- 09 Feb, 2015 9 commits
-
-
Morris Jette authored
-
Morris Jette authored
Fix slurmctld initialization problem which could cause requeue of the last task in a job array to fail if executed prior to the slurmctld loading the maximum size of a job array into a variable in the job_mgr.c module.
-
Morris Jette authored
Fix slurmctld job recovery logic which could cause the last task in a job array to be lost on restart.
-
Morris Jette authored
-
Brian Christiansen authored
Only supported with task/affinity plugin.
-
Pär Lindfors authored
When CgroupMountpoint was not defined in cgroup.conf the mount point got undefined. This resulted in cgroups not being released.
-
Morris Jette authored
-
Nicolas Joly authored
-
Morris Jette authored
In order to support inter-cluster job dependencies, the MaxJobID configuration parameter default value has been reduced from 4,294,901,760 to 2,147,418,112 and it's maximum value is now 2,147,463,647. ANY JOBS WITH A JOB ID ABOVE 2,147,463,647 WILL BE PURGED WHEN SLURM IS UPGRADED FROM AN OLDER VERSION!
-
- 08 Feb, 2015 1 commit
-
-
Danny Auble authored
-
- 07 Feb, 2015 1 commit
-
-
Morris Jette authored
Add PowerParameter and user options to level power cap for all jobs associated with a parallel job. Per-job option can be disabled on a global basis or job power leveling can be forced for all jobs.
-
- 06 Feb, 2015 6 commits
-
-
Morris Jette authored
Add the sicp_mode and power_flags to the slurmctld job record. Save and restore the new fields. Pack them in the job_info structure and view them using "scontrol show job"
-
Morris Jette authored
-- Add job submission command options: --sicp (available for inter-cluster dependencies) and --power (specify power management options) to salloc, sbatch, and srun commands. -- Add DebugFlags option of SICP (inter-cluster option logging). -- Added DebugFlags value "SICP". -- Added job_descriptor field of "cluster".
-
David Bigagli authored
-
David Bigagli authored
-
Magnus Jonsson authored
footprint of a job. Add an option not to kill jobs that is over memory limit.
-
Brian Christiansen authored
Use %__make in slum.spec
-
- 05 Feb, 2015 7 commits
-
-
Morris Jette authored
Fix a couple of dead assignments and uninitialized variable issues reported by CLANG
-
David Bigagli authored
event REQUEUED to slurmdbd.
-
Morris Jette authored
Related to bug 1429
-
Brian Christiansen authored
Improve "Prolog and Epilog Scripts" in slurm.conf(5)
-
Pär Lindfors authored
-
Pär Lindfors authored
The environment variable name SLURM_JOB_CLUSTER_NAME should be SLURM_CLUSTER_NAME. This is also available in Prolog and Epilog, so remove note about it only being available in PrologSlurmctld and EpilogSlurmctld.
-
J.T. Conklin authored
-
- 04 Feb, 2015 9 commits
-
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
Previously it was not possible to distinguish between a job needing exclusive nodes and the default job/partition configuration.
-
Morris Jette authored
-
David Bigagli authored
-
Brian Christiansen authored
Fix hv_to_job_cond in slurmdb perl api to accept "step_list" as a string of comma separated job/step ids.
-
Morris Jette authored
Fix job array logic that can cause slurmctld to abort. bug 1426
-
Morris Jette authored
Conflicts: src/common/Makefile.am src/common/Makefile.in src/plugins/proctrack/cgroup/proctrack_cgroup.c
-
Morris Jette authored
Enable CUDA v7.0+ use with a Slurm configuration of TaskPlugin=task/cgroup ConstrainDevices=yes (in cgroup.conf). With that configuration CUDA_VISIBLE_DEVICES will start at 0 rather than the device number. bug 1421
-
- 03 Feb, 2015 7 commits
-
-
Morris Jette authored
Move the functions that read cgroup.conf from src/slurmd/common to slurmd/common so that the gres/gpu plugin can use it.
-
Brian Christiansen authored
-
Brian Christiansen authored
-
David Bigagli authored
-
David Bigagli authored
debug2 instead of info.
-
David Bigagli authored
SLURM_JOB_PARTITION to be the one in which the job started.
-
Danny Auble authored
-