All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Chris Friesen" <cfriesen@nortel.com>
To: John Richard Moser <nigelenki@comcast.net>
Cc: linux-kernel@vger.kernel.org
Subject: Re: Can context switches be faster?
Date: Thu, 12 Oct 2006 13:57:59 -0600	[thread overview]
Message-ID: <452E9E47.8070306@nortel.com> (raw)
In-Reply-To: <452E62F8.5010402@comcast.net>

John Richard Moser wrote:

> Linux ported onto the L4-Iguana microkernel is reported to be faster
> than the monolith[1]; it's not like microkernels are faster, but the
> L4-Iguana apparently just has super awesome context switching code:
> 
>    Wombat's context-switching overheads as measured by lmbench on an
>    XScale processor are up to thirty times less than those of native
>    Linux, thanks to Wombat profiting from the implementation of fast
>    context switches in L4-embedded.

The Xscale is a fairly special beast, and it's context-switch times are 
pretty slow by default.

Here are some context-switch times from lmbench on a modified 2.6.10 
kernel. Times are in microseconds:

cpu		clock speed	context switch	
pentium-M	1.8GHz		0.890
dual-Xeon	2GHz		7.430
Xscale		700MHz		108.2
dual 970FX	1.8GHz		5.850
ppc 7447	1GHz		1.720

Reducing the Xscale time by a factor of 30 would basically bring it into 
line with the other uniprocessor machines.

Chris

  parent reply	other threads:[~2006-10-12 19:58 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-10-12 15:44 Can context switches be faster? John Richard Moser
2006-10-12 15:53 ` John Richard Moser
2006-10-12 17:19 ` Russell King
2006-10-12 18:25   ` John Richard Moser
2006-10-12 18:37     ` Arjan van de Ven
2006-10-12 18:56       ` John Richard Moser
2006-10-12 19:02         ` Arjan van de Ven
2006-10-13 11:05       ` James Courtier-Dutton
2006-10-13 14:51         ` Chase Venters
2006-10-12 18:20 ` Phillip Susi
2006-10-12 18:29   ` John Richard Moser
2006-10-13  2:53     ` Andrew James Wade
2006-10-13  5:29       ` John Richard Moser
2006-10-13 16:56         ` Andrew James Wade
2006-10-13 17:24           ` John Richard Moser
2006-10-12 19:57 ` Chris Friesen [this message]
2006-10-12 20:23   ` John Richard Moser
2006-10-12 20:29     ` Arjan van de Ven
2006-10-12 20:36       ` John Richard Moser
2006-10-12 20:35     ` Jeremy Fitzhardinge
2006-10-13 23:32       ` Andreas Mohr
2006-10-13 23:47         ` David Lang
2006-10-14  0:14         ` Jeremy Fitzhardinge
2006-10-14  0:30         ` Alan Cox
2006-10-14  0:14           ` Jeremy Fitzhardinge

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=452E9E47.8070306@nortel.com \
    --to=cfriesen@nortel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nigelenki@comcast.net \
    /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.