caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
Despite the error message for preempted jobs containing the words
"cancelled", these are considered workflow "failures" by github.

This is important, because if we fail to distinguish between "failed"
and "cancelled" jobs, the restarter will fight to restart jobs a user
intentionally cancelled (either by pressing the "cancel" button, or by
pushing an update to a PR).

This reverts commit 3ea7fc7339. This also
reverts earlier attempts to solve this problem by matching the messages
to detect manual cancellations.

This change also removes ldionne's test workflow, as its hard to
correctly keep in sync.

This change does not attempt to address the maintainability or
testability of this script, which continues to be an issue. If asked to
address these issues, my plan is to write the script in python (which
most people are more familar with), and turn this action into a "docker
action" using a container with the python action and dependencies built
into it. Let me know if that's a direction we're interested in heading.
This commit is contained in:
Eric
2025-07-02 10:04:37 -04:00
committed by GitHub
parent 8b3cc4d1ed
commit d78036f06e
1 changed files with 4 additions and 92 deletions
Download Patch File Download Diff File Expand all files Collapse all files

96
.github/workflows/libcxx-restart-preempted-jobs.yaml vendored
View File

@@ -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
@@ -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: ${wf_run.html_url}`)
@@ -77,7 +77,7 @@ jobs:
console.log('Check run was not completed. Skipping.');
continue;
}
if (check_run.conclusion != 'failure' && check_run.conclusion != 'cancelled') {
if (check_run.conclusion != 'failure') {
console.log('Check run had conclusion: ' + check_run.conclusion + '. Skipping.');
continue;
}
@@ -156,91 +156,3 @@ jobs:
run_id: context.payload.workflow_run.id
})
await create_check_run('success', 'Restarted workflow run due to preempted job')
restart-test:
if: github.repository_owner == 'llvm' && (github.event.workflow_run.conclusion == 'failure' || github.event.workflow_run.conclusion == 'cancelled') && github.event.actor.login == 'ldionne' # TESTING ONLY
name: "Restart Job (test)"
permissions:
statuses: read
checks: write
actions: write
runs-on: ubuntu-24.04
steps:
- name: "Restart Job (test)"
uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea #v7.0.1
with:
script: |
const FAILURE_REGEX = /(Process completed with exit code 1.)|(Canceling since a higher priority waiting request)|(The run was canceled by)/
const PREEMPTION_REGEX = /(The runner has received a shutdown signal)|(The operation was canceled)/
function log(msg) {
core.notice(msg)
}
const wf_run = context.payload.workflow_run
log(`Running on "${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.');
}