# =============================================================================
# RUNPOD DEPLOYMENT DOCKERFILE - VOLUME MOUNT ARCHITECTURE
# =============================================================================
# Purpose: Provides CUDA 12.9.1 + cuDNN 9 development environment for pre-built binaries
# Size: ~4.3GB (includes CUDA 12.9.1 development libraries + cuDNN 9)
# Build time: ~2-3 minutes (vs 20+ minutes with compilation)
#
# Architecture:
#   - Docker image: CUDA runtime environment + entrypoint script
#   - Training binaries: Pre-uploaded to Runpod Network Volume at /runpod-volume/binaries/
#   - Test data: Pre-uploaded to Runpod Network Volume at /runpod-volume/test_data/
#   - Credentials: Pre-uploaded to Runpod Network Volume at /runpod-volume/.env
#
# NO COMPILATION IN DOCKER - Binaries are pre-built locally with CUDA support
# =============================================================================

# Base image: CUDA 12.9.1 with cuDNN 9 on Ubuntu 24.04
# CRITICAL: Runpod driver 550 requires CUDA 12.9 (CUDA 13.0 requires driver 580+)
# CUDA 12.9.1 provides libcublas.so.12 (compatible with local compilation environment)
# Includes: libcuda.so.1, libcurand.so.10, libcublas.so.12, libcublasLt.so.12, cuDNN 9.x
# Note: Using Ubuntu 24.04 for GLIBC 2.39 (matches local build environment)
# Note: Using 'cudnn-devel' variant for complete CUDA development libraries + cuDNN 9
# Image size: ~4.3GB (includes CUDA 12.9.1 development libraries + cuDNN 9)
FROM nvidia/cuda:12.9.1-cudnn-devel-ubuntu24.04

# Prevent interactive prompts during apt installations
ENV DEBIAN_FRONTEND=noninteractive

# Install minimal runtime dependencies
# Runtime dependencies identified from ldd output:
#   - libcuda.so.1 (from CUDA 12.9.1 base image)
#   - libcurand.so.10 (from CUDA 12.9.1 base image)
#   - libcublas.so.12 (from CUDA 12.9.1 base image)
#   - libcublasLt.so.12 (from CUDA 12.9.1 base image)
#   - libcudnn.so.9 (included in cudnn-devel variant, compatible with CUDA 12.9.1)
#   - libstdc++6, libgcc-s1 (C++ runtime, from base)
#   - ca-certificates (HTTPS support)
RUN apt-get update && apt-get install -y \
    ca-certificates \
    wget \
    && rm -rf /var/lib/apt/lists/*

# Note: cuDNN 9 is already included in the base image (cudnn-devel variant)
# No additional installation required - libcudnn.so.9 is pre-installed

# Set CUDA environment variables (for runtime library loading)
# CRITICAL: Include compat path FIRST to fix CUDA_ERROR_UNSUPPORTED_PTX_VERSION
# Driver 550 needs compat libraries for CUDA 12.9 PTX (see CUDA_PTX_VERSION_DEEP_INVESTIGATION.md)
ENV CUDA_HOME=/usr/local/cuda
ENV PATH="${CUDA_HOME}/bin:${PATH}"
ENV LD_LIBRARY_PATH="${CUDA_HOME}/compat:${CUDA_HOME}/lib64:${LD_LIBRARY_PATH}"

# NVIDIA runtime configuration
ENV NVIDIA_VISIBLE_DEVICES=all
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
ENV CUDA_VISIBLE_DEVICES=0

# Rust runtime environment
ENV RUST_BACKTRACE=1
ENV RUST_LOG=info

# Copy entrypoint scripts (self-terminate wrapper + generic base)
COPY entrypoint-generic.sh /entrypoint-generic.sh
COPY entrypoint-self-terminate.sh /entrypoint.sh
RUN chmod +x /entrypoint-generic.sh /entrypoint.sh

# Create workspace directory
WORKDIR /workspace

# Health check to verify GPU is accessible
HEALTHCHECK --interval=60s --timeout=10s --start-period=30s --retries=3 \
    CMD nvidia-smi || exit 1

# Entrypoint executes training binary from volume mount
# NO DOWNLOADS - binaries and data are already on the mounted Runpod Network Volume
# Override binary via environment variable: BINARY_NAME (default: train_tft_parquet)
ENTRYPOINT ["/entrypoint.sh"]

