEDDING=true
      - GF_SECURITY_COOKIE_SAMESITE=lax
      # 功能开关
      - GF_FEATURE_TOGGLES_ENABLE=traceqlEditor tempoSearch tempoBackendSearch
      # 日志级别
      - GF_LOG_LEVEL=${GRAFANA_LOG_LEVEL:-info}
    ports:
      - "${GRAFANA_PORT:-3030}:3000"
    volumes:
      - grafana_data:/var/lib/grafana
      - ./grafana/provisioning:/etc/grafana/provisioning:ro
    healthcheck:
      test: ["CMD-SHELL", "wget -q --spider http://localhost:3000/api/health || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 5
    restart: unless-stopped
    networks:
      - rwa-infra
    profiles:
      - grafana
      - full

  # ===========================================================================
  # Prometheus - 指标收集 (可选，如果 api-gateway 已有可跳过)
  # ===========================================================================
  prometheus:
    image: docker.io/prom/prometheus:v2.49.1
    container_name: rwa-prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=15d'
      - '--web.enable-lifecycle'
      - '--web.enable-admin-api'
    ports:
      - "${PROMETHEUS_PORT:-9090}:9090"
    volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./prometheus/rules:/etc/prometheus/rules:ro
      - prometheus_data:/prometheus
    healthcheck:
      test: ["CMD-SHELL", "wget -q --spider http://localhost:9090/-/healthy || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 5
    restart: unless-stopped
    networks:
      - rwa-infra
    profiles:
      - prometheus
      - metrics
      - full

# =============================================================================
# Volumes - 持久化存储
# =============================================================================
volumes:
  consul_data:
    driver: local
  jaeger_data:
    driver: local
  loki_data:
    driver: local
  promtail_positions:
    driver: local
  grafana_data:
    driver: local
  prometheus_data:
    driver: local

# =============================================================================
# Networks
# =============================================================================
networks:
  rwa-infra:
    driver: bridge
    name: rwa-infra