xBis7 commented on code in PR #71737:
URL: https://github.com/apache/airflow/pull/71737#discussion_r3864808558
##########
airflow-core/src/airflow/models/dagrun.py:
##########
@@ -1465,10 +1512,38 @@ def _filter_tis_and_exclude_removed(dag: SerializedDAG,
tis: list[TI]) -> Iterab
else:
yield ti
- tis = list(_filter_tis_and_exclude_removed(self.get_dag(), tis))
+ def _build_finished_tis(dag: SerializedDAG, rows) -> list[FinishedTI]:
+ """Attach the serialized task, dropping (and marking REMOVED) rows
whose task is gone."""
+ finished: list[FinishedTI] = []
+ orphaned: list[str] = []
+ for row in rows:
+ try:
+ task = dag.get_task(row.task_id)
+ except TaskNotFound:
+ if row.state != TaskInstanceState.REMOVED:
+ orphaned.append(row.task_id)
+ continue
+ finished.append(FinishedTI(**row._mapping, task=task))
+ if orphaned:
+ self.log.error("Failed to get task for finished tis %s.
Marking them as removed.", orphaned)
+ session.execute(
+ update(TI)
+ .where(
+ TI.dag_id == self.dag_id,
+ TI.run_id == self.run_id,
+ TI.task_id.in_(orphaned),
+ TI.state != TaskInstanceState.REMOVED,
+ )
+ .values(state=TaskInstanceState.REMOVED)
+ .execution_options(synchronize_session=False)
+ )
+ return finished
+
+ dag = self.get_dag()
+ unfinished_tis = list(_filter_tis_and_exclude_removed(dag,
unfinished_tis))
Review Comment:
It would change how scheduling works today.
Look at the diff
```diff
- tis = list(_filter_tis_and_exclude_removed(self.get_dag(), tis))
-
- unfinished_tis = [t for t in tis if t.state in State.unfinished]
- finished_tis = [t for t in tis if t.state in State.finished]
```
The current code makes sure that the behavior stays the same.
--
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]
