Files
LEANN/.github/workflows/build-reusable.yml
Andy Lee 360a3ec732 debug: increase timeouts to 600s for comprehensive hang investigation
- Increase pytest timeout from 300s to 600s for thorough testing
- Increase import testing timeout from 60s to 120s
- Allow more time for C++ extension loading (faiss/diskann)
- Still provides timeout protection against infinite hangs

This gives the system more time to complete imports and tests
while still catching genuine hangs that exceed reasonable limits.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-08-12 00:43:18 -07:00

375 lines
14 KiB
YAML

name: Reusable Build
on:
workflow_call:
inputs:
ref:
description: 'Git ref to build'
required: false
type: string
default: ''
jobs:
lint:
name: Lint and Format Check
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
with:
ref: ${{ inputs.ref }}
- name: Setup Python
uses: actions/setup-python@v5
with:
python-version: '3.11'
- name: Install uv
uses: astral-sh/setup-uv@v4
- name: Install ruff
run: |
uv tool install ruff
- name: Run ruff check
run: |
ruff check .
- name: Run ruff format check
run: |
ruff format --check .
build:
needs: lint
name: Build ${{ matrix.os }} Python ${{ matrix.python }}
strategy:
matrix:
include:
- os: ubuntu-22.04
python: '3.9'
- os: ubuntu-22.04
python: '3.10'
- os: ubuntu-22.04
python: '3.11'
- os: ubuntu-22.04
python: '3.12'
- os: ubuntu-22.04
python: '3.13'
- os: macos-14
python: '3.9'
- os: macos-14
python: '3.10'
- os: macos-14
python: '3.11'
- os: macos-14
python: '3.12'
- os: macos-14
python: '3.13'
- os: macos-13
python: '3.9'
- os: macos-13
python: '3.10'
- os: macos-13
python: '3.11'
- os: macos-13
python: '3.12'
# Note: macos-13 + Python 3.13 excluded due to PyTorch compatibility
# (PyTorch 2.5+ supports Python 3.13 but not Intel Mac x86_64)
runs-on: ${{ matrix.os }}
steps:
- uses: actions/checkout@v4
with:
ref: ${{ inputs.ref }}
submodules: recursive
- name: Setup Python
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python }}
- name: Install uv
uses: astral-sh/setup-uv@v4
- name: Install system dependencies (Ubuntu)
if: runner.os == 'Linux'
run: |
sudo apt-get update
sudo apt-get install -y libomp-dev libboost-all-dev protobuf-compiler libzmq3-dev \
pkg-config libopenblas-dev patchelf libabsl-dev libaio-dev libprotobuf-dev
# Install Intel MKL for DiskANN
wget -q https://registrationcenter-download.intel.com/akdlm/IRC_NAS/79153e0f-74d7-45af-b8c2-258941adf58a/intel-onemkl-2025.0.0.940.sh
sudo sh intel-onemkl-2025.0.0.940.sh -a --components intel.oneapi.lin.mkl.devel --action install --eula accept -s
source /opt/intel/oneapi/setvars.sh
echo "MKLROOT=/opt/intel/oneapi/mkl/latest" >> $GITHUB_ENV
echo "LD_LIBRARY_PATH=/opt/intel/oneapi/mkl/latest/lib/intel64:$LD_LIBRARY_PATH" >> $GITHUB_ENV
- name: Install system dependencies (macOS)
if: runner.os == 'macOS'
run: |
# Don't install LLVM, use system clang for better compatibility
brew install libomp boost protobuf zeromq
- name: Install build dependencies
run: |
uv pip install --system scikit-build-core numpy swig Cython pybind11
if [[ "$RUNNER_OS" == "Linux" ]]; then
uv pip install --system auditwheel
else
uv pip install --system delocate
fi
- name: Set macOS environment variables
if: runner.os == 'macOS'
run: |
# Use brew --prefix to automatically detect Homebrew installation path
HOMEBREW_PREFIX=$(brew --prefix)
echo "HOMEBREW_PREFIX=${HOMEBREW_PREFIX}" >> $GITHUB_ENV
echo "OpenMP_ROOT=${HOMEBREW_PREFIX}/opt/libomp" >> $GITHUB_ENV
# Set CMAKE_PREFIX_PATH to let CMake find all packages automatically
echo "CMAKE_PREFIX_PATH=${HOMEBREW_PREFIX}" >> $GITHUB_ENV
# Set compiler flags for OpenMP (required for both backends)
echo "LDFLAGS=-L${HOMEBREW_PREFIX}/opt/libomp/lib" >> $GITHUB_ENV
echo "CPPFLAGS=-I${HOMEBREW_PREFIX}/opt/libomp/include" >> $GITHUB_ENV
- name: Build packages
run: |
# Build core (platform independent)
cd packages/leann-core
uv build
cd ../..
