docker-compose.prod.yml

version: '3.8'

services:
  wifi-densepose:
    build:
      context: .
      dockerfile: Dockerfile
      target: production
    image: wifi-densepose:latest
    container_name: wifi-densepose-prod
    ports:
      - "8000:8000"
    volumes:
      - wifi_densepose_logs:/app/logs
      - wifi_densepose_data:/app/data
      - wifi_densepose_models:/app/models
    environment:
      - ENVIRONMENT=production
      - DEBUG=false
      - LOG_LEVEL=info
      - RELOAD=false
      - WORKERS=4
      - ENABLE_TEST_ENDPOINTS=false
      - ENABLE_AUTHENTICATION=true
      - ENABLE_RATE_LIMITING=true
      - DATABASE_URL=${DATABASE_URL}
      - REDIS_URL=${REDIS_URL}
      - SECRET_KEY=${SECRET_KEY}
      - JWT_SECRET=${JWT_SECRET}
      - ALLOWED_HOSTS=${ALLOWED_HOSTS}
    secrets:
      - db_password
      - redis_password
      - jwt_secret
      - api_key
    deploy:
      replicas: 3
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
        window: 120s
      update_config:
        parallelism: 1
        delay: 10s
        failure_action: rollback
        monitor: 60s
        max_failure_ratio: 0.3
      rollback_config:
        parallelism: 1
        delay: 0s
        failure_action: pause
        monitor: 60s
        max_failure_ratio: 0.3
      resources:
        limits:
          cpus: '2.0'
          memory: 4G
        reservations:
          cpus: '1.0'
          memory: 2G
    networks:
      - wifi-densepose-network
      - monitoring-network
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

  postgres:
    image: postgres:15-alpine
    container_name: wifi-densepose-postgres-prod
    environment:
      - POSTGRES_DB=${POSTGRES_DB}
      - POSTGRES_USER=${POSTGRES_USER}
      - POSTGRES_PASSWORD_FILE=/run/secrets/db_password
    volumes:
      - postgres_data:/var/lib/postgresql/data
      - ./scripts/init-db.sql:/docker-entrypoint-initdb.d/init-db.sql
      - ./backups:/backups
    secrets:
      - db_password
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
      resources:
        limits:
          cpus: '1.0'
          memory: 2G
        reservations:
          cpus: '0.5'
          memory: 1G
    networks:
      - wifi-densepose-network
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER} -d ${POSTGRES_DB}"]
      interval: 10s
      timeout: 5s
      retries: 5
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

  redis:
    image: redis:7-alpine
    container_name: wifi-densepose-redis-prod
    command: redis-server --appendonly yes --requirepass-file /run/secrets/redis_password
    volumes:
      - redis_data:/data
    secrets:
      - redis_password
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
      resources:
        limits:
          cpus: '0.5'
          memory: 1G
        reservations:
          cpus: '0.25'
          memory: 512M
    networks:
      - wifi-densepose-network
    healthcheck:
      test: ["CMD", "redis-cli", "--raw", "incr", "ping"]
      interval: 10s
      timeout: 3s
      retries: 5
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

  nginx:
    image: nginx:alpine
    container_name: wifi-densepose-nginx-prod
    volumes:
      - ./nginx/nginx.prod.conf:/etc/nginx/nginx.conf
      - ./nginx/ssl:/etc/nginx/ssl
      - nginx_logs:/var/log/nginx
    ports:
      - "80:80"
      - "443:443"
    deploy:
      replicas: 2
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
      resources:
        limits:
          cpus: '0.5'
          memory: 512M
        reservations:
          cpus: '0.25'
          memory: 256M
    networks:
      - wifi-densepose-network
    depends_on:
      - wifi-densepose
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost/health"]
      interval: 30s
      timeout: 10s
      retries: 3
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

  prometheus:
    image: prom/prometheus:latest
    container_name: wifi-densepose-prometheus-prod
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.console.libraries=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--storage.tsdb.retention.time=15d'
      - '--web.enable-lifecycle'
      - '--web.enable-admin-api'
    volumes:
      - ./monitoring/prometheus-config.yml:/etc/prometheus/prometheus.yml
      - ./monitoring/alerting-rules.yml:/etc/prometheus/alerting-rules.yml
      - prometheus_data:/prometheus
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
      resources:
        limits:
          cpus: '1.0'
          memory: 2G
        reservations:
          cpus: '0.5'
          memory: 1G
    networks:
      - monitoring-network
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

  grafana:
    image: grafana/grafana:latest
    container_name: wifi-densepose-grafana-prod
    environment:
      - GF_SECURITY_ADMIN_PASSWORD_FILE=/run/secrets/grafana_password
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_INSTALL_PLUGINS=grafana-piechart-panel
    volumes:
      - grafana_data:/var/lib/grafana
      - ./monitoring/grafana-dashboard.json:/etc/grafana/provisioning/dashboards/dashboard.json
      - ./monitoring/grafana-datasources.yml:/etc/grafana/provisioning/datasources/datasources.yml
    secrets:
      - grafana_password
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
      resources:
        limits:
          cpus: '0.5'
          memory: 1G
        reservations:
          cpus: '0.25'
          memory: 512M
    networks:
      - monitoring-network
    depends_on:
      - prometheus
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 10s
      retries: 3
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

volumes:
  postgres_data:
    driver: local
  redis_data:
    driver: local
  prometheus_data:
    driver: local
  grafana_data:
    driver: local
  wifi_densepose_logs:
    driver: local
  wifi_densepose_data:
    driver: local
  wifi_densepose_models:
    driver: local
  nginx_logs:
    driver: local

networks:
  wifi-densepose-network:
    driver: overlay
    attachable: true
  monitoring-network:
    driver: overlay
    attachable: true

secrets:
  db_password:
    external: true
  redis_password:
    external: true
  jwt_secret:
    external: true
  api_key:
    external: true
  grafana_password:
    external: true