- 25 Jan, 2018 10 commits
-
-
Felip Moll authored
Avoid memory leaks. Bug 4036
-
Felip Moll authored
Bug 4036
-
Felip Moll authored
Added support for printing configuration of cgroups and slurmctld plugstack plugins (nonstop at the moment) in 'scontrol show config' and 'sview'. Bug 4036
-
Morris Jette authored
-
Isaac Hartung authored
bug 3536
-
Morris Jette authored
-
Alejandro Sanchez authored
Bug 4674
-
Dominik Bartkiewicz authored
-
Morris Jette authored
Coverity CID 182262 and 182263
-
Danny Auble authored
Coverity 182357
-
- 24 Jan, 2018 19 commits
-
-
Danny Auble authored
-
Danny Auble authored
before the primary takes control. The primary will wait until the backup has replied with it all the way done shutting down before it takes over. Before it would just wait 2 seconds which probably was ok in most situations. Now we don't return until it is completely out. This also ups the CONTROL_TIMEOUT from 10 -> 30 seconds.
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
TRES positions. Bug 4665
-
Danny Auble authored
-
Morris Jette authored
-
Dominik Bartkiewicz authored
-
Dominik Bartkiewicz authored
Bug 4446
-
Dominik Bartkiewicz authored
-
Dominik Bartkiewicz authored
-
Danny Auble authored
introduced in commit ea85d123 Bug 4613
-
Morris Jette authored
Lost a "!" in the edit
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
CID 182336
-
Morris Jette authored
Coverity CID 182335
-
Morris Jette authored
Expand advanced reservation feature specification to support parenthesis and counts of nodes with specified features. Nodes with the feature currently active will be prefered. bug 4604
-
- 23 Jan, 2018 10 commits
-
-
Morris Jette authored
Coverity CID 182262, 182263, 182264
-
Morris Jette authored
Make sure that --batch option arguments are also found in job --constraint option. bug 4604
-
Isaac Hartung authored
-
Morris Jette authored
Much of the logic does work, but better to prevent users from trying this and failing in some way
-
Morris Jette authored
-
Morris Jette authored
-
Alejandro Sanchez authored
Reported by Jenkins after 17.11 merge 93e67a13.
-
Alejandro Sanchez authored
-
Alejandro Sanchez authored
Commit 818a09e8 introduced a new state JOB_OOM and a new state reason FAIL_OOM (OutOfMemory). The problem was that it based the decision upon the value of the different memory.[*].failcnt being > 0. That lead to "false positives" situations when the usage hit the limit but the Kernel was able to reclaim pages and the process managed to finish successfully. When this happens there might not necessary be OOM_KILL events happening. This patch makes it so the JOB_OOM state is set based upon OOM_KILL events detected instead of usage hitting the limit. The usage hit will still be logged as an info() message, and further work will be needed in the master branch to better discern both type of events, maybe changing the API and getting rid of the current SIG_OOM and a potential new SIG_OOM_KILL. OOM_KILL event is detected using the eventfd notification mechanism on the cgroup v1 control/event files: https://www.kernel.org/doc/Documentation/cgroup-v1/memory.txt If we plan to support cgroup v2, we should monitor 'memory.events' file modified events. That would mean that any of the available entries changed its value upon notification. Entries include: low, high, max, oom, oom_kill: https://www.kernel.org/doc/Documentation/cgroup-v2.txt https://patchwork.kernel.org/patch/9737381 but since this is a fairly recent change many sites might be running kernels still not supporting this feature. Bug 3820.
-
Brian Christiansen authored
-
- 22 Jan, 2018 1 commit
-
-
Danny Auble authored
-