foxhunt/deployment/docker/docker-compose.production.yml

version: '3.8'

services:
  foxhunt-core:
    build:
      context: ../../core
      dockerfile: Dockerfile.production
      args:
        RUST_VERSION: 1.75.0
        BUILD_MODE: release
    container_name: foxhunt-core-prod
    hostname: foxhunt-core
    ports:
      - "8080:8080"
      - "9090:9090"  # Metrics
    volumes:
      - /opt/foxhunt/config/production.toml:/app/config/config.toml:ro
      - /opt/foxhunt/data:/app/data:rw
      - /var/log/foxhunt:/app/logs:rw
      - /dev/shm:/dev/shm  # Shared memory for IPC
    environment:
      - RUST_LOG=info
      - FOXHUNT_ENV=production
      - FOXHUNT_CONFIG=/app/config/config.toml
    networks:
      - foxhunt-prod-net
    # HFT Performance Optimizations
    cpuset: "2-5"  # Dedicated CPU cores
    cpu_count: 4
    cpu_percent: 400  # 4 cores * 100%
    mem_limit: 4g
    memswap_limit: 4g
    mem_swappiness: 1
    oom_kill_disable: true
    # Real-time capabilities
    cap_add:
      - SYS_NICE
      - IPC_LOCK
    ulimits:
      memlock:
        soft: -1
        hard: -1
      nofile:
        soft: 65536
        hard: 65536
      rtprio:
        soft: 90
        hard: 90
    # Network optimizations
    sysctls:
      - net.core.rmem_max=134217728
      - net.core.wmem_max=134217728
      - net.ipv4.tcp_rmem=4096 65536 134217728
      - net.ipv4.tcp_wmem=4096 65536 134217728
      - net.core.netdev_max_backlog=5000
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
      interval: 10s
      timeout: 5s
      retries: 3
      start_period: 30s
    logging:
      driver: "json-file"
      options:
        max-size: "100m"
        max-file: "10"

  foxhunt-tli:
    build:
      context: ../../tli
      dockerfile: Dockerfile.production
      args:
        RUST_VERSION: 1.75.0
        BUILD_MODE: release
    container_name: foxhunt-tli-prod
    hostname: foxhunt-tli
    ports:
      - "50051:50051"  # gRPC port
      - "8081:8081"    # Health check port
    volumes:
      - /opt/foxhunt/config/production.toml:/app/config/config.toml:ro
      - /var/log/foxhunt:/app/logs:rw
    environment:
      - RUST_LOG=info
      - FOXHUNT_CORE_ENDPOINT=http://foxhunt-core:8080
      - FOXHUNT_CONFIG=/app/config/config.toml
      - FOXHUNT_ENV=production
    depends_on:
      foxhunt-core:
        condition: service_healthy
    networks:
      - foxhunt-prod-net
    cpuset: "6-7"
    mem_limit: 2g
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "grpcurl", "-plaintext", "localhost:50051", "list"]
      interval: 15s
      timeout: 10s
      retries: 3
      start_period: 45s

  foxhunt-ml-training:
    build:
      context: ../../ml
      dockerfile: Dockerfile.production
      args:
        RUST_VERSION: 1.75.0
        BUILD_MODE: release
        CUDA_VERSION: "12.1"
    container_name: foxhunt-ml-training-prod
    hostname: foxhunt-ml-training
    ports:
      - "8082:8082"  # Health check port
      - "6006:6006"  # TensorBoard
    volumes:
      - /opt/foxhunt/config/production.toml:/app/config/config.toml:ro
      - /opt/foxhunt/models:/app/models:rw
      - /opt/foxhunt/data:/app/data:ro
      - /opt/foxhunt/checkpoints:/app/checkpoints:rw
      - /var/log/foxhunt:/app/logs:rw
      - /tmp/cuda-cache:/tmp/cuda-cache:rw
    environment:
      - RUST_LOG=info
      - FOXHUNT_CORE_ENDPOINT=http://foxhunt-core:8080
      - FOXHUNT_DATA_ENDPOINT=http://foxhunt-data:8084
      - FOXHUNT_CONFIG=/app/config/config.toml
      - FOXHUNT_ENV=production
      # CUDA/GPU environment
      - CUDA_VISIBLE_DEVICES=0
      - NVIDIA_VISIBLE_DEVICES=0
      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
      - NVIDIA_REQUIRE_CUDA=cuda>=11.8
      # ML framework optimizations
      - OMP_NUM_THREADS=6
      - MKL_NUM_THREADS=6
      - PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:512
      - TF_GPU_MEMORY_GROWTH=true
    depends_on:
      foxhunt-core:
        condition: service_healthy
      foxhunt-data:
        condition: service_healthy
    networks:
      - foxhunt-prod-net
    # GPU-optimized resource allocation
    cpuset: "8-13"  # Dedicated cores for ML
    mem_limit: 16g
    memswap_limit: 16g
    shm_size: 2g  # Shared memory for ML frameworks
    # GPU access
    runtime: nvidia
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8082/health"]
      interval: 30s
      timeout: 15s
      retries: 5
      start_period: 120s

