_win-test.yml

name: win-test

on:
  workflow_call:
    inputs:
      build-environment:
        required: true
        type: string
        description: Top-level label for what's being built/tested.
      cuda-version:
        required: true
        type: string
        description: What CUDA version to build with, "cpu" for none.
      test-matrix:
        required: true
        type: string
        description: JSON description of what test configs to run.
      sync-tag:
        required: false
        type: string
        default: ""
        description: |
          If this is set, our linter will use this to make sure that every other
          job with the same `sync-tag` is identical.
      timeout-minutes:
        required: false
        type: number
        default: 240
        description: |
          Set the maximum (in minutes) how long the workflow should take to finish

env:
  GIT_DEFAULT_BRANCH: ${{ github.event.repository.default_branch }}

jobs:
  test:
    # Don't run on forked repos or empty test matrix
    if: github.repository_owner == 'pytorch' && toJSON(fromJSON(inputs.test-matrix).include) != '[]'
    strategy:
      matrix: ${{ fromJSON(inputs.test-matrix) }}
      fail-fast: false
    runs-on: ${{ matrix.runner }}
    timeout-minutes: ${{ matrix.mem_leak_check == 'mem_leak_check' && 600 || inputs.timeout-minutes }}
    defaults:
      run:
        shell: bash
    steps:
      # Duplicated in win-build because this MUST go before a checkout
      - name: Enable git long paths and symlinks on Windows and disable fsmonitor daemon
        shell: bash
        run: |
          git config --global core.longpaths true
          git config --global core.symlinks true

          # https://git-scm.com/docs/git-fsmonitor--daemon.  The daemon could lock
          # the directory on Windows and prevent GHA from checking out as reported
          # in https://github.com/actions/checkout/issues/1018
          git config --global core.fsmonitor false

      - name: Clean up leftover processes on non-ephemeral Windows runner
        uses: pytorch/test-infra/.github/actions/cleanup-runner@main

      - name: Setup SSH (Click me for login details)
        uses: pytorch/test-infra/.github/actions/setup-ssh@main
        with:
          github-secret: ${{ secrets.GITHUB_TOKEN }}
          instructions: |
            To forward remote desktop on your local machine ssh as follows:
              ssh -L 3389:localhost:3389 %%username%%@%%hostname%%
            And then change password using `passwd` command.

            To start tests locally, change working folder to \actions-runner\_work\pytorch\pytorch\test,
            Activate miniconda and Visual Studio environment and set PYTHON_PATH, by running:
              call C:\Jenkins\Miniconda3\Scripts\activate.bat C:\Jenkins\Miniconda3
              call "C:\Program Files (x86)\Microsoft Visual Studio\2019\BuildTools\VC\Auxiliary\Build\vcvarsall.bat" x64
              set PYTHONPATH=C:\actions-runner\_work\pytorch\pytorch\build\win_tmp\build

      # [see note: pytorch repo ref]
      - name: Checkout PyTorch
        uses: pytorch/pytorch/.github/actions/checkout-pytorch@main
        with:
          no-sudo: true

      - name: Setup Windows
        uses: ./.github/actions/setup-win
        with:
          cuda-version: ${{ inputs.cuda-version }}

      # TODO: Move to a requirements.txt file for windows
      - name: Install pip dependencies
        uses: nick-fields/retry@v3.0.0
        with:
          shell: bash
          timeout_minutes: 5
          max_attempts: 5
          retry_wait_seconds: 30
          command: |
            set -eu
            python3 -m pip install rockset==1.0.3 'xdoctest>=1.1.0'

      - name: Start monitoring script
        id: monitor-script
        shell: bash
        continue-on-error: true
        run: |
          # Windows conda doesn't have python3 binary, only python, but it's python3
          ${CONDA_RUN} python -m tools.stats.monitor > usage_log.txt 2>&1 &
          echo "monitor-script-pid=${!}" >> "${GITHUB_OUTPUT}"

      - name: Download PyTorch Build Artifacts
        uses: seemethere/download-artifact-s3@v4
        with:
          name: ${{ inputs.build-environment }}
          path: C:\${{ github.run_id }}\build-results

      - name: Check build-results folder
        shell: powershell
        run: |
          tree /F C:\$Env:GITHUB_RUN_ID\build-results

      - name: Download TD artifacts
        continue-on-error: true
        uses: ./.github/actions/download-td-artifacts

      - name: Get workflow job id
        id: get-job-id
        uses: ./.github/actions/get-workflow-job-id
        if: always()
        with:
          github-token: ${{ secrets.GITHUB_TOKEN }}

      - name: Check for keep-going label and re-enabled test issues
        # This uses the filter-test-configs action because it conviniently
        # checks for labels and re-enabled test issues.  It does not actually do
        # any filtering.  All filtering is done in the build step.
        id: keep-going
        uses: ./.github/actions/filter-test-configs
        with:
          github-token: ${{ secrets.GITHUB_TOKEN }}
          test-matrix: ${{ inputs.test-matrix }}
          job-name: ${{ steps.get-job-id.outputs.job-name }}

