[slurm-users] Slurm 20.02.3 error: CPUs=1 match no Sockets, Sockets*CoresPerSocket or Sockets*CoresPerSocket*ThreadsPerCore. Resetting CPUs.

[Ole Holm Nielsen]

Hi Ahmet,

On 6/16/20 11:27 AM, mercan wrote:
> Did you check /var/log/messages file for errors. Systemctl logs this file, 
> instead of the slurmctl log file.
> 
> Ahmet M.

The syslog reports the same errors from slurmctld as are being reported by 
every Slurm 20.02 command.

I have found a workaround:  Replace NodeName lines "Boards=1 
SocketsPerBoard=2" by "Sockets=2" in slurm.conf and reconfigure the 
daemons.  For some reason 20.02 doesn't handle "Boards" configurations 
correctly.

Any site with "Boards" in slurm.conf should reconfigure to "Sockets" 
before installing/upgrading to 20.02.

It may be a good idea to track updates to bug 
https://bugs.schedmd.com/show_bug.cgi?id=9241

Best regards,
Ole

> 16.06.2020 11:12 tarihinde Ole Holm Nielsen yazdı:
>> Today we upgraded the controller node from 19.05 to 20.02.3, and 
>> immediately all Slurm commands (on the controller node) give error 
>> messages for all partitions:
>>
>> # sinfo --version
>> sinfo: error: NodeNames=a[001-140] CPUs=1 match no Sockets, 
>> Sockets*CoresPerSocket or Sockets*CoresPerSocket*ThreadsPerCore. 
>> Resetting CPUs.
>> (lines deleted)
>> slurm 20.02.3
>>
>> In slurm.conf we have defined NodeName like:
>>
>> NodeName=a[001-140] Weight=10001 Boards=1 SocketsPerBoard=2 
>> CoresPerSocket=4 ThreadsPerCore=1 ...
>>
>> According to the slurm.conf manual the CPUs should then be calculated 
>> automatically:
>>
>> "If CPUs is omitted, its default will be set equal to the product of 
>> Boards, Sockets, CoresPerSocket, and ThreadsPerCore."
>>
>> Has anyone else seen this error with Slurm 20.02?
>>
>> I wonder if there is a problem with specifying SocketsPerBoard in stead 
>> of Sockets?  The slurm.conf manual doesn't seem to prefer one over the 
>> other.
>>
>> I've opened a bug https://bugs.schedmd.com/show_bug.cgi?id=9241