sternr commented on code in PR #28128:
URL: https://github.com/apache/airflow/pull/28128#discussion_r1047066039
##########
airflow/jobs/scheduler_job.py:
##########
@@ -880,13 +880,22 @@ def _run_scheduler_loop(self) -> None:
# is finished to avoid concurrent access to the DB.
self.log.debug("Waiting for processors to finish since
we're using sqlite")
self.processor_agent.wait_until_finished()
-
- with create_session() as session:
- num_queued_tis = self._do_scheduling(session)
-
- self.executor.heartbeat()
- session.expunge_all()
- num_finished_events =
self._process_executor_events(session=session)
+
+ for attempt in run_with_db_retries():
+ with attempt:
+ start_time = time.time()
+ try:
+ with create_session() as session:
+ num_queued_tis = self._do_scheduling(session)
+
+ self.executor.heartbeat()
+ session.expunge_all()
+ num_finished_events =
self._process_executor_events(session=session)
+ except OperationalError as e:
+ total_time = time.time() - start_time
+ self.log.error("got a DB exception (retry:%d,
total time in seconds: %d), details: %s", attempt.retry_state.attempt_number,
total_time, e)
Review Comment:
Do you prefer I completely remove the try & ctch and let tenacity handle it
completely (it does print the exception, it just might be a little less easier
to infer the context of the error)?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