# Default CMD shows help (deployment script overrides this with dockerStartCmd)
CMD ["--help"]

# =============================================================================
# BUILD AND RUN INSTRUCTIONS - VOLUME MOUNT ARCHITECTURE
# =============================================================================
#
# 1. BUILD IMAGE (minimal runtime, NO binaries or data embedded):
#    docker build -f Dockerfile.runpod -t jgrusewski/foxhunt:latest .
#    # Image size: ~2GB (CUDA runtime only)
#    # Build time: ~2 minutes
#
# 2. PUSH TO DOCKER HUB:
#    docker login  # Login to Docker Hub as jgrusewski
#    docker push jgrusewski/foxhunt:latest
#    # IMPORTANT: Set repository to PRIVATE in Docker Hub settings
#
# 3. RUNPOD DEPLOYMENT (binaries and data already uploaded to volume):
#    - GPU: Tesla V100-PCIE-16GB (16GB VRAM, $0.29/hr)
#    - Docker Image: jgrusewski/foxhunt:latest (PRIVATE, requires Docker Hub auth)
#    - Volume Mount: Select Runpod Network Volume, mount at /runpod-volume
#    - Environment Variables:
#      * BINARY_NAME=train_tft_parquet (default, or train_mamba2_parquet/train_dqn/train_ppo)
#      * RUST_LOG=info (logging level)
#
# 4. TRAIN DIFFERENT MODELS (all binaries on mounted volume):
#    Override BINARY_NAME environment variable:
#    - TFT: BINARY_NAME=train_tft_parquet
#    - MAMBA-2: BINARY_NAME=train_mamba2_parquet
#    - DQN: BINARY_NAME=train_dqn
#    - PPO: BINARY_NAME=train_ppo
#
# 5. AVAILABLE DATA ON MOUNTED VOLUME (pre-uploaded, NO download required):
#    /runpod-volume/
#    ├── .env                        (512B, credentials, chmod 600)
#    ├── binaries/                   (77MB total)
#    │   ├── train_tft_parquet       (23MB, TFT-225 features)
#    │   ├── train_mamba2_parquet    (22MB, MAMBA-2 model)
#    │   ├── train_dqn               (22MB, Deep Q-Network)
#    │   └── train_ppo               (13MB, Proximal Policy Optimization)
#    ├── test_data/                  (14MB total, 9 Parquet files)
#    │   ├── ES_FUT_180d.parquet     (2.9MB, 180 days)
#    │   ├── NQ_FUT_180d.parquet     (4.4MB, 180 days)
#    │   ├── 6E_FUT_180d.parquet     (2.8MB, 180 days)
#    │   ├── ZN_FUT_90d.parquet      (2.8MB, 90 days)
#    │   └── [5 more small test files]
#    └── models/                      (Empty, populated by training runs)
#
# 6. UPDATING BINARIES (NO Docker rebuild required):
#    # Simply upload new binary to Runpod Network Volume via S3 API
#    # Next pod start will use updated binary automatically
#    # Instant deployment (seconds, not minutes)
#
# =============================================================================
# OPTIMIZATION NOTES - VOLUME MOUNT ARCHITECTURE
# =============================================================================
#
# Memory Optimization:
# - cudnn-devel variant includes CUDA 12.9.1 + cuDNN 9 in ~4.3GB
# - NO binaries or data embedded (stored on mounted volume)
# - Includes development libraries (libcublas.so.12, libcublasLt.so.12, cuDNN 9)
# - Optimized for pre-built binaries = faster pod startup (~1-2min vs 3-5min)
#
# Build Speed:
# - No compilation = 2 minute build (vs 20+ minutes)
# - Image build is one-time only (binaries update via volume upload)
# - No Docker rebuild needed for code changes (instant deployment)
#
# Deployment Speed:
# - Docker image: Build once, use forever (~2GB, CUDA runtime only)
# - Binary updates: Upload to volume (seconds, NO rebuild)
# - Pod startup: ~30 seconds (volume already mounted)
# - Total deployment time: <60 seconds for new binary
#
# GPU Compatibility:
# - CUDA 12.9.1 compatible with Tesla V100, RTX 4090, A100, H100
# - cuDNN 9 (9.13.0+) included for optimal neural network performance
# - Target: Tesla V100-PCIE-16GB (16GB VRAM, $0.29/hr) or RTX 4090 (24GB VRAM)
# - Minimum driver: r525 or newer (CUDA 12.x driver compatibility)
#
# Security:
# - PRIVATE Docker Hub repository required
# - PRIVATE Runpod Network Volume (binaries + data isolated per account)
# - No sensitive data in image (only CUDA runtime)
# - Minimal attack surface (runtime-only image, no build tools)
#
# =============================================================================