We have a cluster with multi-core nodes (168) that can be shared by
multiple jobs at the same time. How do I configure a partition such that
it only accepts jobs requesting up to (say) 8 cores, but will run
multiple jobs at the same time? The following is apparently not working:
PartitionName=debug Nodes=node01 MaxTime=02:00:00 DefMemPerCPU=1000
MaxCPUsPerNode=8 Default=NO
It allows one job using 8 cores, but a second one will not start because
the limit is apparently for the partition as a whole.
Thanks in advance,
Herbert
--
Herbert Fruchtl (he/him)
Senior Scientific Computing Officer / HPC Administrator
School of Chemistry, IT Services
University of St Andrews
--
The University of St Andrews is a charity registered in Scotland:
No SC013532
--
slurm-users mailing list -- slurm-users@lists.schedmd.com
To unsubscribe send an email to slurm-users-leave@lists.schedmd.com