Set up a workflow to run pgbench against captest (#2077)

.github/actions/upload/action.yml

@@ -29,8 +29,12 @@ runs:
           time tar -C ${SOURCE} -cf ${ARCHIVE} --zstd .
         elif [ -f ${SOURCE} ]; then
           time tar -cf ${ARCHIVE} --zstd ${SOURCE}
+        elif ! ls ${SOURCE} > /dev/null 2>&1; then
+          echo 2>&1 "${SOURCE} does not exist"
+          exit 2
         else
-          echo 2>&1 "${SOURCE} neither directory nor file, don't know how to handle it"
+          echo 2>&1 "${SOURCE} is neither a directory nor a file, do not know how to handle it"
+          exit 3
         fi
 
     - name: Upload artifact

.github/workflows/benchmarking.yml

@@ -1,4 +1,4 @@
-name: benchmarking
+name: Benchmarking
 
 on:
   # uncomment to run on push for debugging your PR
@@ -15,6 +15,15 @@ on:
 
   workflow_dispatch: # adds ability to run this manually
 
+defaults:
+  run:
+    shell: bash -euxo pipefail {0}
+
+concurrency:
+  # Allow only one workflow per any non-`main` branch.
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
+  cancel-in-progress: true
+
 jobs:
   bench:
     # this workflow runs on self hosteed runner
@@ -60,7 +69,6 @@ jobs:
     - name: Setup cluster
       env:
         BENCHMARK_CONNSTR: "${{ secrets.BENCHMARK_STAGING_CONNSTR }}"
-      shell: bash -euxo pipefail {0}
       run: |
         set -e
 
@@ -96,7 +104,9 @@ jobs:
         # since it might generate duplicates when calling ingest_perf_test_result.py
         rm -rf perf-report-staging
         mkdir -p perf-report-staging
-        ./scripts/pytest test_runner/performance/ -v -m "remote_cluster" --skip-interfering-proc-check --out-dir perf-report-staging --timeout 3600
+        # Set --sparse-ordering option of pytest-order plugin to ensure tests are running in order of appears in the file,
+        # it's important for test_perf_pgbench.py::test_pgbench_remote_* tests
+        ./scripts/pytest test_runner/performance/ -v -m "remote_cluster" --sparse-ordering --skip-interfering-proc-check --out-dir perf-report-staging --timeout 3600
 
     - name: Submit result
       env:
@@ -113,3 +123,106 @@ jobs:
         slack-message: "Periodic perf testing: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
       env:
         SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
+
+  pgbench-compare:
+    env:
+      TEST_PG_BENCH_DURATIONS_MATRIX: "60m"
+      TEST_PG_BENCH_SCALES_MATRIX: "10gb"
+      REMOTE_ENV: "1"
+      POSTGRES_DISTRIB_DIR: /usr
+      TEST_OUTPUT: /tmp/test_output
+
+    strategy:
+      fail-fast: false
+      matrix:
+        connstr: [ BENCHMARK_CAPTEST_CONNSTR, BENCHMARK_RDS_CONNSTR ]
+
+    runs-on: dev
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rustlegacy:2817580636
+
+    timeout-minutes: 360 # 6h
+
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Cache poetry deps
+      id: cache_poetry
+      uses: actions/cache@v3
+      with:
+        path: ~/.cache/pypoetry/virtualenvs
+        key: v2-${{ runner.os }}-python-deps-${{ hashFiles('poetry.lock') }}
+
+    - name: Install Python deps
+      run: ./scripts/pysync
+
+    - name: Calculate platform
+      id: calculate-platform
+      env:
+        CONNSTR: ${{ matrix.connstr }}
+      run: |
+        if [ "${CONNSTR}" = "BENCHMARK_CAPTEST_CONNSTR" ]; then
+          PLATFORM=neon-captest
+        elif [ "${CONNSTR}" = "BENCHMARK_RDS_CONNSTR" ]; then
+          PLATFORM=rds-aurora
+        else
+          echo 2>&1 "Unknown CONNSTR=${CONNSTR}. Allowed are BENCHMARK_CAPTEST_CONNSTR, and BENCHMARK_RDS_CONNSTR only"
+          exit 1
+        fi
+
+        echo "::set-output name=PLATFORM::${PLATFORM}"
+
+    - name: Install Deps
+      run: |
+        echo "deb http://apt.postgresql.org/pub/repos/apt focal-pgdg main" | sudo tee /etc/apt/sources.list.d/pgdg.list
+        wget --quiet -O - https://www.postgresql.org/media/keys/ACCC4CF8.asc | sudo apt-key add -
+        sudo apt -y update
+        sudo apt install -y postgresql-14 postgresql-client-14
+
+    - name: Benchmark init
+      env:
+        PLATFORM: ${{ steps.calculate-platform.outputs.PLATFORM }}
+        BENCHMARK_CONNSTR: ${{ secrets[matrix.connstr] }}
+      run: |
+        mkdir -p perf-report-captest
+
+        psql $BENCHMARK_CONNSTR -c "SELECT 1;"
+        ./scripts/pytest test_runner/performance/test_perf_pgbench.py::test_pgbench_remote_init -v -m "remote_cluster" --skip-interfering-proc-check --out-dir perf-report-captest --timeout 21600
+
+    - name: Benchmark simple-update
+      env:
+        PLATFORM: ${{ steps.calculate-platform.outputs.PLATFORM }}
+        BENCHMARK_CONNSTR: ${{ secrets[matrix.connstr] }}
+      run: |
+        psql $BENCHMARK_CONNSTR -c "SELECT 1;"
+        ./scripts/pytest test_runner/performance/test_perf_pgbench.py::test_pgbench_remote_simple_update -v -m "remote_cluster" --skip-interfering-proc-check --out-dir perf-report-captest --timeout 21600
+
+    - name: Benchmark select-only
+      env:
+        PLATFORM: ${{ steps.calculate-platform.outputs.PLATFORM }}
+        BENCHMARK_CONNSTR: ${{ secrets[matrix.connstr] }}
+      run: |
+        psql $BENCHMARK_CONNSTR -c "SELECT 1;"
+        ./scripts/pytest test_runner/performance/test_perf_pgbench.py::test_pgbench_remote_select_only -v -m "remote_cluster" --skip-interfering-proc-check --out-dir perf-report-captest --timeout 21600
+
+    - name: Submit result
+      env:
+        VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
+        PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
+      run: |
+        REPORT_FROM=$(realpath perf-report-captest) REPORT_TO=staging scripts/generate_and_push_perf_report.sh
+
+    - name: Upload logs
+      if: always()
+      uses: ./.github/actions/upload
+      with:
+        name: bench-captest-${{ steps.calculate-platform.outputs.PLATFORM }}
+        path: /tmp/test_output/
+
+    - name: Post to a Slack channel
+      if: ${{ github.event.schedule && failure() }}
+      uses: slackapi/slack-github-action@v1
+      with:
+        channel-id: "C033QLM5P7D" # dev-staging-stream
+        slack-message: "Periodic perf testing: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
+      env:
+        SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}