Skip to content

fix google provider DataprocSubmitTrigger deferred tasks stuck forever #62082

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
shahar1 merged 1 commit into from
Feb 27, 2026
Merged

fix google provider DataprocSubmitTrigger deferred tasks stuck forever #62082

Show file tree
Hide file tree
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
8 changes: 5 additions & 3 deletions providers/google/src/airflow/providers/google/cloud/triggers/dataproc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -187,11 +187,13 @@ async def safe_to_cancel(self) -> bool:
return task_state != TaskInstanceState.DEFERRED

async def run(self):
hook = self.get_async_hook()
# Trigger client cache with sync call get_credentials(), evaluated once.
await hook.get_job_client(region=self.region)
Comment thread
olegkachur-e marked this conversation as resolved.

try:
while True:
job = await self.get_async_hook().get_job(
project_id=self.project_id, region=self.region, job_id=self.job_id
)
job = await hook.get_job(project_id=self.project_id, region=self.region, job_id=self.job_id)
state = job.status.state
self.log.info("Dataproc job: %s is in state: %s", self.job_id, state)
if state in (JobStatus.State.DONE, JobStatus.State.CANCELLED, JobStatus.State.ERROR):
Expand Down
17 changes: 10 additions & 7 deletions providers/google/tests/unit/google/cloud/triggers/test_dataproc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -587,10 +587,8 @@ def test_submit_trigger_serialization(self, submit_trigger):
async def test_submit_trigger_run_success(self, mock_get_async_hook, submit_trigger):
"""Test the trigger correctly handles a job completion."""
mock_job = Job(status=JobStatus(state=JobStatus.State.DONE))
future = asyncio.Future()
future.set_result(mock_job)
mock_get_async_hook.return_value.get_job.return_value = future

mock_get_async_hook.return_value.get_job_client = mock.AsyncMock()
mock_get_async_hook.return_value.get_job = mock.AsyncMock(return_value=mock_job)
async_gen = submit_trigger.run()
event = await async_gen.asend(None)
expected_event = TriggerEvent(
Expand All @@ -603,9 +601,12 @@ async def test_submit_trigger_run_success(self, mock_get_async_hook, submit_trig
async def test_submit_trigger_run_error(self, mock_get_async_hook, submit_trigger):
"""Test the trigger correctly handles a job error."""
mock_job = Job(status=JobStatus(state=JobStatus.State.ERROR))
future = asyncio.Future()
future.set_result(mock_job)
mock_get_async_hook.return_value.get_job.return_value = future
mock_get_async_hook.return_value.get_job_client = mock.AsyncMock()
mock_get_async_hook.return_value.get_job = mock.AsyncMock(return_value=mock_job)

# future = asyncio.Future()
# future.set_result(mock_job)
# mock_get_async_hook.return_value.get_job.return_value = future

async_gen = submit_trigger.run()
event = await async_gen.asend(None)
Expand All @@ -625,6 +626,8 @@ async def test_submit_trigger_run_cancelled(
"""Test the trigger correctly handles an asyncio.CancelledError."""
mock_safe_to_cancel.return_value = is_safe_to_cancel
mock_async_hook = mock_get_async_hook.return_value
mock_async_hook.get_job_client = mock.AsyncMock()

mock_async_hook.get_job.side_effect = asyncio.CancelledError

mock_sync_hook = mock_get_sync_hook.return_value
Expand Down