public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Rik van Riel <riel@redhat.com>,
	linux-kernel <linux-kernel@vger.kernel.org>,
	Michael Neuling <mikey@neuling.org>,
	Ingo Molnar <mingo@kernel.org>,
	jhladky@redhat.com, ktkhai@parallels.com,
	tim.c.chen@linux.intel.com,
	Nicolas Pitre <nicolas.pitre@linaro.org>
Subject: Re: [PATCH 1/2] sched: fix and clean up calculate_imbalance
Date: Tue, 29 Jul 2014 16:59:10 +0200	[thread overview]
Message-ID: <20140729145910.GH3935@laptop> (raw)
In-Reply-To: <CAKfTPtDuFLOf3Kzt4PSdox3HpBoz9aWXb-QzkibAL-Z4xBm=tw@mail.gmail.com>

On Tue, Jul 29, 2014 at 11:04:50AM +0200, Vincent Guittot wrote:
> > In situations where all the domains are overloaded, or where only the
> > busiest domain is overloaded, that code is also superfluous, since
> > the normal env->imbalance calculation will figure out how much to move.
> > Remove the load_above_capacity calculation.
> 
> IMHO, we should not remove that part which is used by prefer_sibling
> 
> Originally, we had 2 type of busiest group: overloaded or imbalanced.
> You add a new one which has only a avg_load higher than other so you
> should handle this new case and keep the other ones unchanged

Right, so we want that code for overloaded -> overloaded migrations such
as not to cause idle cpus in an attempt to balance things. Idle cpus are
worse than imbalance.

But in case of overloaded/imb -> !overloaded migrations we can allow it,
and in fact want to allow it in order to balance idle cpus.

  parent reply	other threads:[~2014-07-29 14:59 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-07-28 18:16 [PATCH 0/2] load balancing fixes riel
2014-07-28 18:16 ` [PATCH 1/2] sched: fix and clean up calculate_imbalance riel
2014-07-29  9:04   ` Vincent Guittot
2014-07-29 14:53     ` Rik van Riel
2014-07-29 15:31       ` Vincent Guittot
2014-07-29 15:39         ` Rik van Riel
2014-07-29 14:59     ` Peter Zijlstra [this message]
2014-07-29 15:15       ` Rik van Riel
2014-07-29 15:49         ` Peter Zijlstra
2014-07-29 17:04           ` Rik van Riel
2014-07-29 15:27       ` Peter Zijlstra
2014-07-30  9:32         ` Vincent Guittot
2014-07-30 10:13           ` Peter Zijlstra
2014-08-12 14:52         ` [tip:sched/core] sched/fair: Allow calculate_imbalance() to move idle cpus tip-bot for Peter Zijlstra
2014-07-29 14:49   ` [PATCH 1/2] sched: fix and clean up calculate_imbalance Peter Zijlstra
2014-07-29 14:53     ` Peter Zijlstra
2014-07-29 15:26       ` Peter Zijlstra
2014-08-12 14:52         ` [tip:sched/core] sched/fair: Make calculate_imbalance() independent tip-bot for Peter Zijlstra
2014-07-28 18:16 ` [PATCH 2/2] sched: make update_sd_pick_busiest return true on a busier sd riel
2014-07-29 15:27   ` Peter Zijlstra
2014-08-12 14:52     ` [tip:sched/core] sched/fair: Make update_sd_pick_busiest() return 'true' " tip-bot for Rik van Riel

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=20140729145910.GH3935@laptop \
    --to=peterz@infradead.org \
    --cc=jhladky@redhat.com \
    --cc=ktkhai@parallels.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mikey@neuling.org \
    --cc=mingo@kernel.org \
    --cc=nicolas.pitre@linaro.org \
    --cc=riel@redhat.com \
    --cc=tim.c.chen@linux.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox