- 09 Nov, 2017 12 commits
-
-
Danny Auble authored
Force tres change on a job to send data to the database. This should be happening already, but this just makes it always happen.
-
Danny Auble authored
This fixes the possibility of going into this loop when we hadn't setup the tres_req_cnt. The simple case Coverity reported is if the job is already finished it goes here and we never set up tres_req_cnt. Coverity CID 178897
-
Danny Auble authored
This fixes the possibility of referencing a NULL pointer if the reservation doesn't exist anymore when testing. Coverity CID 178898
-
Tim Wickberg authored
Bug 3647.
-
Tim Wickberg authored
Bug 4353.
-
Doug Jacobsen authored
Also collapse a nested %{with cray} block leftover from earlier work. Bug 4332.
-
Doug Jacobsen authored
Logic was inverted from the correct behavior. Bug 4332.
-
Doug Jacobsen authored
Slurm package should not try to manage configs; leave this to the admin to setup as they wish. This avoids an issue on RPM install if /etc/slurm is a symlink to somewhere else. Bug 4332.
-
Doug Jacobsen authored
Bug 4332.
-
Tim Wickberg authored
Bug 4332.
-
Brian Christiansen authored
-
Brian Christiansen authored
-
- 08 Nov, 2017 13 commits
-
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Tim Wickberg authored
%{_libdir} is /usr/lib64. Adding this can cause ordering problems with the library search path, and is redundant. And %{_libdir}/slurm is not needed by Slurm itself; it relies on rpath to resolve the install location instead. So, this is only useful on a non-standard install, in which case it's best left to the site to decide how to handle this instead. Bug 4344.
-
Brian Christiansen authored
as to why SLURM_MPI_TYPE is uninitialized in a step. Bug 4141
-
Brian Christiansen authored
Bug 4141
-
Brian Christiansen authored
When updating NumNodes, cpus, tasks, gres, memory, etc. need to adjusted so that counts are correct. Co-authored with Danny Auble
-
- 07 Nov, 2017 5 commits
-
-
Danny Auble authored
-
Danny Auble authored
This requires changing the resv_id and then also updating that on all the jobs. Since this requires having the job write lock we spawn a new thread instead of altering all the paths into _advance_resv_time(). Bug 4246
-
Alejandro Sanchez authored
Issue could be triggered when updating a partition node(s) with node(s) that were already in the partition, incorrectly increasing the node_record->part_cnt (number of associated partitions) and thus incorrectly extending the array of pointers to partitions associated with this node, leading to an array with repeated associated partitions pointers. Bug 4318.
-
Tim Wickberg authored
-
Brian Gilmer authored
On CLE 6.0 mungedir is /usr; a 'module unload' call then removes /usr/bin from PATH which is rather inconvenient. Bug 4334.
-
- 06 Nov, 2017 2 commits
-
-
Alejandro Sanchez authored
-
Alejandro Sanchez authored
A slurmctld lock needs to at least have a node and partition write lock set before set_cluster_tres() is called. The slurmctld "cold-restart" path was not covered. Bug 4318.
-
- 05 Nov, 2017 4 commits
-
-
Tim Wickberg authored
-
Tim Wickberg authored
This needs to be an email address, but slurm-dev (now slurm-users) will drop postings from non-subscribors. Just drop the setting instead.
-
Tim Wickberg authored
Mailing list has been renamed. Update links. Drop Gmane link, as they apparently stopped archiving things over a year ago, and the relay point has now been dropped from the slurm-users list. Drop mentions of emailing slurm-dev from the FAQ. The mailing list auto-discards anything from non-subscribors.
-
Doug Jacobsen authored
Accidentally committed in 1b743ca1. Bug 4332.
-
- 04 Nov, 2017 1 commit
-
-
Doug Jacobsen authored
Bug 4332.
-
- 03 Nov, 2017 3 commits
-
-
Brian Christiansen authored
-
Isaac Hartung authored
Memory TRES was getting the pn_min_memroy value when updating the job. But the TRES memory value is the total memory of the job (e.g pn_min_memory * cpus || pn_min_memory * nodes). Bug 4177
-
Brian Christiansen authored
"information each job"
-