Date: Fri, 15 Apr 2016 04:05:23 +0800
From: Yuyang Du <yuyang.du@intel.com>
To: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>,
        Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@kernel.org>,
        linux-kernel <linux-kernel@vger.kernel.org>,
        Benjamin Segall <bsegall@google.com>, Paul Turner <pjt@google.com>,
        Morten Rasmussen <morten.rasmussen@arm.com>,
        Juri Lelli <juri.lelli@arm.com>
Subject: Re: [PATCH 2/4] sched/fair: Drop out incomplete current period when
 sched averages accrue
Message-ID: <20160414200523.GP8697@intel.com>
References: <1460327765-18024-1-git-send-email-yuyang.du@intel.com>
 <1460327765-18024-3-git-send-email-yuyang.du@intel.com>
 <570E61FE.4060000@arm.com>
 <CAKfTPtCc3t+g7hESEJ53EnwzvOGr+oE_NF=eOvq0YVo-YXN=HQ@mail.gmail.com>
 <20160413184412.GO8697@intel.com>
 <570F929B.1070805@arm.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <570F929B.1070805@arm.com>
User-Agent: Mutt/1.5.21 (2010-09-15)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1591
Lines: 48

Hi Dietmar,

On Thu, Apr 14, 2016 at 01:52:43PM +0100, Dietmar Eggemann wrote:
> On 13/04/16 19:44, Yuyang Du wrote:
> > On Wed, Apr 13, 2016 at 05:28:18PM +0200, Vincent Guittot wrote:
> 
> [...]
> 
> > By "bailing out", you mean return without update because the delta is less
> > than 1ms?
> 
> yes.
> 
> > 
> >>> Examples of 1 periodic task pinned to a cpu on an ARM64 system, HZ=250
> >>> in steady state:
> >>>
> >>> (1) task runtime = 100us period = 200us
> >>>
> >>>   pelt          load/util signal
> >>>
> >>>   1us:          488-491
> >>>
> >>>   1ms:          483-534
> > 
> > 100us/200us = 50%, so the util should center around 512, it seems in this
> > regard, it is better, but the variance is undesirable.
> 
> I see. You mentioned the over-decay thing in the patch header. Is this
> also why you change the contribution of the most recent period from 1002
> (1024*y) to 1024?

Yes, it is because that (most recent) period is the "current" period.
 
> This variance gets worse if the ratio runtime/period is further reduced
> (e.g. 25us/1000us).
> 
> You can even create tasks which go stealth mode (e.g. 25us/1048us).

En... this is a good case to beat it.

> It shows periods of 0 load/util (~1.55s) and than massive spikes (~700 for
> ~300ms). The short runtime and the task period synced to 1024*1024ns
> allow that we hit consecutive enqueues or dequeues for a long time even
> the task might drift relative to the pelt window.

But whenever we pass 1ms, we will update. And I am curious, how does the
current 1us works in this case? Anyway, I will reproduce it myself.