public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Jeremy Fitzhardinge <jeremy@goop.org>
To: Ingo Molnar <mingo@elte.hu>
Cc: Nick Piggin <npiggin@suse.de>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	hpa@zytor.com, jeremy@xensource.com, chrisw@sous-sol.org,
	zach@vmware.com, rusty@rustcorp.com.au
Subject: Re: lmbench lat_mmap slowdown with CONFIG_PARAVIRT
Date: Thu, 22 Jan 2009 14:26:44 -0800	[thread overview]
Message-ID: <4978F2A4.8010807@goop.org> (raw)
In-Reply-To: <20090120112634.GA20858@elte.hu>

Ingo Molnar wrote:
> Ouch, that looks unacceptably expensive. All the major distros turn 
> CONFIG_PARAVIRT on. paravirt_ops was introduced in x86 with the express 
> promise to have no measurable runtime overhead.
>
> ( And i suspect the real life mmap cost is probably even more expensive,
>   as on a Barcelona all of lmbench fits into the cache hence we dont see
>   any real $cache overhead. )
>
> Jeremy, any ideas where this slowdown comes from and how it could be 
> fixed?
>   

I just posted a couple of patches to pick some low-hanging fruit.  It 
turns out that we don't need to do any pvops calls to do pte flag 
manipulations.  I'd be interested to see how much of a difference it 
makes (it reduces the static code size by a few k).

    J

  parent reply	other threads:[~2009-01-22 22:27 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-01-20 11:05 lmbench lat_mmap slowdown with CONFIG_PARAVIRT Nick Piggin
2009-01-20 11:26 ` Ingo Molnar
2009-01-20 12:34   ` Nick Piggin
2009-01-20 12:45     ` Ingo Molnar
2009-01-20 13:41       ` Nick Piggin
2009-01-20 14:03   ` Ingo Molnar
2009-01-20 14:14     ` Nick Piggin
2009-01-20 14:17       ` Ingo Molnar
2009-01-20 14:41         ` Nick Piggin
2009-01-20 15:00           ` Ingo Molnar
2009-01-20 15:13     ` Ingo Molnar
2009-01-20 19:37     ` Ingo Molnar
2009-01-20 20:45     ` Jeremy Fitzhardinge
2009-01-20 20:56       ` Ingo Molnar
2009-01-21  7:27         ` Nick Piggin
2009-01-21 22:23           ` Jeremy Fitzhardinge
2009-01-22 22:28             ` Zachary Amsden
2009-01-22 22:44               ` Jeremy Fitzhardinge
2009-01-22 22:49                 ` H. Peter Anvin
2009-01-22 22:58                   ` Zachary Amsden
2009-01-22 23:52                     ` H. Peter Anvin
2009-01-23  0:08                       ` Jeremy Fitzhardinge
2009-01-22 22:55                 ` Zachary Amsden
2009-01-23  0:14                   ` Jeremy Fitzhardinge
2009-01-27  7:59                     ` Ingo Molnar
2009-01-27  8:24                       ` Jeremy Fitzhardinge
2009-01-27 10:17                       ` Jeremy Fitzhardinge
2009-01-20 19:05   ` Zachary Amsden
2009-01-20 19:31     ` Ingo Molnar
2009-01-22 22:26   ` Jeremy Fitzhardinge [this message]
2009-01-22 23:04     ` Ingo Molnar
2009-01-22 23:30       ` Zachary Amsden

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=4978F2A4.8010807@goop.org \
    --to=jeremy@goop.org \
    --cc=chrisw@sous-sol.org \
    --cc=hpa@zytor.com \
    --cc=jeremy@xensource.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=npiggin@suse.de \
    --cc=rusty@rustcorp.com.au \
    --cc=torvalds@linux-foundation.org \
    --cc=zach@vmware.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