-
Notifications
You must be signed in to change notification settings - Fork 56
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Migrate to sitrep mechanism for T5X and PAXML MGMN tests (#401)
Addresses #399, #235 and #236 Example badge:  Completed run: https://github.com/NVIDIA/JAX-Toolbox/actions/runs/7039302468 ## Changes - Create a reusable job for publishing sitrep for MGMN workflows - Integrate it in T5X MGMN - Integrate it in PAX MGMN ## TODO - [ ] Change badge endpoint in README for T5X - [ ] Change badge endpoint in README for PAX Closes #399 Closes #235 Closes #236 --------- Co-authored-by: Yu-Hang Maxin Tang <Tang.Maxin@gmail.com>
- Loading branch information
1 parent
5b2c1b4
commit fe2b422
Showing
7 changed files
with
302 additions
and
268 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,134 @@ | ||
| name: ~Generate sitrep for Multi-Node Multi-GPU tests | ||
|
|
||
| on: | ||
| workflow_call: | ||
| inputs: | ||
| BADGE_FILENAME: | ||
| type: string | ||
| description: 'Name of the endpoint JSON file for shields.io badge' | ||
| required: true | ||
| ARTIFACT_NAME: | ||
| type: string | ||
| description: 'Name of the artifact zip file' | ||
| required: true | ||
| FW_NAME: | ||
| type: string | ||
| description: 'Name of the framework being used' | ||
| required: true | ||
| outputs: | ||
| STATUS: | ||
| description: 'Summary of all tests run for the workflow. Set to "success" when all metrics per job and all jobs pass, whereas a single metric failure or job error sets the status to "failure"' | ||
| value: ${{ jobs.sitrep.outputs.STATUS }} | ||
|
|
||
| jobs: | ||
| sitrep: | ||
| runs-on: ubuntu-22.04 | ||
| outputs: | ||
| STATUS: ${{ steps.gen-sitrep.outputs.STATUS }} | ||
| steps: | ||
| - name: Check out repository | ||
| uses: actions/checkout@v3 | ||
|
|
||
| - name: Download all artifacts from the previous jobs | ||
| uses: actions/download-artifact@v3 | ||
|
|
||
| - name: Write exit status summary | ||
| id: exit-status | ||
| shell: bash -x -e {0} | ||
| run: | | ||
| EXIT_STATUSES="${{ inputs.FW_NAME }}-${GITHUB_RUN_ID}-*/*-status.json" | ||
| EXIT_STATUS_SUMMARY_FILE="exit_status_summary.json" | ||
| echo -e "\n\n## ${{ inputs.FW_NAME }} MGMN+SPMD Test Status" >> $EXIT_STATUS_SUMMARY_FILE | ||
| cat <<EOF >>$EXIT_STATUS_SUMMARY_FILE | ||
| | Test Case | State | Exit Code | | ||
| | --- | --- | --- | | ||
| EOF | ||
| for i in $EXIT_STATUSES; do | ||
| # Files are named <FW_NAME>-<GHID>-<NAME>/<NAME>-status.json | ||
| echo "| $(echo $i | cut -d/ -f1 | awk -F- '{print $NF}') | $(jq -r .state $i) | $(jq -r .exitcode $i)" | ||
| done | tee -a $EXIT_STATUS_SUMMARY_FILE | ||
| echo "Test statuses:" | ||
| jq -rc 'input_filename,.' $EXIT_STATUSES | ||
| echo "EXIT_STATUS_SUMMARY_FILE=$EXIT_STATUS_SUMMARY_FILE" >> ${GITHUB_OUTPUT} | ||
| - name: Write metrics summary | ||
| id: metrics | ||
| shell: bash -x -e {0} | ||
| run: | | ||
| METRICS_SUMMARY_FILE="metrics_summary.json" | ||
| echo -e "\n\n## ${{ inputs.FW_NAME }} MGMN Test Metrics" >> $METRICS_SUMMARY_FILE | ||
| for i in metrics-test-log/*_metrics.json; do | ||
| echo $i | cut -d'.' -f1 | ||
| echo '```json' | ||
| jq . $i | ||
| echo '```' | ||
| done | tee -a $METRICS_SUMMARY_FILE | ||
| echo "METRICS_SUMMARY_FILE=$METRICS_SUMMARY_FILE" >> ${GITHUB_OUTPUT} | ||
| - name: Generate sitrep | ||
| id: gen-sitrep | ||
| shell: bash -x -e {0} | ||
| run: | | ||
| source .github/workflows/scripts/to_json.sh | ||
| EXIT_STATUSES="${{ inputs.FW_NAME }}-${GITHUB_RUN_ID}-*/*-status.json" | ||
| passed_tests=$(jq -r '. | select ((.state == "COMPLETED") and (.exitcode == "0")) | .state' $EXIT_STATUSES | wc -l) | ||
| failed_tests=$(jq -r '. | select ((.state != "COMPLETED") or (.exitcode != "0")) | .state' $EXIT_STATUSES | wc -l) | ||
| total_tests=$(ls $EXIT_STATUSES | wc -l) | ||
| METRICS_LOG=metrics-test-log/report.jsonl | ||
| all_outcomes() { | ||
| cat $METRICS_LOG | jq -r '. | select((.["$report_type"] == "TestReport") and (.when == "call")) | .outcome' | ||
| } | ||
| cnt_type() { | ||
| cat $METRICS_LOG | jq '. | select((.["$report_type"] == "TestReport") and (.when == "call") and (.outcome | contains("'${1}'"))) | .outcome' | wc -l | ||
| } | ||
| pytest_failed_tests=$(cnt_type failed) | ||
| pytest_passed_tests=$(cnt_type passed) | ||
| pytest_total_tests=$(all_outcomes | wc -l) | ||
| if ([[ $failed_tests -eq 0 ]] && [[ $total_tests -gt 0 ]] && \ | ||
| [[ $pytest_failed_tests -eq 0 ]] && [[ $pytest_total_tests -gt 0 ]]); then | ||
| status=success | ||
| badge_color=brightgreen | ||
| elif [[ $passed_tests -eq 0 ]] || [[ $pytest_passed_tests -eq 0 ]]; then | ||
| status=failure | ||
| badge_color=red | ||
| else | ||
| status=failure | ||
| badge_color=yellow | ||
| fi | ||
| badge_message="${passed_tests}/${total_tests} jobs | ${pytest_passed_tests}/${pytest_total_tests} metrics" | ||
| badge_label='Upstream Tests' | ||
| summary="# ${{ inputs.FW_NAME }} MGMN Test: $badge_message" | ||
| summary+=`cat ${{ steps.exit-status.outputs.EXIT_STATUS_SUMMARY_FILE }}` | ||
| summary+=`cat ${{ steps.metrics.outputs.METRICS_SUMMARY_FILE }}` | ||
| to_json \ | ||
| summary \ | ||
| total_tests passed_tests failed_tests \ | ||
| badge_label badge_color badge_message \ | ||
| > sitrep.json | ||
| schemaVersion=1 \ | ||
| label="${badge_label}" \ | ||
| message="${badge_message}" \ | ||
| color="${badge_color}" \ | ||
| to_json schemaVersion label message color \ | ||
| > ${{ inputs.BADGE_FILENAME }} | ||
| echo "STATUS='${status}'" >> ${GITHUB_OUTPUT} | ||
| - name: Upload artifacts | ||
| uses: actions/upload-artifact@v3 | ||
| with: | ||
| name: ${{ inputs.ARTIFACT_NAME }} | ||
| path: | | ||
| sitrep.json | ||
| ${{ inputs.BADGE_FILENAME }} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.