- 16 Jun, 2017 5 commits
-
-
Alejandro Sanchez authored
Bug 3526
-
Alejandro Sanchez authored
Bug 3526
-
Morris Jette authored
There was a bug in the heterogeneous job work (fixed now) that resulted in a bunch of jobs without time limits from being killed. This patch prevents those jobs from running indefinitely.
-
Tim Shaw authored
Bug 3502.
-
Tim Shaw authored
files on startup. The new default behavior is to 'fatal' if state files are bad. This flag is to avoid that fatal if you expect things to be bad. This commit just adds the flag but doesn't do anything more than that.
-
- 15 Jun, 2017 2 commits
-
-
Morris Jette authored
-
Dominik Bartkiewicz authored
bug 3447
-
- 14 Jun, 2017 3 commits
-
-
Danny Auble authored
Turns out if the extern step is created here and the job was killed long before hand the step is made erroneously and can cause an assert just lines later. Bug 3898
-
Danny Auble authored
specify an alternative --ntasks-per-*
-
Tim Shaw authored
set correctly. Bug 3858
-
- 13 Jun, 2017 9 commits
-
-
Danny Auble authored
on HTC systems finishing many jobs at the same time. See bug 3725
-
Tim Wickberg authored
-
Tim Wickberg authored
Changes the alpsc_configure_nic() call to set the exclusive flag, and 100 for both the cpu and memory scaling values. Should only be used with exclusive jobs without concurrent steps running on a node, otherwise oversubscription of the GNI resources can occur leading to performance issues. Bug 3713.
-
Danny Auble authored
the slurm.conf file.
-
Danny Auble authored
-
Danny Auble authored
What this does is populate the node_hash_table as nodes are being read in instead of after the node_record_table_ptr has been fully populated. This speeds up a start of a slurmd with a system of 10000 nodes from > 1 minute to less than a second. In 17.11 we will remove the linear xstrcmp check as it should no longer be needed. Bug 3885
-
Danny Auble authored
code change. Bug 3885
-
Danny Auble authored
Bug 3888
-
Danny Auble authored
of a hard coded value. This probably needs to be something higher to accommodate potential systems with with oversubscribe given. See bug 3833
-
- 12 Jun, 2017 11 commits
-
-
Morris Jette authored
-
bamb0u authored
-
Danny Auble authored
-
Danny Auble authored
batch job takes longer than it takes to finish. Bug 3833
-
Danny Auble authored
time. Bug 3833
-
Tim Wickberg authored
srun just added it as well. Bug 3880.
-
Tim Wickberg authored
salloc and sbatch will add this, but do not support than long option. Bug 3880.
-
Morris Jette authored
-
Morris Jette authored
An array was only being partially cleared due to bad logic bug 3876
-
Tim Wickberg authored
-
Tim Wickberg authored
Bug 3874.
-
- 09 Jun, 2017 3 commits
-
-
Morris Jette authored
-
Morris Jette authored
-
Brian Christiansen authored
-
- 08 Jun, 2017 7 commits
-
-
Morris Jette authored
-
Dominik Bartkiewicz authored
Improve selection of jobs to preempt when there are multiple partitions with jobs subject to preemption. bug 3824
-
Tim Wickberg authored
-
Dominik Bartkiewicz authored
Prevent segfault from pointer dereference to the QOS that is being deleted. Fix to commit 3e8aa451.
-
Brian Christiansen authored
When not using a nodefeatureplugin the new feature string should just be duplicated and returned. Continuation of 6690685a
-
Brian Christiansen authored
Usage changed
-
Morris Jette authored
-