public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Andi Kleen <ak@suse.de>
To: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Andi Kleen <ak@suse.de>,
	Denis Vlasenko <vda@port.imtp.ilyichevsk.odessa.ua>,
	linux-kernel@vger.kernel.org
Subject: Re: kernel: ldt allocation failed
Date: Wed, 6 Feb 2002 15:09:49 +0100	[thread overview]
Message-ID: <20020206150949.A10871@wotan.suse.de> (raw)
In-Reply-To: <p73ofj2lpdg.fsf@oldwotan.suse.de> <E16YSpV-0005Es-00@the-village.bc.nu>
In-Reply-To: <E16YSpV-0005Es-00@the-village.bc.nu>

On Wed, Feb 06, 2002 at 02:13:45PM +0000, Alan Cox wrote:
> > glibc 2.3 seems to plan to use segment register based thread local data for 
> > even non threaded programs, so it would be a good idea to optimize LDT 
> > allocation a bit (= not allocate 64K of vmalloc space every time 
> > sys_modify_ldt is called - there is only 8MB of it) 
> 
> I think it would be a good idea to modify the glibc authors in that case.
> The ldt costs real performance on task switches. It would be very dumb of
> glibc to use it except when justified in the bigger picture - ie threaded
> apps

Are you sure it does? LGDT with non zero argument shouldn't be that costly. 
The %fs switching adds some locked cycles for reloading the segment cache, 
but because Windows uses that I would it expect to be reasonably optimized 
on CPUs. 

I actually tried to complain because on x86-64 it is more costly, but to
no avail. 

-Andi

  reply	other threads:[~2002-02-06 14:10 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <Pine.LNX.4.21.0112070057480.20196-100000@tombigbee.pixar.com.suse.lists.linux.kernel>
     [not found] ` <5.1.0.14.2.20011207092244.049f6720@pop.cus.cam.ac.uk.suse.lists.linux.kernel>
     [not found]   ` <200202061258.g16CwGt31197@Port.imtp.ilyichevsk.odessa.ua.suse.lists.linux.kernel>
2002-02-06 13:19     ` kernel: ldt allocation failed Andi Kleen
2002-02-06 14:06       ` Dave Jones
2002-02-06 14:13       ` Alan Cox
2002-02-06 14:09         ` Andi Kleen [this message]
2002-02-06 14:39           ` Alan Cox
2002-02-06 16:37             ` bert hubert
2002-02-06 15:51         ` Bill Davidsen
2002-02-06 16:08           ` Alan Cox
2002-02-06 16:29             ` John Levon
2002-02-06 18:01               ` Alan Cox
2002-02-06 18:02       ` Denis Vlasenko
2002-02-06 15:12         ` Jakub Jelinek
2002-02-06 18:11           ` Maciej W. Rozycki
2002-02-06 20:19           ` H. Peter Anvin
2002-02-06 21:15             ` Jakub Jelinek
2002-02-06 21:17               ` H. Peter Anvin
2002-02-06 20:21           ` yodaiken
2002-02-06 21:00             ` H. Peter Anvin
2002-02-06 21:31               ` Jakub Jelinek
2002-02-06 22:05                 ` H. Peter Anvin
2002-02-06 22:20                   ` Jakub Jelinek
2002-02-06 23:35                     ` H. Peter Anvin
2002-02-07  0:21                 ` Alan Cox
2002-02-07  0:12                   ` Jakub Jelinek
2002-02-07  0:15                     ` H. Peter Anvin
2002-02-07  0:13                   ` H. Peter Anvin
2002-02-06 15:37         ` Alan Cox
     [not found] <fa.kit1f7v.j024op@ifi.uio.no>
2001-12-07  7:24 ` Dan Maas
2001-12-07  9:00   ` Kiril Vidimce
2001-12-07  9:15     ` Alan Cox
2001-12-07  9:13       ` Kiril Vidimce
2001-12-07  9:28         ` Alan Cox
2001-12-07  9:26       ` James Davies
2001-12-07  9:43         ` Alan Cox
2001-12-07 13:10           ` James Davies
2001-12-07 13:41             ` Dave Jones
2001-12-07 13:59               ` James Davies
2001-12-07 13:53             ` Alan Cox
2001-12-07  9:45     ` Anton Altaparmakov
2001-12-07 10:38       ` Alan Cox
2002-02-06 16:58       ` Denis Vlasenko
2002-02-06 13:42         ` Alan Cox
2002-02-06 17:20           ` Christoph Hellwig
2001-12-07 10:12     ` Anton Altaparmakov
2001-12-07  5:40 Kiril Vidimce
2001-12-07  5:58 ` Jeffrey H. Ingber

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=20020206150949.A10871@wotan.suse.de \
    --to=ak@suse.de \
    --cc=alan@lxorguk.ukuu.org.uk \
    --cc=linux-kernel@vger.kernel.org \
    --cc=vda@port.imtp.ilyichevsk.odessa.ua \
    /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