Fix to aftercorr job array dependency logic

Fix job array dependency with "aftercorr" option and some task arrays in the first job fail. This fix lets all task array elements that can run proceed rather than stopping all subsequent task array elements. Bug 4590
SchedMD · Jan 12, 2018 · 7b5a367 · 7b5a367
1 parent deaacad
commit 7b5a367
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 1 deletion.
diff --git a/NEWS b/NEWS
@@ -26,6 +26,9 @@ documents those changes that are of interest to users and administrators.
     reconfigured.
  -- node_feature/knl_cray - Fix memory leak that can occur during normal
     operation.
+ -- Fix job array dependency with "aftercorr" option and some task arrays in
+    the first job fail. This fix lets all task array elements that can run
+    proceed rather than stopping all subsequent task array elements.
 
 * Changes in Slurm 17.02.9
 ==========================

diff --git a/src/slurmctld/job_scheduler.c b/src/slurmctld/job_scheduler.c
@@ -2716,7 +2716,11 @@ extern int test_job_dependency(struct job_record *job_ptr)
 						depends = true;
 					else if (array_complete)
 						clear_dep = true;
-					else {
+					else if (job_ptr->array_recs &&
+						 (job_ptr->array_task_id ==
+						  NO_VAL)) {
+						depends = true;
+					} else {
 						failure = true;
 						break;
 					}