[slurm-users] "Low socket*core*thre" - solution?

[Marcus Wagner]

Dear all,

I must say, I'm a bit dazzled, since this configuration should not be 
valid. This is something, I myself observed. According to the manpage of 
slurm.conf, CPUs and Boards are mutually exclusive:

*Boards*    Number of Baseboards in nodes with a baseboard controller.  
Note that when Boards is specified, SocketsPerBoard, CoresPerSocket, and 
ThreadsPerCore should be specified.  Boards and CPUs  are  mutually  
exclusive.   The default value is 1.


Since I needed to tell slurm to not use the hyperthreads, I halved the 
CPUs value and omitted Boards. This configuration works for me:

NodeName=linuxbmc[0021-0036] CPUs=12 SocketsPerBoard=2 CoresPerSocket=6 
ThreadsPerCore=2 RealMemory=96508 TmpDisk=41035 State=UNKNOWN

Yet I do not know, why these options are mutually exclusive, since from 
my sight of view CPUs is the number of cores/threads, I want slurm to 
schedule. The other values, Boards, SocketsPerBoard, CoresPerSocket and 
ThreadsPerCore are "architectural" values, which should help in placing 
the tasks on the node itself, compare --hint of sbatch.


Best
Marcus


On 05/03/2018 02:28 AM, Matt Hohmeister wrote:
>
> I have a two-node cluster: the server/compute node is a Dell PowerEdge 
> R730; the compute node, a Dell PowerEdge R630. On both of these nodes, 
> slurmd -C gives me the exact same line:
>
> [me at odin slurm]$ slurmd -C
>
> NodeName=odin CPUs=40 Boards=1 SocketsPerBoard=2 CoresPerSocket=10 
> ThreadsPerCore=2 RealMemory=128655
>
> [me at thor slurm]$ slurmd -C
>
> NodeName=thor CPUs=40 Boards=1 SocketsPerBoard=2 CoresPerSocket=10 
> ThreadsPerCore=2 RealMemory=128655
>
> So I edited my slurm.conf appropriately:
>
> NodeName=odin CPUs=40 Boards=1 SocketsPerBoard=2 CoresPerSocket=10 
> ThreadsPerCore=2 RealMemory=128655
>
> NodeName=thor CPUs=40 Boards=1 SocketsPerBoard=2 CoresPerSocket=10 
> ThreadsPerCore=2 RealMemory=128655
>
> …and it looks good, except for the drain on my server/compute node:
>
> [me at odin slurm]$ sinfo
>
> PARTITION AVAIL  TIMELIMIT  NODES  STATE NODELIST
>
> debug* up   infinite      1  drain odin
>
> debug* up   infinite      1   idle thor
>
> …for the following reason:
>
> [me at odin slurm]$ sinfo -R
>
> REASON USER      TIMESTAMP           NODELIST
>
> Low socket*core*thre slurm     2018-05-02T11:55:38 odin
>
> Any ideas?
>
> Thanks!
>
> Matt Hohmeister
>
> Systems and Network Administrator
>
> Department of Psychology
>
> Florida State University
>
> PO Box 3064301
>
> Tallahassee, FL 32306-4301
>
> Phone: +1 850 645 1902
>
> Fax: +1 850 644 7739
>

-- 
Marcus Wagner, Dipl.-Inf.

IT Center
Abteilung: Systeme und Betrieb
RWTH Aachen University
Seffenter Weg 23
52074 Aachen
Tel: +49 241 80-24383
Fax: +49 241 80-624383
wagner at itc.rwth-aachen.de
www.itc.rwth-aachen.de

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.schedmd.com/pipermail/slurm-users/attachments/20180503/287ddfaa/attachment.html>