fixes for pod/job metadata race conditions (#704)

Netflix · Oct 7, 2021 · c8d5610 · c8d5610
1 parent c784b16
commit c8d5610
Show file tree

Hide file tree

Showing 2 changed files with 165 additions and 97 deletions.
diff --git a/metaflow/plugins/aws/eks/kubernetes.py b/metaflow/plugins/aws/eks/kubernetes.py
@@ -358,9 +358,7 @@ def _print_available(tail, stream, should_persist=False):
                 "%s. This could be a transient error. "
                 "Use @retry to retry." % msg
             )
-        elif not self._job.is_done:
-            # Kill the job if it is still running by throwing an exception.
-            raise KubernetesKilledException("Task failed!")
+
         exit_code, _ = self._job.reason
         echo(
             "Task finished with exit code %s." % exit_code,