name: Benchmarking

on:
  # uncomment to run on push for debugging your PR
  # push:
  #   branches: [ your branch ]
  schedule:
    # * is a special character in YAML so you have to quote this string
    #          ┌───────────── minute (0 - 59)
    #          │ ┌───────────── hour (0 - 23)
    #          │ │ ┌───────────── day of the month (1 - 31)
    #          │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
    #          │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
    - cron:  '0 3 * * *' # run once a day, timezone is utc

  workflow_dispatch: # adds ability to run this manually
    inputs:
      environment:
        description: 'Environment to run remote tests on (dev or staging)'
        required: false
      region_id:
        description: 'Use a particular region. If not set the default region will be used'
        required: false
      save_perf_report:
        type: boolean
        description: 'Publish perf report or not. If not set, the report is published only for the main branch'
        required: false

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
    # it's environment is quite different from usual guthub runner
    # probably the most important difference is that it doesn't start from clean workspace each time
    # e g if you install system packages they are not cleaned up since you install them directly in host machine
    # not a container or something
    # See documentation for more info: https://docs.github.com/en/actions/hosting-your-own-runners/about-self-hosted-runners
    runs-on: [self-hosted, zenith-benchmarker]

    env:
      POSTGRES_DISTRIB_DIR: /usr/pgsql
      DEFAULT_PG_VERSION: 14

    steps:
    - name: Checkout zenith repo
      uses: actions/checkout@v3

    # actions/setup-python@v2 is not working correctly on self-hosted runners
    # see https://github.com/actions/setup-python/issues/162
    # and probably https://github.com/actions/setup-python/issues/162#issuecomment-865387976 in particular
    # so the simplest solution to me is to use already installed system python and spin virtualenvs for job runs.
    # there is Python 3.7.10 already installed on the machine so use it to install poetry and then use poetry's virtuealenvs
    - name: Install poetry & deps
      run: |
        python3 -m pip install --upgrade poetry wheel
        # since pip/poetry caches are reused there shouldn't be any troubles with install every time
        ./scripts/pysync

    - name: Show versions
      run: |
        echo Python
        python3 --version
        poetry run python3 --version
        echo Poetry
        poetry --version
        echo Pgbench
        ${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/pgbench --version

    - name: Create Neon Project
      id: create-neon-project
      uses: ./.github/actions/neon-project-create
      with:
        environment: ${{ github.event.inputs.environment || 'staging' }}
        api_key: ${{ ( github.event.inputs.environment || 'staging' ) == 'staging' && secrets.NEON_STAGING_API_KEY  || secrets.NEON_CAPTEST_API_KEY }}

    - name: Run benchmark
      # pgbench is installed system wide from official repo
      # https://download.postgresql.org/pub/repos/yum/13/redhat/rhel-7-x86_64/
      # via
      # sudo tee /etc/yum.repos.d/pgdg.repo<<EOF
      # [pgdg13]
      # name=PostgreSQL 13 for RHEL/CentOS 7 - x86_64
      # baseurl=https://download.postgresql.org/pub/repos/yum/13/redhat/rhel-7-x86_64/
      # enabled=1
      # gpgcheck=0
      # EOF
      # sudo yum makecache
      # sudo yum install postgresql13-contrib
      # actual binaries are located in /usr/pgsql-13/bin/
      env:
        # The pgbench test runs two tests of given duration against each scale.
        # So the total runtime with these parameters is 2 * 2 * 300 = 1200, or 20 minutes.
        # Plus time needed to initialize the test databases.
        TEST_PG_BENCH_DURATIONS_MATRIX: "300"
        TEST_PG_BENCH_SCALES_MATRIX: "10,100"
        PLATFORM: "neon-staging"
        BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
        REMOTE_ENV: "1" # indicate to test harness that we do not have zenith binaries locally
      run: |
        # just to be sure that no data was cached on self hosted runner
        # since it might generate duplicates when calling ingest_perf_test_result.py
        rm -rf perf-report-staging
        mkdir -p perf-report-staging
        # 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.
        # Do not run tests from test_runner/performance/test_perf_olap.py because they require a prepared DB. We run them separately in `clickbench-compare` job.
        ./scripts/pytest test_runner/performance/ -v \
          -m "remote_cluster" \
          --sparse-ordering \
          --out-dir perf-report-staging \
          --timeout 5400 \
          --ignore test_runner/performance/test_perf_olap.py

