Date: Fri, 28 Oct 2016 11:23:08 +0200
From: Peter Zijlstra <peterz@infradead.org>
To: Vikram Mulukutla <markivx@codeaurora.org>
Cc: linux-kernel@vger.kernel.org, Ingo Molnar <mingo@kernel.org>,
        Srivatsa Vaddagiri <vatsa@codeaurora.org>,
        Steve Muckle <steve.muckle@linaro.org>,
        Olav Haugan <ohaugan@codeaurora.org>,
        Syed Rameez Mustafa <rameezmustafa@codeaurora.org>,
        Joonwoo Park <joonwoop@codeaurora.org>,
        Pavankumar Kondeti <pkondeti@codeaurora.org>,
        Saravana Kannan <skannan@codeaurora.org>,
        Bryan Huntsman <bryanh@codeaurora.org>,
        Juri Lelli <juri.lelli@arm.com>,
        Morten Rasmussen <morten.rasmussen@arm.com>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Chris Redpath <chris.redpath@arm.com>,
        Robin Randhawa <robin.randhawa@arm.com>,
        Patrick Bellasi <patrick.bellasi@arm.com>,
        Todd Kjos <tkjos@google.com>, Srinath Sridharan <srinathsr@google.com>,
        Andres Oportus <andresoportus@google.com>,
        Leo Yan <leo.yan@linaro.org>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Vikram Mulukutla <markivx@codeauorora.org>
Subject: Re: [RFC PATCH 0/3] sched: Introduce Window Assisted Load Tracking
Message-ID: <20161028092308.GZ3102@twins.programming.kicks-ass.net>
References: <1477638642-17428-1-git-send-email-markivx@codeaurora.org>
 <20161028072949.GQ3102@twins.programming.kicks-ass.net>
 <107c17a07b42bb5aa9039600db4a47a5@codeaurora.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <107c17a07b42bb5aa9039600db4a47a5@codeaurora.org>
User-Agent: Mutt/1.5.23.1 (2014-03-12)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1715
Lines: 35

On Fri, Oct 28, 2016 at 12:55:52AM -0700, Vikram Mulukutla wrote:
> On 2016-10-28 00:29, Peter Zijlstra wrote:
> >On Fri, Oct 28, 2016 at 12:10:39AM -0700, Vikram Mulukutla wrote:
> >>
> >>We propose Window-Assisted Load Tracking (WALT) as an alternative or
> >>additional load tracking scheme in lieu of or along with PELT, one
> >>that in our estimation better tracks task demand and CPU utilization
> >>especially for use cases on mobile devices. WALT was conceived by
> >>Srivatsa Vaddagiri to provide better perf-per-watt numbers on
> >>asymmetric CPU (frequency and/or IPC) implementations, (specifically
> >>on Qualcomm Snapgdragon chipsets running Android) and its metrics
> >>have been used to guide task placement and p-state selection (load
> >>balancing in CFS still uses PELT statistics). WALT is now present in
> >>the android-common kernel as well.
> >
> >And how come we only learn of it after its already shipping? Isn't that
> >arse backwards?
> 
> Yes, but also we were not confident that it would be close to being
> acceptable
> upstream since it was intricately tied to our HMP scheduler. However now
> that
> more parties including the folks at ARM are interested, and given that EAS
> exists and schedutil was merged into mainline, we felt it the right time
> to try and introduce the concept. In general we are seriously trying to get
> more things upstream and converge.

That's good to hear, great!

That said, I would much prefer to modify/augment existing PELT stuff
than to add an entirely new set of accounting on the side of it. But
yes, I (and others) are aware of the pain points you mentioned with
using the PELT signal for schedutil.

We'll have to see what we can come up with.