foxhunt/docker-compose.production.yml

version: '3.8'

#============================================================================
# FOXHUNT HFT TRADING SYSTEM - PRODUCTION DOCKER COMPOSE
#============================================================================
# High-performance containerized deployment with:
# - Trading, ML Training, Backtesting, TLI Services
# - HashiCorp Vault (secrets management)
# - PostgreSQL (primary database with configuration system)
# - Redis (caching and pub/sub)
# - InfluxDB (time series data)
# - Prometheus & Grafana (monitoring)
# - Production-grade security and performance optimizations
#============================================================================

services:
  #==========================================================================
  # INFRASTRUCTURE SERVICES (Boot First)
  #==========================================================================

  vault:
    image: hashicorp/vault:1.15.0
    container_name: foxhunt-vault-prod
    hostname: foxhunt-vault
    ports:
      - "8200:8200"
    volumes:
      - vault-data:/vault/data
      - vault-logs:/vault/logs
      - ./deployment/vault/config:/vault/config:ro
      - ./deployment/vault/policies:/vault/policies:ro
    environment:
      - VAULT_ADDR=http://0.0.0.0:8200
      - VAULT_API_ADDR=http://foxhunt-vault:8200
      - VAULT_LOG_LEVEL=INFO
      - VAULT_DEV_ROOT_TOKEN_ID=${VAULT_ROOT_TOKEN:-foxhunt-dev-root}
    cap_add:
      - IPC_LOCK
    command: >
      sh -c "
        vault server -config=/vault/config/vault.hcl &
        sleep 10 &&
        vault operator init -key-shares=5 -key-threshold=3 > /vault/data/init.txt 2>/dev/null || true &&
        vault operator unseal \$$(grep 'Unseal Key 1:' /vault/data/init.txt | cut -d' ' -f4) 2>/dev/null || true &&
        vault operator unseal \$$(grep 'Unseal Key 2:' /vault/data/init.txt | cut -d' ' -f4) 2>/dev/null || true &&
        vault operator unseal \$$(grep 'Unseal Key 3:' /vault/data/init.txt | cut -d' ' -f4) 2>/dev/null || true &&
        vault auth -method=userpass username=foxhunt password=${VAULT_FOXHUNT_PASSWORD:-foxhunt123} 2>/dev/null || true &&
        wait
      "
    networks:
      - infrastructure-network
      - backend-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "vault", "status"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s
    mem_limit: 512m
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "5"

  postgresql:
    image: postgres:15.4-alpine
    container_name: foxhunt-postgres-prod
    hostname: foxhunt-postgres
    ports:
      - "5432:5432"
    volumes:
      - postgres-data:/var/lib/postgresql/data
      - ./deployment/postgres/init:/docker-entrypoint-initdb.d:ro
      - ./deployment/postgres/config/postgresql.conf:/etc/postgresql/postgresql.conf:ro
      - ./deployment/postgres/config/pg_hba.conf:/etc/postgresql/pg_hba.conf:ro
    environment:
      - POSTGRES_DB=foxhunt
      - POSTGRES_USER=${POSTGRES_USER:-foxhunt}
      - POSTGRES_PASSWORD=${POSTGRES_PASSWORD:-foxhunt123}
      - POSTGRES_INITDB_ARGS="--auth-host=md5"
      - PGUSER=${POSTGRES_USER:-foxhunt}
    command: >
      postgres
        -c config_file=/etc/postgresql/postgresql.conf
        -c hba_file=/etc/postgresql/pg_hba.conf
        -c shared_preload_libraries=pg_stat_statements
        -c max_connections=200
        -c shared_buffers=256MB
        -c effective_cache_size=1GB
        -c maintenance_work_mem=64MB
        -c checkpoint_completion_target=0.9
        -c wal_buffers=16MB
        -c default_statistics_target=100
    networks:
      - database-network
      - backend-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-foxhunt} -d foxhunt"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s
    mem_limit: 2g
    logging:
      driver: "json-file"
      options:
        max-size: "100m"
        max-file: "10"

