It would be cool if CPUEfctv was available as an environment variable? Maybe worth opening an issue?
I am of course assuming that the job gets a set of nodes with a consistent CPUEfctv which leads me to an idiot question - how do jobs get node information if you request N nodes with --exclusive but the nodes have differing CPU core counts On Thu, 21 May 2026 at 03:05, Dan Healy via slurm-users < [email protected]> wrote: > I think I've found my answer. When running `scontrol show node <node>` I > can use the variable called `CPUEfctv` to represent exactly how many > effective schedulable CPUs are available. I'll probably wrap this up into a > helper script too for our users plus add to our documentation. > > On Tue, May 19, 2026 at 1:45 PM Dan Healy <[email protected]> > wrote: > >> I'm curious how to report to our users that the number of available CPU >> cores on a given node are *(CoresPerSocket * SocketsPerBoard * >> ThreadsPerCore) - CpuSpecCount*. In a basic example, if the node has 32 >> cores and CpuSpecCount=1, then there's actually 31 cores available. If a >> user runs `srun -n32 -N1 bash` he/she will be denied for resources. Then, >> If a user runs `sinfo -O cpus,nodes` shows there's 32 cores available and >> the user is confused. >> >> How can the user clearly identify that in the above case, the exact >> number of available CPU cores available are 31 and *not* 32? >> >> -- >> Thanks, >> >> Daniel Healy >> > > > -- > Thanks, > > Daniel Healy > > -- > slurm-users mailing list -- [email protected] > To unsubscribe send an email to [email protected] >
-- slurm-users mailing list -- [email protected] To unsubscribe send an email to [email protected]
