Skip to content

Only restart failed libc++ jobs, not cancelled ones. #146397

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jul 2, 2025
+4 −92
Merged

Only restart failed libc++ jobs, not cancelled ones. #146397

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
96 changes: 4 additions & 92 deletions .github/workflows/libcxx-restart-preempted-jobs.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ permissions:

jobs:
restart:
if: github.repository_owner == 'llvm' && (github.event.workflow_run.conclusion == 'failure' || github.event.workflow_run.conclusion == 'cancelled')
if: github.repository_owner == 'llvm' && (github.event.workflow_run.conclusion == 'failure')
name: "Restart Job"
permissions:
statuses: read
Expand All @@ -35,8 +35,8 @@ jobs:
// The "The run was canceled by" message comes from a user manually canceling a workflow
// the "higher priority" message comes from github canceling a workflow because the user updated the change.
// And the "exit code 1" message indicates a genuine failure.
const failure_regex = /(Process completed with exit code 1.)|(Canceling since a higher priority waiting request)|(The run was canceled by)/
const preemption_regex = /(The runner has received a shutdown signal)/
const failure_regex = /(Process completed with exit code 1.)/
const preemption_regex = /(The runner has received a shutdown signal)|(The operation was canceled)/

const wf_run = context.payload.workflow_run
core.notice(`Running on "${wf_run.display_title}" by @${wf_run.actor.login} (event: ${wf_run.event})\nWorkflow run URL: ${wf_run.html_url}`)
Expand Down Expand Up @@ -77,7 +77,7 @@ jobs:
console.log('Check run was not completed. Skipping.');
continue;
}
if (check_run.conclusion != 'failure' && check_run.conclusion != 'cancelled') {
if (check_run.conclusion != 'failure') {
console.log('Check run had conclusion: ' + check_run.conclusion + '. Skipping.');
continue;
}
Expand Down Expand Up @@ -156,91 +156,3 @@ jobs:
run_id: context.payload.workflow_run.id
})
await create_check_run('success', 'Restarted workflow run due to preempted job')

restart-test:
if: github.repository_owner == 'llvm' && (github.event.workflow_run.conclusion == 'failure' || github.event.workflow_run.conclusion == 'cancelled') && github.event.actor.login == 'ldionne' # TESTING ONLY
name: "Restart Job (test)"
permissions:
statuses: read
checks: write
actions: write
runs-on: ubuntu-24.04
steps:
- name: "Restart Job (test)"
uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea #v7.0.1
with:
script: |
const FAILURE_REGEX = /(Process completed with exit code 1.)|(Canceling since a higher priority waiting request)|(The run was canceled by)/
const PREEMPTION_REGEX = /(The runner has received a shutdown signal)|(The operation was canceled)/

function log(msg) {
core.notice(msg)
}

const wf_run = context.payload.workflow_run
log(`Running on "${wf_run.display_title}" by @${wf_run.actor.login} (event: ${wf_run.event})\nWorkflow run URL: ${wf_run.html_url}`)

log('Listing check runs for suite')
const check_suites = await github.rest.checks.listForSuite({
owner: context.repo.owner,
repo: context.repo.repo,
check_suite_id: context.payload.workflow_run.check_suite_id,
per_page: 100 // FIXME: We don't have 100 check runs yet, but we should handle this better.
})

preemptions = [];
legitimate_failures = [];
for (check_run of check_suites.data.check_runs) {
log(`Checking check run: ${check_run.id}`);
if (check_run.status != 'completed') {
log('Check run was not completed. Skipping.');
continue;
}

if (check_run.conclusion != 'failure' && check_run.conclusion != 'cancelled') {
log(`Check run had conclusion: ${check_run.conclusion}. Skipping.`);
continue;
}

annotations = await github.rest.checks.listAnnotations({
owner: context.repo.owner,
repo: context.repo.repo,
check_run_id: check_run.id
})

preemption_annotation = annotations.data.find(function(annotation) {
return annotation.annotation_level == 'failure' &&
annotation.message.match(PREEMPTION_REGEX) != null;
});
if (preemption_annotation != null) {
log(`Found preemption message: ${preemption_annotation.message}`);
preemptions.push(check_run);
break;
}

failure_annotation = annotations.data.find(function(annotation) {
return annotation.annotation_level == 'failure' &&
annotation.message.match(FAILURE_REGEX) != null;
});
if (failure_annotation != null) {
log(`Found legitimate failure annotation: ${failure_annotation.message}`);
legitimate_failures.push(check_run);
break;
}
}

if (preemptions) {
log('Found some preempted jobs');
if (legitimate_failures) {
log('Also found some legitimate failures, so not restarting the workflow.');
} else {
log('Did not find any legitimate failures. Restarting workflow.');
await github.rest.actions.reRunWorkflowFailedJobs({
owner: context.repo.owner,
repo: context.repo.repo,
run_id: context.payload.workflow_run.id
})
}
} else {
log('Did not find any preempted jobs. Not restarting the workflow.');
}
Loading