dimberman commented on a change in pull request #6175:
URL: https://github.com/apache/airflow/pull/6175#discussion_r496782063
##########
File path: airflow/models/dag.py
##########
@@ -1467,22 +1467,26 @@ def _test_cycle_helper(self, visit_map, task_id):
"""
from airflow.models.dagbag import DagBag # Avoid circular imports
- # print('Inspecting %s' % task_id)
- if visit_map[task_id] == DagBag.CYCLE_DONE:
- return False
-
- visit_map[task_id] = DagBag.CYCLE_IN_PROGRESS
-
- task = self.task_dict[task_id]
- for descendant_id in task.get_direct_relative_ids():
- if visit_map[descendant_id] == DagBag.CYCLE_IN_PROGRESS:
- msg = "Cycle detected in DAG. Faulty task: {0} to {1}".format(
- task_id, descendant_id)
+ path, visited = [task_id], []
+
+ while path:
+ current_task_id = path.pop()
+ if visit_map[current_task_id] == DagBag.CYCLE_DONE:
+ return False
+ if visit_map[current_task_id] == DagBag.CYCLE_IN_PROGRESS:
+ msg = "Cycle detected in DAG. Faulty task: {}".format(
+ current_task_id)
raise AirflowDagCycleException(msg)
- else:
- self._test_cycle_helper(visit_map, descendant_id)
-
- visit_map[task_id] = DagBag.CYCLE_DONE
+ visit_map[current_task_id] = DagBag.CYCLE_IN_PROGRESS
+ task = self.task_dict[current_task_id]
+ for descendant_id in task.get_direct_relative_ids():
+ path.append(descendant_id)
+ if current_task_id in path:
Review comment:
I ran this test on 100,000 tasks and it saved about 1/2 of a second.
Don't really think it's worth it.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
