xBis7 commented on code in PR #54103:
URL: https://github.com/apache/airflow/pull/54103#discussion_r2718328310
##########
airflow-core/src/airflow/jobs/scheduler_job_runner.py:
##########
@@ -490,10 +515,60 @@ def _executable_task_instances_to_queued(self, max_tis:
int, session: Session) -
.where(~DM.is_paused)
.where(TI.state == TaskInstanceState.SCHEDULED)
.where(DM.bundle_name.is_not(None))
+ .join(
+ dr_task_concurrency_subquery,
+ and_(
+ TI.dag_id == dr_task_concurrency_subquery.c.dag_id,
+ TI.run_id == dr_task_concurrency_subquery.c.run_id,
+ ),
+ isouter=True,
+ )
+ .where(
+
func.coalesce(dr_task_concurrency_subquery.c.task_per_dr_count, 0) <
DM.max_active_tasks
+ )
.options(selectinload(TI.dag_model))
.order_by(-TI.priority_weight, DR.logical_date, TI.map_index)
)
+ # Create a subquery with row numbers partitioned by dag_id and
run_id.
+ # Different dags can have the same run_id but
+ # the dag_id combined with the run_id uniquely identify a run.
+ ranked_query = (
+ query.add_columns(
+ func.row_number()
+ .over(
+ partition_by=[TI.dag_id, TI.run_id],
+ order_by=[-TI.priority_weight, DR.logical_date,
TI.map_index],
+ )
+ .label("row_num"),
+ DM.max_active_tasks.label("dr_max_active_tasks"),
+ # Create columns for the order_by checks here for sqlite.
+ TI.priority_weight.label("priority_weight_for_ordering"),
+ DR.logical_date.label("logical_date_for_ordering"),
+ TI.map_index.label("map_index_for_ordering"),
+ )
+ ).subquery()
Review Comment:
You don't have to do it concurrently. If we run the starvation checks first
and them apply the `max_active_tasks` limit, that gives us the desired behavior.
--
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]
