Restart volcano job on pod failure

stackhpc · Oct 2, 2023 · 2dbc456 · 2dbc456
1 parent 2fc0f27
commit 2dbc456
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/python/perftest/templates/_macros.j2 b/python/perftest/templates/_macros.j2
@@ -166,6 +166,8 @@ spec:
   queue: {{ settings.queue_name }}
   priorityClassName: {{ benchmark.status.priority_class_name }}
   policies:
+    - event: PodFailed
+      action: RestartJob
     - event: PodEvicted
       action: RestartJob
   {{ caller() | indent(2) }}