# Build HNSW backend
cd packages/leann-backend-hnsw
if [[ "${{ matrix.os }}" == macos-* ]]; then
# Use system clang for better compatibility
export CC=clang
export CXX=clang++
export MACOSX_DEPLOYMENT_TARGET=11.0
uv build --wheel --python ${{ matrix.python }} --find-links ${GITHUB_WORKSPACE}/packages/leann-core/dist
else
uv build --wheel --python ${{ matrix.python }} --find-links ${GITHUB_WORKSPACE}/packages/leann-core/dist
fi
cd ../..
# Build DiskANN backend
cd packages/leann-backend-diskann
if [[ "${{ matrix.os }}" == macos-* ]]; then
# Use system clang for better compatibility
export CC=clang
export CXX=clang++
# DiskANN requires macOS 13.3+ for sgesdd_ LAPACK function
export MACOSX_DEPLOYMENT_TARGET=13.3
uv build --wheel --python ${{ matrix.python }} --find-links ${GITHUB_WORKSPACE}/packages/leann-core/dist
else
uv build --wheel --python ${{ matrix.python }} --find-links ${GITHUB_WORKSPACE}/packages/leann-core/dist
fi
cd ../..
# Build meta package (platform independent)
cd packages/leann
uv build
cd ../..
- name: Repair wheels (Linux)
if: runner.os == 'Linux'
run: |
# Repair HNSW wheel
cd packages/leann-backend-hnsw
if [ -d dist ]; then
auditwheel repair dist/*.whl -w dist_repaired
rm -rf dist
mv dist_repaired dist
fi
cd ../..
# Repair DiskANN wheel
cd packages/leann-backend-diskann
if [ -d dist ]; then
auditwheel repair dist/*.whl -w dist_repaired
rm -rf dist
mv dist_repaired dist
fi
cd ../..
- name: Repair wheels (macOS)
if: runner.os == 'macOS'
run: |
# Repair HNSW wheel
cd packages/leann-backend-hnsw
if [ -d dist ]; then
delocate-wheel -w dist_repaired -v dist/*.whl
rm -rf dist
mv dist_repaired dist
fi
cd ../..
# Repair DiskANN wheel
cd packages/leann-backend-diskann
if [ -d dist ]; then
delocate-wheel -w dist_repaired -v dist/*.whl
rm -rf dist
mv dist_repaired dist
fi
cd ../..
- name: List built packages
run: |
echo "📦 Built packages:"
find packages/*/dist -name "*.whl" -o -name "*.tar.gz" | sort
- name: Install built packages for testing
run: |
# Create a virtual environment with the correct Python version
uv venv --python ${{ matrix.python }}
source .venv/bin/activate || source .venv/Scripts/activate
# Install packages using --find-links to prioritize local builds
uv pip install --find-links packages/leann-core/dist --find-links packages/leann-backend-hnsw/dist --find-links packages/leann-backend-diskann/dist packages/leann-core/dist/*.whl || uv pip install --find-links packages/leann-core/dist packages/leann-core/dist/*.tar.gz
uv pip install --find-links packages/leann-core/dist packages/leann-backend-hnsw/dist/*.whl
uv pip install --find-links packages/leann-core/dist packages/leann-backend-diskann/dist/*.whl
uv pip install packages/leann/dist/*.whl || uv pip install packages/leann/dist/*.tar.gz
# Install test dependencies using extras
uv pip install -e ".[test]"
- name: Run tests with pytest
env:
CI: true # Mark as CI environment to skip memory-intensive tests
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
HF_HUB_DISABLE_SYMLINKS: 1
TOKENIZERS_PARALLELISM: false
PYTORCH_ENABLE_MPS_FALLBACK: 0 # Disable MPS on macOS CI to avoid memory issues
OMP_NUM_THREADS: 1 # Disable OpenMP parallelism to avoid libomp crashes
MKL_NUM_THREADS: 1 # Single thread for MKL operations
run: |
# Activate virtual environment
source .venv/bin/activate || source .venv/Scripts/activate
# Add targeted debugging for pytest hangs (especially Ubuntu 22.04)
if [[ "${{ matrix.os }}" == "ubuntu-22.04" ]]; then
echo "🔍 [HANG DEBUG] Ubuntu 22.04 detected - enabling enhanced process monitoring"
# Pre-test state
echo "📊 [HANG DEBUG] Pre-test process state:"
ps aux | grep -E "(python|embedding|zmq)" | grep -v grep || echo "No relevant processes"
echo "🔌 [HANG DEBUG] Pre-test network state:"
ss -tulpn | grep -E "(555[0-9]|556[0-9])" || echo "No embedding server ports"
# Function to monitor processes during test
monitor_processes() {
while true; do
sleep 30
echo "⏰ [HANG DEBUG] $(date): Process check during test execution"
ps aux | grep -E "(python|pytest|embedding)" | grep -v grep | head -10
ss -tulpn | grep -E "(555[0-9]|556[0-9])" || echo "No ports"
done
}
# Start background monitoring
monitor_processes &
MONITOR_PID=$!
echo "🔍 [HANG DEBUG] Started background monitor (PID: $MONITOR_PID)"
# Run pytest with timeout and enhanced logging
echo "🚀 [HANG DEBUG] Starting pytest with 600s timeout..."
