Commits · 8befe6396659e7e45cd523dfc00235df29dda39c · Manuel G. Marciani / ces_slurm_simulator

15 May, 2017 2 commits
- node_features/knl_generic - If a node is rebooted for a pending job, but · 8befe639
  Morris Jette authored May 15, 2017
```
fails to enter the desired NUMA and/or MCDRAM mode then drain the node and
requeue the job.

Bug 3785
```
  8befe639
- When rebooting a node and using the PrologFlags=alloc make sure the · 7f8ac296
  Tim Shaw authored May 15, 2017
```
prolog is ran after the reboot.

Bug 3618
```
  7f8ac296
13 May, 2017 2 commits
- Remove log files from test20.12 · 7bb4d9a1
  Isaac Hartung authored May 12, 2017
```
Bug 3695
```
  7bb4d9a1
- knl_cray plugin: Change capmc parsing of mcdram_pct from string to number · 7bd276b1
  Morris Jette authored May 12, 2017
```
bug 3779
```
  7bd276b1
12 May, 2017 4 commits

knl_cray plugin: Log incomplete capmc output for a node · 80b27490

Morris Jette authored May 12, 2017

If capmc reports a node name, but not mcdram_cfg for the node, then
  log the missing data rather than assume the value is zero and
  report a value mismatch with cnselect.

80b27490

Prevent scontrol crash when operating on array and no-array jobs at once. · 006f7eeb

Alejandro Sanchez authored May 12, 2017

When requesting an operation on jobs, where the operation permits to specify
more than one job in the same request, and a job array appears before a
regular job (no-array job) in the list of jobs to operate with, the
job_array_resp_msg_t pointer was not properly NULL'ed and thus incorrectly
accessed when processing the no-array job. This fix prevents the crash from
happening in the following scontrol operations:

uhold, hold, suspend, requeue, requeuehold, update, release

when the same request has <array_jobid>,<non-array_jobid> in this order in
the job list to process.

Bug 3759

006f7eeb

Enhance job expansion example · 02b790bc

Morris Jette authored May 12, 2017

Job expansion example in FAQ enhanced to demonstrate operation in
    heterogeneous environments.
bug 2979

02b790bc

avoid starting scheduler on busy system after power cap change · e29e8511
Alejandro Sanchez authored May 12, 2017
```
Do not attempt to schedule jobs after changing the power cap if there are
    already many active threads.
```
e29e8511

11 May, 2017 1 commit
- Update NEWS for next release. · d65ed698
  Danny Auble authored May 10, 2017
  
  d65ed698
10 May, 2017 1 commit
- Return error when bad separator is given for scontrol update job licenses. · 521a574c
  Dominik Bartkiewicz authored May 10, 2017
```
Bug 3760
```
  521a574c
09 May, 2017 5 commits
- Revert "Return error when bad separator is given for scontrol update job licenses." · 36718220
  Danny Auble authored May 09, 2017
```
This reverts commit ecfd007f.
```
  36718220
- Return error when bad separator is given for scontrol update job licenses. · ecfd007f
  Dominik Bartkiewicz authored May 09, 2017
  
  ecfd007f
- Don't remove admin comment when updating a job. · 6cf363c4
  Danny Auble authored May 09, 2017
```
It was noticed that while doing any update to a job the admin comment would
be blown away.  This patch fixes that.
```
  6cf363c4
- Fix updating job priority on multiple partitions to be correct. · bf7e0e7b
  Dominik Bartkiewicz authored May 09, 2017
```
Bug 3789
```
  bf7e0e7b
- Message Aggr - Remove race condition on slurmd shutdown with respects to · bc3cdabf
  Danny Auble authored May 09, 2017
```
destroying a mutex.
```
  bc3cdabf
08 May, 2017 2 commits
- Allow reboot program to use arguments. · 64c3fc37
  Tim Shaw authored May 08, 2017
```
Bug 3612

Looks like a regression in commit ad07aebc
```
  64c3fc37
- Sanity check to make sure we have started a job in acct_policy.c before we · f795589d
  Danny Auble authored May 08, 2017
```
clear it as started.
```
  f795589d
05 May, 2017 1 commit
- Fix race condition in priority/multifactor init · bf1fc12b
  Brian Christiansen authored May 05, 2017
```
The decay thread could signal the cond before the init thread waits for
it causing deadlock.
```
  bf1fc12b
04 May, 2017 6 commits
- MYSQL - Fix memory leak when loading archived jobs into the database. · 75a71f87
  Tim Wickberg authored May 04, 2017
  