    - 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-staging) REPORT_TO=staging scripts/generate_and_push_perf_report.sh

    - name: Delete Neon Project
      if: ${{ always() }}
      uses: ./.github/actions/neon-project-delete
      with:
        environment: staging
        project_id: ${{ steps.create-neon-project.outputs.project_id }}
        api_key: ${{ secrets.NEON_STAGING_API_KEY }}

    - 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 }}

  pgbench-compare:
    strategy:
      fail-fast: false
      matrix:
        # neon-captest-new: Run pgbench in a freshly created project
        # neon-captest-reuse: Same, but reusing existing project
        # neon-captest-prefetch: Same, with prefetching enabled (new project)
        # rds-aurora: Aurora Postgres Serverless v2 with autoscaling from 0.5 to 2 ACUs
        # rds-postgres: RDS Postgres db.m5.large instance (2 vCPU, 8 GiB) with gp3 EBS storage
        platform: [ neon-captest-new, neon-captest-reuse, neon-captest-prefetch, rds-postgres ]
        db_size: [ 10gb ]
        include:
          - platform: neon-captest-new
            db_size: 50gb
          - platform: neon-captest-prefetch
            db_size: 50gb
          - platform: rds-aurora
            db_size: 50gb

    env:
      TEST_PG_BENCH_DURATIONS_MATRIX: "60m"
      TEST_PG_BENCH_SCALES_MATRIX: ${{ matrix.db_size }}
      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
      DEFAULT_PG_VERSION: 14
      TEST_OUTPUT: /tmp/test_output
      BUILD_TYPE: remote
      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
      PLATFORM: ${{ matrix.platform }}

    runs-on: [ self-hosted, dev, x64 ]
    container:
      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rustlegacy:pinned
      options: --init

    timeout-minutes: 360 # 6h

    steps:
    - uses: actions/checkout@v3

    - name: Download Neon artifact
      uses: ./.github/actions/download
      with:
        name: neon-${{ runner.os }}-release-artifact
        path: /tmp/neon/
        prefix: latest

    - name: Add Postgres binaries to PATH
      run: |
        ${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/pgbench --version
        echo "${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin" >> $GITHUB_PATH

    - name: Create Neon Project
      if: contains(fromJson('["neon-captest-new", "neon-captest-prefetch"]'), matrix.platform)
      id: create-neon-project
      uses: ./.github/actions/neon-project-create
      with:
        environment: ${{ github.event.inputs.environment || 'dev' }}
        api_key: ${{ ( github.event.inputs.environment || 'dev' ) == 'staging' && secrets.NEON_STAGING_API_KEY  || secrets.NEON_CAPTEST_API_KEY }}

    - name: Set up Connection String
      id: set-up-connstr
      run: |
        case "${PLATFORM}" in
          neon-captest-reuse)
            CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CONNSTR }}
            ;;
          neon-captest-new | neon-captest-prefetch)
            CONNSTR=${{ steps.create-neon-project.outputs.dsn }}
            ;;
          rds-aurora)
            CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_CONNSTR }}
            ;;
          rds-postgres)
            CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CONNSTR }}
            ;;
          *)
            echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'neon-captest-new', 'neon-captest-prefetch', 'rds-aurora', or 'rds-postgres'"
            exit 1
            ;;
        esac

        echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT

        psql ${CONNSTR} -c "SELECT version();"

    - name: Set database options
      if: matrix.platform == 'neon-captest-prefetch'
      run: |
        DB_NAME=$(psql ${BENCHMARK_CONNSTR} --no-align --quiet -t -c "SELECT current_database()")

        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET enable_seqscan_prefetch=on"
        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET effective_io_concurrency=32"
        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET maintenance_io_concurrency=32"
      env:
        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}

    - name: Benchmark init
      uses: ./.github/actions/run-python-test-set
      with:
        build_type: ${{ env.BUILD_TYPE }}
        test_selection: performance
        run_in_parallel: false
        save_perf_report: ${{ env.SAVE_PERF_REPORT }}
        extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_init
      env:
        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
        VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
        PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"

    - name: Benchmark simple-update
      uses: ./.github/actions/run-python-test-set
      with:
        build_type: ${{ env.BUILD_TYPE }}
        test_selection: performance
        run_in_parallel: false
        save_perf_report: ${{ env.SAVE_PERF_REPORT }}
        extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_simple_update
      env:
        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
        VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
        PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"

