ashb closed pull request #3650: [AIRFLOW-2703] exceptions from scheduler's
heartbeat is handled so that scheduler does not crash
URL: https://github.com/apache/incubator-airflow/pull/3650
This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:
As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):
diff --git a/airflow/jobs.py b/airflow/jobs.py
index 04d596b9b7..38f96e2247 100644
--- a/airflow/jobs.py
+++ b/airflow/jobs.py
@@ -160,33 +160,36 @@ def heartbeat(self):
heart rate. If you go over 60 seconds before calling it, it won't
sleep at all.
"""
- with create_session() as session:
- job = session.query(BaseJob).filter_by(id=self.id).one()
- make_transient(job)
- session.commit()
+ try:
+ with create_session() as session:
+ job = session.query(BaseJob).filter_by(id=self.id).one()
+ make_transient(job)
+ session.commit()
- if job.state == State.SHUTDOWN:
- self.kill()
+ if job.state == State.SHUTDOWN:
+ self.kill()
- # Figure out how long to sleep for
- sleep_for = 0
- if job.latest_heartbeat:
- sleep_for = max(
- 0,
- self.heartrate - (
- timezone.utcnow() - job.latest_heartbeat).total_seconds())
+ # Figure out how long to sleep for
+ sleep_for = 0
+ if job.latest_heartbeat:
+ sleep_for = max(
+ 0,
+ self.heartrate - (timezone.utcnow() -
+ job.latest_heartbeat).total_seconds())
- sleep(sleep_for)
+ sleep(sleep_for)
- # Update last heartbeat time
- with create_session() as session:
- job = session.query(BaseJob).filter(BaseJob.id == self.id).first()
- job.latest_heartbeat = timezone.utcnow()
- session.merge(job)
- session.commit()
+ # Update last heartbeat time
+ with create_session() as session:
+ job = session.query(BaseJob).filter(BaseJob.id ==
self.id).first()
+ job.latest_heartbeat = timezone.utcnow()
+ session.merge(job)
+ session.commit()
- self.heartbeat_callback(session=session)
- self.log.debug('[heartbeat]')
+ self.heartbeat_callback(session=session)
+ self.log.debug('[heartbeat]')
+ except OperationalError as e:
+ self.log.error("Scheduler heartbeat got an exception: %s", str(e))
def run(self):
Stats.incr(self.__class__.__name__.lower() + '_start', 1, 1)
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
