- 29 May, 2013 1 commit
-
-
jette authored
The most notable problem case is on a cray where a job step specifically requests one or more node that are not the first nodes in the job allocation
-
- 23 May, 2013 8 commits
-
-
Morris Jette authored
The problem we have observed is the backfill scheduler temporarily gives up its locks (one second), but then reclaims them before the backlog of work completes, basically keeping the backfill scheduler running for a really long time when under a heavy load. bug 297
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
Fix minor bug in sdiag backfill scheduling time reported on Bluegene systems Improve explanation of backfill scheduling cycle time calculation.
-
Morris Jette authored
Defers (rather than forgets) reboot request with job running on the node within a reservation.
-
Danny Auble authored
-
Danny Auble authored
-
- 22 May, 2013 5 commits
-
-
Danny Auble authored
-
Danny Auble authored
-
Morris Jette authored
-
jette authored
-
jette authored
-
- 21 May, 2013 1 commit
-
-
Morris Jette authored
-
- 18 May, 2013 2 commits
-
-
Danny Auble authored
all preemptable jobs on the midplane instead of just the ones it needed to.
-
Danny Auble authored
-
- 16 May, 2013 2 commits
-
-
Morris Jette authored
This bug was introduced in commit f1cf6d2d fix for bug 290
-
Danny Auble authored
-
- 14 May, 2013 2 commits
-
-
Morris Jette authored
-
Morris Jette authored
-
- 13 May, 2013 2 commits
-
-
Morris Jette authored
-
Morris Jette authored
Downing the node will kill all jobs allocated to the node, very bad on something like a BlueGene system
-
- 11 May, 2013 1 commit
-
-
David Bigagli authored
-
- 10 May, 2013 1 commit
-
-
Hongjia Cao authored
fix of the following problem: if a node is excised from a job and a reconfiguration(e.g., update partition) is done when the job is still running, the node will be left in state idle but not available any more until the next reconfiguration/restart of slurmctld after the job finished.
-
- 08 May, 2013 3 commits
-
-
David Bigagli authored
-
David Bigagli authored
-
Danny Auble authored
the node tab and we didn't notice.
-
- 07 May, 2013 1 commit
-
-
David Bigagli authored
-
- 04 May, 2013 1 commit
-
-
Morris Jette authored
Response to bug 274
-
- 03 May, 2013 1 commit
-
-
jette authored
Make test work if current working directory not in the search path Check for appropriate task rank on POE based systems Disable the entire test on POE systems
-
- 02 May, 2013 4 commits
-
-
jette authored
Without this change pmdv12 was bound to one CPU and could not use all of the resources allocated to the job step for the tasks that it launches
-
jette authored
This only changes behaviour when the --ntasks option is not used, but the --cpus-per-task option is use
-
jette authored
-
Danny Auble authored
-
- 01 May, 2013 5 commits
-
-
Danny Auble authored
we used cpus erroneously but now we use tasks. The cpus variable will be taken out in 2.6.
-
Morris Jette authored
-
Danny Auble authored
-
Danny Auble authored
-
Morris Jette authored
-