mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Tim Bird <tim.bird@am.sony.com>
To: Christoph Hellwig <hch@infradead.org>
Cc: Greg KH <greg@kroah.com>,
	Alessio Igor Bogani <abogani@kernel.org>,
	Rusty Russell <rusty@rustcorp.com.au>,
	Anders Kaseorg <andersk@ksplice.com>,
	Tim Abbott <tabbott@ksplice.com>,
	LKML <linux-kernel@vger.kernel.org>,
	Linux Embedded <linux-embedded@vger.kernel.org>,
	Jason Wessel <jason.wessel@windriver.com>,
	Dirk Behme <dirk.behme@googlemail.com>
Subject: Re: [PATCH] module: Use binary search in lookup_symbol()
Date: Wed, 18 May 2011 10:00:12 -0700	[thread overview]
Message-ID: <4DD3FB1C.3040103@am.sony.com> (raw)
In-Reply-To: <20110518075428.GA29998@infradead.org>

On 05/18/2011 12:54 AM, Christoph Hellwig wrote:
> On Tue, May 17, 2011 at 04:33:07PM -0700, Tim Bird wrote:
>> That said, I can answer Greg's question.  This is to speed up
>> the symbol resolution on module loading.  The last numbers I
>> saw showed a reduction of about 15-20% for the module load
>> time, for large-ish modules.  Of course this is highly dependent
>> on the size of the modules, what they do at load time, and how many
>> symbols are looked up to link them into the kernel.
> 
> How large are these very large modules, and what are good examples for
> that?

usbcore seems to be a large-ish module whose
load time is improved by this.  More details follow:

I don't know the exact modules, but Alan Jenkins reported a .3
second reduction in overall boot time, on a EEE PC, presumably
running a stock Linux distribution, and loading 41 modules.

See http://lkml.org/lkml/2009/11/3/93

Carmelo Amoroso reported some good performance gains
in this presentation:
http://elinux.org/images/1/18/C_AMOROSO_Fast_lkm_loader_ELC-E_2009.pdf
(See slide 22).

He doesn't report the overall time savings, and
he was using a different method (hash tables as opposed to
binary search), but I believe the results are comparable
to what the binary search enhancement provides.

The biggest offenders in his testing were usbcore,
ehci_hcd and ohci_hcd.

> And why do people overly care for the load time?

To reduce overall boot time.
 -- Tim

=============================
Tim Bird
Architecture Group Chair, CE Workgroup of the Linux Foundation
Senior Staff Engineer, Sony Network Entertainment
=============================


  reply	other threads:[~2011-05-18 17:00 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-05-03 20:42 Alessio Igor Bogani
2011-05-04 15:34 ` Dirk Behme
2011-05-04 17:30   ` Alessio Igor Bogani
2011-05-16 15:36 ` Dirk Behme
2011-05-16 18:02   ` Anders Kaseorg
2011-05-16 20:23     ` Alessio Igor Bogani
2011-05-16 21:01       ` Joe Perches
2011-05-16 21:08         ` Joe Perches
2011-05-17  3:52       ` Rusty Russell
2011-05-17 19:18         ` Dirk Behme
2011-05-17 19:41           ` Alessio Igor Bogani
2011-05-17 20:56             ` Alessio Igor Bogani
2011-05-17 23:22               ` Greg KH
2011-05-17 23:33                 ` Tim Bird
2011-05-18  7:54                   ` Christoph Hellwig
2011-05-18 17:00                     ` Tim Bird [this message]
2011-05-18 19:21                       ` Greg KH
2011-05-18 21:10                         ` module boot time (was Re: [PATCH] module: Use binary search in lookup_symbol()) Tim Bird
2011-05-18 21:34                           ` Greg KH
2011-05-19 19:56                             ` Jeff Mahoney
2011-05-20 21:29                               ` Tim Bird
2011-05-21 14:23                                 ` Jeff Mahoney
2011-05-18 18:55                   ` Alessio Igor Bogani
2011-05-18 19:22                     ` your mail Greg KH
2011-05-18 20:35                       ` Alessio Igor Bogani
2011-05-18 20:35                         ` [PATCH] module: Use binary search in lookup_symbol() Alessio Igor Bogani
2011-05-18  1:07                 ` Rusty Russell
2011-05-18 15:26               ` Dirk Behme
2011-05-19  7:26                 ` Rusty Russell
2011-05-18  1:10           ` Rusty Russell

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=4DD3FB1C.3040103@am.sony.com \
    --to=tim.bird@am.sony.com \
    --cc=abogani@kernel.org \
    --cc=andersk@ksplice.com \
    --cc=dirk.behme@googlemail.com \
    --cc=greg@kroah.com \
    --cc=hch@infradead.org \
    --cc=jason.wessel@windriver.com \
    --cc=linux-embedded@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=rusty@rustcorp.com.au \
    --cc=tabbott@ksplice.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