linux-hotplug.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Greg KH <greg@kroah.com>
To: linux-hotplug@vger.kernel.org
Subject: Re: [UDEV, PATCH] Add profiling support to Makefile
Date: Tue, 15 Feb 2005 23:10:49 +0000	[thread overview]
Message-ID: <20050215231049.GB16991@kroah.com> (raw)
In-Reply-To: <200502131716.55756.mbuesch@freenet.de>

On Tue, Feb 15, 2005 at 10:12:56AM +0100, Kay Sievers wrote:
> On Tue, 2005-02-15 at 09:45 +0100, Michael Buesch wrote:
> >Quoting Greg KH <greg@kroah.com>:
> >> On Sun, Feb 13, 2005 at 05:16:51PM +0100, Michael Buesch wrote:
> >> > Hi,
> >> > 
> >> > This patch adds an option to the Makefile to enable
> >> > profiling. Profiling is only enabled, when not building
> >> > against klibc, as klibc lacks support for mcount().
> >> > 
> >> > Please apply. Thanks.
> >> 
> >> You forgot to update the documentation about this option, so I'll hold
> >> off till you redo that :)
> >
> >Oops. :O Here it is.
> >
> >> Also, what has profiling information helped you out with in udev?  Found
> >> anything interesting?  Or are you just using it for coverage analysis
> >> (which is a flawed thing, but that's another topic...)
> >
> >I did not do much testing, yet, because of missing time.
> >But I will do that.
> >My first testrun showed that the namedev matchrule function and the udevdb
> >are the slowest parts of the whole executable. So maybe there's some
> >optimization possible. But I'll look closer at it later.
> 
> The biggest part of it seems libsysfs. A replacement of the attribute
> reading functions with a simple open() gives ~20% speed increase for
> udevstart on my box.

As I doubt libsysfs will be fixed in this regard anytime soon, want to
add this to the tree?  A 20% speed increase for such a simple change is
a very good thing to have :)

thanks,

greg k-h


-------------------------------------------------------
SF email is sponsored by - The IT Product Guide
Read honest & candid reviews on hundreds of IT Products from real users.
Discover which products truly live up to the hype. Start reading now.
http://ads.osdn.com/?ad_ide95&alloc_id\x14396&op=click
_______________________________________________
Linux-hotplug-devel mailing list  http://linux-hotplug.sourceforge.net
Linux-hotplug-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-hotplug-devel

      parent reply	other threads:[~2005-02-15 23:10 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-02-13 16:16 [UDEV, PATCH] Add profiling support to Makefile Michael Buesch
2005-02-15  3:54 ` Greg KH
2005-02-15  8:45 ` Michael Buesch
2005-02-15  9:12 ` Kay Sievers
2005-02-15 23:10 ` Greg KH [this message]

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=20050215231049.GB16991@kroah.com \
    --to=greg@kroah.com \
    --cc=linux-hotplug@vger.kernel.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;
as well as URLs for NNTP newsgroup(s).