8406: Treat EXIT_TEMPFAIL as EXIT_RETRY_UNLOCKED if we have previously gotten

EXIT_RETRY_UNLOCKED (because the job is now in "Running" state.)

diff --git a/services/api/lib/crunch_dispatch.rb b/services/api/lib/crunch_dispatch.rb
index 05f85c7bb67f8c7863ed46fd793ad6a96fa2cf77..06a8a4b633b00353d4d96f099fcff97ef610bab6 100644 (file)
--- a/services/api/lib/crunch_dispatch.rb
+++ b/services/api/lib/crunch_dispatch.rb
@@ -637,7 +637,7 @@ class CrunchDispatch
 
     jobrecord = Job.find_by_uuid(job_done.uuid)
 
-    if exit_status == EXIT_RETRY_UNLOCKED
+    if exit_status == EXIT_RETRY_UNLOCKED or (exit_tempfail and @job_retry_counts[jobrecord.uuid])
       # The job failed because all of the nodes allocated to it
       # failed.  Only this crunch-dispatch process can retry the job:
       # it's already locked, and there's no way to put it back in the