- 10 Nov, 2016 4 commits
-
-
Morris Jette authored
Check for zonesort file first, to save time over attempting to load a module that is already loaded. It may be loaded by default per administrator configuration.
-
Morris Jette authored
-
Brian Christiansen authored
Missed from 1aa299ab
-
Morris Jette authored
-
- 09 Nov, 2016 9 commits
-
-
Morris Jette authored
-
Morris Jette authored
This should make a Coverity error go away. The error is being generated in error by Coverity, but it isn't smart enough to determine the range of values possible from a modulo function (if the input is negative, its results can't be less than the negative of the divisor). This should clear about a dozen errors.
-
Morris Jette authored
Leaks reported by Coverity
-
Morris Jette authored
as reported by Coverity
-
Morris Jette authored
Plug about 20 memory leaks reported by Coverity
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
Set per-node HBM availability as a GRES based upon the KNL node's MCDRAM state bug 3171
-
Alejandro Sanchez authored
Caused by race for local_energy which is dynamically allocated. Bail out of the update if that hasn't been allocated yet. Bug 3237.
-
- 08 Nov, 2016 11 commits
-
-
Morris Jette authored
avoid unused variable in front-end mode
-
Morris Jette authored
Add new node state flag of NODE_STATE_REBOOT for node reboots triggered by "scontrol reboot" commands. Previous logic re-used NODE_STATE_MAINT flag, which could lead to inconsistencies. Add "ASAP" option to "scontrol reboot" command that will drain a node in order to reboot it as soon as possible, then return it to service. bug 3210
-
Morris Jette authored
-
Morris Jette authored
bug 3213
-
Morris Jette authored
-
Morris Jette authored
select/linear plugin modified to better support heterogeneous clusters when topology/none is also configured. Note that use of the select/cons_res plugin is strongly recommended for heterogeneous clusters. The use of OverSubscribe=exclusive can be used if whole node allocations is desired. bug 3212
-
Alejandro Sanchez authored
Bug 3224.
-
Morris Jette authored
-
Morris Jette authored
Different paths were used in various locations. All changed to use the /var/spool directory.
-
Morris Jette authored
-
Morris Jette authored
If a job is started by the main scheduling logic and requeued while the backfill scheduler has locks released, that can result in an invalid data structure in select/cons_res. Namely, the backfill scheduler's attempt to start the job would clear the job resources node_bitmap. That leaves a NULL pointer in the select/cons_res plugin generating an abort. (That pointer is needed to clean up the job allocation records when the Epilog or Cray Node Health Check, NHC, are complete and the resources become available for another job. bug 3230
-
- 07 Nov, 2016 6 commits
-
-
Danny Auble authored
task and can get quite verbose on a KNL node.
-
Danny Auble authored
warning fix.
-
Danny Auble authored
if the pointer is valid
-
Danny Auble authored
-
Morris Jette authored
-
Morris Jette authored
Backup slurmctld will now 1. Not abort due to NULL pointer (needed to move code around on restart) 2. Recover KNL MCDRAM and NUMA modes from state save files if capmc and cnselect not available bug 3241
-
- 05 Nov, 2016 2 commits
-
-
Morris Jette authored
-
Morris Jette authored
cray/burst_buffer - Update "instance" parsing to match updated dw_wlm_cli output. bug 3222
-
- 04 Nov, 2016 8 commits
-
-
Morris Jette authored
No change to logic
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
cons_res.
-
Danny Auble authored
requests when they = 1. What we did was just increase the cpus_per_task to equal the amount of threads in the core|socket. This was done with an array to handle heterogeneous systems. Bug 2519
-
Danny Auble authored
Hopefully this will make alterations to this function easier as it doesn't now consider ntasks_per_*.
-
Brian Christiansen authored
-