name: Setup XPU host

description: Set up XPU host for CI

runs:
  using: composite
  steps:
    - name: Clean all stopped docker containers
      if: always()
      shell: bash
      run: |
        # Prune all stopped containers.
        # If other runner is pruning on this node, will skip.
        nprune=$(ps -ef | grep -c "docker container prune")
        if [[ $nprune -eq 1 ]]; then
          docker container prune -f
        fi

    - name: Runner health check system info
      if: always()
      shell: bash
      run: |
        cat /etc/os-release || true
        cat /etc/apt/sources.list.d/oneAPI.list || true
        cat /etc/apt/sources.list.d/intel-gpu-jammy.list || true
        whoami

    - name: Runner health check xpu-smi
      if: always()
      shell: bash
      run: |
        xpu-smi discovery

    - name: Runner health check GPU count
      if: always()
      shell: bash
      run: |
        ngpu=$(xpu-smi discovery | grep -c -E 'Device Name')
        msg="Please file an issue on pytorch/pytorch reporting the faulty runner. Include a link to the runner logs so the runner can be identified"
        if [[ $ngpu -eq 0 ]]; then
          echo "Error: Failed to detect any GPUs on the runner"
          echo "$msg"
          exit 1
        fi

    - name: Runner diskspace health check
      uses: ./.github/actions/diskspace-cleanup
      if: always()

    - name: Runner health check disconnect on failure
      if: ${{ failure() }}
      shell: bash
      run: |
        killall runsvc.sh

    - name: Preserve github env variables for use in docker
      shell: bash
      run: |
        env | grep '^GITHUB' >> "/tmp/github_env_${GITHUB_RUN_ID}"
        env | grep '^CI' >> "/tmp/github_env_${GITHUB_RUN_ID}"

    - name: XPU set GPU_FLAG
      shell: bash
      run: |
        # Add render group for container creation.
        render_gid=`cat /etc/group | grep render | cut -d: -f3`
        echo "GPU_FLAG=--device=/dev/mem --device=/dev/dri --group-add video --group-add $render_gid" >> "${GITHUB_ENV}"