diff --git a/NEWS b/NEWS
index be529ef12959e69cbd186445c0d4ae7763e3c6a6..19e8a866bf1c2eb0d4880ff14f871abea4dccf5a 100644
--- a/NEWS
+++ b/NEWS
@@ -59,6 +59,11 @@ documents those changes that are of interest to users and admins.
-- Fix for accounting where your cluster isn't numbered in counting order
(i.e. 1-9,0 instead of 0-9). The bug would cause 'sacct -N nodename' to
not give correct results on these systems.
+ -- Fix to GRES allocation logic when resources are associated with specific
+ CPUs on a node. Patch from Steve Trofinoff, CSCS.
+ -- Fix bugs in sched/backfill with respect to QOS reservation support and job
+ time limits. Patch from Alejandro Lucero Palau (Barcelona Supercomputer
+ Center).
* Changes in SLURM 2.3.0-2
==========================
diff --git a/doc/man/man1/sacctmgr.1 b/doc/man/man1/sacctmgr.1
index 9fe7558b4bd21732b3db014266a4d3ac5215954c..17cd414e236976c739bcc623d5ba938475223f25 100644
--- a/doc/man/man1/sacctmgr.1
+++ b/doc/man/man1/sacctmgr.1
@@ -914,12 +914,12 @@ any jobs submitted with this QOS that fall below the UsageThreshold
will be held until their Fairshare Usage goes above the Threshold.
.TP
\fINoReserve\fP
-If set, and using backfill, jobs using this QOS will all be considered
-at the same level within this QOS meaning if a larger, higher priority
-job is unable to run a smaller job will run if possible even if the
-larger higher priority job will be delayed starting.
-NOTE: This could cause starvation on these larger jobs, but if that is
-ok, this flag most likely will increase utilization.
+If this flag is set and backfill scheduling is used, jobs using this QOS will
+not reserve resources in the backfill schedule's map of resources allocated
+through time. This flag is intended for use with a QOS that may be preempted
+by jobs associated with all other QOS (e.g use with a "standby" QOS). If the
+allocated is used with a QOS which can not be preempted by all other QOS, it
+could result in starvation of larger jobs.
.TP
\fIPartitionMaxNodes\fP
If set jobs using this QOS will be able to
diff --git a/src/common/gres.c b/src/common/gres.c
index d48e3e2b8ccca9661713657c7bcbeec247d37065..7debdd3581d49952837d93a6a494d9eb5ea471e8 100644
--- a/src/common/gres.c
+++ b/src/common/gres.c
@@ -2653,7 +2653,12 @@ extern uint32_t gres_plugin_job_test(List job_gres_list, List node_gres_list,
cpu_start_bit, cpu_end_bit,
&topo_set, job_id, node_name,
gres_context[i].gres_name);
- cpu_cnt = MIN(tmp_cnt, cpu_cnt);
+ if (tmp_cnt != NO_VAL) {
+ if (cpu_cnt == NO_VAL)
+ cpu_cnt = tmp_cnt;
+ else
+ cpu_cnt = MIN(tmp_cnt, cpu_cnt);
+ }
break;
}
if (cpu_cnt == 0)
@@ -4062,7 +4067,12 @@ extern uint32_t gres_plugin_step_test(List step_gres_list, List job_gres_list,
node_offset, ignore_alloc,
gres_context[i].gres_name,
job_id, step_id);
- cpu_cnt = MIN(tmp_cnt, cpu_cnt);
+ if (tmp_cnt != NO_VAL) {
+ if (cpu_cnt == NO_VAL)
+ cpu_cnt = tmp_cnt;
+ else
+ cpu_cnt = MIN(tmp_cnt, cpu_cnt);
+ }
break;
}
if (cpu_cnt == 0)
diff --git a/src/plugins/sched/backfill/backfill.c b/src/plugins/sched/backfill/backfill.c
index f1471eec6da4b8973a627c8b449971916fdfe436..efb17bc6bb6b2971e56cf65f4b5db75a8df0a263 100644
--- a/src/plugins/sched/backfill/backfill.c
+++ b/src/plugins/sched/backfill/backfill.c
@@ -567,6 +567,7 @@ static int _attempt_backfill(void)
}
comp_time_limit = time_limit;
orig_time_limit = job_ptr->time_limit;
+ qos_ptr = job_ptr->qos_ptr;
if (qos_ptr && (qos_ptr->flags & QOS_FLAG_NO_RESERVE))
time_limit = job_ptr->time_limit = 1;
else if (job_ptr->time_min && (job_ptr->time_min < time_limit))
@@ -634,15 +635,17 @@ static int _attempt_backfill(void)
bit_not(resv_bitmap);
if ((time(NULL) - sched_start) >= this_sched_timeout) {
+ uint32_t save_time_limit = job_ptr->time_limit;
+ job_ptr->time_limit = orig_time_limit;
debug("backfill: loop taking too long, yielding locks");
if (_yield_locks()) {
debug("backfill: system state changed, "
"breaking out");
rc = 1;
break;
- } else {
- this_sched_timeout += sched_timeout;
}
+ job_ptr->time_limit = save_time_limit;
+ this_sched_timeout += sched_timeout;
}
/* this is the time consuming operation */
debug2("backfill: entering _try_sched for job %u.",
@@ -664,8 +667,11 @@ static int _attempt_backfill(void)
}
if (job_ptr->start_time <= now) {
int rc = _start_job(job_ptr, resv_bitmap);
- if (qos_ptr && (qos_ptr->flags & QOS_FLAG_NO_RESERVE))
+ if (qos_ptr && (qos_ptr->flags & QOS_FLAG_NO_RESERVE)){
job_ptr->time_limit = orig_time_limit;
+ job_ptr->end_time = job_ptr->start_time +
+ (orig_time_limit * 60);
+ }
else if ((rc == SLURM_SUCCESS) && job_ptr->time_min) {
/* Set time limit as high as possible */
job_ptr->time_limit = comp_time_limit;
@@ -724,7 +730,6 @@ static int _attempt_backfill(void)
/*
* Add reservation to scheduling table if appropriate
*/
- qos_ptr = job_ptr->qos_ptr;
if (qos_ptr && (qos_ptr->flags & QOS_FLAG_NO_RESERVE))
continue;
bit_not(avail_bitmap);