linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
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
Date: Fri, 15 Apr 2016 04:05:23 +0800	[thread overview]
Message-ID: <20160414200523.GP8697@intel.com> (raw)
In-Reply-To: <570F929B.1070805@arm.com>

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.

  reply	other threads:[~2016-04-15  3:47 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-04-10 22:36 [PATCH 0/4] Optimize sched avg computation and implement flat util hierarchy Yuyang Du
2016-04-10 22:36 ` [PATCH 1/4] sched/fair: Optimize sum computation with a lookup table Yuyang Du
2016-04-11  9:08   ` Vincent Guittot
2016-04-11 10:41   ` Juri Lelli
2016-04-11 19:12     ` Yuyang Du
2016-04-12 10:14       ` Juri Lelli
2016-04-12 18:07         ` Yuyang Du
2016-04-13  9:11           ` Juri Lelli
2016-04-11 16:59   ` Dietmar Eggemann
2016-04-11 19:17     ` Yuyang Du
2016-04-12 14:19       ` Peter Zijlstra
2016-04-12 18:12         ` Yuyang Du
2016-04-11 23:21     ` Joe Perches
2016-04-12 12:02       ` Juri Lelli
2016-04-11 23:07   ` Joe Perches
2016-04-10 22:36 ` [PATCH 2/4] sched/fair: Drop out incomplete current period when sched averages accrue Yuyang Du
2016-04-11  9:08   ` Vincent Guittot
2016-04-11 19:41     ` Yuyang Du
2016-04-12 11:56       ` Vincent Guittot
2016-04-12 21:09         ` Yuyang Du
2016-04-13 11:11           ` Vincent Guittot
2016-04-12 12:02   ` Dietmar Eggemann
2016-04-12 20:14     ` Yuyang Du
2016-04-13  4:04       ` Joe Perches
2016-04-13  8:40       ` Morten Rasmussen
2016-04-13 15:13   ` Dietmar Eggemann
2016-04-13 15:28     ` Vincent Guittot
2016-04-13 16:20       ` Vincent Guittot
2016-04-13 18:44       ` Yuyang Du
2016-04-14 12:52         ` Dietmar Eggemann
2016-04-14 20:05           ` Yuyang Du [this message]
2016-04-18 17:59             ` Yuyang Du
2016-04-10 22:36 ` [PATCH 3/4] sched/fair: Modify accumulated sums for load/util averages Yuyang Du
2016-04-11 17:14   ` Dietmar Eggemann
2016-04-10 22:36 ` [PATCH 4/4] sched/fair: Implement flat hierarchical structure for util_avg Yuyang Du
2016-04-11 12:29   ` Vincent Guittot
2016-04-11 20:37     ` Yuyang Du
2016-04-13 11:27       ` Vincent Guittot
2016-04-13 18:20         ` Yuyang Du

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20160414200523.GP8697@intel.com \
    --to=yuyang.du@intel.com \
    --cc=bsegall@google.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=juri.lelli@arm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=morten.rasmussen@arm.com \
    --cc=peterz@infradead.org \
    --cc=pjt@google.com \
    --cc=vincent.guittot@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).