docker-compose.yml

version: '3.8'

services:
  # Nginx Load Balancer
  nginx:
    image: nginx:1.25-alpine
    container_name: falcon-nginx
    ports:
      - "80:80"
      - "8080:8080"
    volumes:
      - ./nginx/nginx.conf:/etc/nginx/nginx.conf:ro
      - ./nginx/conf.d:/etc/nginx/conf.d:ro
    depends_on:
      - worker-1
      - worker-2
      - worker-3
    networks:
      - falcon-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "--quiet", "--tries=1", "--spider", "http://localhost:8080/health"]
      interval: 10s
      timeout: 5s
      retries: 3

  # Inference Workers
  worker-1:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: falcon-worker-1
    environment:
      - WORKER_ID=worker-1
    env_file:
      - .env
    expose:
      - "8000"
    volumes:
      - ./models:/app/models
      - ./logs:/app/logs
    depends_on:
      redis:
        condition: service_healthy
      postgres:
        condition: service_healthy
    networks:
      - falcon-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/healthz"]
      interval: 10s
      timeout: 5s
      retries: 3
      start_period: 30s

  worker-2:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: falcon-worker-2
    environment:
      - WORKER_ID=worker-2
    env_file:
      - .env
    expose:
      - "8000"
    volumes:
      - ./models:/app/models
      - ./logs:/app/logs
    depends_on:
      redis:
        condition: service_healthy
      postgres:
        condition: service_healthy
    networks:
      - falcon-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/healthz"]
      interval: 10s
      timeout: 5s
      retries: 3
      start_period: 30s

  worker-3:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: falcon-worker-3
    environment:
      - WORKER_ID=worker-3
    env_file:
      - .env
    expose:
      - "8000"
    volumes:
      - ./models:/app/models
      - ./logs:/app/logs
    depends_on:
      redis:
        condition: service_healthy
      postgres:
        condition: service_healthy
    networks:
      - falcon-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/healthz"]
      interval: 10s
      timeout: 5s
      retries: 3
      start_period: 30s

  # Redis Cache
  redis:
    image: redis:7-alpine
    container_name: falcon-redis
    ports:
      - "6379:6379"
    command: redis-server --maxmemory 256mb --maxmemory-policy allkeys-lru
    networks:
      - falcon-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 3s
      retries: 3
    volumes:
      - redis-data:/data

  # Postgres Database
  postgres:
    image: postgres:15-alpine
    container_name: falcon-postgres
    environment:
      - POSTGRES_DB=falcon_inference
      - POSTGRES_USER=falcon
      - POSTGRES_PASSWORD=falcon_dev_password_change_in_prod
    ports:
      - "5432:5432"
    networks:
      - falcon-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U falcon"]
      interval: 10s
      timeout: 5s
      retries: 5
    volumes:
      - postgres-data:/var/lib/postgresql/data
      - ./init-db:/docker-entrypoint-initdb.d

  # Prometheus
  prometheus:
    image: prom/prometheus:v2.48.0
    container_name: falcon-prometheus
    ports:
      - "9090:9090"
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
      - '--web.enable-lifecycle'
    volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./prometheus/alerts:/etc/prometheus/alerts:ro
      - prometheus-data:/prometheus
    networks:
      - falcon-network
    restart: unless-stopped

  # Grafana
  grafana:
    image: grafana/grafana:10.2.2
    container_name: falcon-grafana
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=admin_change_in_prod
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_SERVER_ROOT_URL=http://localhost:3000
      - GF_INSTALL_PLUGINS=
    volumes:
      - ./grafana/provisioning:/etc/grafana/provisioning:ro
      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
      - grafana-data:/var/lib/grafana
    depends_on:
      - prometheus
    networks:
      - falcon-network
    restart: unless-stopped

  # cAdvisor for container metrics
  cadvisor:
    image: gcr.io/cadvisor/cadvisor:v0.47.2
    container_name: falcon-cadvisor
    ports:
      - "8081:8080"
    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
    networks:
      - falcon-network
    restart: unless-stopped
    command:
      - '--housekeeping_interval=10s'
      - '--docker_only=true'

networks:
  falcon-network:
    driver: bridge
    name: falcon-network

volumes:
  redis-data:
  postgres-data:
  prometheus-data:
  grafana-data: