[slurm-users] Where to adjust the memory limit from sinfo vs free command?
Renfro, Michael
Renfro at tntech.edu
Thu May 16 22:19:09 UTC 2019
Should be set on your NodeName lines in slurm.conf. For a 256 GB node, I’ve got:
NodeName=node038 CoresPerSocket=14 RealMemory=254000 Sockets=2 ThreadsPerCore=1
so that users can’t reserve every bit of physical memory, leaving a small amount for OS operation.
> On May 16, 2019, at 3:47 PM, Robert Kudyba <rkudyba at fordham.edu> wrote:
>
> External Email Warning
> This email originated from outside the university. Please use caution when opening attachments, clicking links, or responding to requests.
> The MEMORY limit here shows 1, which I believe is 1 MB? But the results of the free command clearly shows we have more than that. Where is this configured?
>
> sinfo -lNe
> Thu May 16 16:41:23 2019
> NODELIST NODES PARTITION STATE CPUS S:C:T MEMORY TMP_DISK WEIGHT AVAIL_FE REASON
> node001 1 defq* idle 24 2:12:1 1 0 1 (null) none
> node002 1 defq* idle 24 2:12:1 1 0 1 (null) none
> node003 1 defq* idle 24 2:12:1 1 0 1 (null) none
> [rkudyba at ciscluster ~]$ squeue
> JOBID PARTITION NAME USER ST TIME NODES NODELIST(REASON)
>
> free -h
> total used free shared buff/cache available
> Mem: 187G 7.8G 128G 992M 50G 176G
> Swap: 15G 3.3G 12G
> [rkudyba at ciscluster ~]$ srun -N 3 free -h
> total used free shared buff/cache available
> Mem: 187G 4.5G 147G 1.8G 35G 179G
> Swap: 11G 382M 11G
> total used free shared buff/cache available
> Mem: 187G 4.5G 145G 1.6G 36G 179G
> Swap: 11G 658M 11G
> total used free shared buff/cache available
> Mem: 187G 95G 78G
More information about the slurm-users
mailing list