- 05 Jul, 2017 3 commits
-
-
Morris Jette authored
-
Morris Jette authored
$ srun --pack-group=1,2 -l tmp 0: JOBID:43740 HOST:nid00002 0: JOBID:43741 HOST:nid00003 1: JOBID:43741 HOST:nid00003 1: JOBID:43740 HOST:nid00002 2: JOBID:43740 HOST:nid00002 2: JOBID:43741 HOST:nid00003 3: JOBID:43741 HOST:nid00003 srun: error: Task 0 reported exit for a second time. srun: error: Task 1 reported exit for a second time. srun: error: Task 2 reported exit for a second time.
-
Morris Jette authored
srun now parsing for the "-pack-group" option first, then processes the environment variables for that pack group, then processes the remaining options for the pack group. srun will still only spawn tasks for one pack group at a time, but will at least handled forwarded options from the job allocation phase (i.e. sbatch or salloc).
-
- 03 Jul, 2017 1 commit
-
-
Morris Jette authored
-
- 29 Jun, 2017 2 commits
-
-
Morris Jette authored
-
Morris Jette authored
Change (almost) all references to use pointer to structure for pack-job support with multiple components
-
- 28 Jun, 2017 2 commits
-
-
Morris Jette authored
Previous logic could fail on step allocation in larger job allocation
-
Morris Jette authored
-
- 27 Jun, 2017 3 commits
-
-
Morris Jette authored
Underlying logic not yet available, just the new option parsing and documentation.
-
Morris Jette authored
-
Isaac Hartung authored
-
- 26 Jun, 2017 6 commits
-
-
Morris Jette authored
-
Isaac Hartung authored
-
Isaac Hartung authored
Make packjobid, packjoboffset, and packjobidset fields available in squeue output.
-
Isaac Hartung authored
Test salloc/sbatch job options passed and resulting environment variables.
-
Morris Jette authored
-
Dominik Bartkiewicz authored
Improve backfill scheduling algorithm with respect to starting jobs as soon as possible while avoiding advanced reservations. bug 3757
-
- 24 Jun, 2017 4 commits
-
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
- 23 Jun, 2017 7 commits
-
-
Morris Jette authored
bug 3886
-
Morris Jette authored
-
Tim Shaw authored
Not necessarily fatal(), but of potential interest when debugging odd slurmctld crashes. Cannot go where the limit is originally set, as the logging infrastructure is not avaiable at that point. Bug 3886.
-
Morris Jette authored
test1.91 fails with non-default binding
-
Tim Wickberg authored
-
Tim Shaw authored
Bug 3581.
-
Morris Jette authored
Fix for commit 250378c2 test7.3 was failing without this patch bug 3502
-
- 22 Jun, 2017 12 commits
-
-
Morris Jette authored
-
Morris Jette authored
test 17.12 was leaving slurm-#.out files around. Explicitly set output file to /dev/null and set time limit to 1 minute to avoid vestigial jobs.
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
Handle syncing between siblings (not the origin). Job could have been canclled or started while the origin was down. The sibling should see this and remove it's copy if the job is running or cancelled on the remote cluster. Handle case where job was cancelled or finished while the origin was down and the siblings were up.
-
Brian Christiansen authored
The controller will keeps job in the job_list until the origin comes back up and will find out about it then.
-
Brian Christiansen authored
This allows the origin to be able to sync up jobs after it has been down.
-