- 26 Mar, 2010 2 commits
-
-
Moe Jette authored
-
-
- 25 Mar, 2010 9 commits
-
-
Danny Auble authored
-
Moe Jette authored
"scontrol update JobId=# NumNodes=#" or "scontrol update JobId=# NodeList=<names>". Subsequent job steps must explicitly specify an appropriate node count to work properly.
-
Danny Auble authored
-
Moe Jette authored
-
-
Danny Auble authored
-
Moe Jette authored
daemon's nice value.
-
Danny Auble authored
-
-
- 24 Mar, 2010 5 commits
-
-
Danny Auble authored
-
Moe Jette authored
which gets group members
-
Moe Jette authored
See "man slurm.conf" for details about how these control when slurmctld updates its information of which users are in the groups allowed to use partitions.
-
-
Moe Jette authored
-
- 23 Mar, 2010 7 commits
-
-
Moe Jette authored
ESLURM_REQUESTED_NODE_CONFIG_UNAVAILABLE when slurmctld has restarted and nodes have not yet registered (in unknown state).
-
https://eris.llnl.gov/svn/slurm/branches/slurm-2.2.step.max.nodesMoe Jette authored
-- Add support for maximum node count in job step request. -- Fix bug in CPU count logic for job step allocation (used count of CPUS per node rather than CPUs allocated to the job).
-
-
Danny Auble authored
-
Danny Auble authored
updated documentation for the new purge options and made them backwards compatible with 0 meaning don't run
-
Danny Auble authored
-
Danny Auble authored
-
- 22 Mar, 2010 4 commits
-
-
Danny Auble authored
Applied patch from David Egolf (David.Egolf@Bull.com) Added the ability to purge/archive accounting data on a day or hour basis, previously it was only available on a monthly basis.
-
-
Moe Jette authored
-
Moe Jette authored
-
- 19 Mar, 2010 9 commits
-
-
Danny Auble authored
Altered srun to set max_nodes to min_nodes if not set when doing an allocation to mimic that which salloc and sbatch do. If running a step if the max isn't set it remains unset.
-
Moe Jette authored
-
-
Moe Jette authored
polling
-
Danny Auble authored
Fixed slurm_load_slurmd_status and slurm_pid2jobid to work correctly when multiple slurmds are in use.
-
Don Lipari authored
-
Moe Jette authored
to restrict spawned task nice values to that of the slurmd daemon plus 1. This insures that the slurmd daemon always have a higher scheduling priority than spawned tasks.
-
-
Moe Jette authored
set down based upon slurm.conf state.
-
- 18 Mar, 2010 4 commits