Re: [HTCondor-users] Future improvements to NUMA affinity algorithms

[Jaime Frey <jfrey@xxxxxxxxxxx>]

My suspicion is that this wonât have much effect on the difference in CPU scheduling efficiency between ASSIGN_CPU_AFFINITY and cgroups for enforcing CPU usage limitations.
HTCondor will still ignore NUMA locality when selecting which cores to assign to a job.
And ASSIGN_CPU_AFFINITY doesnât allow a job to use additional cores when theyâre idle (if job has more processes/threads than assigned cores).

 - Jaime

> On Jul 30, 2025, at 4:00âAM, Valerio Bellizzomi <valerio@xxxxxxxxxx> wrote:
> 
> Today on Phoronix I read this:
> 
> https://urldefense.com/v3/__https://www.phoronix.com/news/Linux-6.17-NUMA-Locality-Random__;!!Mak6IKo!PqQT_f5zicZdSyBzgbJkmFMR5W6nhqLtSL4Z-QzBjNtrZErhK1QMrAFKCgpblPubjZHjM9saI78BCD8wXg$ 
> 
> 
> Should this improve things when using the ASSIGN_CPU_AFFINITY knob, and
> perhaps without forcing things via cgroups ?
> 
> 
> Thanks
> Valerio
>