- 19 Feb, 2016 24 commits
-
-
Alejandro Sanchez authored
-
Danny Auble authored
-
Morris Jette authored
If a job was requeued while some prolog was running (e.g. waiting for node boot, burst buffer, PrologSlurmctld, etc.) then wait until that completes before considering starting the job again.
-
Gennaro Oliva authored
No functional change, although confine to master to limit any chance of bad interaction with pre-existing plugins.
-
Tim Wickberg authored
-
Danny Auble authored
back the way it was before commit cf354d1e and 7a187dce.
-
Danny Auble authored
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Gennaro Oliva authored
Consistantly use American English for existant -> existent assocation -> association Correct some typos, and one grammatical mistake.
-
Morris Jette authored
-
Danny Auble authored
payload whereas before it didn't.
-
Morris Jette authored
Conflicts: src/slurmctld/job_mgr.c
-
Morris Jette authored
BurstBuffer/cray - Defer job cancellation or time limit while "pre-run" operation in progress to avoid inconsistent state due to multiple calls to job termination functions. bug 2454
-
Tim Wickberg authored
-
Tim Wickberg authored
Otherwise call fclose(NULL) iff the ClusterName is not set and the clustername file does not exist. Should not happen in production. Coverity #67041.
-
Morris Jette authored
-
Danny Auble authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
Conflicts: NEWS
-
Morris Jette authored
-
Morris Jette authored
Conflicts: META
-
Morris Jette authored
-
- 18 Feb, 2016 16 commits
-
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
a new account and making it a default all at once. Bug 2428
-
Alejandro Sanchez authored
Match acct_gather_energy/rapl plugin. Bug 2397.
-
Tim Wickberg authored
Control whether the scheduler will continue to try to run jobs in a partition if a higher priority job is stuck due to an association limit. Can cause starvation for larger jobs, but will improve throughput and utilization for systems that have extensively divvyed up their resources through association/QOS limits. Bug 2388 and 2452.
-
Danny Auble authored
Bug 2453
-
Morris Jette authored
-
Morris Jette authored
This should have no effect, but is a belt-and-suspenders approach to checking node state.
-
Morris Jette authored
libpmi was previously using the slurm_mutex_un/lock functions, which are dependent upon other slurm functions (e.g. "fatal()"). Since this library is used by user applications and outside of slurm proper, we want to us the pthread_mutex_un/lock functions instead. Previous use of slurm functions was invoking glibc error() function rather than slurm's error() function and causing test7.2 to fail.
-
Jeff White authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
Make srun logic work more like sbatch/salloc.
-
Morris Jette authored
Jenkins was reporting unused function otherwise
-
Tim Wickberg authored
have been selected set the time limit appropriately if the job didn't request one. If the partition has no DefaultTime setting, and no time_limit was given for the job, job_ptr->time_limit == NO_VAL. With AccountingStorageEnforce=safe this will prevent jobs from ever starting if the association has any limit set for CPUMins. (NO_VAL * cpus is a very large number, but if no time_limit is given anywhere that is what they get :)) Bug 2388.
-
Morris Jette authored
Fix for when a feature is available, but not active on any node.
-