- 21 Jan, 2015 2 commits
-
-
Morris Jette authored
Conflicts: src/squeue/print.c
-
Morris Jette authored
Squeue modified to not merge tasks of a job array if their wait reasons differ. bug 1388
-
- 20 Jan, 2015 4 commits
-
-
David Bigagli authored
--export sbatch/srun command line option, propagate the users' environ to the execution side. #1367
-
Danny Auble authored
a Cray being that of a normal Linux system.
-
Danny Auble authored
-
Danny Auble authored
-
- 19 Jan, 2015 1 commit
-
-
jette authored
bug 1379
-
- 17 Jan, 2015 1 commit
-
-
jette authored
bug 1375
-
- 16 Jan, 2015 2 commits
-
-
Morris Jette authored
-
Taras Shapovalov authored
based upon email from Taras to slurm mailing list
-
- 15 Jan, 2015 6 commits
-
-
Danny Auble authored
-
Danny Auble authored
What this does is use the core level binding after each task is laid out to skip all the extra threads in the core so it doesn't give them to another task. It probably isn't perfect, but does solve all the scenarios I found.
-
Morris Jette authored
Fix for GRES scheduling in which there is CPU topology defined or GRES types defined and there is more than 1 GPU per topology record in slurmctld. Without this fix, only one GRES could be allocated from each defined topology. bug 1369
-
Morris Jette authored
The slurmctld could abort with a gres configuration having Type= configured, but no CPU binding configured.
-
Morris Jette authored
Revert a changed definition used only in the debugging work from commit ac9436bc
-
Brian Christiansen authored
-
- 14 Jan, 2015 3 commits
-
-
David Bigagli authored
-
Josko Plazonic authored
-
Danny Auble authored
-
- 13 Jan, 2015 3 commits
-
-
Danny Auble authored
Make sure correct locks are held when messing with the assoc_mgr cache.
-
Danny Auble authored
-
Danny Auble authored
Most of these don't matter as they are all NO_LOCK Fallout from commit f1ebdef1 when the resources were added.
-
- 09 Jan, 2015 6 commits
-
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
This is needed for setups like this TaskPlugin = affinity TaskPlugin = task/affinity,task/cgroup TaskPlugin = affinity,cgroup
-
- 08 Jan, 2015 1 commit
-
-
Brian Christiansen authored
-
- 07 Jan, 2015 7 commits
-
-
Danny Auble authored
-
Danny Auble authored
-
David Bigagli authored
Slurm 14.03 nccs
-
Aaron Knister authored
-
Rémi Palancher authored
Intel MPI, on MPI jobs initialisation through PMI, uses to call PMI_KVS_Put() many many times from task at rank 0, and each on these call is followed by PMI_KVS_Commit(). Slurm implementation of PMI_KVS_Commit() imposes a delay to avoid DDOS on original srun. This delay is proportional to the total number. It could be up to 3 secs for large jobs for ex. with 7168 tasks. Therefore, when Intel MPI calls PMI_KVS_Commit() 475 times (mesured on a test case) from task at rank 0, 28 minutes are spent in delay function. All other tasks in the job are waiting for a PMI_Barrier. Therefore, there is no risk for a DDOS from this single task 0. The patch alters the delaying time calculation to make sure task at rank 0 will does not be delayed. All other tasks are globally spreaded in the same time range as before.
-
Aaron Knister authored
-
Artem Polyakov authored
-
- 06 Jan, 2015 4 commits
-
-
David Bigagli authored
-
Morris Jette authored
Ammendment to commit 744f114b
-
Morris Jette authored
-
David Bigagli authored
-