mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Mike Galbraith <umgwanakikbuti@gmail.com>
To: Rik van Riel <riel@redhat.com>
Cc: linux-kernel@vger.kernel.org, morten.rasmussen@arm.com,
	mingo@kernel.org, peterz@infradead.org,
	george.mccollister@gmail.com, ktkhai@parallels.com
Subject: Re: [PATCH RFC/TEST] sched: make sync affine wakeups work
Date: Fri, 02 May 2014 08:51:09 +0200	[thread overview]
Message-ID: <1399013469.5233.85.camel@marge.simpson.net> (raw)
In-Reply-To: <1399012619.5233.76.camel@marge.simpson.net>

On Fri, 2014-05-02 at 08:36 +0200, Mike Galbraith wrote:

> Reason why is that case was on a box where FAIR_SLEEPERS is disabled by
> default, meaning there is no such thing as wakeup preemption.  Guess
> what happens when you don't have shared LLC for a fast/light wakee to
> escape to when the waker is a pig.  The worst thing possible in that
> case is to wake affine.  Leave the poor thing wherever it was, else it
> will take a latency hit that need not have been.

Oh yeah, and you'll see similar issues playing with kvm.  No escape
routes are available, as no llc domain exists.  Globally do a sync
wakeup CPU affine, and for some loads that will induce massive wreckage
where as If select_isle_sibling() had been there to save the day, all
would have been peachy.  Is it good, or is it evil... depends.

-Mike


  reply	other threads:[~2014-05-02  6:51 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-05-02  4:42 Rik van Riel
2014-05-02  5:32 ` Mike Galbraith
2014-05-02  5:41   ` Mike Galbraith
2014-05-02  5:58   ` Mike Galbraith
2014-05-02  6:08     ` Rik van Riel
2014-05-02  6:36       ` Mike Galbraith
2014-05-02  6:51         ` Mike Galbraith [this message]
2014-05-02  6:13 ` Mike Galbraith
2014-05-02  6:30   ` Rik van Riel
2014-05-02  7:37     ` Mike Galbraith
2014-05-02 10:56       ` Rik van Riel
2014-05-02 11:27         ` Mike Galbraith
2014-05-02 12:51           ` Mike Galbraith
     [not found]           ` <5363B793.9010208@redhat.com>
2014-05-06 11:54             ` Peter Zijlstra
2014-05-06 20:19               ` Rik van Riel
2014-05-06 20:39                 ` Peter Zijlstra
2014-05-06 23:46                   ` Rik van Riel
2014-05-09  2:20                   ` Rik van Riel
2014-05-09  5:27                     ` [PATCH] sched: wake up task on prev_cpu if not in SD_WAKE_AFFINE domain with cpu Rik van Riel
2014-05-09  6:04                       ` [PATCH] sched: clean up select_task_rq_fair conditionals and indentation Rik van Riel
2014-05-09  7:34                       ` [PATCH] sched: wake up task on prev_cpu if not in SD_WAKE_AFFINE domain with cpu Mike Galbraith
2014-05-09 14:22                         ` Rik van Riel
2014-05-09 15:24                           ` Mike Galbraith
2014-05-09 15:24                             ` Rik van Riel
2014-05-09 17:55                               ` Mike Galbraith
2014-05-09 18:16                                 ` Rik van Riel
2014-05-10  3:54                                   ` Mike Galbraith
2014-05-13 14:08                                     ` Rik van Riel
2014-05-14  4:08                                       ` Mike Galbraith
2014-05-14 15:40                                         ` [PATCH] sched: call select_idle_sibling when not affine_sd Rik van Riel
2014-05-14 15:45                                           ` Peter Zijlstra
2014-05-19 13:08                                           ` [tip:sched/core] " tip-bot for Rik van Riel
2014-05-22 12:27                                           ` [tip:sched/core] sched: Call select_idle_sibling() " tip-bot for Rik van Riel
2014-05-04 11:44     ` [PATCH RFC/TEST] sched: make sync affine wakeups work Preeti Murthy
2014-05-04 12:04       ` Mike Galbraith
2014-05-05  4:38         ` Preeti U Murthy
2014-05-04 12:41       ` Rik van Riel
2014-05-05  4:50         ` Preeti U Murthy
2014-05-05  6:43           ` Preeti U Murthy
2014-05-05 11:28           ` Rik van Riel
2014-05-06 13:26           ` Peter Zijlstra
2014-05-06 13:25         ` Peter Zijlstra
2014-05-06 20:20           ` Rik van Riel
2014-05-06 20:41             ` Peter Zijlstra
2014-05-07 12:17               ` Ingo Molnar
2014-05-06 11:56       ` 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=1399013469.5233.85.camel@marge.simpson.net \
    --to=umgwanakikbuti@gmail.com \
    --cc=george.mccollister@gmail.com \
    --cc=ktkhai@parallels.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=morten.rasmussen@arm.com \
    --cc=peterz@infradead.org \
    --cc=riel@redhat.com \
    /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

Powered by JetHome