Skip to content

fix(ci): keep the cron queue moving when one test fails to start #1244

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
cfsmp3 merged 2 commits into from
Oct 25, 2026
Merged

fix(ci): keep the cron queue moving when one test fails to start #1244

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8a98f50
fix(ci): keep the cron queue moving when one test fails to start
x15sr71 Oct 24, 2026
3628b49
Merge branch 'master' into fix/ci-one-test-cant-stall-queue
x15sr71 Oct 24, 2026
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
7 changes: 6 additions & 1 deletion mod_ci/controllers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -719,7 +719,12 @@ def gcp_instance(app, db, platform, repository, delay) -> None:
except Exception as e:
log.error(f"Unexpected error checking PR status for test {test.id}: {e}")
continue
start_test(compute, app, db, repository, test, github_config['bot_token'])
try:
start_test(compute, app, db, repository, test, github_config['bot_token'])
except Exception:
# One test that can't be started (e.g. its files under vm_data raising OSError) must not
# stop the tests queued after it, or the other platform. It stays pending and is retried.
log.exception(f"[{platform}] Test {test.id}: could not be started, will retry on next cron run")


def get_compute_service_object() -> googleapiclient.discovery.Resource:
Expand Down
21 changes: 21 additions & 0 deletions tests/test_ci/test_controllers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -171,6 +171,27 @@ def test_start_platform_windows_specified(self, mock_log, mock_gcp_instance,
mock_delete_expired_instances.assert_called_once()
mock_get_compute_service_object.assert_called_once()

@mock.patch('mod_ci.controllers.start_test')
@mock.patch('mod_ci.controllers.get_compute_service_object')
@mock.patch('mod_ci.controllers.delete_expired_instances')
@mock.patch('run.log')
def test_start_platforms_continues_after_a_test_fails_to_start(self, mock_log, mock_delete_expired_instances,
mock_get_compute_service_object, mock_start_test):
"""Test that a test failing to start doesn't stop the tests after it or the other platform."""
commit = "1978060bf7d2edd119736ba3ba88341f3bec3323"
queued = [Test(TestPlatform.linux, TestType.commit, 1, "master", commit),
Test(TestPlatform.linux, TestType.commit, 1, "master", commit),
Test(TestPlatform.windows, TestType.commit, 1, "master", commit)]
g.db.add_all(queued)
g.db.commit()
queued_ids = [test.id for test in queued]
mock_start_test.side_effect = [OSError(5, 'Input/output error'), None, None]

start_platforms(mock.ANY)

self.assertEqual(queued_ids, [call.args[4].id for call in mock_start_test.call_args_list])
mock_log.exception.assert_called_once()

@mock.patch('run.log')
@mock.patch('mod_ci.controllers.MaintenanceMode')
def test_gcp_instance_maintenance_mode(self, mock_maintenance, mock_log):
Expand Down
Loading