ashb commented on a change in pull request #16182:
URL: https://github.com/apache/airflow/pull/16182#discussion_r663757194
##########
File path: airflow/jobs/scheduler_job.py
##########
@@ -807,6 +810,37 @@ def _clean_tis_without_dagrun(self, session):
raise
guard.commit()
+ @provide_session
+ def _clean_tis_without_dag(self, session: Session = None):
+ """Fails task instances and DagRuns of DAGs that no longer exist in
the dagbag/DB"""
+ states_to_check = State.unfinished - frozenset([State.NONE,
State.SHUTDOWN])
+ tis = session.query(TI).filter(TI.state.in_(states_to_check)).all()
+ missing_dags = {}
+ dag_runs = set()
+
+ for ti in tis:
+ if ti.dag_id in missing_dags:
+ ti.set_state(State.FAILED, session=session)
+ continue
+ # Dag no longer in dagbag?
+ if not self.dagbag.has_dag(ti.dag_id, session=session):
+ ti.set_state(State.FAILED, session=session)
+ dag_runs.add(ti.dag_run)
+ missing_dags[ti.dag_id] = [ti]
+ continue
+ if missing_dags:
+ self.log.warning(
+ "The following Dags are missing, therefore the DAG's "
+ "task instances have been set to failed: \t\n%s",
+ [
+ (f"Missing DAGs: {dag_name}", f"Failed TaskInstances:
[{ti}]")
+ for dag_name, ti in missing_dags.items()
+ ],
+ )
+ self.log.warning("Failing the corresponding DagRuns of the missing
DAGs. DagRuns: %s", dag_runs)
+ for dr in dag_runs:
+ dr.set_state(State.FAILED)
Review comment:
```suggestion
dr.state = State.FAILED
```
--
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]
