Re: [PATCH 1/2] x86/CPU/AMD: Present package as die instead of socket

[Borislav Petkov]

On Tue, Jun 27, 2017 at 06:32:34PM +0000, Ghannam, Yazen wrote:
> > you want all those threads to belong to a single scheduling group.
> > Correct?
> > 
> > Now that thing has a memory controller attached to it, correct?
> > 
> > If so, why is this thing not a logical NUMA node, as described in SRAT/SLIT?
> > 
> > If not, what does a NUMA node entail on Zen as described by SRAT/SLIT?
> > I.e., what is the difference between the two things? I.e., how many dies as
> > above are in a NUMA node?
> > 
> > Now, SRAT should contain the assignment which core belongs to which node.
> > Why is that not sufficient?
> > 
> > Ok, that should be enough questions for now. Let's start with them.
> > 
> 
> This group is a NUMA node. It is the "identity" NUMA node. Linux skips the

Please be more specific. Which group exactly? Which question above are
you answering?

> identity NUMA node when finding the NUMA levels. This is fine as long as the
> MC domain is equivalent to the identity NUMA node. However, this is not the
> case on Zen systems.
> 
> We could patch the sched/topology.c to not skip the identity NUMA node.
> Though this will affect all systems not just AMD.

We can always add a X86_FEATURE flag but we need to agree on what you
guys are actually trying to change and why?

-- 
Regards/Gruss,
    Boris.

Good mailing practices for 400: avoid top-posting and trim the reply.