You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@airflow.apache.org by GitBox <gi...@apache.org> on 2019/10/04 09:04:34 UTC

[GitHub] [airflow] ashb commented on a change in pull request #6175: [AIRFLOW-5545] Fixes recursion in DAG cycle testing

ashb commented on a change in pull request #6175: [AIRFLOW-5545] Fixes recursion in DAG cycle testing
URL: https://github.com/apache/airflow/pull/6175#discussion_r331406550
 
 

 ##########
 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:
   Sounds like a good idea to me (and I'm always in favour of using numbers to make performance decisions)

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services