docker-compose.prod.yml

# Docker Compose for Production Environment
# Usage: docker-compose -f docker-compose.yml -f docker-compose.prod.yml up -d


services:
  # ===========================================
  # 生产环境优化配置
  # ===========================================

  phone-gateway:
    build:
      target: production
    deploy:
      replicas: 2
      resources:
        limits:
          cpus: '1.0'
          memory: 512M
        reservations:
          cpus: '0.5'
          memory: 256M
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
    environment:
      - NODE_ENV=production
      - LOG_LEVEL=info
    command: npm start
    volumes:
      - ./logs/phone-gateway:/app/logs:rw

  realtime-processor:
    build:
      target: production
    deploy:
      replicas: 3  # 核心服务，需要更多实例
      resources:
        limits:
          cpus: '2.0'
          memory: 1G
        reservations:
          cpus: '1.0'
          memory: 512M
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
    environment:
      - NODE_ENV=production
      - LOG_LEVEL=info
    command: npm start

  conversation-engine:
    build:
      target: production
    deploy:
      replicas: 2
      resources:
        limits:
          cpus: '1.5'
          memory: 768M
        reservations:
          cpus: '0.75'
          memory: 384M
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
    environment:
      - NODE_ENV=production
      - LOG_LEVEL=info
    command: npm start

  profile-analytics:
    build:
      target: production
    deploy:
      replicas: 2
      resources:
        limits:
          cpus: '1.0'
          memory: 512M
        reservations:
          cpus: '0.5'
          memory: 256M
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
    environment:
      - NODE_ENV=production
      - LOG_LEVEL=info
    command: npm start

  user-management:
    build:
      target: production
    deploy:
      replicas: 2
      resources:
        limits:
          cpus: '0.5'
          memory: 256M
        reservations:
          cpus: '0.25'
          memory: 128M
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
    environment:
      - NODE_ENV=production
      - LOG_LEVEL=info
    command: npm start

  smart-whitelist:
    build:
      target: production
    deploy:
      replicas: 2
      resources:
        limits:
          cpus: '0.5'
          memory: 256M
        reservations:
          cpus: '0.25'
          memory: 128M
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
    environment:
      - NODE_ENV=production
      - LOG_LEVEL=info
    command: npm start

  configuration:
    build:
      target: production
    deploy:
      replicas: 1
      resources:
        limits:
          cpus: '0.25'
          memory: 128M
        reservations:
          cpus: '0.1'
          memory: 64M
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
    environment:
      - NODE_ENV=production
      - LOG_LEVEL=info
    command: npm start

  storage:
    build:
      target: production
    deploy:
      replicas: 2
      resources:
        limits:
          cpus: '0.5'
          memory: 256M
        reservations:
          cpus: '0.25'
          memory: 128M
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
    environment:
      - NODE_ENV=production
      - LOG_LEVEL=info
    command: npm start

  monitoring:
    build:
      target: production
    deploy:
      replicas: 1
      resources:
        limits:
          cpus: '1.0'
          memory: 512M
        reservations:
          cpus: '0.5'
          memory: 256M
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
    environment:
      - NODE_ENV=production
      - LOG_LEVEL=info
    command: npm start

  # ===========================================
  # 生产数据库配置
  # ===========================================

  postgres:
    deploy:
      replicas: 1
      resources:
        limits:
          cpus: '2.0'
          memory: 2G
        reservations:
          cpus: '1.0'
          memory: 1G
      restart_policy:
        condition: on-failure
        delay: 10s
        max_attempts: 5
    environment:
      - POSTGRES_DB=ai_ninja
      - POSTGRES_USER=postgres
      - POSTGRES_PASSWORD=${POSTGRES_PASSWORD}
      - POSTGRES_INITDB_ARGS=--encoding=UTF8 --locale=C
    command: >
      postgres
      -c shared_preload_libraries=pg_stat_statements
      -c pg_stat_statements.max=10000
      -c pg_stat_statements.track=all
      -c max_connections=500
      -c shared_buffers=512MB
      -c effective_cache_size=2GB
      -c work_mem=8MB
      -c maintenance_work_mem=128MB
      -c checkpoint_completion_target=0.9
      -c wal_buffers=16MB
      -c default_statistics_target=500

  redis:
    deploy:
      replicas: 1
      resources:
        limits:
          cpus: '1.0'
          memory: 512M
        reservations:
          cpus: '0.5'
          memory: 256M
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
    command: >
      redis-server
      /usr/local/etc/redis/redis.conf
      --maxmemory 256mb
      --maxmemory-policy allkeys-lru
      --save 900 1
      --save 300 10
      --save 60 10000

  # ===========================================
  # 生产环境负载均衡器
  # ===========================================

  nginx:
    deploy:
      replicas: 2
      resources:
        limits:
          cpus: '0.5'
          memory: 128M
        reservations:
          cpus: '0.25'
          memory: 64M
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
    ports:
      - "80:80"
      - "443:443"

  # ===========================================
  # 生产监控和日志收集
  # ===========================================

  # Filebeat for log shipping
  filebeat:
    image: docker.elastic.co/beats/filebeat:8.8.0
    container_name: ai-ninja-filebeat
    user: root
    environment:
      - ELASTICSEARCH_HOSTS=${ELASTICSEARCH_HOSTS:-http://elasticsearch:9200}
    networks:
      - ai-ninja-network
    volumes:
      - ./config/filebeat/filebeat.yml:/usr/share/filebeat/filebeat.yml:ro
      - ./logs:/var/log/ai-ninja:ro
      - /var/lib/docker/containers:/var/lib/docker/containers:ro
      - /var/run/docker.sock:/var/run/docker.sock:ro
    deploy:
      replicas: 1
      resources:
        limits:
          cpus: '0.25'
          memory: 128M

  # Prometheus Node Exporter
  node-exporter:
    image: prom/node-exporter:latest
    container_name: ai-ninja-node-exporter
    ports:
      - "9100:9100"
    networks:
      - ai-ninja-network
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - '--path.procfs=/host/proc'
      - '--path.rootfs=/rootfs'
      - '--path.sysfs=/host/sys'
      - '--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|host|etc)($$|/)'
    deploy:
      replicas: 1
      resources:
        limits:
          cpus: '0.1'
          memory: 64M

  # cAdvisor for container monitoring
  cadvisor:
    image: gcr.io/cadvisor/cadvisor:latest
    container_name: ai-ninja-cadvisor
    ports:
      - "8083:8080"
    networks:
      - ai-ninja-network
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:ro
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
      - /dev/disk/:/dev/disk:ro
    privileged: true
    devices:
      - /dev/kmsg
    deploy:
      replicas: 1
      resources:
        limits:
          cpus: '0.3'
          memory: 256M