- 02 Aug, 2016 1 commit
-
-
Sergey Meirovich authored
If slurmstepd had been swapped out before upgrade happened it could easily lead to SIGBUS at any time after upgrade. Prevent that by mlocking it. bug 2334
-
- 29 Jul, 2016 5 commits
-
-
Moe Jette authored
SLURM_JOB_RESERVAION environment variables are set for the salloc command. Document the same environment variables for the salloc, sbatch and srun commands in their man pages.
-
Danny Auble authored
Also we are making extern lower case in the api to match this and sacct.
-
Danny Auble authored
-
Janne Blomqvist authored
Bugs 2681 and 2703
-
Danny Auble authored
that had a partition in them.
-
- 28 Jul, 2016 3 commits
-
-
Morris Jette authored
Add support for setting the SLURM_JOB_ACCOUNT, SLURM_JOB_QOS and SLURM_JOB_RESERVAION environment variables are set for the srun command. Document the same environment variables for the salloc, sbatch and srun commands in their man pages. bug 2945
-
Morris Jette authored
Document that the SLURM_JOB_ACCOUNT and SLURM_JOB_QOS environment variables are set for the srun command in its man page. bug 2945
-
Morris Jette authored
Document that the SLURM_JOB_ACCOUNT and SLURM_JOB_QOS environment variables are set for the salloc and sbatch commands in their man pages. bug 2945
-
- 27 Jul, 2016 6 commits
-
-
Morris Jette authored
Document that persistent burst buffers can not be created or destroyed using the salloc or srun --bb options. bug 2404
-
Brian Christiansen authored
Missed in b5bba34c
-
Morris Jette authored
Add new RPC (REQUEST_EVENT_LOG) so that slurmd and slurmstepd can log events through the slurmctld daemon. bug 1828
-
Danny Auble authored
on batch script completes.
-
Danny Auble authored
-
Morris Jette authored
-
- 26 Jul, 2016 5 commits
-
-
Morris Jette authored
-
Brian Christiansen authored
-
Brian Christiansen authored
New jobs will get job IDs within the new range. Even though the pre-existing large jobid-jobs will have federated jobids, they will be treated as local jobs.
-
Brian Christiansen authored
Bits: 0-26: Local Job ID Bits: 26-31: Cluster ID Default MaxJobId changed from 2,147,418,112 to 67,043,328.
-
Danny Auble authored
(difference between start of job and when it was eligible).
-
- 25 Jul, 2016 2 commits
-
-
David Gloe authored
Bug 2939.
-
Danny Auble authored
-
- 23 Jul, 2016 1 commit
-
-
Morris Jette authored
-
- 22 Jul, 2016 5 commits
-
-
Alejandro Sanchez authored
Bug 2894.
-
Dominik Bartkiewicz authored
Inadvertently broken in commit 05eac196. Bug 2912.
-
Danny Auble authored
or failed based on the signal that would always be killing it.
-
Danny Auble authored
end of the job to do it.
-
Danny Auble authored
make them using the master job ID instead of the normal job ID.
-
- 21 Jul, 2016 4 commits
-
-
Tim Wickberg authored
Logically equivalent, but fewer characters and easier to read. Appears to have a slight performance advantage in testing. MySQL has no limit on the number of elements in a () clause. Bug 2875.
-
Morris Jette authored
Add new sacctmgr commands: "shutdown" (shutdown the server), "list stats" (get server statistics) "clear stats" (clear server statistics). bugs 2077 and 2080
-
Morris Jette authored
Add SLURM_ARRAY_TASK_COUNT environment variable. Total number of tasks in a job array (e.g. "--array=2,4,8" will set SLURM_ARRAY_TASK_COUNT=3). bug 2150
-
Morris Jette authored
Treat invalid user ID in AllowUserBoot option of knl.conf file as error rather than fatal (log and do not exit).
-
- 20 Jul, 2016 3 commits
-
-
Morris Jette authored
Prevent slurmctld abort if job is killed or requeued while waiting for reboot of its allocated compute nodes. The _wait_boot() would reference job_ptr->node_bitmap, which would be NULL.
-
Boris Karasev authored
Bug 2908
-
Tim Wickberg authored
Step hasn't been assigned resources, so the select_jobinfo struct hasn't yet been populated. Calling select_g_step_finish will dereference causing a segfault. Bug 2922.
-
- 19 Jul, 2016 5 commits
-
-
Morris Jette authored
-
Brian Christiansen authored
-
Brian Christiansen authored
Happens when there are running jobs on the cluster.
-
Brian Christiansen authored
-
Morris Jette authored
If the user is now allowed to use the partition, then do not check that user's group access again for 5 seconds. bug 2913
-