Lee-W commented on code in PR #71072:
URL: https://github.com/apache/airflow/pull/71072#discussion_r3977414381


##########
airflow-core/src/airflow/jobs/scheduler_job_runner.py:
##########
@@ -2296,6 +2310,89 @@ def _create_dagruns_for_partitioned_asset_dags(self, 
session: Session) -> set[st
         if not pending_apdrs:
             return set()
 
+        if len(pending_apdrs) >= self._max_partition_dag_runs_per_loop:
+            # A full fetch alone can't tell us whether that's the entire 
backlog or just
+            # this tick's slice of a larger one, so we only pay for this query 
then.
+            # Per-Dag counts across the *whole* backlog, not just this tick's 
oldest-cap
+            # slice (`pending_apdrs`) — a Dag whose partitions haven't reached 
the front of
+            # the FIFO queue yet would otherwise be missing from the log/audit 
row until its
+            # turn comes up.
+            backlogs_per_dag: dict[str, int] = {
+                dag_id: count
+                for dag_id, count in session.execute(
+                    select(AssetPartitionDagRun.target_dag_id, func.count())
+                    .select_from(AssetPartitionDagRun)
+                    .join(DagModel, DagModel.dag_id == 
AssetPartitionDagRun.target_dag_id)
+                    .where(
+                        AssetPartitionDagRun.created_dag_run_id.is_(None),
+                        DagModel.is_stale.is_(False),
+                    )
+                    .group_by(AssetPartitionDagRun.target_dag_id)
+                )
+            }
+            backlog_total = sum(backlogs_per_dag.values())
+            # No SQL-side ORDER BY: it would have no dag_id tie-break, and 
relying on dict
+            # insertion order mirroring DB row order across backends (SQLite 
in tests vs
+            # Postgres/MySQL in production) isn't a contract worth trusting — 
sort explicitly.
+            sorted_dag_ids = sorted(backlogs_per_dag, key=lambda dag_id: 
(-backlogs_per_dag[dag_id], dag_id))
+        else:
+            backlog_total = len(pending_apdrs)
+            self._partition_cap_backlog_reported = False
+
+        if backlog_total > self._max_partition_dag_runs_per_loop:
+            displayed_dag_ids = 
sorted_dag_ids[:MAX_PARTITION_CAP_BACKLOG_DAG_IDS_LOGGED]
+            remaining_dag_id_count = len(sorted_dag_ids) - 
len(displayed_dag_ids)
+            log_cap_reached = self.log.debug if 
self._partition_cap_backlog_reported else self.log.warning

Review Comment:
   Fixed by giving `sorted_dag_ids` an explicit default outside the branch, so 
it no longer depends on the two conditions staying in sync.



-- 
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]

Reply via email to