potiuk commented on code in PR #37541:
URL: https://github.com/apache/airflow/pull/37541#discussion_r1498179774


##########
airflow/jobs/job.py:
##########
@@ -183,30 +184,32 @@ def heartbeat(
         previous_heartbeat = self.latest_heartbeat
 
         try:
-            # This will cause it to load from the db
-            self._merge_from(Job._fetch_from_db(self, session))
-            previous_heartbeat = self.latest_heartbeat
-
-            if self.state == JobState.RESTARTING:
-                self.kill()
-
-            # Figure out how long to sleep for
-            sleep_for = 0
-            if self.latest_heartbeat:
-                seconds_remaining = (
-                    self.heartrate - (timezone.utcnow() - 
self.latest_heartbeat).total_seconds()
-                )
-                sleep_for = max(0, seconds_remaining)
-            sleep(sleep_for)
-
-            job = Job._update_heartbeat(job=self, session=session)
-            self._merge_from(job)
-
-            # At this point, the DB has updated.
-            previous_heartbeat = self.latest_heartbeat
-
-            heartbeat_callback(session)
-            self.log.debug("[heartbeat]")
+            for attempt in run_with_db_retries(logger=self.log):
+                with attempt:
+                    # This will cause it to load from the db
+                    self._merge_from(Job._fetch_from_db(self, session))
+                    previous_heartbeat = self.latest_heartbeat
+        
+                    if self.state == JobState.RESTARTING:
+                        self.kill()
+        
+                    # Figure out how long to sleep for
+                    sleep_for = 0
+                    if self.latest_heartbeat:
+                        seconds_remaining = (
+                            self.heartrate - (timezone.utcnow() - 
self.latest_heartbeat).total_seconds()
+                        )
+                        sleep_for = max(0, seconds_remaining)
+                    sleep(sleep_for)
+        
+                    job = Job._update_heartbeat(job=self, session=session)
+                    self._merge_from(job)
+        
+                    # At this point, the DB has updated.
+                    previous_heartbeat = self.latest_heartbeat
+        
+                    heartbeat_callback(session)
+                    self.log.debug("[heartbeat]")
         except OperationalError:

Review Comment:
   Yep. I agree that might make it a bit quit a bit more resilient to 
intermittent issues. 



-- 
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: commits-unsubscr...@airflow.apache.org

For queries about this service, please contact Infrastructure at:
us...@infra.apache.org

Reply via email to