hunjing/docker/docker-compose.infra.yml

# ==============================
# 魂镜数据基础设施编排（关系库 / 缓存 / 向量 / 图库 / 对象存储）。
# 与应用层 docker-compose.app.yml 解耦：本文件创建并拥有共享网络 hunjing-net 与全部命名卷，
# 应用层以 external 方式引用该网络连接数据库等服务。
# 本地开发默认 SQLite，无需启动本文件；详见根目录 CLAUDE.md 与 docker/README.md。
#
# 常用命令：
#   # 启动全部基础设施（首次会创建 hunjing-net 网络）
#   docker compose -f docker/docker-compose.infra.yml up -d
#   # 仅启动部分按需服务
#   docker compose -f docker/docker-compose.infra.yml up -d hunjing-postgres hunjing-redis
#   # 启用后期大规模图数据库 NebulaGraph（需带 --profile）
#   docker compose -f docker/docker-compose.infra.yml --profile nebulagraph up -d hunjing-nebula-graphd hunjing-nebula-console-init
#   # 停止并保留数据卷
#   docker compose -f docker/docker-compose.infra.yml down
#   # 停止并清除数据卷（谨慎，会丢失数据）
#   docker compose -f docker/docker-compose.infra.yml down -v
#
# 内存限制：每个服务通过 deploy.resources.limits/reservations 约束内存，
# 默认值为本地模拟正式环境的保守配置，可按宿主机规格调整。
# ==============================
name: hunjing

networks:
  hunjing-net:
    name: hunjing-net
    driver: bridge

volumes:
  hunjing-pg-data:
  hunjing-redis-data:
  hunjing-neo4j-data:
  hunjing-neo4j-logs:
  hunjing-nebula-data:
  hunjing-nebula-logs:
  hunjing-etcd-data:
  hunjing-minio-data:
  hunjing-milvus-data:

services:
  # ============================== 金匮 · 正式环境关系型数据库（PostgreSQL） ==============================
  hunjing-postgres:
    image: postgres:16-alpine
    container_name: hunjing-postgres
    restart: unless-stopped
    networks: [hunjing-net]
    environment:
      POSTGRES_DB: ${POSTGRES_DB:-hunjing}
      POSTGRES_USER: ${POSTGRES_USER:-hunjing}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-change-me}
      TZ: ${TIMEZONE:-Asia/Shanghai}
    volumes:
      - hunjing-pg-data:/var/lib/postgresql/data
      - ./postgres/init-shenshi.sql:/docker-entrypoint-initdb.d/10-init-shenshi.sql:ro
    ports:
      - "${POSTGRES_PORT:-5432}:5432"
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-hunjing} -d ${POSTGRES_DB:-hunjing}"]
      interval: 10s
      timeout: 5s
      retries: 5
    deploy:
      resources:
        limits: { memory: 512M }
        reservations: { memory: 128M }

  # ============================== 灵泉 · 缓存与后台任务队列（Redis） ==============================
  hunjing-redis:
    image: redis:7-alpine
    container_name: hunjing-redis
    restart: unless-stopped
    networks: [hunjing-net]
    command: ["redis-server", "--appendonly", "yes"]
    volumes:
      - hunjing-redis-data:/data
    ports:
      - "${REDIS_PORT:-6379}:6379"
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 5s
      retries: 5
    deploy:
      resources:
        limits: { memory: 256M }
        reservations: { memory: 64M }

  # ============================== 玄络 · 图数据库 Neo4j（原型 / 中小规模，默认图库） ==============================
  hunjing-neo4j:
    image: neo4j:5-community
    container_name: hunjing-neo4j
    restart: unless-stopped
    networks: [hunjing-net]
    environment:
      NEO4J_AUTH: ${NEO4J_USER:-neo4j}/${NEO4J_PASSWORD:-change-me}
      NEO4J_PLUGINS: '["apoc"]'
      TZ: ${TIMEZONE:-Asia/Shanghai}
    volumes:
      - hunjing-neo4j-data:/data
      - hunjing-neo4j-logs:/logs
    ports:
      - "7474:7474"   # Neo4j Browser（HTTP）
      - "7687:7687"   # Bolt 协议
    deploy:
      resources:
        limits: { memory: 1G }
        reservations: { memory: 256M }

  # ============================== 玄络 · 图数据库 NebulaGraph（后期大规模，二选一） ==============================
  # NebulaGraph 由 metad（元数据）、storaged（存储）、graphd（查询）三个服务组成，
  # 首次启动需通过 console 注册 storage hosts 并创建 space（由下方 console-init 自动完成）。
  # 启用方式（需带 --profile nebulagraph）：
  #   docker compose -f docker/docker-compose.infra.yml --profile nebulagraph up -d hunjing-nebula-graphd hunjing-nebula-console-init
  # 同时在 .env 中设置 GRAPH_DB_TYPE=nebulagraph；默认不启用、不随 up 拉起。
  hunjing-nebula-metad:
    image: vesoft/nebula-metad:v3.6.0
    container_name: hunjing-nebula-metad
    profiles: ["nebulagraph"]
    restart: unless-stopped
    networks: [hunjing-net]
    environment:
      USER: root
      TZ: ${TIMEZONE:-Asia/Shanghai}
    command:
      - --meta_server_addrs=hunjing-nebula-metad:9559
      - --local_ip=hunjing-nebula-metad
      - --ws_ip=hunjing-nebula-metad
      - --port=9559
      - --data_path=/data/meta
      - --log_dir=/logs/meta
    volumes:
      - hunjing-nebula-data:/data
      - hunjing-nebula-logs:/logs
    deploy:
      resources:
        limits: { memory: 512M }
        reservations: { memory: 128M }

  hunjing-nebula-storaged:
    image: vesoft/nebula-storaged:v3.6.0
    container_name: hunjing-nebula-storaged
    profiles: ["nebulagraph"]
    restart: unless-stopped
    networks: [hunjing-net]
    environment:
      USER: root
      TZ: ${TIMEZONE:-Asia/Shanghai}
    command:
      - --meta_server_addrs=hunjing-nebula-metad:9559
      - --local_ip=hunjing-nebula-storaged
      - --ws_ip=hunjing-nebula-storaged
      - --port=9779
      - --data_path=/data/storage
      - --log_dir=/logs/storage
    volumes:
      - hunjing-nebula-data:/data
      - hunjing-nebula-logs:/logs
    depends_on:
      hunjing-nebula-metad:
        condition: service_started
    deploy:
      resources:
        limits: { memory: 1G }
        reservations: { memory: 256M }

  hunjing-nebula-graphd:
    image: vesoft/nebula-graphd:v3.6.0
    container_name: hunjing-nebula-graphd
    profiles: ["nebulagraph"]
    restart: unless-stopped
    networks: [hunjing-net]
    environment:
      USER: root
      TZ: ${TIMEZONE:-Asia/Shanghai}
    command:
      - --meta_server_addrs=hunjing-nebula-metad:9559
      - --ws_ip=hunjing-nebula-graphd
      - --port=9669
      - --log_dir=/logs/graph
    volumes:
      - hunjing-nebula-logs:/logs
    ports:
      - "${NEBULAGRAPH_PORT:-9669}:9669"   # 应用连接端口
    depends_on:
      hunjing-nebula-metad:
        condition: service_started
    deploy:
      resources:
        limits: { memory: 512M }
        reservations: { memory: 128M }

  # 一次性初始化：注册 storage hosts 并创建 space。
  # 若 storaged 尚未 ONLINE 导致失败，待几秒后重跑：
  #   docker compose -f docker/docker-compose.infra.yml --profile nebulagraph up hunjing-nebula-console-init
  hunjing-nebula-console-init:
    image: vesoft/nebula-console:v3.6.0
    container_name: hunjing-nebula-console-init
    profiles: ["nebulagraph"]
    restart: "no"
    networks: [hunjing-net]
    depends_on:
      hunjing-nebula-graphd:
        condition: service_started
      hunjing-nebula-storaged:
        condition: service_started
    environment:
      NEBULA_USER: ${NEBULAGRAPH_USER:-root}
      NEBULA_PASSWORD: ${NEBULAGRAPH_PASSWORD:-nebula}
      NEBULA_SPACE: ${NEBULAGRAPH_SPACE:-hunjing}
    entrypoint:
      - sh
      - -c
      - |
        echo "等待 graphd 就绪..."
        for i in $$(seq 1 30); do
          if nebula-console -addr=hunjing-nebula-graphd -port=9669 -u "$$NEBULA_USER" -p "$$NEBULA_PASSWORD" -e "SHOW HOSTS;" >/dev/null 2>&1; then
            echo "graphd 就绪，开始注册 hosts 并创建 space"
            nebula-console -addr=hunjing-nebula-graphd -port=9669 -u "$$NEBULA_USER" -p "$$NEBULA_PASSWORD" -e \
              "ADD HOSTS \"hunjing-nebula-storaged\":9779; CREATE SPACE IF NOT EXISTS $$NEBULA_SPACE(vid_type=FIXED_STRING(64), partition_num=10, replica_factor=1);"
            echo "初始化完成"
            exit 0
          fi
          echo "graphd 尚未就绪，2s 后重试 ($$i/30)"
          sleep 2
        done
        echo "graphd 在超时内未就绪" >&2
        exit 1
    deploy:
      resources:
        limits: { memory: 256M }
        reservations: { memory: 64M }