      - name: Set Test step time
        id: test-timeout
        shell: bash
        env:
          JOB_TIMEOUT: ${{ matrix.mem_leak_check == 'mem_leak_check' && 600 || inputs.timeout-minutes }}
        run: |
          echo "timeout=$((JOB_TIMEOUT-30))" >> "${GITHUB_OUTPUT}"

      - name: Test
        id: test
        shell: bash
        timeout-minutes: ${{ fromJson(steps.test-timeout.outputs.timeout) }}
        env:
          USE_CUDA: ${{ inputs.cuda-version != 'cpu' && '1' || '0' }}
          INSTALL_WINDOWS_SDK: 1
          PYTHON_VERSION: 3.9
          CONTINUE_THROUGH_ERROR: ${{ steps.keep-going.outputs.keep-going }}
          VERBOSE_TEST_LOGS: ${{ steps.keep-going.outputs.ci-verbose-test-logs }}
          TEST_SHOWLOCALS: ${{ steps.keep-going.outputs.ci-test-showlocals }}
          NO_TEST_TIMEOUT: ${{ steps.keep-going.outputs.ci-no-test-timeout }}
          NO_TD: ${{ steps.keep-going.outputs.ci-no-td }}
          VC_PRODUCT: "BuildTools"
          VC_VERSION: ""
          VS_VERSION: "16.8.6"
          VC_YEAR: "2019"
          AWS_DEFAULT_REGION: us-east-1
          PR_NUMBER: ${{ github.event.pull_request.number }}
          GITHUB_REPOSITORY: ${{ github.repository }}
          GITHUB_WORKFLOW: ${{ github.workflow }}
          GITHUB_JOB: ${{ github.job }}
          GITHUB_RUN_ID: ${{ github.run_id }}
          GITHUB_RUN_NUMBER: ${{ github.run_number }}
          GITHUB_RUN_ATTEMPT: ${{ github.run_attempt }}
          JOB_ID: ${{ steps.get-job-id.outputs.job-id }}
          JOB_NAME: ${{ steps.get-job-id.outputs.job-name }}
          SHA1: ${{ github.event.pull_request.head.sha || github.sha }}
          CUDA_VERSION: ${{ inputs.cuda-version }}
          PYTORCH_FINAL_PACKAGE_DIR: /c/${{ github.run_id }}/build-results/
          BUILD_ENVIRONMENT: ${{ inputs.build-environment }}
          ALPINE_IMAGE: "308535385114.dkr.ecr.us-east-1.amazonaws.com/tool/alpine"
          SHARD_NUMBER: ${{ matrix.shard }}
          NUM_TEST_SHARDS: ${{ matrix.num_shards }}
          TEST_CONFIG: ${{ matrix.config }}
          REENABLED_ISSUES: ${{ github.event.pull_request.reenabled-issues }}
          TORCH_CUDA_ARCH_LIST: "8.6"
          PYTORCH_TEST_CUDA_MEM_LEAK_CHECK: ${{ matrix.mem_leak_check && '1' || '0' }}
          PYTORCH_TEST_RERUN_DISABLED_TESTS: ${{ matrix.rerun_disabled_tests && '1' || '0' }}
        run: |
          pushd "${PYTORCH_FINAL_PACKAGE_DIR}"
          # shellcheck disable=SC2046,SC2102
          python3 -mpip install $(echo *.whl)[opt-einsum,optree] optree==0.13.0
          popd

          .ci/pytorch/win-test.sh

      - name: Upload pytest cache if tests failed
        uses: ./.github/actions/pytest-cache-upload
        continue-on-error: true
        if: failure() && steps.test.conclusion && steps.test.conclusion == 'failure'
        with:
          cache_dir: .pytest_cache
          shard: ${{ matrix.shard }}
          sha: ${{ github.event.pull_request.head.sha || github.sha }}
          test_config: ${{ matrix.config }}
          job_identifier: ${{ github.workflow }}_${{ inputs.build-environment }}

      - name: Print remaining test logs
        shell: bash
        if: always() && steps.test.conclusion
        run: |
          cat test/**/*_toprint.log || true

      - name: Stop monitoring script
        if: always() && steps.monitor-script.outputs.monitor-script-pid
        shell: bash
        continue-on-error: true
        env:
          MONITOR_SCRIPT_PID: ${{ steps.monitor-script.outputs.monitor-script-pid }}
        run: |
          kill "$MONITOR_SCRIPT_PID"

      - name: Upload test artifacts
        uses: ./.github/actions/upload-test-artifacts
        if: always() && steps.test.conclusion && steps.test.conclusion != 'skipped'
        with:
          file-suffix: ${{ github.job }}-${{ matrix.config }}-${{ matrix.shard }}-${{ matrix.num_shards }}-${{ matrix.runner }}_${{ steps.get-job-id.outputs.job-id }}

      - name: Parse ref
        id: parse-ref
        shell: bash
        run: python3 .github/scripts/parse_ref.py

      - name: Uninstall PyTorch
        if: always()
        continue-on-error: true
        shell: bash
        run: |
          # This step removes PyTorch installed by the test to give a clean slate
          # to the next job
          python3 -mpip uninstall -y torch

      - name: Teardown Windows
        uses: ./.github/actions/teardown-win
        if: always()
        timeout-minutes: 120