  foxhunt-risk:
    build:
      context: ../../risk
      dockerfile: Dockerfile.production
      args:
        RUST_VERSION: 1.75.0
        BUILD_MODE: release
    container_name: foxhunt-risk-prod
    hostname: foxhunt-risk
    ports:
      - "8083:8083"
    volumes:
      - /opt/foxhunt/config/production.toml:/app/config/config.toml:ro
      - /opt/foxhunt/data:/app/data:ro
      - /var/log/foxhunt:/app/logs:rw
    environment:
      - RUST_LOG=info
      - FOXHUNT_CORE_ENDPOINT=http://foxhunt-core:8080
      - FOXHUNT_CONFIG=/app/config/config.toml
      - FOXHUNT_ENV=production
    depends_on:
      foxhunt-core:
        condition: service_healthy
    networks:
      - foxhunt-prod-net
    cpuset: "14-15"
    mem_limit: 3g
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8083/health"]
      interval: 15s
      timeout: 5s
      retries: 3
      start_period: 30s

  foxhunt-data:
    build:
      context: ../../data
      dockerfile: Dockerfile.production
      args:
        RUST_VERSION: 1.75.0
        BUILD_MODE: release
    container_name: foxhunt-data-prod
    hostname: foxhunt-data
    ports:
      - "8084:8084"
    volumes:
      - /opt/foxhunt/config/production.toml:/app/config/config.toml:ro
      - /opt/foxhunt/data:/app/data:rw
      - /var/log/foxhunt:/app/logs:rw
    environment:
      - RUST_LOG=info
      - FOXHUNT_CONFIG=/app/config/config.toml
      - FOXHUNT_ENV=production
      - POLYGON_API_KEY=${POLYGON_API_KEY}
    networks:
      - foxhunt-prod-net
    cpuset: "16-17"
    mem_limit: 2g
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8084/health"]
      interval: 10s
      timeout: 5s
      retries: 3
      start_period: 30s

  # Monitoring and Infrastructure Services
  prometheus:
    image: prom/prometheus:v2.45.0
    container_name: foxhunt-prometheus
    ports:
      - "9090:9090"
    volumes:
      - ../monitoring/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - prometheus-data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=30d'
      - '--web.console.libraries=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--web.enable-lifecycle'
    networks:
      - foxhunt-prod-net
    restart: unless-stopped

  grafana:
    image: grafana/grafana:10.0.0
    container_name: foxhunt-grafana
    ports:
      - "3000:3000"
    volumes:
      - grafana-data:/var/lib/grafana
      - ../monitoring/grafana/dashboards:/etc/grafana/provisioning/dashboards:ro
      - ../monitoring/grafana/datasources:/etc/grafana/provisioning/datasources:ro
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_SERVER_ROOT_URL=http://localhost:3000
    networks:
      - foxhunt-prod-net
    restart: unless-stopped

  redis:
    image: redis:7.0-alpine
    container_name: foxhunt-redis
    ports:
      - "6379:6379"
    volumes:
      - redis-data:/data
      - ../monitoring/redis.conf:/usr/local/etc/redis/redis.conf:ro
    command: redis-server /usr/local/etc/redis/redis.conf
    networks:
      - foxhunt-prod-net
    # Memory optimization for Redis
    mem_limit: 1g
    sysctls:
      - net.core.somaxconn=65535
    restart: unless-stopped

networks:
  foxhunt-prod-net:
    driver: bridge
    driver_opts:
      com.docker.network.bridge.name: foxhunt-br0
    ipam:
      config:
        - subnet: 172.20.0.0/16

volumes:
  prometheus-data:
    driver: local
  grafana-data:
    driver: local
  redis-data:
    driver: local