  # ============================== 灵犀 · 向量数据库（Milvus）及其依赖 ==============================
  # 灵犀 standalone 依赖 etcd（灵犀·元册，元数据）与 minio（玉函，对象存储块）。
  hunjing-etcd:
    image: quay.io/coreos/etcd:v3.5.16
    container_name: hunjing-etcd
    restart: unless-stopped
    networks: [hunjing-net]
    environment:
      - ETCD_AUTO_COMPACTION_MODE=revision
      - ETCD_AUTO_COMPACTION_RETENTION=1000
      - ETCD_QUOTA_BACKEND_BYTES=4294967296
      - ETCD_SNAPSHOT_COUNT=50000
    volumes:
      - hunjing-etcd-data:/etcd
    command: >-
      etcd
      -advertise-client-urls=http://127.0.0.1:2379
      -listen-client-urls=http://0.0.0.0:2379
      --data-dir=/etcd
    healthcheck:
      test: ["CMD", "etcdctl", "endpoint", "health"]
      interval: 30s
      timeout: 20s
      retries: 3
    deploy:
      resources:
        limits: { memory: 512M }
        reservations: { memory: 128M }

  # 玉函 · 对象存储 MinIO（兼灵犀块存储）
  hunjing-minio:
    image: minio/minio:RELEASE.2024-11-07T00-52-20Z
    container_name: hunjing-minio
    restart: unless-stopped
    networks: [hunjing-net]
    # MinIO 同时作为 Milvus 的存储后端与魂镜对象存储（STORAGE_PROVIDER=minio）。
    environment:
      MINIO_ROOT_USER: ${MINIO_ACCESS_KEY_ID:-minioadmin}
      MINIO_ROOT_PASSWORD: ${MINIO_SECRET_ACCESS_KEY:-minioadmin}
    volumes:
      - hunjing-minio-data:/minio_data
    command: minio server /minio_data --console-address ":9001"
    ports:
      - "${MINIO_EXTERNAL_PORT:-9000}:9000"   # S3 API
      - "9001:9001"                            # 管理控制台
    healthcheck:
      test: ["CMD-SHELL", "mc ready local || exit 0"]
      interval: 30s
      timeout: 20s
      retries: 3
    deploy:
      resources:
        limits: { memory: 512M }
        reservations: { memory: 128M }

  # 灵犀 · 向量数据库 Milvus
  hunjing-milvus:
    image: milvusdb/milvus:v2.4.17
    container_name: hunjing-milvus
    restart: unless-stopped
    networks: [hunjing-net]
    command: ["milvus", "run", "standalone"]
    security_opt:
      - seccomp:unconfined
    environment:
      ETCD_ENDPOINTS: hunjing-etcd:2379
      MINIO_ADDRESS: hunjing-minio:9000
      TZ: ${TIMEZONE:-Asia/Shanghai}
    volumes:
      - hunjing-milvus-data:/var/lib/milvus
    ports:
      - "${MILVUS_PORT:-19530}:19530"
      - "9091:9091"   # 健康检查 / metrics
    depends_on:
      hunjing-etcd:
        condition: service_healthy
      hunjing-minio:
        condition: service_started
    healthcheck:
      test: ["CMD-SHELL", "curl -sf http://localhost:9091/healthz || exit 1"]
      interval: 30s
      start_period: 120s
      timeout: 20s
      retries: 3
    deploy:
      resources:
        limits: { memory: 2G }
        reservations: { memory: 512M }

  # ============================== 灵犀·观 · Milvus 可视化管理（Attu） ==============================
  # Attu 是 Milvus 官方 Web 管理界面，用于查看 collection、数据与运行查询。
  # 启动 Milvus 后访问 http://localhost:${ATTU_PORT:-8001}，连接地址默认指向 hunjing-milvus。
  hunjing-attu:
    image: zilliztech/attu:v2.4
    container_name: hunjing-attu
    restart: unless-stopped
    networks: [hunjing-net]
    environment:
      MILVUS_URL: hunjing-milvus:19530
      TZ: ${TIMEZONE:-Asia/Shanghai}
    ports:
      - "${ATTU_PORT:-8001}:3000"
    depends_on:
      hunjing-milvus:
        condition: service_started
    deploy:
      resources:
        limits: { memory: 256M }
        reservations: { memory: 64M }

  # ============================== 金匮·摹本 · PostgreSQL 备份 / 恢复（手动触发，profile: backup） ==============================
  # 备份：docker compose -f docker/docker-compose.infra.yml --profile backup run --rm hunjing-pg-backup
  # 恢复：见 docker/backup/backup-restore.sh 顶部命令（需 override entrypoint 并传 RESTORE_FILE）。
  # 备份产物落在项目根 backups/ 目录（已加入 .gitignore）。
  hunjing-pg-backup:
    image: postgres:16-alpine
    container_name: hunjing-pg-backup
    profiles: ["backup"]
    restart: "no"
    networks: [hunjing-net]
    environment:
      PGHOST: hunjing-postgres
      PGPORT: "5432"
      PGUSER: ${POSTGRES_USER:-hunjing}
      PGPASSWORD: ${POSTGRES_PASSWORD:-change-me}
      PGDATABASE: ${POSTGRES_DB:-hunjing}
      BACKUP_RETAIN_DAYS: ${BACKUP_RETAIN_DAYS:-7}
    volumes:
      - ./backup:/backup:ro
      - ../backups:/backups
    entrypoint: ["/bin/sh", "/backup/backup-postgres.sh"]
    deploy:
      resources:
        limits: { memory: 256M }
        reservations: { memory: 64M }