- 19 May, 2014 1 commit
-
-
Morris Jette authored
Add support for a job step's CPU governor and/or frequency to be reset on suspend/resume (or gang scheduling). The default for an idle CPU will now be "ondemand" rather than "userspace" with the lowest frequency (to recover from hard slurmd failures and support gang scheduling).
-
- 16 May, 2014 1 commit
-
-
Morris Jette authored
Add srun --cpu-freq options to set the CPU governor (OnDemand, Performance, Conservative, PowerSave or UserSpace). task/affinity: support set cpu_freq without cpuset (using hwloc and sched functions) Fix calculation used to set --cpu-freq=highm1 (relied upon ordering of possible CPU frequencies).
-
- 15 May, 2014 4 commits
-
-
Morris Jette authored
Add SelectTypeParameters option of CR_PACK_NODES to pack a job's tasks tightly on its allocated nodes rather than distributing them evenly across the allocated nodes. bug 819
-
Danny Auble authored
something you also get a signal which would produce deadlock. Fix Bug 601.
-
Morris Jette authored
If a job step reqeusts specific cores outside of their allocation with the --core-spec option, then bind the tasks to only those CPUs available to the job.
-
Morris Jette authored
task/cgroup - Correct specialized core task binding with user supplied invalid CPU mask or map. Rather than generating an error and ignoring user specification. Mask user supplied map against available CPUs or bind to all available CPUs. In either case, log the invalid CPU map or mask. bug 782
-
- 14 May, 2014 2 commits
-
-
Morris Jette authored
Run EpilogSlurmctld for a job is killed during slurmctld reconfiguration. bug 806
-
Morris Jette authored
Only if ALL of their partitions are hidden will a job be hidden by default. bug 812
-
- 13 May, 2014 4 commits
-
-
Morris Jette authored
Correct SelectTypeParameters=CR_LLN with job selecition of specific nodes. Previous logic would in most instances allocate resources on all nodes to the job.
-
Morris Jette authored
Correct squeue's job node and CPU counts for requeued jobs. Previously, when a job was requeued, its CPU count reported was that of the previous execution. When combined with the --ntasks-per-node option, squeue would compute the expected node count. If the --exclusive option is also used, the node count reported by squeue could be off by a large margin (e.g. "sbatch --exclusive --ntasks-per-node=1 -N1 .." on requeue would use the number of CPUs on the allocated node to recompute the expected node count). bug 756
-
Danny Auble authored
jobacct_gather/cgroup.
-
Morris Jette authored
Support SLURM_CONF path which does not have "slurm.conf" as the file name. bug 803
-
- 12 May, 2014 5 commits
-
-
Morris Jette authored
-
Morris Jette authored
If a job has non-responding node, retry job step create rather than returning with DOWN node error. bug 734
-
Morris Jette authored
-
Puenlap Lee authored
Also correct related documentation
-
Hongjia Cao authored
Completing nodes is removed when calling _try_sched() for a job, which is the case in select_nodes(). If _try_sched() thinks the job can run now but select_nodes() returns ESLURM_NODES_BUSY, the backfill loop will be ended.
-
- 09 May, 2014 3 commits
-
-
Danny Auble authored
-
Danny Auble authored
-
Morris Jette authored
Do not resume a job with specialized cores on a node running another job with specialized cores (only one can run at a time). bug 792
-
- 08 May, 2014 2 commits
-
-
Morris Jette authored
Fix sinfo -R to print each down/drained node once, rather than once per partition. This was broken in the sinfo change to process each partition's information in a separate pthread.
-
Morris Jette authored
Correct sinfo --sort fields to match documentation: E => Reason, H -> Reason Time (new), R -> Partition Name, u/U -> Reason user (new)
-
- 07 May, 2014 5 commits
-
-
Morris Jette authored
Without this patch, jobs with an infinite time limit would have their preemption GraceTime ignored.
-
Morris Jette authored
related to bug 789
-
Danny Auble authored
-
Danny Auble authored
them.
-
Morris Jette authored
Added ChosLoc configuration parameter in slurm.conf (Chroot OS tool location). bug 685
-
- 06 May, 2014 6 commits
-
-
Morris Jette authored
-
Danny Auble authored
-
Danny Auble authored
-
Morris Jette authored
-
Morris Jette authored
In slurm.spec file, replace "Requires cray-MySQL-devel-enterprise" with "Requires mysql-devel" per David Gloe.
-
Morris Jette authored
Permit jobs steps full control over cpu_bind options if specialized cores are included in the job allocation. bug 782
-
- 05 May, 2014 5 commits
-
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
Related to bug 771
-
Morris Jette authored
In version 14.03.2 was using "slurm_<jobid>_4294967294.out" due to error in job array logic.
-
Danny Auble authored
cnode counts.
-
- 02 May, 2014 2 commits
-
-
Danny Auble authored
-
Danny Auble authored
This is for bug 775
-