Files
xiaoxia-saas/infra/docker/compose.yml
CI Bot e4ac398397 fix: Worker 健康检查彻底修复 - 移除不可用的 pgrep 和 PID1 检查
根因:#1714 队列隔离后 entrypoint 启动两个 celery worker 子进程,
PID 1 变为 bash。旧健康检查依赖 pgrep(容器内不存在)或
/proc/1/cmdline(PID 1 是 bash 不是 celery),永远返回失败。
此前靠 cron 脚本 fix-worker-healthcheck.sh 每 30 分钟擦屁股。

修复:统一改为扫描 /proc/[0-9]*/cmdline 查找 celery 进程,
覆盖所有部署/回滚/CI 脚本(10 处替换)。已移除 cron 补丁。
2026-09-08 19:07:37 +08:00

232 lines
7.3 KiB
YAML
Executable File

# ===========================================
# 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)
# WEB_DOCKERFILE - Web Dockerfile 路径
# WEB_NGINX_CONF - Nginx 配置文件路径
# 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
# WORKER_CONCURRENCY - Worker 并发数 (默认: 4)
# WORKER_MAX_TASKS_PER_CHILD - Worker 每个子进程最大任务数 (默认: 100)
#
# 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
#
# ===========================================
# 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: ${API_IMAGE:-xiaoxia-saas-api:dev}
# 不在生产环境构建镜像,使用预构建的镜像
# build:
# context: ../..
# dockerfile: infra/docker/api.Dockerfile
container_name: xiaoxia-api-${ENV:-staging}
restart: unless-stopped
stop_grace_period: 30s
stop_signal: SIGTERM
# 环境变量文件(包含数据库密码等敏感信息)
env_file:
- ../../.env
environment:
APP_ENV: ${APP_ENV:-staging}
APP_VERSION: ${APP_VERSION:-unknown}
GENERATED_FILES_DIR: /app/generated
GENERATED_FILES_URL_PREFIX: /generated-files
PUBLIC_API_BASE_URL: ${PUBLIC_API_BASE_URL:-https://api.xiaoxiajianji.com}
# 端口映射
# Staging: 8000 -> 8000
# Production: 8001 -> 8000
ports:
- "127.0.0.1:${API_PORT:-8000}:8000"
# 共享生成文件目录
volumes:
- generated-files:/app/generated
networks:
- xiaoxia-net
# 健康检查配置
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
# =========================================
# 资源限制建议(生产环境建议启用)
# =========================================
deploy:
resources:
limits:
cpus: '2.0'
memory: 2g
reservations:
cpus: '0.5'
memory: 512M
# =========================================
# Worker 服务(Celery 任务队列)
# =========================================
worker:
image: ${WORKER_IMAGE:-xiaoxia-saas-worker:dev}
container_name: xiaoxia-worker-${ENV:-staging}
restart: unless-stopped
stop_grace_period: 300s
stop_signal: SIGTERM
env_file:
- ../../.env
environment:
APP_ENV: ${APP_ENV:-staging}
APP_VERSION: ${APP_VERSION:-unknown}
WORKER_CONCURRENCY: ${WORKER_CONCURRENCY:-4}
WORKER_MAX_TASKS_PER_CHILD: ${WORKER_MAX_TASKS_PER_CHILD:-100}
# #1714 队列隔离:generation 队列独占 worker(默认并发 2),其余并发给转码
GENERATION_CONCURRENCY: ${GENERATION_CONCURRENCY:-2}
GENERATED_FILES_DIR: /app/generated
GENERATED_FILES_URL_PREFIX: /generated-files
PUBLIC_API_BASE_URL: ${PUBLIC_API_BASE_URL:-https://api.xiaoxiajianji.com}
volumes:
- generated-files:/app/generated
networks:
- xiaoxia-net
# 健康检查配置
# 注:celery inspect ping 依赖 broker 连接,在容器内不可靠,改用进程检查
healthcheck:
test: ["CMD-SHELL", "for pid in /proc/[0-9]*/cmdline; do if grep -ql celery \"$pid\" 2>/dev/null; then exit 0; fi; done; exit 1"]
interval: 30s
timeout: 10s
retries: 3
start_period: 40s
logging: *default-logging
# =========================================
# 资源限制建议(生产环境建议启用)
# =========================================
# 注意: Worker 需要处理视频,建议分配更多资源
# #1714 队列隔离后容器内运行 generation + transcode 两个 worker 进程,
# 总并发 = WORKER_CONCURRENCY(默认 4),4C8G 以上确保视频渲染不 OOM
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}
# 不在生产环境构建镜像,使用 web-artifact.Dockerfile
# build:
# context: ../..
# dockerfile: ${WEB_DOCKERFILE:-infra/docker/web.Dockerfile}
# args:
# NGINX_CONF: ${WEB_NGINX_CONF:-infra/docker/nginx.conf}
container_name: xiaoxia-web-${ENV:-staging}
restart: unless-stopped
# 端口映射
# Staging: 3001 -> 80
# Production: 3002 -> 80 (通过 Nginx 反向代理)
ports:
- "127.0.0.1:${WEB_PORT:-3001}:80"
networks:
- xiaoxia-net
# =========================================
# Nginx 配置运行时覆盖
# 确保容器使用正确环境的 nginx 配置,即使镜像构建时使用了默认配置
# 注意: 只覆盖 /etc/nginx/conf.d/default.conf,不挂载 /usr/share/nginx/html
# =========================================
environment:
- NGINX_ENV=${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
# =========================================
# 资源限制建议
# =========================================
deploy:
resources:
limits:
cpus: '0.5'
memory: 512M
# ===========================================
# 共享卷配置
# ===========================================
volumes:
generated-files:
driver: local
driver_opts:
type: none
o: bind
# 重要: 确保主机目录存在且有正确权限
# Staging: /var/lib/xiaoxia-saas-staging/generated
# Production: /var/lib/xiaoxia-saas-production/generated
device: ${GENERATED_FILES_HOST_DIR:?GENERATED_FILES_HOST_DIR must be set in .env}
# ===========================================
# 网络配置
# ===========================================
networks:
xiaoxia-net:
external: true
# 网络名根据 ENV 变量区分,实现 staging/production 环境隔离
# staging: xiaoxia-net-staging
# production: xiaoxia-net-production
name: xiaoxia-net-${ENV:-staging}