  redis:
    image: redis:7.2-alpine
    container_name: foxhunt-redis-prod
    hostname: foxhunt-redis
    ports:
      - "6379:6379"
    volumes:
      - redis-data:/data
      - ./deployment/redis/redis.conf:/usr/local/etc/redis/redis.conf:ro
    command: >
      redis-server /usr/local/etc/redis/redis.conf
        --requirepass ${REDIS_PASSWORD:-foxhunt123}
        --maxmemory 1gb
        --maxmemory-policy allkeys-lru
        --save 900 1
        --save 300 10
        --save 60 10000
    networks:
      - database-network
      - backend-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "redis-cli", "--raw", "incr", "ping"]
      interval: 10s
      timeout: 3s
      retries: 5
      start_period: 30s
    mem_limit: 1g
    sysctls:
      - net.core.somaxconn=65535
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "5"

  influxdb:
    image: influxdb:2.7-alpine
    container_name: foxhunt-influxdb-prod
    hostname: foxhunt-influxdb
    ports:
      - "8086:8086"
    volumes:
      - influxdb-data:/var/lib/influxdb2
      - influxdb-config:/etc/influxdb2
    environment:
      - DOCKER_INFLUXDB_INIT_MODE=setup
      - DOCKER_INFLUXDB_INIT_USERNAME=${INFLUXDB_USERNAME:-foxhunt}
      - DOCKER_INFLUXDB_INIT_PASSWORD=${INFLUXDB_PASSWORD:-foxhunt123}
      - DOCKER_INFLUXDB_INIT_ORG=foxhunt
      - DOCKER_INFLUXDB_INIT_BUCKET=trading_metrics
      - DOCKER_INFLUXDB_INIT_RETENTION=30d
      - DOCKER_INFLUXDB_INIT_ADMIN_TOKEN=${INFLUXDB_TOKEN:-foxhunt-token-12345}
    networks:
      - database-network
      - monitoring-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "influx", "ping"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s
    mem_limit: 2g
    logging:
      driver: "json-file"
      options:
        max-size: "100m"
        max-file: "10"

  #==========================================================================
  # CORE TRADING SERVICES
  #==========================================================================

  trading-service:
    build:
      context: .
      dockerfile: services/trading_service/Dockerfile
      args:
        RUST_VERSION: 1.75.0
        BUILD_MODE: release
    container_name: foxhunt-trading-prod
    hostname: foxhunt-trading
    ports:
      - "8080:8080"    # Main service
      - "9001:9001"    # Metrics
    volumes:
      - /opt/foxhunt/config:/app/config:ro
      - /opt/foxhunt/data:/app/data:rw
      - /var/log/foxhunt:/app/logs:rw
      - /dev/shm:/dev/shm  # Shared memory for HFT IPC
      - ./certs:/app/certs:ro
    environment:
      - RUST_LOG=info,foxhunt=debug
      - FOXHUNT_ENV=production
      - DATABASE_URL=postgresql://${POSTGRES_USER:-foxhunt}:${POSTGRES_PASSWORD:-foxhunt123}@foxhunt-postgres:5432/foxhunt
      - REDIS_URL=redis://:${REDIS_PASSWORD:-foxhunt123}@foxhunt-redis:6379
      - INFLUXDB_URL=http://foxhunt-influxdb:8086
      - INFLUXDB_TOKEN=${INFLUXDB_TOKEN:-foxhunt-token-12345}
      - VAULT_ADDR=http://foxhunt-vault:8200
      - VAULT_TOKEN=${VAULT_ROOT_TOKEN:-foxhunt-dev-root}
    depends_on:
      postgresql:
        condition: service_healthy
      redis:
        condition: service_healthy
      vault:
        condition: service_healthy
    networks:
      - backend-network
      - frontend-network
    # HFT Performance Optimizations
    cpuset: "2-5"  # Dedicated CPU cores
    cpu_count: 4
    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 for HFT
    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"

