All of lore.kernel.org
 help / color / mirror / Atom feed
From: Yuyang Du <yuyang.du@intel.com>
To: Vincent Guittot <vincent.guittot@linaro.org>
Cc: peterz@infradead.org, mingo@redhat.com,
	linux-kernel@vger.kernel.org, pjt@google.com, bsegall@google.com,
	arjan.van.de.ven@intel.com, len.brown@intel.com,
	rafael.j.wysocki@intel.com, alan.cox@intel.com,
	mark.gross@intel.com, fengguang.wu@intel.com,
	morten.rasmussen@arm.com
Subject: Re: [PATCH 2/2 v4] sched: Rewrite per entity runnable load average
Date: Fri, 1 Aug 2014 03:16:38 +0800	[thread overview]
Message-ID: <20140731191638.GG28673@intel.com> (raw)
In-Reply-To: <1406800573-9692-1-git-send-email-vincent.guittot@linaro.org>

Hi Vincent,

On Thu, Jul 31, 2014 at 11:56:13AM +0200, Vincent Guittot wrote:
> 
> load_sum is now the average runnable time before being weighted
 
So when weight changes, load_avg will completely use new weight. I have
some cents:

1) Task does not change weight much, so it is practically ok

2) Group entity does change weight much, and very likely back and forth,
   so I really think keeping the intact history will make everything
   more predictable/stable, prevent thrashing, etc.

3) If you do the same for cfs_rq->load.weight, then we simply abandoned
   blocked entities, and all states won't compute. So we then need to
   maintain blocked load average again, and we just can't do cfs_rq load
   average as a whole anymore, but must update at the granularity of an
   entity...

Anyway, it does not seem to me you really need to change load_sum, no? So
could you please not change it?

> The sum of usage_sum of the tasks that are on a rq, is used to detect
> the overload of a rq.

I think you only need usage_sum for task and rq, but not cfs_rq. Others
are ok.
 
> Does something like the patch below to be applied of top of your patchset, seem
> reasonable add-on?
> 

If you only add running statistics, I am all good, and indeed reasonable if
you can make good use of it. I am not at all against adding anything or
adding running average or unweighted anything...

Thanks,
Yuyang

  reply	other threads:[~2014-08-01  3:18 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-07-17 23:26 [PATCH 0/2 v4] sched: Rewrite per entity runnable load average tracking Yuyang Du
2014-07-17 23:26 ` [PATCH 1/2 v4] sched: Remove update_rq_runnable_avg Yuyang Du
2014-07-17 23:26 ` [PATCH 2/2 v4] sched: Rewrite per entity runnable load average tracking Yuyang Du
2014-07-18  9:43   ` Vincent Guittot
2014-07-27 17:36     ` Yuyang Du
2014-07-29  9:12       ` Vincent Guittot
2014-07-29  1:43         ` Yuyang Du
2014-07-29 13:17           ` Vincent Guittot
2014-07-29 22:27             ` Yuyang Du
2014-07-30  8:30               ` Peter Zijlstra
2014-07-30  0:40                 ` Yuyang Du
2014-07-29  9:39         ` Peter Zijlstra
2014-07-29  1:53           ` Yuyang Du
2014-07-29 13:35             ` Peter Zijlstra
2014-07-29 15:55               ` Peter Zijlstra
2014-07-29 23:08               ` Yuyang Du
2014-07-31  9:40             ` Vincent Guittot
2014-07-31  9:56             ` [PATCH 2/2 v4] sched: Rewrite per entity runnable load average Vincent Guittot
2014-07-31 19:16               ` Yuyang Du [this message]
2014-08-01  9:28                 ` Vincent Guittot
2014-07-28 10:48   ` [PATCH 2/2 v4] sched: Rewrite per entity runnable load average tracking Peter Zijlstra
2014-07-29  0:56     ` Yuyang Du
2014-07-29 13:15       ` Peter Zijlstra
2014-07-28 11:39   ` Peter Zijlstra
2014-07-29  1:09     ` Yuyang Du
2014-07-29 13:19       ` Peter Zijlstra
2014-07-28 12:01   ` Peter Zijlstra
2014-07-28 13:51   ` Peter Zijlstra
2014-07-28 16:58     ` bsegall
2014-07-28 17:19       ` Peter Zijlstra
2014-07-29  1:13         ` Yuyang Du
2014-07-18 15:39 ` [PATCH 0/2 " Morten Rasmussen
2014-07-27 19:02   ` Yuyang Du
2014-07-28 10:38     ` Peter Zijlstra
2014-07-29  1:17       ` Yuyang Du
2014-07-29 13:06         ` Peter Zijlstra
2014-07-30 10:13     ` Morten Rasmussen
2014-07-30 10:21       ` Peter Zijlstra
2014-07-30 10:57         ` Morten Rasmussen
2014-07-30 19:17       ` Yuyang Du
2014-07-31  8:54         ` Morten Rasmussen
2014-07-31  2:15           ` Yuyang Du
2014-07-20  5:46 ` Mike Galbraith
2014-07-27 19:34   ` Yuyang Du
2014-07-28  7:49     ` Mike Galbraith
2014-07-28  0:01       ` Yuyang Du
2014-07-28  8:55     ` Peter Zijlstra

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=20140731191638.GG28673@intel.com \
    --to=yuyang.du@intel.com \
    --cc=alan.cox@intel.com \
    --cc=arjan.van.de.ven@intel.com \
    --cc=bsegall@google.com \
    --cc=fengguang.wu@intel.com \
    --cc=len.brown@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.gross@intel.com \
    --cc=mingo@redhat.com \
    --cc=morten.rasmussen@arm.com \
    --cc=peterz@infradead.org \
    --cc=pjt@google.com \
    --cc=rafael.j.wysocki@intel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.