Ticket 16523

Summary:	Limiting the number of jobs and cores per user per partition
Product:	Slurm	Reporter:	Navneet Khetrapal <navneet.khetrapal>
Component:	Limits	Assignee:	Jacob Jenson <jacob>
Status:	OPEN ---	QA Contact:
Severity:	6 - No support contract
Priority:	---
Version:	21.08.8
Hardware:	Linux
OS:	Linux
Site:	-Other-	Alineos Sites:	---
Atos/Eviden Sites:	---	Confidential Site:	---
Coreweave sites:	---	Cray Sites:	---
DS9 clusters:	---	HPCnow Sites:	---
HPE Sites:	---	IBM Sites:	---
NOAA SIte:	---	NoveTech Sites:	---
Nvidia HWinf-CS Sites:	---	OCF Sites:	---
Recursion Pharma Sites:	---	SFW Sites:	---
SNIC sites:	---	Tzag Elita Sites:	---
Linux Distro:	Rocky Linux	Machine Name:	Cruntch4
CLE Version:		Version Fixed:
Target Release:	---	DevPrio:	---
Emory-Cloud Sites:	---

Description Navneet Khetrapal 2023-04-13 15:05:44 MDT

Hi Everyone,

I am having trouble in enforcing limits on maximum number of jobs and cores per user per partition. I tired using QOS for this purpose on one partition:

1) Created a test account: 
sacctmgr add account testac

2) Added a user to the account:
sacctmgr add user nsk0051 account=testac

3) Added a qos:
sacctmgr add qos share.64

4) Limited the number of jobs and CPUs for the qos:
sacctmgr modify qos share.64 set GrpJobs=1 GrpTRES=cpu=64

5)sacctmgr show qos share.64 format=name,GrpJobs,GrpTRES
      Name GrpJobs       GrpTRES
---------- ------- -------------
  share.64       1        cpu=64

6) Added QOS=share.64 and AccountingStorageEnforce=qos to partition line in slurm.conf 

Ideally the maximum running jobs should be 1 and cpus should be 64 in this case. But users able to exceed this. The QOS limits don't seem to imposed.  Can anyone help me to please resolve this issue ?