fix(performance): eliminate redundant regex calls in structured output mode #103
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Performance Benchmarks | |
| on: | |
| push: | |
| branches: [main, dev] | |
| pull_request: | |
| branches: [main, dev] | |
| # Schedule benchmarks to run weekly | |
| schedule: | |
| - cron: "0 0 * * 0" # Run at midnight on Sundays | |
| jobs: | |
| benchmark: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 0 # Fetch all history for proper comparison | |
| - name: Set up Python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.10" | |
| cache: "pip" | |
| - name: Install dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install -e ".[nlp]" | |
| pip install -r requirements-dev.txt | |
| - name: Restore benchmark data | |
| uses: actions/cache@v4 | |
| with: | |
| path: .benchmarks | |
| key: benchmark-${{ runner.os }}-${{ hashFiles('**/requirements*.txt') }} | |
| restore-keys: | | |
| benchmark-${{ runner.os }}- | |
| - name: Run benchmarks and save baseline | |
| env: | |
| # DO NOT set CI=true or GITHUB_ACTIONS=true here to avoid memory optimization slowdowns | |
| # Set optimal performance environment for benchmarks | |
| OMP_NUM_THREADS: 4 | |
| MKL_NUM_THREADS: 4 | |
| OPENBLAS_NUM_THREADS: 4 | |
| run: | | |
| # Run benchmarks with optimal performance settings (no memory debugging) | |
| echo "Running benchmarks with performance-optimized settings..." | |
| python -m pytest tests/benchmark_text_service.py -v --benchmark-autosave --benchmark-json=benchmark-results.json --tb=short | |
| - name: Check for performance regression | |
| run: | | |
| # Compare against the previous benchmark if available | |
| # Fail if performance degrades by more than 10% | |
| if [ -d ".benchmarks" ]; then | |
| benchmark_dir=".benchmarks/Linux-CPython-3.10-64bit" | |
| BASELINE=$(ls -t $benchmark_dir | head -n 2 | tail -n 1) | |
| CURRENT=$(ls -t $benchmark_dir | head -n 1) | |
| if [ -n "$BASELINE" ] && [ "$BASELINE" != "$CURRENT" ]; then | |
| # Set full paths to the benchmark files | |
| BASELINE_FILE="$benchmark_dir/$BASELINE" | |
| CURRENT_FILE="$benchmark_dir/$CURRENT" | |
| echo "Comparing current run ($CURRENT) against baseline ($BASELINE)" | |
| # First just show the comparison | |
| pytest tests/benchmark_text_service.py --benchmark-compare | |
| # Then check for significant regressions | |
| echo "Checking for performance regressions (>100% slower)..." | |
| # Use our Python script for benchmark comparison | |
| python scripts/compare_benchmarks.py "$BASELINE_FILE" "$CURRENT_FILE" | |
| else | |
| echo "No previous benchmark found for comparison or only one benchmark exists" | |
| fi | |
| else | |
| echo "No benchmarks directory found" | |
| fi | |
| - name: Upload benchmark results | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: benchmark-results | |
| path: | | |
| .benchmarks/ | |
| benchmark-results.json | |
| - name: Alert on regression | |
| if: failure() | |
| run: | | |
| echo "::warning::Performance regression detected! Check benchmark results." |