  ml-training-service:
    build:
      context: .
      dockerfile: ./ml/Dockerfile
      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"  # Main service
      - "6006:6006"  # TensorBoard
      - "9002:9002"  # Metrics
    volumes:
      - /opt/foxhunt/config:/app/config: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_ml=debug
      - FOXHUNT_ENV=production
      - DATABASE_URL=postgresql://${POSTGRES_USER:-foxhunt}:${POSTGRES_PASSWORD:-foxhunt123}@foxhunt-postgres:5432/foxhunt
      - REDIS_URL=redis://:${REDIS_PASSWORD:-foxhunt123}@foxhunt-redis:6379
      - TRADING_SERVICE_URL=http://foxhunt-trading:8080
      # 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:
      trading-service:
        condition: service_healthy
      postgresql:
        condition: service_healthy
    networks:
      - backend-network
    # 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 (requires nvidia-container-runtime)
    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
    logging:
      driver: "json-file"
      options:
        max-size: "100m"
        max-file: "10"

  backtesting-service:
    build:
      context: .
      dockerfile: services/backtesting_service/Dockerfile
      args:
        RUST_VERSION: 1.75.0
        BUILD_MODE: release
    container_name: foxhunt-backtesting-prod
    hostname: foxhunt-backtesting
    ports:
      - "8083:8083"  # Main service
      - "9003:9003"  # Metrics
    volumes:
      - /opt/foxhunt/config:/app/config:ro
      - /opt/foxhunt/data:/app/data:ro
      - /opt/foxhunt/backtests:/app/backtests:rw
      - /var/log/foxhunt:/app/logs:rw
    environment:
      - RUST_LOG=info,foxhunt_backtesting=debug
      - FOXHUNT_ENV=production
      - DATABASE_URL=postgresql://${POSTGRES_USER:-foxhunt}:${POSTGRES_PASSWORD:-foxhunt123}@foxhunt-postgres:5432/foxhunt
      - REDIS_URL=redis://foxhunt-redis:6379
      - ML_SERVICE_URL=http://foxhunt-ml-training:8082
    depends_on:
      trading-service:
        condition: service_healthy
      ml-training-service:
        condition: service_healthy
    networks:
      - backend-network
    cpuset: "14-17"
    mem_limit: 8g
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8083/health"]
      interval: 15s
      timeout: 5s
      retries: 3
      start_period: 60s
    logging:
      driver: "json-file"
      options:
        max-size: "100m"
        max-file: "10"

  tli:
    build:
      context: .
      dockerfile: tli/Dockerfile
      args:
        RUST_VERSION: 1.75.0
        BUILD_MODE: release
    container_name: foxhunt-tli-prod
    hostname: foxhunt-tli
    ports:
      - "50051:50051"  # gRPC port
      - "8081:8081"    # Web interface
      - "9004:9004"    # Metrics
    volumes:
      - /opt/foxhunt/config:/app/config:ro
      - /var/log/foxhunt:/app/logs:rw
    environment:
      - RUST_LOG=info,foxhunt_tli=debug
      - FOXHUNT_ENV=production
      - TRADING_SERVICE_URL=http://foxhunt-trading:8080
      - ML_SERVICE_URL=http://foxhunt-ml-training:8082
      - BACKTESTING_SERVICE_URL=http://foxhunt-backtesting:8083
      - GRAFANA_URL=http://foxhunt-grafana:3000
    depends_on:
      trading-service:
        condition: service_healthy
      ml-training-service:
        condition: service_healthy
      backtesting-service:
        condition: service_healthy
    networks:
      - frontend-network
      - backend-network
    cpuset: "18-19"
    mem_limit: 2g
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8081/health"]
      interval: 15s
      timeout: 10s
      retries: 3
      start_period: 45s
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "5"

  #==========================================================================
  # MONITORING & OBSERVABILITY
  #==========================================================================

  prometheus:
    image: prom/prometheus:v2.47.0
    container_name: foxhunt-prometheus-prod
    hostname: foxhunt-prometheus
    ports:
      - "9090:9090"
    volumes:
      - prometheus-data:/prometheus
      - ./deployment/monitoring/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./deployment/monitoring/rules:/etc/prometheus/rules:ro
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=30d'
      - '--storage.tsdb.retention.size=50GB'
      - '--web.console.libraries=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--web.enable-lifecycle'
      - '--web.enable-admin-api'
      - '--query.max-concurrency=50'
      - '--query.max-samples=50000000'
    networks:
      - monitoring-network
      - backend-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    mem_limit: 4g
    logging:
      driver: "json-file"
      options:
        max-size: "100m"
        max-file: "5"

