Ankurdeewan commented on code in PR #59798:
URL: https://github.com/apache/airflow/pull/59798#discussion_r2700713367
##########
providers/microsoft/azure/src/airflow/providers/microsoft/azure/operators/batch.py:
##########
@@ -296,24 +313,67 @@ def execute(self, context: Context) -> None:
)
# Add task to job
self.hook.add_single_task_to_job(job_id=self.batch_job_id, task=task)
- # Wait for tasks to complete
- fail_tasks =
self.hook.wait_for_job_tasks_to_complete(job_id=self.batch_job_id,
timeout=self.timeout)
- # Clean up
- if self.should_delete_job:
- # delete job first
- self.clean_up(job_id=self.batch_job_id)
- if self.should_delete_pool:
- self.clean_up(self.batch_pool_id)
- # raise exception if any task fail
+ if self.deferrable:
+ # Verify pool and nodes are in terminal state before deferral
+ pool = self.hook.connection.pool.get(self.batch_pool_id)
+ nodes =
list(self.hook.connection.compute_node.list(self.batch_pool_id))
+ if pool.resize_errors:
Review Comment:
Yess, that makes sense! I’ve reordered it so we check resize_errors first
and only list compute nodes if the pool looks healthy.
--
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]
