- 10 Feb, 2019 16 commits
-
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
was recalculating if a new higher was larger than the previous but not if existing highest decreased.
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
associations, partitions, qos, tres Bug 6288
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
Bug 6286
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
gets out of sync easily when adding new sections.
-
Brian Christiansen authored
-
Brian Christiansen authored
Can be set by job_submit plugin to adjust a job's priority based on size of job. It can also be updated with: scontrol update jobid=<> adminpriofactor=# Bug 6287
-
- 09 Feb, 2019 1 commit
-
-
Morris Jette authored
Modify GrpNodes limit to apply to unique nodes allocated (avoid double counting nodes allocated to multiple jobs in the same QOS or association).
-
- 08 Feb, 2019 5 commits
-
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
Bug 6458
-
Brian Christiansen authored
Bug 6458
-
Kilian Cavalotti authored
Lustre client stats moved to /sys/kernel/debug/lustre/llite with 2.12. Bug 6385. Co-authored-by:
Tim Wickberg <tim@schedmd.com>
-
- 07 Feb, 2019 2 commits
-
-
Morris Jette authored
-
Morris Jette authored
Add scontrol requeue option of "Incomplete" which will requeue jobs only if they failed to complete with an exit code of zero. bug 6397
-
- 06 Feb, 2019 6 commits
-
-
Morris Jette authored
This is useful for job requeue. bug 5693
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Morris Jette authored
Estimate the total count of GRES of a job at submit time. This is used to reject jobs that will definitely exceed a GRES limit rather than queuing them and rejecting them when we finally determine their GRES count. bug 6410
-
Morris Jette authored
A block of code was repeated and does nothing but recompute a value
-
Morris Jette authored
-
- 05 Feb, 2019 5 commits
-
-
Tim Wickberg authored
Option rejects user requests to shrink running jobs. (Jobs using --no-kill may still shrink due to node failures.) Bug 5716.
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Tim Wickberg authored
Only call to it was removed in the prior commit, and all the interfaces returned "true" (even if they probably shouldn't have, such as select/cray).
-
Tim Wickberg authored
Add new SchedulerParameter of permit_job_expansion to permit expansion of running jobs. Replace the two calls to select_g_job_expand_allow() as all plugins return true anyways at this point. Return ESLURM_NOT_SUPPORTED instead of ESLURM_DEPENDENCY in one location as well to provide a better error message back to the user. Bug 5716.
-
- 04 Feb, 2019 5 commits
-
-
Brian Christiansen authored
thrown when compiling with CFLAGS="--converage"
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Albert Gil authored
Logs are produced by regression.py, and should not be checked in.
-