Commits · c15f0f3ceb360b00e6a13a878bcb4b7484504a0a · Manuel G. Marciani / ces_slurm_simulator

12 Sep, 2019 3 commits
- select/cons_tres - fix gres code infinite loop. · c15f0f3c
  Marcin Stolarek authored Sep 06, 2019
```
An incorrect logic with the variables holding available cores in the
gres_plugin_job_core_filter3() function lead to a potential infinite
"while (avail_cores_tot > req_cores)" loop, leaving slurmctld unresponsive.

Bug 7685.
```
  c15f0f3c
- Fix race condition preventing held array job from getting db_index · 6d6711b3
  Brian Christiansen authored Sep 11, 2019
```
Bug 7719

Signed-off-by: Danny Auble <da@schedmd.com>
```
  6d6711b3
- Fix preemption issue when picking nodes for a feature job request. · 0d432cae
  Dominik Bartkiewicz authored Sep 11, 2019
```
Regression caused by 72736af2.

Bug 7708.
```
  0d432cae
10 Sep, 2019 1 commit

Danny Auble authored Sep 05, 2019



FastSchedule will be removed in 20.02.
FastSchedule=2 functionality has been moved to
SlurmdParameters=config_overrides.

Bug 7496.


Signed-off-by: Tim Wickberg <tim@schedmd.com>

2c44fcf6

07 Sep, 2019 1 commit
- typo in sched_config.html string->strict · f85a7d70
  Marcin Stolarek authored Aug 09, 2019
  
  f85a7d70
06 Sep, 2019 4 commits
- Merge remote-tracking branch 'origin/slurm-18.08' into slurm-19.05 · 72ada689
  Brian Christiansen authored Sep 06, 2019
  
  72ada689
- Fix bjobs test to only work with 7 character jobids · 6de00f40
  Brian Christiansen authored Sep 06, 2019
```
Bug 7664
```
  6de00f40
- Correct "extern" definition of variable if compiling with __APPLE__ · 25e6f4d8
  Brian Christiansen authored Sep 06, 2019
```
Bug 7699
```
  25e6f4d8
- Fix checking for flag with logical AND · 9083eed2
  Danny Auble authored Sep 06, 2019
```
Continuation of 64876087

Bug 7698
```
  9083eed2
05 Sep, 2019 1 commit
- Fix typo for 'comparison'. · ffef6849
  Nate Rini authored Sep 05, 2019
  
  ffef6849
04 Sep, 2019 3 commits
- Have safe_[read|write] handle EAGAIN and EINTR. · 9c0a206f
  Danny Auble authored Sep 04, 2019
```
Bug 4781
```
  9c0a206f
- sched/backfill - clear estimated sched_nodes as done for start_time. · 32feee0b
  Dominik Bartkiewicz authored Sep 04, 2019
```
Otherwise, there could be time frames where printed schednodes
information could be obsolete.

Bug 7676.
```
  32feee0b
- Properly enforce a job's mem-per-cpu option when allocate the node · 1c22ed8b
  Dominik Bartkiewicz authored Aug 26, 2019
```
exclusively to that job.

Bug 7510
```
  1c22ed8b
03 Sep, 2019 8 commits
- Add missing files from testsuite to Makefile.am · 1e84bb3b
  Danny Auble authored Sep 03, 2019
  
  1e84bb3b
- Fix create_resv() · c55f6d65
  Dominik Bartkiewicz authored Aug 06, 2019
```
use correct start_time for TIME_FLOAT resevation
in _job_overlap()

Bug 7458
```
  c55f6d65
- Improve test3.14 · cbe5b12a
  Dominik Bartkiewicz authored Aug 05, 2019
```
Bug 7458
```
  cbe5b12a
- Add sub-test 3.11.10 · 27628783
  Dominik Bartkiewicz authored Aug 05, 2019
```
Test DAILY reservation conflict

Bug 7458
```
  27628783
- Remove duplicate logic · 166c2d36
  Dominik Bartkiewicz authored Jul 31, 2019
```
use _resv_time_overlap() in _resv_overlap()

Bug 7458
```
  166c2d36
- Set mising resv_desc.flags before call _select_nodes() · 6d89c126
  Dominik Bartkiewicz authored Jul 31, 2019
```
Bug 7458
```
  6d89c126
- look forward one week while create new reservation · d72a02c6
  Dominik Bartkiewicz authored Jul 30, 2019
```
Bug 7458
```
  d72a02c6
- Fix job_resv_check() · 10043b8a
  Dominik Bartkiewicz authored Jul 26, 2019
```
Move _validate_node_choice() before prolog/epilog check

Bug 7458
```
  10043b8a
30 Aug, 2019 3 commits
- Merge branch 'bug6513' into slurm-19.05 · 32c41b86
  Brian Christiansen authored Aug 29, 2019
  
