- 11 Apr, 2014 18 commits
-
-
Morris Jette authored
-
Morris Jette authored
controls how frequently the main scheduling loop will execute.
-
Morris Jette authored
limits how long the main scheduling loop can execute for
-
David Bigagli authored
This reverts commit e2018b65. Conflicts: NEWS
-
Morris Jette authored
-
Marcin Stolarek authored
Display nodes to be used in the scheduling of a pending job.
-
Danny Auble authored
This reverts commit ebb3ec3c.
-
David Bigagli authored
This reverts commit e2018b65. Conflicts: NEWS
-
Martins Innus authored
-
Danny Auble authored
-
Morris Jette authored
-
Morris Jette authored
-
Franco Broi authored
-
David Bigagli authored
-
Steve Huston authored
-
Morris Jette authored
Add support for allocation of GRES by model type for heterogenous systems (e.g. request a Kepler GPU, a Tesla GPU, or a GPU of any type).
-
Morris Jette authored
-
David Bigagli authored
-
- 10 Apr, 2014 15 commits
-
-
David Bigagli authored
not been processed by the scheduler yet.
-
Morris Jette authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Morris Jette authored
No change in logic
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
Modify srun to report an exit code of zero rather than nine if some tasks exit with a return code of zero and others are killed with SIGKILL. Only an exit code of zero did this.
-
Morris Jette authored
The fprintf(stderr will generally fail as stderr will usually be closed.
-
Morris Jette authored
-
Morris Jette authored
Cache job information and drop out of loop after finding the desired array task. This improves performance a fair bit. bug 684
-
Morris Jette authored
Rather than attempting a scheduling loop as frequently as every 1 second, wait 3 seconds for performance reasons.
-
- 09 Apr, 2014 7 commits
-
-
David Bigagli authored
-
Josko Plazonic authored
set it in the job env otherwise the exec() fails.
-
Morris Jette authored
-
Morris Jette authored
Rather than immediately invoking an execution of the scheduling logic on every event type that can enable the execution of a new job, queue its execution. This permits faster execution of some operations, such as modifying large counts of jobs, by executing the scheduling logic less frequently, but still in a timely fashion.
-
Danny Auble authored
If you have multiple partitions the output from sinfo -o "%D %F" would have unexpected results, hardly ever correct.
-
Morris Jette authored
-
Morris Jette authored
-