public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Nick Piggin <npiggin@suse.de>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: William Lee Irwin III <wli@holomorphy.com>,
	Kasper Sandberg <lkml@metanurb.dk>, Willy Tarreau <w@1wt.eu>,
	Ingo Molnar <mingo@elte.hu>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Gene Heskett <gene.heskett@gmail.com>,
	linux-kernel@vger.kernel.org, Con Kolivas <kernel@kolivas.org>,
	Mike Galbraith <efault@gmx.de>,
	Arjan van de Ven <arjan@infradead.org>,
	Peter Williams <pwil3058@bigpond.net.au>,
	caglar@pardus.org.tr, Mark Lord <lkml@rtr.ca>,
	Zach Carter <linux@zachcarter.com>,
	buddabrod <buddabrod@gmail.com>
Subject: Re: [patch] CFS scheduler, -v6
Date: Tue, 1 May 2007 09:55:15 +0200	[thread overview]
Message-ID: <20070501075515.GD10590@wotan.suse.de> (raw)
In-Reply-To: <1177853867.5791.120.camel@localhost.localdomain>

On Sun, Apr 29, 2007 at 03:37:47PM +0200, Thomas Gleixner wrote:
> On Sun, 2007-04-29 at 05:55 -0700, William Lee Irwin III wrote:
> > You'll also hit the same holes should you attempt to write such a
> > modularity patch for mainline as opposed to porting current mainline to
> > the driver API as-given. It takes a bit more work to get something that
> > actually works for all this, and it borders on disingenuity to
> > suggest that the scheduler class/driver API as it now stands is
> > capable of any such thing as porting current mainline, nicksched, or SD
> > to it without significant code impact to the core scheduler code.
> 
> I never said, that the current implementation of CFS fits the criteria
> of modularity, but it is a step in that direction. I'm well aware that
> there is a bunch of things missing and it has hard coded leftovers,
> which are related to the current two hard coded policy classes.

[ I've tuned out of most of the scheduler discussion lately, sorry ;) ]


People seem to be confusing scheduler policy with a modular framework.

First of all, I don't know that any of the schedulers can "just go in"
and replace the mainline one, because they are still under development
and have not been sufficiently tested and contrasted IMO.

Secondly, if we want to have a modular framework, it should:
- be a seperate patchset to any new scheduler policy
- obviously retain the existing policy for testing / comparison purposes
- be able to be compiled out. I don't know whether it's CFS policy or
  the framework (maybe both), but CFS is quite a bit slower at context
  switching when I last measured with lmbench (several releases ago).

I still would rather not have a modular framework unless we decide
that is the only wake to make upstream progress. But if we did have
the modular framework, we still need to decide on the process of
avoiding profileration, selecting a default scheduler, and a plan for
future phasing out of non-default GP schedulers once a new one gets
selected.


  reply	other threads:[~2007-05-01  7:56 UTC|newest]

