- 22 Jun, 2016 6 commits
-
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Dominik Bartkiewicz authored
-
Morris Jette authored
-
Morris Jette authored
Cray/capmc_resume script modify a node's features (as needed) when the reinit (reboot) command is issued rather than wait for the nodes to change to the "on" state. This will insure the correct node features in the event the capmc_resume script times out or otherwise fails before the nodes come back up. bug 2832
-
- 21 Jun, 2016 1 commit
-
-
Brian Christiansen authored
-t10 made the job's time limit 60 and not 6. -t1s are already being added by passed in limits.
-
- 20 Jun, 2016 5 commits
-
-
Danny Auble authored
-
Dominik Bartkiewicz authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
bug 2582
-
- 19 Jun, 2016 3 commits
-
-
Morris Jette authored
This is an addition to commit c5ace562
-
Morris Jette authored
-
Morris Jette authored
The slurm_get_auth_info() function returns an xmalloc'ed string which few places were xfree'ing. The function in the past did not xmalloc a value, but returned a pointer to a cached string. When that was changed, the calls to the function were not all changed, resulting in leaks if AuthInfo was defined in slurm.conf.
-
- 16 Jun, 2016 4 commits
-
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
- 15 Jun, 2016 11 commits
-
-
Danny Auble authored
-
Brian Christiansen authored
-
Danny Auble authored
-
Tim Wickberg authored
-
Tim Wickberg authored
Any access to this would be out of range. ASAN reports this as a two-word leak (due to allocaction[-2] and [-1] being used for xmalloc header info).
-
Tim Wickberg authored
ASAN detected an issue with the uninitialized one_liner variable, move all initialization to global variable definitions for simplicity.
-
Tim Wickberg authored
Found by ASAN.
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Tim Wickberg authored
Presumably you're okay handling timeouts when calling slurm_cond_timedwait otherwise you should have used slurm_cond_wait. Bug 2829.
-
Danny Auble authored
it.
-
- 14 Jun, 2016 9 commits
-
-
Danny Auble authored
deleted make it possible.
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Tim Wickberg authored
This reverts commit 7843e158. Conflicts: NEWS
-
Morris Jette authored
-
Morris Jette authored
Recalculate a job's memory allocation after node reboot if job requests all of a node's memory and FastSchedule=0 is configurated. Intel KNL memory size can change on reboot with various MCDRAM modes. bug 2822
-
Morris Jette authored
-
Alejandro Sanchez authored
Initially I wanted to record somehow the time a job has been in PD state until it actually starts. To do so, I derived an eligible_time field which was calculated as start_time - begin_time. This was not correct and a user of the plugin reported that if the job remained a lot of time in PD state the field underflowed. A more accurate approach would be calculating the field as start_time - eligible_time (the actual Slurm eligible_time). Since this field is not accessible within the log_record function which receives a job_record struct as parameter, I've decided to just remove this field from being logged.
-
Morris Jette authored
Recalculate a job's memory allocation after node reboot if job requests all of a node's memory and FastSchedule=0 is configurated. Intel KNL memory size can change on reboot with various MCDRAM modes. bug 2822
-
- 13 Jun, 2016 1 commit
-
-
Morris Jette authored
-