# Pre-test import debugging to identify hang point
echo "🔍 [HANG DEBUG] Testing individual imports to identify hang source..."
timeout 120 python -c "
import sys
import time
def timed_import(module, desc):
start = time.time()
print(f'⏳ Importing {desc}...', flush=True)
try:
__import__(module)
elapsed = time.time() - start
print(f'✅ {desc} imported in {elapsed:.2f}s', flush=True)
except Exception as e:
elapsed = time.time() - start
print(f'❌ {desc} failed after {elapsed:.2f}s: {e}', flush=True)
raise
print('🧪 Testing individual module imports...', flush=True)
timed_import('leann', 'Core LEANN package')
timed_import('leann.api', 'LEANN API module')
print('🧪 Testing backend imports (most likely hang point)...', flush=True)
timed_import('leann_backend_hnsw', 'HNSW backend package')
timed_import('leann_backend_diskann', 'DiskANN backend package')
print('🧪 Testing deep imports...', flush=True)
timed_import('leann_backend_hnsw.hnsw_backend', 'HNSW backend module')
timed_import('leann_backend_diskann.diskann_backend', 'DiskANN backend module')
print('✅ All imports completed successfully', flush=True)
" 2>&1 | while IFS= read -r line; do
echo "$(date +"%H:%M:%S") [IMPORT] $line"
done
IMPORT_EXIT=$?
if [ $IMPORT_EXIT -eq 124 ]; then
echo "⚠️ [HANG DEBUG] IMPORT TIMEOUT! Import process hung - this is likely the root cause"
echo "💀 [HANG DEBUG] Killing any hanging Python processes..."
pkill -KILL -f python || true
exit 1
elif [ $IMPORT_EXIT -ne 0 ]; then
echo "❌ [HANG DEBUG] Import tests failed with exit code: $IMPORT_EXIT"
exit $IMPORT_EXIT
fi
echo "✅ [HANG DEBUG] Import tests passed, proceeding with pytest..."
timeout --preserve-status --signal=TERM --kill-after=30 600 bash -c '
echo "▶️ [HANG DEBUG] Pytest starting at: $(date)"
pytest tests/ -v --tb=short --maxfail=5 -x 2>&1 | while IFS= read -r line; do
echo "$(date +"%H:%M:%S") [PYTEST] $line"
done
echo "✅ [HANG DEBUG] Pytest completed at: $(date)"
'
PYTEST_EXIT=$?
# Stop background monitoring
kill $MONITOR_PID 2>/dev/null || true
echo "🔚 [HANG DEBUG] Pytest exit code: $PYTEST_EXIT"
if [ $PYTEST_EXIT -eq 124 ]; then
echo "⚠️ [HANG DEBUG] TIMEOUT! Pytest hung for >600s"
echo "🔍 [HANG DEBUG] Final process state:"
ps aux | grep -E "(python|pytest|embedding)" | grep -v grep
echo "🔍 [HANG DEBUG] Final network state:"
ss -tulpn | grep -E "(555[0-9]|556[0-9])" || echo "No ports"
echo "💀 [HANG DEBUG] Killing remaining processes..."
pkill -TERM -f "pytest\|embedding_server\|zmq" || true
sleep 3
pkill -KILL -f "pytest\|embedding_server\|zmq" || true
fi
exit $PYTEST_EXIT
else
# For non-Ubuntu or non-22.04, run normally
echo "🚀 [HANG DEBUG] Running tests on ${{ matrix.os }} (normal mode)"
pytest tests/ -v --tb=short
fi
- name: Run sanity checks (optional)
run: |
# Activate virtual environment
source .venv/bin/activate || source .venv/Scripts/activate
# Run distance function tests if available
if [ -f test/sanity_checks/test_distance_functions.py ]; then
echo "Running distance function sanity checks..."
python test/sanity_checks/test_distance_functions.py || echo "⚠️ Distance function test failed, continuing..."
fi
- name: Upload artifacts
uses: actions/upload-artifact@v4
with:
name: packages-${{ matrix.os }}-py${{ matrix.python }}
path: packages/*/dist/