xiaoxia-saas/infra/docker/compose.yml

# ===========================================
# 小虾剪辑 SaaS Docker Compose 配置
# ===========================================
#
# 用法:
#   Staging: docker compose --env-file ../../.env -f compose.yml up -d
#   Production: 设置相关环境变量后执行
#
# 环境变量说明:
#   API_IMAGE        - API 镜像名称 (默认: xiaoxia-saas-api:dev)
#   WORKER_IMAGE     - Worker 镜像名称 (默认: xiaoxia-saas-worker:dev)
#   WEB_IMAGE        - Web 镜像名称 (默认: xiaoxia-saas-web:dev)
#   API_PORT         - API 端口映射 (staging: 8000, production: 8001)
#   WEB_PORT         - Web 端口映射 (staging: 3001, production: 3002)
#   GENERATED_FILES_HOST_DIR - 生成文件的主机目录
#   GENERATION_CONCURRENCY    - Generation worker 并发（用户实时任务，默认 2）
#   TRANSCODE_CONCURRENCY     - Transcode worker 并发（后台/转码/AI，默认 2）
#   WORKER_MAX_TASKS_PER_CHILD - Worker 每个子进程最大任务数 (默认: 100)
#   BEAT_ENABLED              - 容器内启动 celery beat（默认 1；独立 beat 容器部署设为 0）
#   WORKER_CONCURRENCY        - 兼容旧变量：未显式设置上面两个并发时按此总数分配
#
# 重要:
#   - 生产环境不要挂载 web-dist volume，否则会导致 403
#   - 确保环境隔离网络已创建: docker network create xiaoxia-net-${ENV}
#   - ENV=staging  -> xiaoxia-net-staging
#   - ENV=production -> xiaoxia-net-production
#
# #2073 队列分流：worker 容器内跑三个独立进程——beat(只发定时任务)、
# generation worker(只消费 generation 队列，实时高优)、transcode worker(消费
# transcode + celery 队列，后台任务)。beat 不再嵌入 generation worker，
# 不占实时任务槽位；TRANSCODE_CONCURRENCY 独立伸缩，不再依赖 WORKER_CONCURRENCY 差值。

# ===========================================
# 日志轮转配置（所有服务共享）
# ===========================================
x-logging: &default-logging
  driver: json-file
  options:
    max-size: "50m"
    max-file: "3"

services:
  # =========================================
  # API 服务
  # =========================================
  api:
    image: ${API_IMAGE:-xiaoxia-saas-api:dev}
    container_name: xiaoxia-api-${ENV:-staging}
    restart: unless-stopped
    stop_grace_period: 30s
    stop_signal: SIGTERM

    env_file:
      - ../../.env

    environment:
      APP_ENV: ${APP_ENV:-staging}
      GENERATED_FILES_DIR: /app/generated
      GENERATED_FILES_URL_PREFIX: /generated-files
      PUBLIC_API_BASE_URL: ${PUBLIC_API_BASE_URL:-https://api.xiaoxiajianji.com}

    ports:
      - "127.0.0.1:${API_PORT:-8000}:8000"

    volumes:
      - generated-files:/app/generated
      - ../../deploy/configs:/app/configs:ro

    networks:
      - xiaoxia-net

    healthcheck:
      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health', timeout=5)"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

    logging: *default-logging

    deploy:
      resources:
        limits:
          cpus: '2.0'
          memory: 2g
        reservations:
          cpus: '0.5'
          memory: 512M

  # =========================================
  # Worker 服务（#2073 队列分流：beat + generation + transcode 同容器三进程）
  # =========================================
  # 三个进程独立启动，任一退出则容器整体退出由 docker restart 拉起；
  # 各自的并发与资源占用通过环境变量控制：
  #   - generation：GENERATION_CONCURRENCY（默认 2），消费 generation 队列
  #   - transcode： TRANSCODE_CONCURRENCY（默认 2），消费 transcode,celery 队列
  #   - beat：      不消费任务，只发定时任务到 celery 默认队列
  worker:
    image: ${WORKER_IMAGE:-xiaoxia-saas-worker:dev}

    container_name: xiaoxia-worker-${ENV:-staging}
    restart: unless-stopped
    # 长任务（ingest HEVC 转码最长 30min、生成硬超时 11min）给足优雅关闭窗口
    stop_grace_period: 300s
    stop_signal: SIGTERM

    env_file:
      - ../../.env

    environment:
      APP_ENV: ${APP_ENV:-staging}
      # 兼容旧变量：若两个 *_CONCURRENCY 均未显式设置，entrypoint 会按此总数分配
      WORKER_CONCURRENCY: ${WORKER_CONCURRENCY:-4}
      WORKER_MAX_TASKS_PER_CHILD: ${WORKER_MAX_TASKS_PER_CHILD:-100}
      # #2073 队列独立伸缩：generation 默认 2，transcode 默认 2（不再差值计算）
      GENERATION_CONCURRENCY: ${GENERATION_CONCURRENCY:-2}
      TRANSCODE_CONCURRENCY: ${TRANSCODE_CONCURRENCY:-2}
      # beat 默认在本容器启动；独立 beat 容器部署时设为 0
      BEAT_ENABLED: ${BEAT_ENABLED:-1}
      GENERATED_FILES_DIR: /app/generated
      GENERATED_FILES_URL_PREFIX: /generated-files
      PUBLIC_API_BASE_URL: ${PUBLIC_API_BASE_URL:-https://api.xiaoxiajianji.com}

    volumes:
      - generated-files:/app/generated

    networks:
      - xiaoxia-net

    # 健康检查：至少有一个 celery worker 进程在跑（beat 本身不作为存活依据）
    healthcheck:
      test: ["CMD-SHELL", "grep -q 'celery.*worker' /proc/[0-9]*/cmdline 2>/dev/null || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

    logging: *default-logging

    # 资源限制：容器总资源 = gen + trans + beat，按 2+2 并发场景建议 4C8G；
    # 后续如需独立扩容/重启，可拆为 worker-generation / worker-transcode / worker-beat 三个 service。
    deploy:
      resources:
        limits:
          cpus: '4.0'
          memory: 8g
        reservations:
          cpus: '1.0'
          memory: 2G

  # =========================================
  # Web 服务（Nginx + 前端静态文件）
  # =========================================
  web:
    image: ${WEB_IMAGE:-xiaoxia-saas-web:dev}

    container_name: xiaoxia-web-${ENV:-staging}
    restart: unless-stopped

    ports:
      - "127.0.0.1:${WEB_PORT:-3001}:80"

    networks:
      - xiaoxia-net

    environment:
      - APP_ENV=${ENV:-staging}
    volumes:
      - ./nginx-${ENV:-staging}.conf:/etc/nginx/conf.d/default.conf:ro

    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://127.0.0.1:80"]
      interval: 30s
      timeout: 5s
      retries: 3

    logging: *default-logging

    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 512M

# ===========================================
# 共享卷配置
# ===========================================
volumes:
  generated-files:
    driver: local
    driver_opts:
      type: none
      o: bind
      device: ${GENERATED_FILES_HOST_DIR:?GENERATED_FILES_HOST_DIR must be set in .env}

# ===========================================
# 网络配置
# ===========================================
networks:
  xiaoxia-net:
    external: true
    name: xiaoxia-net-${ENV:-staging}