  75a71f87
- CRAY - Move delay waiting for job cleanup to after we check once. · 6aa5af45
  Danny Auble authored May 04, 2017
```
Bug 3725
```
  6aa5af45
- Fix incorrect locks levels when submitting a batch job or updating a job · f3a302e5
  Tim Wickberg authored May 04, 2017
```
in general.
```
  f3a302e5
- Fix race condition w/closing of persist conns · 2195829d
  Brian Christiansen authored May 04, 2017
```
at shutdown. More likely to happen in the fed_mgr than the dbd since the
fed_mgr closes the persistent connections before they are signaled by
the persistent connection server.
```
  2195829d
- Handle a job that made it out of the select plugin without a job_resrcs · bf0429d1
  Alejandro Sanchez authored May 04, 2017
```
pointer.
```
  bf0429d1
- Fix potential memory leak if job fails to begin after nodes have been · e3a8e2b4
  Alejandro Sanchez authored May 04, 2017
```
selected for a job.

Bug 3690
```
  e3a8e2b4
03 May, 2017 2 commits

Strongly encourage use of proctrack/cgroup. · 0195f083

Tim Wickberg authored May 03, 2017

Remove outdated disclaimers, proctrack/cgroup is awesome.

(jobacct_gather/cgroup is still not recommended though.)

Change it to the default with the configurators as well.

0195f083

Fix dereference of NULL pointer · d39075ae
Brian Christiansen authored May 03, 2017
```
As found by CLANG
```
d39075ae

01 May, 2017 1 commit
- Fix priority/multifactor priorities on a slurmctld restart if not using · 236eb865
  Morris Jette authored May 01, 2017
```
accounting_storage/[mysql|slurmdbd].

Bug 3574
```
  236eb865
28 Apr, 2017 2 commits
- Fix double-xfree() on clusters element of the job_record when using job arrays. · 732fe434
  Tim Wickberg authored Apr 28, 2017
```
Bug 3738.
```
  732fe434
- When using node_features/knl_generic make it so the slurmd doesn't segfault · 65d9062c
  Danny Auble authored Apr 27, 2017
```
when shutting down.

Fix regression introduced by commit 32ded0c3.
```
  65d9062c
26 Apr, 2017 1 commit
- Fix to make task/affinity work with ldoms where there are more than 64 · 430e6459
  Danny Auble authored Apr 25, 2017
```
cpus on the node.
```
  430e6459
24 Apr, 2017 3 commits
- Fix incorrect casts in preempt/job_prio plugin sorting function. · f2d4c39a
  Gary B Skouson authored Apr 24, 2017
```
Bug 3714.
```
  f2d4c39a
- Fix incorrect casts in preempt_youngest_first mode. · 6e08d59f
  Gary B Skouson authored Apr 24, 2017
```
Bug 3714.
```
  6e08d59f
- Fix check for 'preempt_youngest_first' option to PreemptParameters. · 588387a2
  Dominik Bartkiewicz authored Apr 24, 2017
```
Match documented string.

Bug 3711.
```
  588387a2
21 Apr, 2017 5 commits

Fix backfill scheduling bug · 98b9f217

Dominik Bartkiewicz authored Apr 21, 2017

sched/backfill: Fix bug related to advanced reservations and the need to
    reboot nodes to change KNL mode.
bug 3645

98b9f217

CRAY - Add ansible play and README · 5802faf4
David Gloe authored Apr 21, 2017
```
Bug 3616
```
5802faf4

backfill scheduling bug fix · 76f5d135

Morris Jette authored Apr 21, 2017

Fix to backfill scheduling with respect to QOS and association limits. Jobs
    submitted to multiple partitions are most likley to be effected.
bugs 3680 and 3689

76f5d135

backfill scheduling bug fix · 0b7b2e60

Morris Jette authored Apr 21, 2017

Fix to backfill scheduling with respect to QOS and association limits. Jobs
    submitted to multiple partitions are most likley to be effected.
bugs 3680 and 3689

0b7b2e60

Fix seg fault if loading attempting to load non-existent burstbuffer plugin. · 2057100b
Danny Auble authored Apr 20, 2017

2057100b

20 Apr, 2017 2 commits
- When removing a partition make sure it isn't part of a reservation. · 3c44681a
  Tim Shaw authored Apr 20, 2017
```
Bug 3646
```
  3c44681a
- ALPS - Fix scheduling when ALPS doesn't agree with Slurm on what nodes · f9aa610c
  Danny Auble authored Apr 20, 2017
```
are free.
```
  f9aa610c