fix: correctly handle schema evolution in DF #14757
Workflow file for this run
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
| # Runs once when we add the `benchmark` tag to a pull request. | |
| name: PR Benchmarks | |
| on: | |
| pull_request: | |
| types: [labeled, synchronize] | |
| branches: ["develop"] | |
| workflow_dispatch: {} | |
| permissions: | |
| actions: write # for removing labels | |
| contents: read | |
| pull-requests: write # for commenting on PRs | |
| id-token: write # enables AWS-GitHub OIDC | |
| deployments: write # for Polar Signals profiling | |
| jobs: | |
| label_trigger: | |
| runs-on: ubuntu-latest | |
| timeout-minutes: 120 | |
| if: ${{ contains(github.event.head_commit.message, '[benchmark]') || github.event.label.name == 'benchmark' && github.event_name == 'pull_request' }} | |
| steps: | |
| # We remove the benchmark label first so that the workflow can be re-triggered. | |
| - uses: actions-ecosystem/action-remove-labels@v1 | |
| with: | |
| labels: benchmark | |
| bench: | |
| needs: label_trigger | |
| timeout-minutes: 120 | |
| runs-on: | |
| - runs-on=${{ github.run_id }} | |
| - family=c6id.8xlarge | |
| - image=ubuntu24-full-x64 | |
| - spot=false | |
| - ${{ github.event.pull_request.head.repo.fork == false && 'extras=s3-cache' || '' }} | |
| - tag=${{ matrix.benchmark.id }} | |
| strategy: | |
| matrix: | |
| benchmark: | |
| - id: random_access | |
| name: Random Access | |
| - id: compress | |
| name: Compression | |
| if: ${{ contains(github.event.head_commit.message, '[benchmark]') || github.event.label.name == 'benchmark' && github.event_name == 'pull_request' }} | |
| steps: | |
| - uses: runs-on/action@v2 | |
| if: github.event.pull_request.head.repo.fork == false | |
| with: | |
| sccache: s3 | |
| - uses: actions/checkout@v6 | |
| with: | |
| ref: ${{ github.event.pull_request.head.sha }} | |
| - uses: ./.github/actions/setup-rust | |
| with: | |
| repo-token: ${{ secrets.GITHUB_TOKEN }} | |
| - name: Install DuckDB | |
| run: | | |
| wget -qO- https://github.com/duckdb/duckdb/releases/download/v1.4.2/duckdb_cli-linux-amd64.zip | funzip > duckdb | |
| chmod +x duckdb | |
| echo "$PWD" >> $GITHUB_PATH | |
| - name: Build binary | |
| shell: bash | |
| env: | |
| RUSTFLAGS: "-C target-cpu=native -C force-frame-pointers=yes" | |
| run: | | |
| cargo build --bin ${{ matrix.benchmark.id }} --package bench-vortex --profile release_debug | |
| - name: Setup Polar Signals | |
| if: github.event.pull_request.head.repo.fork == false | |
| uses: polarsignals/gh-actions-ps-profiling@v0.6.0 | |
| with: | |
| polarsignals_cloud_token: ${{ secrets.POLAR_SIGNALS_API_KEY }} | |
| labels: "branch=${{ github.ref_name }};gh_run_id=${{ github.run_id }};benchmark=${{ matrix.benchmark.id }}" | |
| parca_agent_version: "0.42.0" | |
| project_uuid: "e5d846e1-b54c-46e7-9174-8bf055a3af56" | |
| extra_args: "--off-cpu-threshold=0.001" # Personally tuned by @brancz | |
| - name: Run ${{ matrix.benchmark.name }} benchmark | |
| shell: bash | |
| env: | |
| RUST_BACKTRACE: full | |
| run: | | |
| target/release_debug/${{ matrix.benchmark.id }} -d gh-json -o ${{ matrix.benchmark.id }}.json | |
| - name: Setup AWS CLI | |
| if: github.event.pull_request.head.repo.fork == false | |
| uses: aws-actions/configure-aws-credentials@v5 | |
| with: | |
| role-to-assume: arn:aws:iam::375504701696:role/GitHubBenchmarkRole | |
| aws-region: us-east-1 | |
| - name: Install uv | |
| uses: spiraldb/actions/.github/actions/setup-uv@0.18.5 | |
| with: | |
| sync: false | |
| - name: Compare results | |
| shell: bash | |
| run: | | |
| set -Eeu -o pipefail -x | |
| base_commit_sha=$(\ | |
| curl -L \ | |
| -H "Accept: application/vnd.github+json" \ | |
| -H "Authorization: Bearer ${{ secrets.GITHUB_TOKEN }}" \ | |
| https://api.github.com/repos/vortex-data/vortex/actions/workflows/bench.yml/runs\?branch\=develop\&status\=success\&per_page\=1 \ | |
| | jq -r '.workflow_runs[].head_sha' \ | |
| ) | |
| aws s3 cp s3://vortex-benchmark-results-database/data.json.gz - --no-sign-request \ | |
| | gzip -d \ | |
| | grep $base_commit_sha \ | |
| > base.json | |
| echo '# Benchmarks: ${{ matrix.benchmark.name }}' > comment.md | |
| echo '' >> comment.md | |
| uv run --no-project scripts/compare-benchmark-jsons.py base.json ${{ matrix.benchmark.id }}.json "${{ matrix.benchmark.name }}" \ | |
| >> comment.md | |
| - name: Comment PR | |
| uses: thollander/actions-comment-pull-request@v3 | |
| with: | |
| file-path: comment.md | |
| comment-tag: bench-pr-comment-${{ matrix.benchmark.id }} | |
| sql: | |
| needs: label_trigger | |
| uses: ./.github/workflows/sql-benchmarks.yml | |
| secrets: inherit | |
| with: | |
| mode: "pr" |