Try profiling

.github/workflows/benchmark.yml

@@ -3,13 +3,97 @@ name: hello-world
 on:
   push:
 
+
+env:
+  DAFT_ANALYTICS_ENABLED: '0'
+  TPCH_SCALE_FACTOR: '4'
+  TPCH_NUM_PARTS: '32'
+  PYTHON_VERSION: '3.9'
+
 jobs:
-  my-job:
+  profile-daft:
     runs-on: [self-hosted, linux, arm64, default]
+    timeout-minutes: 30
+    strategy:
+      fail-fast: false
     steps:
-    - name: my-step
-      run: echo "hello, world!"
-    - name: show-workdir
-      run: ls -lah /opt/actions-runner/_work/
-    - name: show-disks
-      run: df -h
+    - uses: actions/checkout@v3
+    - uses: moonrepo/setup-rust@v0
+      with:
+        cache: false
+    - uses: Swatinem/rust-cache@v2
+      with:
+        key: ${{ runner.os }}-profile
+        cache-all-crates: 'true'
+
+    - name: Set up Python ${{ env.PYTHON_VERSION }}
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ env.PYTHON_VERSION }}
+
+    - name: Setup Virtual Env
+      run: |
+        python -m venv venv
+        echo "$GITHUB_WORKSPACE/venv/bin" >> $GITHUB_PATH
+
+    - name: Install dependencies
+      run: |
+        pip install --upgrade pip
+        pip install -r requirements-dev.txt
+
+    - name: Build Rust Library
+      env:
+        RUSTFLAGS: -Ctarget-cpu=native
+
+      run: |
+        source activate
+        maturin develop --release
+
+    - uses: actions/cache@v3
+      env:
+        cache-name: profiling-cache-tpch-data
+      with:
+        path: data/tpch-dbgen
+        key: ${{ runner.os }}-build-${{ env.cache-name }}-${{ env.TPCH_SCALE_FACTOR }}-${{ env.TPCH_NUM_PARTS }}-${{ hashFiles('tests/integration/test_tpch.py', 'benchmarking/tpch/**') }}
+
+    - name: Generate TPCH Data
+      run: python benchmarking/tpch/data_generation.py --scale_factor=${{ env.TPCH_SCALE_FACTOR }} --num_parts=${{ env.TPCH_NUM_PARTS }} --generate_parquet
+
+    - name: Run Profiling on TPCH Benchmark
+      env:
+        DAFT_DEVELOPER_USE_THREAD_POOL: '0'
+      run: |
+        py-spy record --native --function -o tpch-${{github.run_id}}.txt -f speedscope -- python benchmarking/tpch/__main__.py --scale_factor=${{ env.TPCH_SCALE_FACTOR }} --num_parts=${{ env.TPCH_NUM_PARTS }} --skip_warmup || true
+
+    - name: Run GIL Profiling on TPCH Benchmark
+      env:
+        DAFT_DEVELOPER_USE_THREAD_POOL: '0'
+      run: |
+        py-spy record --native --function --gil -o tpch-gil-${{github.run_id}}.txt -f speedscope -- python benchmarking/tpch/__main__.py --scale_factor=${{ env.TPCH_SCALE_FACTOR }} --num_parts=${{ env.TPCH_NUM_PARTS }} --skip_warmup || true
+
+
+    - name: Upload Profile
+      uses: actions/upload-artifact@v3
+      with:
+        name: speedscope-profile
+        path: tpch-*.txt
+
+    - name: Send Slack notification on failure
+      uses: slackapi/[email protected]
+      if: failure()
+      with:
+        payload: |
+          {
+            "blocks": [
+              {
+                "type": "section",
+                "text": {
+                  "type": "mrkdwn",
+                  "text": ":rotating_light: Run Profiling on the TPCH Benchmark <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|workflow> *FAILED* :rotating_light:"
+                }
+              }
+            ]
+          }
+      env:
+        SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
+        SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK