Re: [RFC/PATCH] powerpc/smp: Add SD_SHARE_PKG_RESOURCES flag to MC sched-domain

From: Mel Gorman <mgorman@techsingularity.net>
To: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>,
	Michael Ellerman <mpe@ellerman.id.au>,
	Michael Neuling <mikey@neuling.org>,
	Rik van Riel <riel@surriel.com>,
	Valentin Schneider <valentin.schneider@arm.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Nicholas Piggin <npiggin@gmail.com>,
	Anton Blanchard <anton@ozlabs.org>,
	Parth Shah <parth@linux.ibm.com>,
	Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>,
	LKML <linux-kernel@vger.kernel.org>,
	linuxppc-dev@lists.ozlabs.org
Subject: Re: [RFC/PATCH] powerpc/smp: Add SD_SHARE_PKG_RESOURCES flag to MC sched-domain
Date: Mon, 12 Apr 2021 10:37:22 +0100	[thread overview]
Message-ID: <20210412093722.GS3697@techsingularity.net> (raw)
In-Reply-To: <20210412062436.GB2633526@linux.vnet.ibm.com>

On Mon, Apr 12, 2021 at 11:54:36AM +0530, Srikar Dronamraju wrote:
> * Gautham R. Shenoy <ego@linux.vnet.ibm.com> [2021-04-02 11:07:54]:
> 
> > 
> > To remedy this, this patch proposes that the LLC be moved to the MC
> > level which is a group of cores in one half of the chip.
> > 
> >       SMT (SMT4) --> MC (Hemisphere)[LLC] --> DIE
> > 
> 
> I think marking Hemisphere as a LLC in a P10 scenario is a good idea.
> 
> > While there is no cache being shared at this level, this is still the
> > level where some amount of cache-snooping takes place and it is
> > relatively faster to access the data from the caches of the cores
> > within this domain. With this change, we no longer see regressions on
> > P10 for applications which require single threaded performance.
> 
> Peter, Valentin, Vincent, Mel, etal
> 
> On architectures where we have multiple levels of cache access latencies
> within a DIE, (For example: one within the current LLC or SMT core and the
> other at MC or Hemisphere, and finally across hemispheres), do you have any
> suggestions on how we could handle the same in the core scheduler?
> 

Minimally I think it would be worth detecting when there are multiple
LLCs per node and detecting that in generic code as a static branch. In
select_idle_cpu, consider taking two passes -- first on the LLC domain
and if no idle CPU is found then taking a second pass if the search depth
allows within the node with the LLC CPUs masked out. While there would be
a latency hit because cache is not shared, it would still be a CPU local
to memory that is idle. That would potentially be beneficial on Zen*
as well without having to introduce new domains in the topology hierarchy.

-- 
Mel Gorman
SUSE Labs