From: Duncan <1i5t5.duncan@cox.net>
To: gentoo-dev@lists.gentoo.org
Subject: [gentoo-dev] Re: Optimizing performance
Date: Tue, 27 Dec 2005 22:37:43 -0700 [thread overview]
Message-ID: <pan.2005.12.28.05.37.43.165015@cox.net> (raw)
In-Reply-To: 200512271638.22215.pauldv@gentoo.org
Paul de Vrieze posted <200512271638.22215.pauldv@gentoo.org>, excerpted
below, on Tue, 27 Dec 2005 16:38:21 +0100:
> On Saturday 24 December 2005 00:52, Diego 'Flameeyes' Pettenò wrote:
>> On Friday 23 December 2005 18:35, Paul de Vrieze wrote:
>> > Just to add. This is not so much related to debugging information in
>> > the library files (what gdb can use). That information never makes it
>> > from disk so is not that much of a speed issue (esp. if it is split
>> > out).
>>
>> Actually, if the binaries are not stripped, they consume more memory.
>> With splitdebug the issue is unseen (I'm happily using it with -g3 for
>> everything now..)
>
> Debug info shouldn't be loaded into memory. Or is it? I agree though that
> splitting them out is probably better for memory use.
>From what I've read, binary files are read into memory as a file, before
being having their elements loaded at specific addresses by ldd. Unsplit
debug information at minimum, then, increases the i/o load, requiring more
data be read into memory initially, even if it's immediately thrown out
again, when it's not actually loaded anywhere. In practice, it would at
least remain in cache rather longer, thereby taking up space that could be
used to cache data that might actually be used, not to mention forcing
other potentially useful data out of cache on initial read into cache.
Debug information split into entirely separate files, then, shouldn't
affect performance at all over stripped, and be rather better performing
than debug information stored in the same file.
That's only what I've read. I have no special knowledge on the subject,
and if what I read was incorrect, than so is the above.
--
Duncan - List replies preferred. No HTML msgs.
"Every nonfree program has a lord, a master --
and if you use the program, he is your master." Richard Stallman in
http://www.linuxdevcenter.com/pub/a/linux/2004/12/22/rms_interview.html
--
gentoo-dev@gentoo.org mailing list
next prev parent reply other threads:[~2005-12-28 5:40 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-12-15 12:48 [gentoo-dev] Optimizing performance Patrick Lauer
2005-12-15 13:43 ` Francesco Riosa
2005-12-15 14:17 ` Diego 'Flameeyes' Pettenò
2005-12-15 16:00 ` Patrick Lauer
2005-12-15 16:57 ` Matthijs van der Vleuten
2005-12-15 14:13 ` Chris Gianelloni
2005-12-15 18:08 ` Wernfried Haas
2005-12-15 18:39 ` Curtis Napier
2005-12-15 14:43 ` [gentoo-dev] " Duncan
2005-12-15 15:43 ` Patrick Lauer
2005-12-15 15:50 ` Donnie Berkholz
2005-12-23 17:28 ` Paul de Vrieze
2005-12-23 17:36 ` Donnie Berkholz
2005-12-23 17:58 ` Lares Moreau
2005-12-15 16:03 ` Diego 'Flameeyes' Pettenò
2005-12-15 17:49 ` [gentoo-dev] " Duncan
2005-12-15 17:06 ` [gentoo-dev] " Francesco Riosa
2005-12-15 15:58 ` [gentoo-dev] " Nathaniel McCallum
2005-12-15 18:38 ` John Myers
2005-12-23 17:35 ` Paul de Vrieze
2005-12-23 23:52 ` Diego 'Flameeyes' Pettenò
2005-12-24 2:08 ` John Myers
2005-12-24 11:37 ` Kevin F. Quinn
2005-12-24 12:05 ` Diego 'Flameeyes' Pettenò
2005-12-27 15:38 ` Paul de Vrieze
2005-12-28 5:37 ` Duncan [this message]
2005-12-28 9:50 ` [gentoo-dev] " Duncan
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=pan.2005.12.28.05.37.43.165015@cox.net \
--to=1i5t5.duncan@cox.net \
--cc=gentoo-dev@lists.gentoo.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