run-profiling.yaml

# Runs a pyinstrument profiling session on the scale_run profiling model,
# capturing the profiling result and sending it to the TLOmodel-profiling
# repository for processing and display.
#
# Profiling script executed is src/scripts/profiling/run-profiling.py.
# Output is the .pyisession file from the profiler, placed into results/
# results/ folder is then pushed to the TLOmodel-profiling repo, results branch.
name: Run profiling

on:
  workflow_dispatch:
  # Allow profiling to be triggered by comments on pull requests
  # Trigger is /run profiling
  issue_comment:
    types:
      - created
  # Profile the model every Saturday at 00:00, 
  # on the HEAD of master
  schedule:
    - cron: 0 0 * * 6

concurrency:
  # Prevent multiple profiling runs from happening on the same
  # commit simultaneously.
  # This ensures we don't overwrite the artifact to be uploaded
  # with another run that uses the same name, before the results
  # can be processed. 
  group: profiling-${{ github.workflow }}-${{ github.ref }}

jobs:
  set-variables:
    name: Create unique output file identifier and artifact name
    runs-on: ubuntu-latest
    if: (github.event_name != 'issue_comment') || ((github.event_name == 'issue_comment') && (github.event.comment.body == '/run profiling'))
    outputs:
      profiling-output-dir: profiling_results/
      profiling-filename: ${{ steps.set-profiling-filename.outputs.name }}
      artifact-name: ${{ steps.set-artifact-name.outputs.name }}
      profiling-on-sha: ${{ steps.determine-correct-sha.outputs.result }}
      profiling-event-trigger: ${{ steps.set-github-info.outputs.event }}
    steps:
      - id: determine-if-pr-comment
        name: Determine if this is a PR comment
        run: |
          if ! [ -z "${{ github.event.issue.pull_request }}" ]; then echo "is-pr=true" >> "${GITHUB_OUTPUT}"; else echo "is-pr=false" >> "${GITHUB_OUTPUT}"; fi

      - id: determine-correct-sha
        name: Determine the SHA to run profiling on
        uses: actions/github-script@v7
        with:
          result-encoding: string
          script: |
            if ("${{ steps.determine-if-pr-comment.outputs.is-pr }}" === "true") {
              const { data: pr } = await github.rest.pulls.get({
                owner: context.issue.owner,
                repo: context.issue.repo,
                pull_number: context.issue.number,
              });
              return pr.head.sha;
            };
            return context.sha;

      - id: set-profiling-filename
        name: Set profiling output file name
        run: |
          echo "name=${GITHUB_EVENT_NAME}_${GITHUB_RUN_NUMBER}_${{ steps.determine-correct-sha.outputs.result }}" >> "${GITHUB_OUTPUT}"

      - id: set-artifact-name
        name: Set artifact name
        run: |
          echo "name=profiling_results_${GITHUB_RUN_NUMBER}" >> "${GITHUB_OUTPUT}"

      - id: set-github-info
        name: Fix Git and GitHub information when passing between workflows
        run: |
          echo "sha=${{ steps.determine-correct-sha.outputs.result }}" >> "${GITHUB_OUTPUT}"
          echo "event=${GITHUB_EVENT_NAME}" >> "${GITHUB_OUTPUT}"

  profile-on-comment:
    name: Comment triggered profiling
    if: github.event_name == 'issue_comment'
    needs: set-variables
    uses: ./.github/workflows/run-on-comment.yml
    with:
      runs-on: '["self-hosted", "profiling"]'
      keyword: profiling
      commands: |
        tox -vv -e profile -- \
          --html \
          --flat-html \
          --root-output-dir ${{ needs.set-variables.outputs.profiling-output-dir }} \
          --output-name ${{ needs.set-variables.outputs.profiling-filename }} \
          --additional-stats \
          sha=${{ needs.set-variables.outputs.profiling-on-sha }} \
          trigger=${{ needs.set-variables.outputs.profiling-event-trigger }} \
          --disable-log-output-to-stdout
      description: Profiled run of the model
      timeout-minutes: 8640
      application-organization: UCL
      artifact-path: ${{ needs.set-variables.outputs.profiling-output-dir }}
      artifact-name: ${{ needs.set-variables.outputs.artifact-name }}
      artifact-retention-days: 1
    secrets:
      application-id: ${{ secrets.COMMENT_BOT_APP_ID }}
      application-private-key: ${{ secrets.COMMENT_BOT_APP_PRIVATE_KEY }}

  profile-on-dispatch:
    name: Scheduled / dispatch triggered profiling
    if: ${{ github.event_name != 'issue_comment' }}
    needs: set-variables
    runs-on: [self-hosted, profiling]
    timeout-minutes: 8640
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          ref: ${{ github.sha }}
          lfs: true

      ## The profile environment produces outputs in the /results directory
      - name: Run profiling in dev environment
        run: |
          tox -vv -e profile -- \
            --html \
            --flat-html \
            --root-output-dir ${{ needs.set-variables.outputs.profiling-output-dir }} \
            --output-name ${{ needs.set-variables.outputs.profiling-filename }} \
            --additional-stats \
            sha=${{ needs.set-variables.outputs.profiling-on-sha }} \
            trigger=${{ needs.set-variables.outputs.profiling-event-trigger }} \
            --disable-log-output-to-stdout

      ## Upload the output as an artifact so we can push it to the profiling repository
      - name: Save results as artifact
        uses: actions/upload-artifact@v4
        with:
          name: ${{ needs.set-variables.outputs.artifact-name }}
          path: ${{ needs.set-variables.outputs.profiling-output-dir }}
          retention-days: 1
  
  upload-profiling-results:
    name: Upload profiling results
    # Run on GH runners to free up self-hosted machines;
    # because we need Docker for the workflow call below,
    # and because we're now just pushing results files to another repo
    runs-on: ubuntu-latest
    # Only run this step if exactly one of the previous two jobs ran successfully
    # see https://stackoverflow.com/a/68952093 for more details
    # NOTE: We need to explicitly depend on set-variables to access the artifact name
    needs: [set-variables, profile-on-comment, profile-on-dispatch]
    if: |
      always() && (
        (needs.profile-on-comment.result == 'success' && needs.profile-on-dispatch.result == 'skipped') ||
        (needs.profile-on-comment.result == 'skipped' && needs.profile-on-dispatch.result == 'success')
      )
    steps:
      - name: Download the profiling results
        uses: actions/download-artifact@v4
        with:
          name: ${{ needs.set-variables.outputs.artifact-name }}
          path: ${{ needs.set-variables.outputs.profiling-output-dir }}

      ## The token provided needs contents and pages access to the target repo
      ## Token can be (re)generated by a member of the UCL organisation, 
      ## the current member is the rc-softdev-admin.
      ## [17-07-2024] New token generated, will expire 10-07-2025
      - name: Push results to profiling repository
        uses: dmnemec/copy_file_to_another_repo_action@v1.1.1
        env:
          API_TOKEN_GITHUB: ${{ secrets.PROFILING_REPO_ACCESS }}
        with:
          source_file: ${{ needs.set-variables.outputs.profiling-output-dir }}
          destination_repo: UCL/TLOmodel-profiling
          destination_folder: .
          destination_branch: results
          user_email: rsd-notifications@ucl.ac.uk
          user_name:  rc-softdev-admin

      - name: Trigger website rebuild
        uses: peter-evans/repository-dispatch@v3
        with:
          token: ${{ secrets.PROFILING_REPO_ACCESS }}
          repository: UCL/TLOmodel-profiling
          event-type: new-profiling-results