[slurm-dev] Re: Power user sstat rights

Hello, anyone know if this is possible? Thanks! ☺ Best, Chris — Christopher Coffey High-Performance Computing Northern Arizona University 928-523-1167 On 3/8/17, 9:19 AM, "Christopher Benjamin Coffey" wrote: Hello, Is it possible to create a slurm account

[slurm-dev] Re: Getting one line per job in the sacct output

Hi Nicholas, Is there a period to which these records will be empty? I.e., does Slurm do some kind of periodic polling so my usual test jobs (doing things sleep 5 or small dd or a short QM test job) might fall between the intervals ? I was trying to use SelectType=select/cons_res

[slurm-dev] Re: Job-Specific Working Directory on Local Scratch

Thanks all for your suggestions. I ended up doing something that is pretty similar, with Prolog creating and TaskProlog exporting the working directory, and then a SPANK plugin is used to give the user options to copy files in and out of scratch. The only thing the user still has to do is

[slurm-dev] Re: Using GrpTRESRunMins

Hi Holger! This works for me as advertised on 14.11.8, just tested it. But the update interval for CPURunMins seems to be longer than a minute. You can check the current value using 'sshare -l'. I set GrpCPURunMins=10 for a user and started two 6min jobs. The second job got blocked and started

[slurm-dev] Using GrpTRESRunMins

Hello, while checking some of the posibilities for setting limits in SLURM I found an older article about GrpCPURunMins: http://tech.ryancox.net/2014/04/scheduler-limit-remaining-cputime-per.html trying this out (using GrpTRESRunMins=cpu=5000) it now seems to work differently - submitting a

[slurm-dev] Fwd: Dependency Problem In Full Queue

Hi, I'm having problems trying to launch jobs with dependency of another one. I'm using '--dependency=afterany:Job_ID' argument. The problem happens when the queue is full and the new job which depends on another one (already running) can't enter in the queue and need to wait. Instead of wait

[slurm-dev] Changing PriorityDecayHalfLife after some time

Hi All I'm wondering if we change PriorityDecayHalfLife from 1 week to 8 weeks whether the changes are applied only from that point in time or whether it acts on a raw usage number internally at the next priority calculation. This has a big effect on the GrpTRESMins limits as if a user has

[slurm-dev] Re: Job-Specific Working Directory on Local Scratch

We do it like this: - Prolog creates $SCRATCH, chowns it to the user - Task Prolog exports the $SCRATCH variable to the job step - Users can use a command "savefile" in their job script that registers the file(s) so that the epilog can copy them back (the command simply writes the file names

[slurm-dev] RE: Job-Specific Working Directory on Local Scratch

What about setting a random named working directory in submit plugin and creation of this directory in prologue?