Peter,

I'm fairly new to SLURM so someone else can feel free to correct me if I'm
wrong, but, I think:
num_cpus_per_node = num_sockets * num_cores_per_socket *
num_threads_per_core

Currently, you have it configured for 4 CPUs.  You should set your
partition configuration to Sockets = 4, CoresPerSocket=12, ThreadsPerCore=1
and that should help.  Check out the documentation for the partition
definition for slurm.conf
http://slurm.schedmd.com/slurm.conf.html#OPT_NodeName starting there, it
should help.

Also consider switching to select/cons_res for more per-core allocation
rather than per-node.  select/linear is only per-node.

On Mon, Apr 20, 2015 at 8:25 PM, Peter Van Buren <[email protected]> wrote:

>  Hello,
>
> I am new to slurm and just started running it on a single node with 4 x 12
> core CPU's (48 physical cores total) and 1TB of memory. I set the following
> in slurm.conf:
> Under scheduling I have:
>
> SchedulerType=sched/backfill
> SelectType=select/linear
>
> and under the NodeName section:
>
> CPUs=4  Sockets=4 CoresPerSocket=12  Shared=FORCE
>
> When I run sinfo --format "%z %h"
> the output is:
>
>  S:C:T     SHARE
> 4:12:1    FORCE:4
>
>
> I am able to submit and run jobs, but no more than 4 will run at one time.
> The 5th job is queued waiting for resources.
> It looks like something is setting a maximum of 4 jobs to run concurrently
> (maybe one per CPU). I'm not sure where this limitation is set. There
> should be plenty of free cores
> and memory available. Should I be setting CR_ONE_TASK_PER_CORE?
>
> Is there a way to specify the number of jobs that can be run concurrently
> on a single shared node (assuming available resources)?
>
> Thanks,
>
> Peter.
>
>

Reply via email to