Benchmarks Website Version 3

.github/workflows/bench.yml

@@ -92,7 +92,7 @@ jobs:
           VORTEX_EXPERIMENTAL_PATCHED_ARRAY: "1"
           FLAT_LAYOUT_INLINE_ARRAY_NODE: "1"
         run: |
-          bash scripts/bench-taskset.sh target/release_debug/${{ matrix.benchmark.id }} --formats ${{ matrix.benchmark.formats }} -d gh-json -o results.json
+          bash scripts/bench-taskset.sh target/release_debug/${{ matrix.benchmark.id }} --formats ${{ matrix.benchmark.formats }} -d gh-json -o results.json --gh-json-v3 results.v3.jsonl
 
       - name: Setup AWS CLI
         uses: aws-actions/configure-aws-credentials@ec61189d14ec14c8efccab744f656cffd0e33f37  # v6
@@ -105,6 +105,19 @@ jobs:
         run: |
           bash scripts/cat-s3.sh vortex-ci-benchmark-results data.json.gz results.json
 
+      - name: Ingest results to v3 server
+        if: vars.V3_INGEST_URL != ''
+        continue-on-error: true
+        shell: bash
+        env:
+          INGEST_BEARER_TOKEN: ${{ secrets.INGEST_BEARER_TOKEN }}
+        run: |
+          python3 scripts/post-ingest.py results.v3.jsonl \
+            --server "${{ vars.V3_INGEST_URL }}" \
+            --commit-sha "${{ github.sha }}" \
+            --benchmark-id "${{ matrix.benchmark.id }}" \
+            --repo-url "${{ github.server_url }}/${{ github.repository }}"
+
       - name: Alert incident.io
         if: failure()
         uses: ./.github/actions/alert-incident-io

.github/workflows/ci.yml

@@ -358,7 +358,8 @@ jobs:
         if: matrix.os == 'windows-x64'
         run: |
           cargo nextest run --cargo-profile ci --locked --workspace --all-features --no-fail-fast `
-            --exclude vortex-bench --exclude vortex-python --exclude vortex-duckdb `
+            --exclude vortex-bench --exclude vortex-bench-server `
+            --exclude vortex-python --exclude vortex-duckdb `
             --exclude vortex-fuzz --exclude vortex-cuda --exclude vortex-nvcomp `
             --exclude vortex-cub --exclude vortex-test-e2e-cuda --exclude duckdb-bench `
             --exclude lance-bench --exclude datafusion-bench --exclude random-access-bench `

.github/workflows/publish-bench-server.yml

@@ -0,0 +1,46 @@
+name: Publish Bench Server
+
+on:
+  push:
+    branches: [develop]
+    paths:
+      - "benchmarks-website/server/**"
+      - "vortex-bench/**"
+      - "Cargo.lock"
+      - ".github/workflows/publish-bench-server.yml"
+  workflow_dispatch: { }
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    permissions:
+      contents: read
+      packages: write
+      id-token: write
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Log in to GHCR
+        uses: docker/login-action@v4
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v4
+
+      - name: Build and push
+        uses: docker/build-push-action@v7
+        with:
+          context: .
+          file: ./benchmarks-website/server/Dockerfile
+          platforms: linux/arm64
+          push: true
+          tags: |
+            ghcr.io/${{ github.repository }}/vortex-bench-server:latest
+            ghcr.io/${{ github.repository }}/vortex-bench-server:${{ github.sha }}

.github/workflows/sql-benchmarks.yml

@@ -376,6 +376,7 @@ jobs:
           bash scripts/bench-taskset.sh uv run --project bench-orchestrator vx-bench run "${{ matrix.subcommand }}" \
             --targets-json '${{ steps.targets.outputs.targets_json }}' \
             --output results.json \
+            --gh-json-v3 results.v3.jsonl \
             --no-build \
             --runner "ec2_${{ inputs.machine_type }}" \
             ${{ matrix.iterations && format('--iterations {0}', matrix.iterations) || '' }} \
@@ -395,6 +396,7 @@ jobs:
           bash scripts/bench-taskset.sh uv run --project bench-orchestrator vx-bench run "${{ matrix.subcommand }}" \
             --targets-json '${{ steps.targets.outputs.targets_json }}' \
             --output results.json \
+            --gh-json-v3 results.v3.jsonl \
             --no-build \
             --runner "ec2_${{ inputs.machine_type }}" \
             ${{ matrix.iterations && format('--iterations {0}', matrix.iterations) || '' }} \
@@ -499,6 +501,19 @@ jobs:
         run: |
           bash scripts/cat-s3.sh vortex-ci-benchmark-results data.json.gz results.json
 
+      - name: Ingest results to v3 server
+        if: inputs.mode == 'develop' && vars.V3_INGEST_URL != ''
+        continue-on-error: true
+        shell: bash
+        env:
+          INGEST_BEARER_TOKEN: ${{ secrets.INGEST_BEARER_TOKEN }}
+        run: |
+          python3 scripts/post-ingest.py results.v3.jsonl \
+            --server "${{ vars.V3_INGEST_URL }}" \
+            --commit-sha "${{ github.sha }}" \
+            --benchmark-id "${{ matrix.id }}" \
+            --repo-url "${{ github.server_url }}/${{ github.repository }}"
+
       - name: Upload File Sizes
         if: inputs.mode == 'develop' && matrix.remote_storage == null
         shell: bash

.github/workflows/v3-commit-metadata.yml

@@ -0,0 +1,35 @@
+# Posts a v3 ingest envelope with no records on every push to develop, so the
+# `commits` dim stays populated even when no benchmark ran.
+
+name: v3 commit metadata
+
+on:
+  push:
+    branches: [develop]
+  workflow_dispatch: { }
+
+permissions:
+  contents: read
+
+jobs:
+  commit-metadata:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          fetch-depth: 2
+
+      - name: Ingest commit metadata to v3 server
+        if: vars.V3_INGEST_URL != ''
+        continue-on-error: true
+        shell: bash
+        env:
+          INGEST_BEARER_TOKEN: ${{ secrets.INGEST_BEARER_TOKEN }}
+        run: |
+          echo -n > empty.jsonl
+          python3 scripts/post-ingest.py empty.jsonl \
+            --server "${{ vars.V3_INGEST_URL }}" \
+            --commit-sha "${{ github.sha }}" \
+            --benchmark-id "commit-metadata" \
+            --repo-url "${{ github.server_url }}/${{ github.repository }}"

.gitignore

@@ -242,3 +242,6 @@ trace*.pb
 
 # pytest-benchmark output
 vortex-python/.benchmarks/
+# For local benchmarks website server and things like the WAL
+**.duckdb*
+.bench-env