- 28 Sep, 2018 1 commit
-
-
Michael Hinton authored
Bug 5165
-
- 27 Sep, 2018 5 commits
-
-
Michael Hinton authored
Bug 5231 Change slurmctld/controller.c's purge_thread_lock from static to global extern, so the mutex can be used in slurmctld/job_mgr.c slurm_cond_signal() needs to always be wrapped in the same mutex as slurm_cond_[timed]wait(), or else there is a possibility that slurm_cond_signal() will trigger before slurm_cond_[timed]wait() is even listening, most likely causing a deadlock.
-
Jason Booth authored
Bug 5703
-
Michael Hinton authored
initialize old fairshare association pointer correctly. Bug 5744
-
Broderick Gardner authored
Bug 5458
-
Felip Moll authored
Bug 5748
-
- 26 Sep, 2018 2 commits
-
-
Danny Auble authored
-
Dominik Bartkiewicz authored
Bug 5775
-
- 24 Sep, 2018 1 commit
-
-
Felip Moll authored
Bug 5613
-
- 21 Sep, 2018 2 commits
-
-
Felip Moll authored
-
Didier GAZEN authored
bug 5669
-
- 13 Sep, 2018 1 commit
-
-
Dominik Bartkiewicz authored
The backup slurmctld can end up without an agent thread if read_slurm_conf() takes too long to complete. Forcing the agent_init() here again ensures it is restarted if not currently running. This was fixed upstream in c1a537db. Bug 5633.
-
- 10 Sep, 2018 2 commits
-
-
Danny Auble authored
is removed from the system. Bug 5665
-
Danny Auble authored
burst buffer. Bug 5665
-
- 06 Sep, 2018 1 commit
-
-
Marshall Garey authored
Bug 5359
-
- 31 Aug, 2018 1 commit
-
-
Marshall Garey authored
Spaces need to be built into each key definition, otherwise it'll all run together. Bug 5657.
-
- 30 Aug, 2018 1 commit
-
-
Danny Auble authored
%n or %h in the spool dir. Bug 5096
-
- 29 Aug, 2018 3 commits
-
-
Dominik Bartkiewicz authored
Fail early when the layout requirements cannot be satisfied in _task_layout_lllp_block(). Otherwise step layout calculations will fail, leading to a "fatal: _task_layout_lllp_block infinite loop" Bug 5415.
-
Dominik Bartkiewicz authored
The conditional for handling --overcommit was not sufficient to prevent other option combinations from using that code path, resulting in unexpected resource allocation behavior. Correct that to check that overcommit is enabled. Bug 5345.
-
Dominik Bartkiewicz authored
Bug 5379.
-
- 27 Aug, 2018 2 commits
-
-
Danny Auble authored
running. Bug 5624
-
Dominik Bartkiewicz authored
for an allocation. Bug 5293 Backport of 9a507584 in 18.08.
-
- 22 Aug, 2018 2 commits
-
-
Danny Auble authored
Bug 5608 Tim approved
-
Brian Christiansen authored
If the dbd comes up after a job array has been submitted to the controller, the controller calls _update_job_tres() which calls assoc_mgr_set_tres_cnt_array() which allocates memory for the job's tres_alloc_cnt. The job array gets scheduled, but job_array_split() doesn't NULL out the pending job's tres_alloc_cnt, so both the array task and the pending array job are pointing to the same memory. The array task calls job_set_alloc_tres() which free's the running job's tres_alloc_cnt and now the pending array job is pointing to bad memory and when the array splits again the new array task tries to free tres_alloc_cnt in job_set_alloc_tres() and segfaults. Bug 5604
-
- 21 Aug, 2018 3 commits
-
-
Danny Auble authored
-
Alejandro Sanchez authored
Bug 5561.
-
Felip Moll authored
Bug 5072
-
- 20 Aug, 2018 12 commits
-
-
Tim Wickberg authored
-
Tim Wickberg authored
Change _build_path to return the xmalloc()'d string, and make sure to free it where appropriate. Add comment about how the processing of the PATH environment variable here is backwards from convention.
-
Tim Wickberg authored
-
Tim Wickberg authored
Fixes GCC 8.2.0 warnings.
-
Tim Wickberg authored
Fix some -Werror=restrict and -Werror=format= issues.
-
Tim Wickberg authored
-
Tim Wickberg authored
Silence GCC 8.2.0 warning.
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Tim Wickberg authored
Nothing modifies this, so don't bother making a copy of it. Related to GCC 8.2.0 compilation fixes.
-
Tim Wickberg authored
Fixes GCC 8.2.0 compilation warnings. Bug 5465.
-
Michael Hinton authored
MySQL permits up to 64-character database names, but Slurm was truncating at 33-characters. If we exceed this limit, let the mysql_query fail and give the admin a chance to sort it out, rather than truncating and then failing to query against the un-truncated name later on. While here correct the fatal() message. Bug 5586.
-
- 18 Aug, 2018 1 commit
-
-
Brian Christiansen authored
Bug 5554
-