fix[duckdb]: no to_struct in exporter (#5750)
#4163
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 after every commit to `develop` (or in other words, _after_ every pull request merges). | |
| name: Benchmarks | |
| on: | |
| push: | |
| branches: [develop] | |
| permissions: | |
| id-token: write # enables AWS-GitHub OIDC | |
| actions: read | |
| contents: write | |
| deployments: write | |
| jobs: | |
| commit-metadata: | |
| runs-on: ubuntu-latest | |
| timeout-minutes: 120 | |
| steps: | |
| - uses: actions/checkout@v6 | |
| - name: Setup AWS CLI | |
| uses: aws-actions/configure-aws-credentials@v5 | |
| with: | |
| role-to-assume: arn:aws:iam::375504701696:role/GitHubBenchmarkRole | |
| aws-region: us-east-1 | |
| - name: Upload Commit Metadata | |
| shell: bash | |
| run: | | |
| set -Eeu -o pipefail -x | |
| sudo apt-get update && sudo apt-get install -y jq | |
| bash scripts/commit-json.sh > new-commit.json | |
| bash scripts/cat-s3.sh vortex-benchmark-results-database commits.json new-commit.json | |
| bench: | |
| timeout-minutes: 120 | |
| runs-on: | |
| - runs-on=${{ github.run_id }} | |
| - family=c6id.8xlarge | |
| - image=ubuntu24-full-x64 | |
| - spot=false | |
| - extras=s3-cache | |
| - tag=${{ matrix.benchmark.id }} | |
| strategy: | |
| matrix: | |
| benchmark: | |
| - id: random_access | |
| name: Random Access | |
| - id: compress | |
| name: Compression | |
| steps: | |
| - uses: runs-on/action@v2 | |
| with: | |
| sccache: s3 | |
| - uses: actions/checkout@v6 | |
| - 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" | |
| # The main difference between this and `bench-pr.yml` is that we add the `lance` feature. | |
| run: | | |
| cargo build --bin ${{ matrix.benchmark.id }} --package bench-vortex --profile release_debug --features lance | |
| - name: Setup Polar Signals | |
| uses: polarsignals/[email protected] | |
| 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 --formats parquet,lance,vortex | |
| - name: Setup AWS CLI | |
| uses: aws-actions/configure-aws-credentials@v5 | |
| with: | |
| role-to-assume: arn:aws:iam::375504701696:role/GitHubBenchmarkRole | |
| aws-region: us-east-1 | |
| - name: Upload Benchmark Results | |
| shell: bash | |
| run: | | |
| bash scripts/cat-s3.sh vortex-benchmark-results-database data.json.gz ${{ matrix.benchmark.id }}.json | |
| sql: | |
| uses: ./.github/workflows/sql-benchmarks.yml | |
| secrets: inherit | |
| with: | |
| mode: "develop" | |
| benchmark_matrix: | | |
| [ | |
| { | |
| "id": "clickbench-nvme", | |
| "subcommand": "clickbench", | |
| "name": "Clickbench on NVME", | |
| "targets": "datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,datafusion:lance,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact,duckdb:duckdb", | |
| "build_args": "--features lance" | |
| }, | |
| { | |
| "id": "tpch-nvme", | |
| "subcommand": "tpch", | |
| "name": "TPC-H SF=1 on NVME", | |
| "targets": "datafusion:arrow,datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,datafusion:lance,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact,duckdb:duckdb", | |
| "scale_factor": "--scale-factor 1.0", | |
| "build_args": "--features lance" | |
| }, | |
| { | |
| "id": "tpch-s3", | |
| "subcommand": "tpch", | |
| "name": "TPC-H SF=1 on S3", | |
| "local_dir": "bench-vortex/data/tpch/1.0", | |
| "remote_storage": "s3://vortex-bench-dev-eu/${{github.ref_name}}/${{github.run_id}}/tpch/1.0/", | |
| "targets": "datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,datafusion:lance,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact", | |
| "scale_factor": "--scale-factor 1.0", | |
| "build_args": "--features lance" | |
| }, | |
| { | |
| "id": "tpch-nvme-10", | |
| "subcommand": "tpch", | |
| "name": "TPC-H SF=10 on NVME", | |
| "targets": "datafusion:arrow,datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,datafusion:lance,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact,duckdb:duckdb", | |
| "scale_factor": "--scale-factor 10.0", | |
| "build_args": "--features lance" | |
| }, | |
| { | |
| "id": "tpch-s3-10", | |
| "subcommand": "tpch", | |
| "name": "TPC-H SF=10 on S3", | |
| "local_dir": "bench-vortex/data/tpch/10.0", | |
| "remote_storage": "s3://vortex-bench-dev-eu/${{github.ref_name}}/${{github.run_id}}/tpch/10.0/", | |
| "targets": "datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,datafusion:lance,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact", | |
| "scale_factor": "--scale-factor 10.0", | |
| "build_args": "--features lance" | |
| }, | |
| { | |
| "id": "tpcds-nvme", | |
| "subcommand": "tpcds", | |
| "name": "TPC-DS SF=1 on NVME", | |
| "targets": "datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact,duckdb:duckdb", | |
| "scale_factor": "--scale-factor 1.0" | |
| }, | |
| { | |
| "id": "statpopgen", | |
| "subcommand": "statpopgen", | |
| "name": "Statistical and Population Genetics", | |
| "local_dir": "bench-vortex/data/statpopgen", | |
| "targets": "duckdb:parquet,duckdb:vortex,duckdb:vortex-compact", | |
| "scale_factor": "--scale-factor 100" | |
| }, | |
| { | |
| "id": "fineweb", | |
| "subcommand": "fineweb", | |
| "name": "FineWeb NVMe", | |
| "targets": "datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact", | |
| "scale_factor": "--scale-factor 100" | |
| }, | |
| { | |
| "id": "fineweb-s3", | |
| "subcommand": "fineweb", | |
| "name": "FineWeb S3", | |
| "local_dir": "bench-vortex/data/fineweb", | |
| "remote_storage": "s3://vortex-bench-dev-eu/${{github.ref_name}}/${{github.run_id}}/fineweb/", | |
| "targets": "datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact", | |
| "scale_factor": "--scale-factor 100" | |
| }, | |
| ] |