  grafana:
    image: grafana/grafana:10.1.0
    container_name: foxhunt-grafana-prod
    hostname: foxhunt-grafana
    ports:
      - "3000:3000"
    volumes:
      - grafana-data:/var/lib/grafana
      - ./deployment/monitoring/grafana/dashboards:/etc/grafana/provisioning/dashboards:ro
      - ./deployment/monitoring/grafana/datasources:/etc/grafana/provisioning/datasources:ro
      - ./deployment/monitoring/grafana/plugins:/var/lib/grafana/plugins
    environment:
      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_SERVER_ROOT_URL=http://localhost:3000
      - GF_INSTALL_PLUGINS=grafana-piechart-panel,grafana-worldmap-panel
      - GF_FEATURE_TOGGLES_ENABLE=ngalert
    depends_on:
      prometheus:
        condition: service_healthy
    networks:
      - monitoring-network
      - frontend-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:3000/api/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    mem_limit: 1g
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "5"

  alertmanager:
    image: prom/alertmanager:v0.26.0
    container_name: foxhunt-alertmanager-prod
    hostname: foxhunt-alertmanager
    ports:
      - "9093:9093"
    volumes:
      - alertmanager-data:/alertmanager
      - ./deployment/monitoring/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
      - '--web.external-url=http://localhost:9093'
      - '--cluster.advertise-address=0.0.0.0:9093'
    networks:
      - monitoring-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9093/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    mem_limit: 512m
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "5"

  #==========================================================================
  # REVERSE PROXY & LOAD BALANCING
  #==========================================================================

  nginx:
    image: nginx:1.25-alpine
    container_name: foxhunt-nginx-prod
    hostname: foxhunt-nginx
    ports:
      - "80:80"
      - "443:443"
    volumes:
      - ./deployment/nginx/nginx.conf:/etc/nginx/nginx.conf:ro
      - ./deployment/nginx/conf.d:/etc/nginx/conf.d:ro
      - ./certs:/etc/nginx/certs:ro
      - nginx-cache:/var/cache/nginx
    depends_on:
      - tli
      - grafana
    networks:
      - frontend-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "nginx", "-t"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    mem_limit: 512m
    logging:
      driver: "json-file"
      options:
        max-size: "100m"
        max-file: "10"

#==============================================================================
# NETWORKS (Layered Security Architecture)
#==============================================================================
networks:
  frontend-network:
    driver: bridge
    driver_opts:
      com.docker.network.bridge.name: foxhunt-frontend
    ipam:
      config:
        - subnet: 172.20.0.0/24
          gateway: 172.20.0.1

  backend-network:
    driver: bridge
    driver_opts:
      com.docker.network.bridge.name: foxhunt-backend
    ipam:
      config:
        - subnet: 172.21.0.0/24
          gateway: 172.21.0.1

  database-network:
    driver: bridge
    driver_opts:
      com.docker.network.bridge.name: foxhunt-database
    ipam:
      config:
        - subnet: 172.22.0.0/24
          gateway: 172.22.0.1

  infrastructure-network:
    driver: bridge
    driver_opts:
      com.docker.network.bridge.name: foxhunt-infra
    ipam:
      config:
        - subnet: 172.23.0.0/24
          gateway: 172.23.0.1

  monitoring-network:
    driver: bridge
    driver_opts:
      com.docker.network.bridge.name: foxhunt-monitoring
    ipam:
      config:
        - subnet: 172.24.0.0/24
          gateway: 172.24.0.1

#==============================================================================
# VOLUMES (Data Persistence)
#==============================================================================
volumes:
  # Infrastructure
  vault-data:
    driver: local
  vault-logs:
    driver: local
  postgres-data:
    driver: local
  redis-data:
    driver: local
  influxdb-data:
    driver: local
  influxdb-config:
    driver: local

  # Monitoring
  prometheus-data:
    driver: local
  grafana-data:
    driver: local
  alertmanager-data:
    driver: local

  # Application
  nginx-cache:
    driver: local