Re: [slurm-users] Limit job_submit.lua script for only srun

2018-04-25 Thread Yair Yarom
Hi, We are also limiting "interactive" jobs through a plugin. What I've found is that in the job_descriptor the following holds: for salloc: argc = 0, script = NULL for srun: argc > 0, script = NULL for sbatch: argc = 0, script != NULL You can look at our plugin in https://github.com/irush-cs/slu

Re: [slurm-users] SLURM on Ubuntu 16.04

2018-04-25 Thread Eric F. Alemany
Hi Chris, Thank you for the update(s). It is what it is - right ? _ Eric F. Alemany System Administrator for Research Division of Radiation & Cancer Biology Department of Radiation Oncology St

Re: [slurm-users] SLURM on Ubuntu 16.04

2018-04-25 Thread Christopher Samuel
On 26/04/18 09:58, Christopher Samuel wrote: Most importantly you will want to be sure that they have backported the patch to close CVE-2018-7033 (fixed in 17.11.5). Went and found their sources, there is no mention of this being fixed in the proposed version, so it seems that bionic will ship

Re: [slurm-users] SLURM on Ubuntu 16.04

2018-04-25 Thread Christopher Samuel
On 26/04/18 09:49, Eric F. Alemany wrote: I am going to follow your suggestion to install slurm via ubuntu 18.04 package. Just be aware that the version in bionic is outdated, it's 17.11.2. Most importantly you will want to be sure that they have backported the patch to close CVE-2018-7033 (f

Re: [slurm-users] SLURM on Ubuntu 16.04

2018-04-25 Thread Eric F. Alemany
Hi Patrick, I am going to follow your suggestion to install slurm via ubuntu 18.04 package. I am waiting for the final release of 18.04 which i believe is tomorrow. As you mentioned I will install: the slurmctld package on the SMS (the master) the slurmd package on the nodes I know there will b

Re: [slurm-users] SLURM on Ubuntu 16.04

2018-04-25 Thread John Kelly
Hi Eric Did you try starting the slurmctl by itself with slurmctl -Dcv to see what errors it gives ? -jfk On Wed, Apr 25, 2018 at 4:15 PM, Eric F. Alemany wrote: > HI John, > > Each time i enabled/started slurmctld the error was that the > slurmctld.service could not be find or did not exist

Re: [slurm-users] SLURM on Ubuntu 16.04

2018-04-25 Thread Eric F. Alemany
HI John, Each time i enabled/started slurmctld the error was that the slurmctld.service could not be find or did not exist when in fact it existed in the correct directory /etc/systemd/system. Same with slurmdbd.service. __

Re: [slurm-users] SLURM on Ubuntu 16.04

2018-04-25 Thread Patrick Goetz
Hi Eric - Did you follow my suggestion of -- on 18.04, mind you; the packages on 16.04 are too old -- - Install the slurmctld package on the SMS (the master) - Install the slurmd package on the nodes? You'll still need to do some configuration, but my guess is this will pull in the neces

Re: [slurm-users] SLURM on Ubuntu 16.04

2018-04-25 Thread Evan Clark
What issues are you encountering? Building the binaries or getting it running? —Regards,Evan Clark On Wed, Apr 25, 2018 at 5:42 PM -0400, "John Kelly" wrote:

Re: [slurm-users] SLURM on Ubuntu 16.04

2018-04-25 Thread John Kelly
Hi Eric I installed on ubuntu 14.04 and I did use the tar ball. What error did you get ? -jfk On Wed, Apr 25, 2018 at 2:15 PM, Eric F. Alemany wrote: > Hi John, > > Thank you for your reply. > > I followed the steps on the same site and am careful with all the steps > but i still cannot mak

Re: [slurm-users] SLURM on Ubuntu 16.04

2018-04-25 Thread Eric F. Alemany
Hi Evan, Thank you for your message. I saw that website which is well done but i am not familiar with CentOS and RedHat. I get the idea but i dont seem to be able to install and configure SLURM on Ubuntu. Thanks ___

Re: [slurm-users] SLURM on Ubuntu 16.04

2018-04-25 Thread Eric F. Alemany
Hi John, Thank you for your reply. I followed the steps on the same site and am careful with all the steps but i still cannot make it work. Some people say that Ubuntu has packages for SLURM and i dont have to deal with downloading tar ball and make sure that all the files go to the right plac

Re: [slurm-users] SLURM on Ubuntu 16.04

2018-04-25 Thread John Kelly
Hi Eric I found this site very useful https://github.com/mknoxnv/ubuntu-slurm -jfk On Wed, Apr 25, 2018 at 1:01 PM, evan clark wrote: > I would also recommend this guide, it helped quite a bit when getting my > personal cluster online. https://wiki.fysik.dtu.dk/niflheim/SLURM > > One recommen

Re: [slurm-users] SLURM on Ubuntu 16.04

2018-04-25 Thread evan clark
I would also recommend this guide, it helped quite a bit when getting my personal cluster online. https://wiki.fysik.dtu.dk/niflheim/SLURM One recommendation is to have ntp, shared storage for home directories, and LDAP so user ids are synced across machines. Eric F. Alemany

Re: [slurm-users] SLURM on Ubuntu 16.04

2018-04-25 Thread Andy Riebs
Let me recommend to you the excellent "Quick Start" documentation at SchedMD.com -- yours should be a very easy cluster to set up. Andy On 04/25/2018 03:27 PM, Eric F. Alemany wrote: Greetings, New to the forum and new to SLURM. I have 5 servers. 1 can be the master/headnode and 4 can be th

[slurm-users] SLURM on Ubuntu 16.04

2018-04-25 Thread Eric F. Alemany
Greetings, New to the forum and new to SLURM. I have 5 servers. 1 can be the master/headnode and 4 can be the compute node. My goal is to help a post-doc run “jobs” on the cluster and utilizing all the CPU’s and RAM from the 4 compute nodes. The post-doc runs radiation Monte Carlo simulation, R

[slurm-users] Memory oversubscription and sheduling

2018-04-25 Thread Cory Holcomb
Hello Is there a configuration where the scheduler will check for enough free memory on a host before dispatching a job. It appears that I have a configuration that only takes into account the allocated memory before dispatching. My goal is to allow jobs to over use memory but not have other job

[slurm-users] Limit job_submit.lua script for only srun

2018-04-25 Thread sysadmin.caos
Hello, I have written my own job_submit.lua script for limiting "srun" executions to one processor, one task and one node. If I test it with "srun", all works fine. However, if now I try to run a sbatch job with "-N 12" or "-n 2", job_submit.lua is also checked and, then, my job is rejected b