[GitHub] feng-tao closed pull request #3562: [WIP][AIRFLOW-2701] Clean up backfill dangling dagrun

[GitBox <gi...@apache.org>]

feng-tao closed pull request #3562: [WIP][AIRFLOW-2701] Clean up backfill dangling dagrun
URL: https://github.com/apache/incubator-airflow/pull/3562
 
 
   

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 00ede5451d..8f19a67231 100644
--- a/airflow/jobs.py
+++ b/airflow/jobs.py
@@ -2008,6 +2008,7 @@ def __init__(
         self.verbose = verbose
         self.conf = conf
         self.rerun_failed_tasks = rerun_failed_tasks
+        self.dag_runs = []
         super(BackfillJob, self).__init__(*args, **kwargs)
 
     def _update_counters(self, ti_status):
@@ -2469,6 +2470,7 @@ def _execute_for_run_dates(self, run_dates, ti_status, executor, pickle_id,
                                                        session=session)
             if dag_run is None:
                 continue
+            self.dag_runs.append(dag_run)
 
             ti_status.active_runs.append(dag_run)
             ti_status.to_run.update(tis_map or {})
@@ -2540,9 +2542,32 @@ def _execute(self, session=None):
                         self.dag_id
                     )
                     time.sleep(self.delay_on_limit_secs)
+
+        except (KeyboardInterrupt, SystemExit):
+            for dag_run in self.dag_runs:
+                dag_run.refresh_from_db(session)
+                make_transient(dag_run)
+
+                # Check all the tasks which are not in success state.
+                check_state = State.unfinished() + State.finished()
+                check_state.remove(State.SUCCESS)
+
+                unfinished_tasks = dag_run.get_task_instances(
+                    state=check_state,
+                    session=session
+                )
+                if unfinished_tasks:
+                    # if there are unfinished tasks and ctrl^c
+                    # set dag run state to failed
+                    for task in unfinished_tasks:
+                        task.set_state(State.FAILED, session)
+                    dag_run.state = State.FAILED
+                else:
+                    dag_run.state = State.SUCCESS
+                session.merge(dag_run)
         finally:
-            executor.end()
             session.commit()
+            executor.end()
 
         self.log.info("Backfill done. Exiting.")
 


 

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services