    - name: Benchmark select-only
      uses: ./.github/actions/run-python-test-set
      with:
        build_type: ${{ env.BUILD_TYPE }}
        test_selection: performance
        run_in_parallel: false
        save_perf_report: ${{ env.SAVE_PERF_REPORT }}
        extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_select_only
      env:
        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
        VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
        PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"

    - name: Create Allure report
      if: success() || failure()
      uses: ./.github/actions/allure-report
      with:
        action: generate
        build_type: ${{ env.BUILD_TYPE }}

    - name: Delete Neon Project
      if: ${{ steps.create-neon-project.outputs.project_id && always() }}
      uses: ./.github/actions/neon-project-delete
      with:
        environment: dev
        project_id: ${{ steps.create-neon-project.outputs.project_id }}
        api_key: ${{ secrets.NEON_CAPTEST_API_KEY }}

    - 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 ${{ matrix.platform }}: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
      env:
        SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}

  clickbench-compare:
    # ClichBench DB for rds-aurora and rds-Postgres deployed to the same clusters
    # we use for performance testing in pgbench-compare.
    # Run this job only when pgbench-compare is finished to avoid the intersection.
    # We might change it after https://github.com/neondatabase/neon/issues/2900.
    #
    # *_CLICKBENCH_CONNSTR: Genuine ClickBench DB with ~100M rows
    # *_CLICKBENCH_10M_CONNSTR: DB with the first 10M rows of ClickBench DB
    if: success() || failure()
    needs: [ pgbench-compare ]

    strategy:
      fail-fast: false
      matrix:
        # neon-captest-prefetch: We have pre-created projects with prefetch enabled
        # rds-aurora: Aurora Postgres Serverless v2 with autoscaling from 0.5 to 2 ACUs
        # rds-postgres: RDS Postgres db.m5.large instance (2 vCPU, 8 GiB) with gp3 EBS storage
        platform: [ neon-captest-prefetch, rds-postgres, rds-aurora ]

    env:
      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
      DEFAULT_PG_VERSION: 14
      TEST_OUTPUT: /tmp/test_output
      BUILD_TYPE: remote
      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
      PLATFORM: ${{ matrix.platform }}

    runs-on: [ self-hosted, dev, x64 ]
    container:
      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rustlegacy:pinned
      options: --init

    timeout-minutes: 360 # 6h

    steps:
    - uses: actions/checkout@v3

    - name: Download Neon artifact
      uses: ./.github/actions/download
      with:
        name: neon-${{ runner.os }}-release-artifact
        path: /tmp/neon/
        prefix: latest

    - name: Add Postgres binaries to PATH
      run: |
        ${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/pgbench --version
        echo "${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin" >> $GITHUB_PATH

    - name: Set up Connection String
      id: set-up-connstr
      run: |
        case "${PLATFORM}" in
          neon-captest-prefetch)
            CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CLICKBENCH_10M_CONNSTR }}
            ;;
          rds-aurora)
            CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_CLICKBENCH_10M_CONNSTR }}
            ;;
          rds-postgres)
            CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CLICKBENCH_10M_CONNSTR }}
            ;;
          *)
            echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-prefetch', 'rds-aurora', or 'rds-postgres'"
            exit 1
            ;;
        esac

        echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT

        psql ${CONNSTR} -c "SELECT version();"

    - name: Set database options
      if: matrix.platform == 'neon-captest-prefetch'
      run: |
        DB_NAME=$(psql ${BENCHMARK_CONNSTR} --no-align --quiet -t -c "SELECT current_database()")

        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET enable_seqscan_prefetch=on"
        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET effective_io_concurrency=32"
        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET maintenance_io_concurrency=32"
      env:
        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}

    - name: Benchmark clickbench
      uses: ./.github/actions/run-python-test-set
      with:
        build_type: ${{ env.BUILD_TYPE }}
        test_selection: performance/test_perf_olap.py
        run_in_parallel: false
        save_perf_report: ${{ env.SAVE_PERF_REPORT }}
        extra_params: -m remote_cluster --timeout 21600 -k test_clickbench
      env:
        VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
        PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}

    - name: Create Allure report
      if: success() || failure()
      uses: ./.github/actions/allure-report
      with:
        action: generate
        build_type: ${{ env.BUILD_TYPE }}

    - 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 OLAP perf testing ${{ matrix.platform }}: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
      env:
        SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}