[PATCH RESEND 0/3] Represent cluster topology and enable load balance between clusters

[Barry Song]

On Tue, Oct 5, 2021 at 8:50 PM Peter Zijlstra <peterz at infradead.org> wrote:
>
> On Fri, Oct 01, 2021 at 04:22:46PM -0700, Tim Chen wrote:
> > On Fri, 2021-10-01 at 16:57 +0200, Peter Zijlstra wrote:
>
> > > The one questino I have is, do we want default y?
> >
> > I also agree that default y is preferable.
>
> I'll change at least the x86 one to:
>
>         default y
>         depends on SMP
>
> > > The one nit I have is the Kconfig text, I'm not really sure that's
> > > clarifying what a cluster is.
> >
> > Do you have a preference of a different name other than cluster?
> > Or simply better documentation on what a cluster is for ARM64
> > and x86 in Kconfig?
>
> Yes, better wording as to what a cluster is. Currently the x86 and arm64
> ones actually differ:
>
> x86:
>         help
>          Cluster scheduler support improves the CPU scheduler's decision
>          making when dealing with machines that have clusters of CPUs
>          sharing L2 cache. If unsure say N here.
>
> arm64:
>         help
>           Cluster scheduler support improves the CPU scheduler's decision
>           making when dealing with machines that have clusters(sharing internal
>           bus or sharing LLC cache tag). If unsure say N here.
>
>
> (also, all this stuff being replicated across arch/*/Kconfig seems
> unfortunate)

perhaps worth a separate patchset to do some cleanup so that SCHED_MC,
SCHED_SMT etc
won't be replicated in different architectures. Right now, this kind
of Kconfig option is copied
everywhere. I am seeing SCHED_SMT in all of
arch/arm/Kconfig
arch/arm64/Kconfig
arch/ia64/Kconfig
arch/mips/Kconfig
arch/powerpc/Kconfig
arch/s390/Kconfig
arch/sparc/Kconfig
arch/x86/Kconfig
...

Is it a better way to move them to a common Kconfig and let the architectures to
declare things like ARCH_HAVE_SMT?

Thanks
Barry