[slurm-users] Slurm versions 17.02.10 and 17.11.5 are now available (CVE-2018-7033)

Slurm versions 17.02.10 and 17.11.5 are now available, and include a series of recent bug fixes, as well as a fix for a recently discovered security vulnerability (CVE-2018-7033). Downloads are available at https://www.schedmd.com/downloads.php . Several issues were discovered with incomplete

Re: [slurm-users] User limits

OK thanks. I see that. My issue with that option is described below. Assume a 2 core program runs about 40 minutes. So I set sacctmgr modify user name=mahmood set MaxWall=00:50:00 which means 50 minutes wall clock limit. That seems to be a per job limit. Therefore, if the users submits for the

Re: [slurm-users] User limits

Mahmood Naderan writes: > Hi, > Among many control commands and option, I want to retrieve the limits > which have been set for users. But I can not find the correct command, > e.g sacctmgr, sreport, ... > > For example, I ran this commnad > > # sacctmgr modify user name=mahmood set MaxWall=00:10

[slurm-users] User limits

Hi, Among many control commands and option, I want to retrieve the limits which have been set for users. But I can not find the correct command, e.g sacctmgr, sreport, ... For example, I ran this commnad # sacctmgr modify user name=mahmood set MaxWall=00:10 Modified user associations... C = or

Re: [slurm-users] Fairshare factor not reflected in job priority

Sorry for spamming, I've found the answer just answer posting the question. The resolution for my issue was to add FAIR_TREE to PriorityFlags. Fairshare factor for the user who submitted the job was low because of his high utilization of resources and sshare -u login was showing 0.0 for him. c

[slurm-users] Fairshare factor not reflected in job priority

I'm working on a priority multifactor plugin configuration and I'm not sure if I'm missing something or the behaviour I see is the result of bug. Basically # sshare | grep XX XX10.0714294367 0.031536 0.736368 which I read as fairshare factor = 0.

[slurm-users] stdout (and stderr) job files

Hello, We are transitioning from Moab/Torque to Slurm. I was wondering if there is a way to have Slurm also create the stdout (and stderr) file for the job on the node (be default), rather than on the shared FS. We sometimes have users who write a lot of stuff to stdout from their job script

[slurm-users] ec2 elastic node

Hello, I'm a bit lost trying to make a single ec2 node work. Would appreciate your help! I have a single aws/ec2 CLOUD node, named slurm-node0. The instance is currently down: # aws-ec2-list-instances | grep slurm-node0 i-006506267531a0511 slurm-node0 stopped I'm doing an allo