- 15 Jan, 2012 1 commit
-
-
jette authored
-
- 14 Jan, 2012 1 commit
-
-
Danny Auble authored
-
- 13 Jan, 2012 3 commits
-
-
Danny Auble authored
number.
-
Morris Jette authored
-
Morris Jette authored
Let operators see reservation data even if "PrivateData=reservations" flag is set in slurm.conf. Patch from Don Albert, Bull.
-
- 09 Jan, 2012 2 commits
-
-
Morris Jette authored
Fix bug in srun --multi-prog configuration file to avoid printing duplicate record error when "*" is used at the end of the file for the task ID. It means all task IDs not otherwise identified.
-
Morris Jette authored
Fix race condition where sbcast command can result in deadlock of slurmd daemon. Patch by Don Albert, Bull.
-
- 04 Jan, 2012 1 commit
-
-
jette authored
Made squeue -n and -w options more consistent with salloc, sbatch, srun, and scancel. Patch by Don Lipari, LLNL.
-
- 28 Dec, 2011 2 commits
-
-
Danny Auble authored
so you can specify any connection type you would like (TORUS or MESH) as the default in dynamic mode. Previously it always defaulted to TORUS.
-
Morris Jette authored
-
- 27 Dec, 2011 1 commit
-
-
jette authored
Add new command, sdiag, which reports a variety of job scheduling statistics. Based upon work by Alejandro Lucero Palau, BSC.
-
- 21 Dec, 2011 1 commit
-
-
Morris Jette authored
-
- 19 Dec, 2011 2 commits
-
-
Morris Jette authored
-
Morris Jette authored
Behavior of srun --multi-prog modified so that any program arguments specified on the command line will be appended to the program arguments specified in the program configuration file.
-
- 17 Dec, 2011 1 commit
-
-
Morris Jette authored
-
- 16 Dec, 2011 1 commit
-
-
Danny Auble authored
source dir.
-
- 15 Dec, 2011 1 commit
-
-
Morris Jette authored
Prevent resetting a held job's priority when updating other job parameters. Patch from Alejandro Lucero Palau, BSC.
-
- 14 Dec, 2011 2 commits
-
-
Morris Jette authored
Patch from John Thiltges, University of Nebraska-Lincoln.
-
Danny Auble authored
-
- 13 Dec, 2011 1 commit
-
-
Danny Auble authored
-
- 09 Dec, 2011 8 commits
-
-
Danny Auble authored
-
Danny Auble authored
starts in accounting.
-
Danny Auble authored
-
Morris Jette authored
Add an srun shepard process to cancel a job and/or step of the srun process is killed abnormally (e.g. SIGKILL).
-
Danny Auble authored
-
Danny Auble authored
starts in accounting.
-
Danny Auble authored
-
Morris Jette authored
-
- 08 Dec, 2011 2 commits
-
-
Danny Auble authored
-
Danny Auble authored
-
- 06 Dec, 2011 3 commits
-
-
Morris Jette authored
One of our testers discovered a regression in version 2.3.1. If a job is pending due to PartitionNodeLimit and the limit is relieved with a 'sacctmgr modify qos name=<qos name> set flags=partitionmaxnodes' new jobs exceeding the partition limit (but not the QOS limit) are allowed to run. However, the pending job is never allowed to run. Attached is a patch to address this problem. FYI, this problem doesn't exist in version 2.4. Patch from Bill Brophy, Bull.
-
Morris Jette authored
-
Morris Jette authored
Let a job be submitted even if it exceeds a QOS limit. Job will be left in a pending state until the QOS limit or job parameters change. Patch by Phil Eckert, LLNL.
-
- 05 Dec, 2011 2 commits
-
-
Morris Jette authored
Patch by Alexander Bersenev (Institute of Mathematics and Mechanics, Russia).
-
Morris Jette authored
-
- 02 Dec, 2011 1 commit
-
-
Danny Auble authored
There was also some bad code that would reset the conn_type of a block to SMALL no matter what type of SMALL it was.
-
- 01 Dec, 2011 1 commit
-
-
jette authored
This was due to a bug in select/cons_res with some configuration optiions and job options, especially if there is more than one thread per core and the job option includes "--threads-per-core=1". Fixes problem reported by CSCS.
-
- 30 Nov, 2011 3 commits
-
-
Morris Jette authored
-
Danny Auble authored
qos on the cluster to fill that in correctly.
-
Danny Auble authored
incorrectly when getting fairshare from the parent.
-