Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Mon, 1 Mar 2021 18:18:28 +0100
From:   Peter Zijlstra <peterz@infradead.org>
To:     Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc:     Rik van Riel <riel@surriel.com>, Ingo Molnar <mingo@kernel.org>,
        LKML <linux-kernel@vger.kernel.org>,
        Mel Gorman <mgorman@techsingularity.net>,
        Thomas Gleixner <tglx@linutronix.de>,
        Valentin Schneider <valentin.schneider@arm.com>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Michael Ellerman <mpe@ellerman.id.au>,
        Michael Neuling <mikey@neuling.org>,
        Gautham R Shenoy <ego@linux.vnet.ibm.com>,
        Parth Shah <parth@linux.ibm.com>
Subject: Re: [PATCH] sched/fair: Prefer idle CPU to cache affinity
Message-ID: <YD0h5I7qmDO2zlkE@hirez.programming.kicks-ass.net>
References: <20210226164029.122432-1-srikar@linux.vnet.ibm.com>
 <ab046b9d5bcd29b2eb759cd999e2f578a683c673.camel@surriel.com>
 <YD0L6sba9RfXX+tM@hirez.programming.kicks-ass.net>
 <20210301170601.GJ2028034@linux.vnet.ibm.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20210301170601.GJ2028034@linux.vnet.ibm.com>
Precedence: bulk

On Mon, Mar 01, 2021 at 10:36:01PM +0530, Srikar Dronamraju wrote:
> * Peter Zijlstra <peterz@infradead.org> [2021-03-01 16:44:42]:
> 
> > On Sat, Feb 27, 2021 at 02:56:07PM -0500, Rik van Riel wrote:
> > > On Fri, 2021-02-26 at 22:10 +0530, Srikar Dronamraju wrote:
> > 
> > > > +	if (sched_feat(WA_WAKER) && tnr_busy < tllc_size)
> > > > +		return this_cpu;
> > > 
> > > I wonder if we need to use a slightly lower threshold on
> > > very large LLCs, both to account for the fact that the
> > > select_idle_cpu code may not find the single idle CPU
> > > among a dozen busy ones, or because on a system with
> > > hyperthreading we may often be better off picking another
> > > LLC for HT contention issues?
> > > 
> > > Maybe we could use "tnr_busy * 4 <
> > > tllc_size * 3" or
> > > something like that?
> > 
> > How about:
> > 
> > 	tnr_busy < tllc_size / topology_max_smt_threads()
> > 
> > ?
> 
> Isn't topology_max_smt_threads only for x86 as of today?
> Or Am I missing out?

Oh, could be, I didn't grep :/ We could have core code keep track of the
smt count I suppose.