- 13 May, 2015 1 commit
-
-
Morris Jette authored
Add PrologFlags option of "Contain" to create a proctrack container at job resource allocation time. At job allocation time, a slurmstepd is spawned on every allocated compute node in which to place external processes (e.g. PAM can place ssh processes into a cgroup). This entity is accounted for and reported by sacct as "<jobid>.extern". Some more testing and development remain, but it mostly works.
-
- 12 May, 2015 2 commits
-
-
Morris Jette authored
-
Morris Jette authored
-
- 11 May, 2015 1 commit
-
-
Morris Jette authored
Make sure that old step data is purged when a job is requeued. Without this logic, if a job terminates abnormally then old step data may be left in slurmctld. If the job is then requeued and started on a different node, referencing that old job step data can result in abnormal events. One specific failure mode is if the job is requeued on a node with a different number of cores, and the step terminated RPC arrives later, the job and step bitmaps of allocated cores can differ in size generating an abort. bug 1660
-
- 08 May, 2015 4 commits
-
-
Danny Auble authored
-
David Gloe authored
Bug 1657
-
Brian Christiansen authored
Bug 1618
-
Jonathon Nelson authored
-
- 07 May, 2015 1 commit
-
-
Danny Auble authored
cpu count.
-
- 06 May, 2015 4 commits
-
-
Morris Jette authored
Add re-entrant versions of glibc time functions (e.g. localtime) to Slurm in order to eliminate rare deadlock of slurmstepd fork and exec calls. bug 1638
-
Danny Auble authored
utilization.
-
Danny Auble authored
random crashing in db2 when the slurmctld is exiting. Signed-off-by:
Danny Auble <da@schedmd.com>
-
David Bigagli authored
-
- 05 May, 2015 1 commit
-
-
Morris Jette authored
-
- 04 May, 2015 1 commit
-
-
Morris Jette authored
-
- 01 May, 2015 1 commit
-
-
Jens Svalgaard Kohrt authored
-
- 30 Apr, 2015 4 commits
-
-
Morris Jette authored
In slurmctld communication agent, make the thread timeout be the configured value of MessageTimeout (or 30 seconds, whichever is larger) rather than 30 seconds.
-
Morris Jette authored
Fix scancel bug which could return an error on attempt to signal a job step. A simple "scancel 12.3" to signal a specific job step would fail. Adding another option (say "-i", "--partion=", etc.) would fix this.
-
David Bigagli authored
-
David Bigagli authored
-
- 29 Apr, 2015 2 commits
-
-
Danny Auble authored
before ending the job.
-
Danny Auble authored
will make it so the slurmctld will not signal the apid's in a batch job. Instead it relies on the rpc coming from the slurmctld to kill the job to end things correctly.
-
- 28 Apr, 2015 4 commits
-
-
Morris Jette authored
Refactor scancel so that all pending jobs are cancelled before starting cancellation of running jobs. Otherwise they happen in parallel and the pending jobs can be scheduled on resources as the running jobs are being cancelled.
-
Danny Auble authored
-
jette authored
Add SchedulerParameters option of sched_min_interval that controls the minimum time interval between any job scheduling action. The default value is zero (disabled). bug 1623
-
Morris Jette authored
-
- 27 Apr, 2015 1 commit
-
-
Morris Jette authored
Fix some power_save mode issues: Parsing of SuspendTime in slurm.conf was bad, powered down nodes would get set non-responding if there was an in-flight message, and permit nodes to be powered down from any state. bug 1619
-
- 24 Apr, 2015 4 commits
-
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Morris Jette authored
Initialize some variables used with the srun --no-alloc option that may cause random failures.
-
Morris Jette authored
-
- 23 Apr, 2015 2 commits
-
-
Alejandro Sanchez Graells authored
Also see: https://github.com/asanchez1987/jobcomp-elasticsearch
-
David Bigagli authored
-
- 22 Apr, 2015 4 commits
-
-
Danny Auble authored
job. This is already handled on the stepd when the script finishes.
-
Danny Auble authored
often an inventory request is handled.
-
Brian Christiansen authored
-
Brian Christiansen authored
-
- 21 Apr, 2015 3 commits
-
-
Danny Auble authored
free afterwards would not have zeroed out memory on the variables that didn't get unpacked.
-
David Bigagli authored
-
Morris Jette authored
sbatch to stop parsing script for "#SBATCH" directives after first command. It keeps parsing so long as lines contain only white space or comments (first non-white space character is '#').
-