MIME-Version: 1.0
In-Reply-To: <20160316085339.GU6344@twins.programming.kicks-ass.net>
References: <1457932932-28444-1-git-send-email-mturquette+renesas@baylibre.com>
	<1457932932-28444-6-git-send-email-mturquette+renesas@baylibre.com>
	<20160315212520.GF6344@twins.programming.kicks-ass.net>
	<20160315220609.30639.67271@quark.deferred.io>
	<20160316074123.GP6344@twins.programming.kicks-ass.net>
	<CAKfTPtA8hJUT4HGXjoyX4=qh9iup3_GUMwuJGgbXtBFGgAPFdQ@mail.gmail.com>
	<20160316085339.GU6344@twins.programming.kicks-ass.net>
Date: Wed, 16 Mar 2016 13:39:10 +0100
Message-ID: <CAJZ5v0jPtobKGR01D9obxhHibz4aPrPFjmuX19zAE5a5Uz8aEQ@mail.gmail.com>
Subject: Re: [PATCH 5/8] sched/cpufreq: pass sched class into cpufreq_update_util
From: "Rafael J. Wysocki" <rafael@kernel.org>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Vincent Guittot <vincent.guittot@linaro.org>,
        Michael Turquette <mturquette@baylibre.com>,
        "rjw@rjwysocki.net" <rjw@rjwysocki.net>,
        linux-kernel <linux-kernel@vger.kernel.org>,
        "linux-pm@vger.kernel.org" <linux-pm@vger.kernel.org>,
        Juri Lelli <Juri.Lelli@arm.com>,
        Steve Muckle <steve.muckle@linaro.org>,
        Morten Rasmussen <morten.rasmussen@arm.com>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Michael Turquette <mturquette+renesas@baylibre.com>
Content-Type: text/plain; charset=UTF-8
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 939
Lines: 19

On Wed, Mar 16, 2016 at 9:53 AM, Peter Zijlstra <peterz@infradead.org> wrote:
> On Wed, Mar 16, 2016 at 09:29:59AM +0100, Vincent Guittot wrote:
>> I wonder if it's really worth passing per sched_class request to
>> sched_util ? sched_util is about selecting a frequency based on the
>> utilization of the CPU, it only needs a value that reflect the whole
>> utilization. Can't we sum  (or whatever the formula we want to apply)
>> utilizations before calling cpufreq_update_util
>
> So I've thought the same; but I'm conflicted, its a shame to compute
> anything if the call then doesn't do anything with it.
>
> And keeping a structure of all the various numbers to pass in also has
> cost of yet another cacheline to touch.

In principle we can use high-order bits of util and max to encode the
information on where they come from.

Of course, that translates to additional ifs in the governor, but I
guess they are unavoidable anyway.