scancel of pack job leader signals all pack job components

doc/html/heterogeneous_jobs.shtml

@@ -41,7 +41,7 @@ unique <i>job_id</i>.</li>
 <li><i>pack_job_id</i>: This identification number applies to all components
 of the heterogeneous job. All components of the same job will have the same
 <i>pack_job_id</i> value and it will be equal to the <i>job_id</i> of the
-first component.</li>
+first component. We refer to this as the "pack leader".</li>
 <li><i>pack_job_id_set</i>: Regular expression identifying all <i>job_id</i>
 values associated with the job.</li>
 <li><i>pack_job_offset</i>: A unique sequence number applied to each component
@@ -72,8 +72,8 @@ For example "123+4" would represent heterogeneous job id 123 and it's fifth
 component (note: the first component has a <i>pack_job_offset</i>value of 0).</p>
 
 <p>A request for a specific job ID that identifes a ID of the first component
-of a heterogenous job will return information about all pack job components.
-For example:</p>
+of a heterogenous job (i.e. the "pack leader" will return information about
+all components of that job. For example:</p>
 <pre>
 $ squeue --job=93
 JOBID PARTITION  NAME  USER ST  TIME  NODES NODELIST
@@ -82,6 +82,25 @@ JOBID PARTITION  NAME  USER ST  TIME  NODES NODELIST
  93+2     debug  bash  adam  R 18:18      1 nid00021
 </pre>
 
+<p>A request to cancel or otherwise signal a pack leader will be applied to
+all components of that pack job. A request to cancel a specific component of
+the pack job using the "#+#" notation will apply on to that specific component.
+For example:</p>
+<pre>
+$ squeue --job=93
+JOBID PARTITION  NAME  USER ST  TIME  NODES NODELIST
+ 93+0     debug  bash  adam  R 19:18      1 nid00001
+ 93+1     debug  bash  adam  R 19:18      1 nid00011
+ 93+2     debug  bash  adam  R 19:18      1 nid00021
+$ scancel 93+1
+$ squeue --job=93
+JOBID PARTITION  NAME  USER ST  TIME  NODES NODELIST
+ 93+0     debug  bash  adam  R 19:38      1 nid00001
+ 93+2     debug  bash  adam  R 19:38      1 nid00021
+$ squeue --job=93
+JOBID PARTITION  NAME  USER ST  TIME  NODES NODELIST
+</pre>
+
 <h2><a name="limitations">Limitations</a></h2>
 
 <p>In a federation of clusters, a heterogeneous job will execute entirely on

src/slurmctld/job_mgr.c

@@ -4785,6 +4785,24 @@ extern int job_signal(uint32_t job_id, uint16_t signal, uint16_t flags,
 	return _job_signal(job_ptr, signal, flags, uid, preempt);
 }
+/* Signal all components of a pack job */
+static int _pack_job_signal(struct job_record *job_ptr, uint16_t signal,
+			    uint16_t flags, uid_t uid, bool preempt)
+{
+	ListIterator iter;
+	int rc = SLURM_SUCCESS, rc1;
+	struct job_record *pack_job_ptr;
+
+	iter = list_iterator_create(job_ptr->pack_job_list);
+	while ((pack_job_ptr = (struct job_record *) list_next(iter))) {
+		rc1 = _job_signal(pack_job_ptr, signal, flags, uid, preempt);
+		rc = MAX(rc, rc1);
+	}
+	list_iterator_destroy(iter);
+
+	return rc;
+}
+
 /*
  * job_str_signal - signal the specified job
  * IN job_id_str - id of the job to be signaled, valid formats include "#"
@@ -4830,6 +4848,10 @@ extern int job_str_signal(char *job_id_str, uint16_t signal, uint16_t flags,
 		int jobs_done = 0, jobs_signalled = 0;
 		struct job_record *job_ptr_done = NULL;
 		job_ptr = find_job_record(job_id);
+		if (job_ptr && job_ptr->pack_job_list) {
+			return _pack_job_signal(job_ptr, signal, flags, uid,
+						preempt);
+		}
 		if (job_ptr && (job_ptr->array_task_id == NO_VAL) &&
 		    (job_ptr->array_recs == NULL)) {
 			/* This is a regular job, not a job array */