Thread overview: 89+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-04-25 21:47 [patch] CFS scheduler, -v6 Ingo Molnar
2007-04-26  2:14 ` Gene Heskett
2007-04-26  3:29 ` Nick Piggin
2007-04-26  3:49   ` Andrew Morton
2007-04-26  4:16   ` William Lee Irwin III
2007-04-26  8:27   ` Ingo Molnar
2007-04-26  9:18 ` Ingo Molnar
2007-04-26 14:06 ` Redeeman
2007-04-26 14:41   ` Gene Heskett
2007-04-26 20:09     ` Kasper Sandberg
2007-04-26 21:21       ` Gene Heskett
2007-04-27  4:02       ` Mike Galbraith
2007-04-27  6:01         ` Mike Galbraith
2007-04-27 11:53       ` Ingo Molnar
2007-04-27 11:55         ` Ingo Molnar
2007-04-27 13:39           ` Thomas Gleixner
2007-04-27 13:41             ` Ingo Molnar
2007-04-27 13:44             ` Thomas Gleixner
2007-04-28 15:35           ` Kasper Sandberg
2007-04-28 20:45             ` Lee Revell
2007-04-29  1:18             ` Kasper Sandberg
2007-04-29  5:30               ` Willy Tarreau
2007-04-29  6:45                 ` Mike Galbraith
2007-04-29  6:59                 ` Ingo Molnar
2007-04-29  7:16                   ` Willy Tarreau
2007-04-29  7:30                     ` Ingo Molnar
2007-04-29  7:38                       ` Willy Tarreau
2007-04-29  8:00                         ` Ingo Molnar
2007-04-29  8:02                           ` Willy Tarreau
2007-04-29  9:52                           ` Con Kolivas
2007-04-29 10:19                             ` Mike Galbraith
2007-04-29  7:54                     ` William Lee Irwin III
2007-04-29  8:03                       ` Ingo Molnar
2007-04-29  8:16                         ` William Lee Irwin III
2007-04-29  8:13                       ` Willy Tarreau
2007-04-29  8:58                         ` William Lee Irwin III
2007-04-29  8:11                     ` Mike Galbraith
2007-04-29 10:30                     ` Thomas Gleixner
2007-04-29 10:33                       ` William Lee Irwin III
2007-04-29 10:48                       ` Kasper Sandberg
2007-04-29 11:25                         ` Thomas Gleixner
2007-04-29 10:53                       ` Con Kolivas
2007-04-29 11:11                         ` Bill Huey
2007-04-29 11:50                         ` Thomas Gleixner
2007-04-29 11:11                       ` Willy Tarreau
2007-04-29 11:46                         ` Con Kolivas
2007-04-29 12:09                           ` Paolo Ciarrocchi
2007-04-29 15:39                             ` Gene Heskett
2007-04-29 11:59                         ` Thomas Gleixner
2007-04-29 12:25                           ` Willy Tarreau
2007-04-29 12:00                         ` Kasper Sandberg
2007-04-29 12:13                           ` Thomas Gleixner
2007-04-29 12:21                             ` Kasper Sandberg
2007-04-29 12:55                             ` William Lee Irwin III
2007-04-29 13:37                               ` Thomas Gleixner
2007-05-01  7:55                                 ` Nick Piggin [this message]
2007-05-01 13:00                                   ` William Lee Irwin III
2007-04-29 20:30                         ` Mark Lord
2007-04-29 15:28                     ` Gene Heskett
2007-04-29  7:59                   ` Kasper Sandberg
2007-04-29  8:05                     ` Ingo Molnar
2007-04-29 15:42                     ` Ray Lee
2007-04-29 17:09                       ` Kasper Sandberg
2007-04-29  6:47               ` Ingo Molnar
     [not found]               ` <20070429170908.GA31417@elte.hu>
     [not found]                 ` <20070429173902.GA4349@elte.hu>
2007-04-30 17:45                   ` 3d smoothness (was: Re: [patch] CFS scheduler, -v6) Kasper Sandberg
2007-04-30 20:17                     ` Ingo Molnar
2007-04-30 20:44                       ` Kasper Sandberg
2007-04-27 12:52         ` [patch] CFS scheduler, -v6 William Lee Irwin III
2007-04-27 13:02         ` Ingo Molnar
2007-04-27 21:16           ` Lee Revell
2007-04-26 22:48     ` Con Kolivas
2007-04-27  0:39       ` Gene Heskett
2007-04-27  0:57         ` Con Kolivas
2007-04-27  1:03           ` Gene Heskett
2007-04-27 20:54           ` Bill Davidsen
2007-04-26 16:05   ` Mike Galbraith
2007-04-26 19:27 ` Thomas Gleixner
2007-04-26 19:35   ` Ingo Molnar
2007-04-26 19:42     ` Thomas Gleixner
2007-04-26 20:11       ` Ingo Molnar
2007-04-27 13:19 ` Mark Lord
2007-04-27 13:22   ` Mark Lord
2007-04-27 13:45     ` Ingo Molnar
2007-04-28 12:45 ` Srivatsa Vaddagiri
2007-04-28 13:53   ` Ingo Molnar
2007-04-28 15:23     ` Srivatsa Vaddagiri
2007-04-28 15:22       ` Ingo Molnar
2007-04-28 15:28       ` Srivatsa Vaddagiri
  -- strict thread matches above, loose matches on Subject: below --
2007-04-27 21:59 Art Haas

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=20070501075515.GD10590@wotan.suse.de \
    --to=npiggin@suse.de \
    --cc=akpm@linux-foundation.org \
    --cc=arjan@infradead.org \
    --cc=buddabrod@gmail.com \
    --cc=caglar@pardus.org.tr \
    --cc=efault@gmx.de \
    --cc=gene.heskett@gmail.com \
    --cc=kernel@kolivas.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux@zachcarter.com \
    --cc=lkml@metanurb.dk \
    --cc=lkml@rtr.ca \
    --cc=mingo@elte.hu \
    --cc=pwil3058@bigpond.net.au \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=w@1wt.eu \
    --cc=wli@holomorphy.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