Root cause of 502 errors under 30 concurrent users: the production server was running dev-mode infrastructure (Vite dev server, NestJS --watch, no DB connection pooling, single Node.js process). Changes: - backend/Dockerfile: multi-stage prod build (compiled JS, no devDeps) - frontend/Dockerfile: multi-stage prod build (static assets served by nginx) - frontend/nginx.conf: SPA routing config for frontend container - docker-compose.prod.yml: production overlay with tuned Postgres, memory limits, health checks, restart policies - nginx/production.conf: keepalive upstreams, proxy buffering, rate limiting - backend/src/main.ts: Node.js clustering (1 worker per CPU, up to 4), conditional request logging, production CORS - backend/src/app.module.ts: TypeORM connection pool (max 30, min 5) - docs/DEPLOYMENT.md: new Production Deployment section Deploy with: docker compose -f docker-compose.yml -f docker-compose.prod.yml up -d --build Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
97 lines
2.7 KiB
YAML
97 lines
2.7 KiB
YAML
# Production override — use with:
|
|
# docker compose -f docker-compose.yml -f docker-compose.prod.yml up -d --build
|
|
#
|
|
# For SSL add docker-compose.ssl.yml as well:
|
|
# docker compose -f docker-compose.yml -f docker-compose.prod.yml -f docker-compose.ssl.yml up -d --build
|
|
#
|
|
# What this changes from the base (dev) config:
|
|
# - Backend: production Dockerfile (compiled JS, no watch, no devDeps)
|
|
# - Frontend: production Dockerfile (static build served by nginx, not Vite)
|
|
# - No source-code volume mounts (uses baked-in built code)
|
|
# - Memory limits and health checks on backend
|
|
# - Restart policies for reliability
|
|
|
|
services:
|
|
nginx:
|
|
ports:
|
|
- "80:80"
|
|
- "443:443"
|
|
volumes:
|
|
- ./nginx/production.conf:/etc/nginx/conf.d/default.conf:ro
|
|
- certbot_www:/var/www/certbot:ro
|
|
- certbot_conf:/etc/letsencrypt:ro
|
|
restart: unless-stopped
|
|
|
|
backend:
|
|
build:
|
|
context: ./backend
|
|
dockerfile: Dockerfile # production Dockerfile (compiled JS)
|
|
volumes: [] # override: no source mounts in prod
|
|
environment:
|
|
- DATABASE_URL=${DATABASE_URL}
|
|
- REDIS_URL=${REDIS_URL}
|
|
- JWT_SECRET=${JWT_SECRET}
|
|
- NODE_ENV=production
|
|
- AI_API_URL=${AI_API_URL}
|
|
- AI_API_KEY=${AI_API_KEY}
|
|
- AI_MODEL=${AI_MODEL}
|
|
- AI_DEBUG=${AI_DEBUG:-false}
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
memory: 1024M
|
|
reservations:
|
|
memory: 256M
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "wget -qO- http://localhost:3000/api || exit 1"]
|
|
interval: 15s
|
|
timeout: 5s
|
|
retries: 3
|
|
start_period: 30s
|
|
restart: unless-stopped
|
|
|
|
frontend:
|
|
build:
|
|
context: ./frontend
|
|
dockerfile: Dockerfile # production Dockerfile (static nginx)
|
|
volumes: [] # override: no source mounts in prod
|
|
environment:
|
|
- NODE_ENV=production
|
|
restart: unless-stopped
|
|
|
|
postgres:
|
|
# Tune PostgreSQL for production workloads
|
|
command: >
|
|
postgres
|
|
-c max_connections=200
|
|
-c shared_buffers=256MB
|
|
-c effective_cache_size=512MB
|
|
-c work_mem=4MB
|
|
-c maintenance_work_mem=64MB
|
|
-c checkpoint_completion_target=0.9
|
|
-c wal_buffers=16MB
|
|
-c random_page_cost=1.1
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
memory: 1024M
|
|
reservations:
|
|
memory: 512M
|
|
restart: unless-stopped
|
|
|
|
redis:
|
|
restart: unless-stopped
|
|
|
|
certbot:
|
|
image: certbot/certbot:latest
|
|
volumes:
|
|
- certbot_www:/var/www/certbot
|
|
- certbot_conf:/etc/letsencrypt
|
|
networks:
|
|
- hoanet
|
|
entrypoint: "/bin/sh -c 'trap exit TERM; while :; do certbot renew --quiet; sleep 12h & wait $${!}; done'"
|
|
|
|
volumes:
|
|
certbot_www:
|
|
certbot_conf:
|