  32c41b86
- Add lua check to test7.20. · d992b883
  Nate Rini authored Apr 30, 2019
```
Bug 6513.
```
  d992b883
- Add HAVE_LUA existence check. · 29907fc4
  Nate Rini authored Apr 30, 2019
```
Bug 6513.
```
  29907fc4
29 Aug, 2019 13 commits
- gres/mic - add missing init() and fini() calls. · 45406061
  Michael Hinton authored Aug 29, 2019
```
Free the gres_devices list to avoid a valgrind warning on exit.

Bug 7644.
```
  45406061
- Merge branch 'slurm-18.08' into slurm-19.05 · b26925a6
  Alejandro Sanchez authored Aug 29, 2019
  
  b26925a6
- Testsuite - add time limit to test12.10 job submissions. · ca123ee5
  Albert Gil authored Jun 07, 2019
```
Bug 7149.
```
  ca123ee5
- Fix undefined variable in test · 1fc2c26f
  Brian Christiansen authored Aug 29, 2019
  
  1fc2c26f
- Merge branch 'bug7445' into slurm-19.05 · daf57df7
  Brian Christiansen authored Aug 29, 2019
  
  daf57df7
- Fix batch_step being created with correct batch_host when using --batch · 55a96bcf
  Brian Christiansen authored Aug 22, 2019
```
Continuations of a2f2894f



Bug 7445

Signed-off-by: Marshall Garey <marshall@schedmd.com>
```
  55a96bcf
- Fix getting batch_host after its been set when requesting --batch · fe2bf9bf
  Brian Christiansen authored Aug 21, 2019
```
Continuation of 30bbc11d



Bug 7445

Signed-off-by: Dominik Bartkiewicz <bart@schedmd.com>
```
  fe2bf9bf
- Add comment in pick_batch_host() · 4b4a11cc
  Brian Christiansen authored Aug 20, 2019
```
Bug 7445

Signed-off-by: Dominik Bartkiewicz <bart@schedmd.com>
```
  4b4a11cc
- Make --batch requests wait for all nodes to boot before launching · 76956c87
  Brian Christiansen authored Aug 20, 2019
```
When --batch=<feature> is used, the batch_host isn't chosen until the
job is being launched -- because the features could be different on boot
(e.g. KNL nodes). Thus if the job is allocated nodes that need to be
booted, it needs to wait till they are all booted so it can make a
decision at launch time.

Bug 7445

Signed-off-by: Dominik Bartkiewicz <bart@schedmd.com>
```
  76956c87
- Don't assume the first node of a job is the batch host · 875cbf9c
  Dominik Bartkiewicz authored Jun 18, 2019
```
This is a continuation to 7da439b4

Bug 7445
```
  875cbf9c
- Merge branch 'slurm-18.08' into slurm-19.05 · 4ff334a0
  Alejandro Sanchez authored Aug 29, 2019
  
  4ff334a0
- Testsuite - fix for test17.25 long default account names. · d3c3906c
  Albert Gil authored Jul 08, 2019
```
The get_default_acct was truncating the account name for long account
names. This commit uses -P/--parsable2 to avoid it.

Bug 7369.
```
  d3c3906c
- pam_slurm_adopt - print errno message when using stat() on cgroup path. · 73ff0e81
  Marcin Stolarek authored Aug 08, 2019
```
Bug 7467.
```
  73ff0e81
28 Aug, 2019 1 commit

Don't update [min|max]_exit_code on job array task requeue. · 0e42eb87

Alejandro Sanchez authored Aug 28, 2019

Only do so once the task actually finishes. Otherwise, a requeued task
could set an incorrect max_exit_code even if completed with exit code 0
after re-running again, leading to problems with i.e. other jobs with an
afterok type of dependency on such array relying on the incorrectly set
max_exit_code.

Bug 7552.

0e42eb87

26 Aug, 2019 2 commits
- Continuation of commit af7b4531. · e57b297e
  Danny Auble authored Aug 26, 2019
```
We only remove from registered_clusters if conn->rem_port != 0,
so only add to it if the same.

Bug 5213

Signed-off-by: Alejandro Sanchez <alex@schedmd.com>
```
  e57b297e
- Remove stray zero-width space characters from x_ac_nvml.m4 comment. · 7a29a3cc
  Tim Wickberg authored Aug 26, 2019
  
  7a29a3cc