[slurm-users] Non-intiutive rank placement/CPU masking

Dear * , I've some question for understanding. Essentially, I use the following job script: ---> #!/bin/bash #SBATCH -J srun_test #SBATCH --time=0:02:00 #SBATCH --export=NONE #SBATCH --partition=test #SBATCH --nodes=2 #SBATCH -o ./%x.%j.out #SBATCH -D . srun --export=a

Re: [slurm-users] srun jobfarming hassle question

rs im Auftrag von Bjørn-Helge Mevik Gesendet: Donnerstag, 19. Januar 2023 08:23 An: slurm-us...@schedmd.com Betreff: Re: [slurm-users] srun jobfarming hassle question "Ohlerich, Martin" writes: > Hello Björn-Helge. > > > Sigh ... > > First of all, of course, many tha

Re: [slurm-users] srun jobfarming hassle question

ming hassle question On 18/01/2023 15:22, Ohlerich, Martin wrote: > But Magnus (Thanks for the Link!) is right. This is still far away from a > feature rich job- or task-farming concept, where at least some overview of > the passed/failed/missing task statistics is available etc. GN

Re: [slurm-users] srun jobfarming hassle question

Sure ;) My example was just for fast reproductivity. The complete job farm script is (if that's of interest): -> #!/bin/bash #SBATCH -J jobfarm_test #SBATCH -o log.%x.%j.%N.out #SBATCH -D ./ #SBATCH --mail-type=NONE #SBATCH --time=00:05:00 #SBATCH --export

Re: [slurm-users] srun jobfarming hassle question

ttwoch, 18. Januar 2023 13:49 An: slurm-us...@schedmd.com Betreff: Re: [slurm-users] srun jobfarming hassle question "Ohlerich, Martin" writes: > Dear Colleagues, > > > already for quite some years now are we again and again facing issues on our > clusters with so-called job

[slurm-users] srun jobfarming hassle question

Dear Colleagues, already for quite some years now are we again and again facing issues on our clusters with so-called job-farming (or task-farming) concepts in Slurm jobs using srun. And it bothers me that we can hardly help users with requests in this regard. >From the documentation (https:

Re: [slurm-users] seff MaxRSS Above 100 Percent?

Dear Daryl, I once posed the same question, and got a dear answer here in the forum some while ago. So, I just forward it approximately. RSS appears to include double counting of memory that is occupied by shared libraries. I was proposed to switch to PSS https://slurm.schedmd.com/slurm.conf

Re: [slurm-users] slurm accounting shows more MaxRSS than physically available memory

size https://bugs.schedmd.com/show_bug.cgi?id=9010 I would also be interested what others think. Best regards Jürgen * Ohlerich, Martin [221102 11:53]: > Dear "Commiserates". > > I wonder a bit about the meaning of MaxRSS. The documentation says: > "Maximum reside

[slurm-users] slurm accounting shows more MaxRSS than physically available memory

Dear "Commiserates". I wonder a bit about the meaning of MaxRSS. The documentation says: "Maximum resident set size of all tasks in job." To what refers here "maximum"? The maximum over job period, I understand hopefully correctly. But it does not seem to be the size of all tasks (summed up, so-