Files
foxhunt/services/ml_training_service/Dockerfile
jgrusewski 39c1028502 🚀 Wave 126 Wave 1 Complete: 6 agents deployed - 4/4 services healthy
Agent 106: ML health endpoint (HTTP/8095)
Agent 107: Redis test fix (serial_test isolation)
Agent 108: CLAUDE.md draft update (95-97% → 100%)
Agent 109: Prometheus/Grafana setup (31 alerts, 6 dashboards)
Agent 110: Deployment docs (9 files + 4 scripts)
Agent 111: Security audit prep (0 critical vulnerabilities)

Service Health: 4/4 healthy (100%)
Tests: 99%+ pass rate
Production: ~98% readiness

Next: Wave 2 (E2E, load, perf, security validation)
2025-10-08 00:11:38 +02:00

114 lines
3.6 KiB
Docker

# Multi-stage build for Foxhunt ML Training Service
# Wave 112 Agent 18: CUDA-enabled production Docker image
# =============================================================================
# Builder Stage with CUDA Support
# =============================================================================
FROM nvidia/cuda:12.3.0-devel-ubuntu22.04 AS builder
# Install Rust
RUN apt-get update && apt-get install -y \
curl \
build-essential \
&& curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y \
&& . $HOME/.cargo/env \
&& rustup default stable \
&& rustup component add rustfmt clippy
ENV PATH="/root/.cargo/bin:${PATH}"
# Install build dependencies including CUDA toolkit
RUN apt-get update && apt-get install -y \
pkg-config \
libssl-dev \
protobuf-compiler \
nvidia-cuda-toolkit \
&& rm -rf /var/lib/apt/lists/*
# Set working directory
WORKDIR /build
# Set CUDA environment variables to skip GPU detection during build
# CUDA 13.0 matches development environment, RTX 3050 Ti = compute capability 8.6
ENV CUDARC_CUDA_VERSION=13000
ENV CUDA_COMPUTE_CAP=86
# Copy workspace manifests
COPY Cargo.toml Cargo.lock ./
# Copy workspace members to satisfy manifest dependencies
COPY trading_engine ./trading_engine
COPY risk ./risk
COPY risk-data ./risk-data
COPY trading-data ./trading-data
COPY tli ./tli
COPY ml ./ml
COPY ml-data ./ml-data
COPY data ./data
COPY backtesting ./backtesting
COPY adaptive-strategy ./adaptive-strategy
COPY common ./common
COPY storage ./storage
COPY model_loader ./model_loader
COPY market-data ./market-data
COPY database ./database
COPY config ./config
COPY services/backtesting_service ./services/backtesting_service
COPY services/trading_service ./services/trading_service
COPY services/ml_training_service ./services/ml_training_service
COPY services/api_gateway ./services/api_gateway
COPY services/load_tests ./services/load_tests
COPY services/stress_tests ./services/stress_tests
COPY services/integration_tests ./services/integration_tests
COPY tests ./tests
COPY migrations ./migrations
# Build the application (CUDA available at runtime via nvidia/cuda base image)
RUN cargo build --release -p ml_training_service
# =============================================================================
# Runtime Stage with CUDA Runtime
# =============================================================================
FROM nvidia/cuda:12.3.0-runtime-ubuntu22.04
# Install runtime dependencies
RUN apt-get update && apt-get install -y \
ca-certificates \
libssl3 \
curl \
&& rm -rf /var/lib/apt/lists/*
# Download and install grpc_health_probe
RUN curl -sSL https://github.com/grpc-ecosystem/grpc-health-probe/releases/download/v0.4.25/grpc_health_probe-linux-amd64 \
-o /usr/local/bin/grpc_health_probe && \
chmod +x /usr/local/bin/grpc_health_probe
# Create non-root user
RUN groupadd --system --gid 1000 foxhunt && \
useradd --system --uid 1000 --gid foxhunt --shell /bin/bash foxhunt
# Create application directories
RUN mkdir -p /app/config /app/logs /app/models /app/checkpoints && \
chown -R foxhunt:foxhunt /app
# Set working directory
WORKDIR /app
# Copy binary from builder
COPY --from=builder /build/target/release/ml_training_service ./ml_training_service
RUN chmod +x ./ml_training_service
# Switch to non-root user
USER foxhunt
# Expose gRPC, metrics, and health ports
EXPOSE 50053 9094 8080
# Health check using HTTP endpoint (no TLS required)
HEALTHCHECK --interval=10s --timeout=5s --start-period=30s --retries=3 \
CMD curl -f http://localhost:8080/health || exit 1
# Run the application with default serve command
ENTRYPOINT ["./ml_training_service"]
CMD ["serve"]