From: Andi Kleen <ak@suse.de>
To: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Denis Vlasenko <vda@ilport.com.ua>,
Alan Cox <alan@lxorguk.ukuu.org.uk>,
lkml <linux-kernel@vger.kernel.org>
Subject: Re: RFC: i386: kill !4KSTACKS
Date: Tue, 6 Sep 2005 09:50:16 +0200 [thread overview]
Message-ID: <200509060950.16752.ak@suse.de> (raw)
In-Reply-To: <1125991977.5138.6.camel@npiggin-nld.site>
> Are there still good reasons to have such a thing?
I think so yes. It just doesn't make much sense to handle larger 64bit
setups with multiple GB of memory with 4K pages. While larger softpage
size will not increase TLB usage it will give you less cache use and in
general less cycles while accessing mem_map and while doing VM operations in
general. Other benefits are faster TLB flush (I saw some bottlenecks
with that in 2.4 on large systems)
Simple example: you have to handle a few GB of memory in the LRU
list. Doing it with half as many objects (8k page instead of 4k) is much more
efficient.
-Andi
next prev parent reply other threads:[~2005-09-06 7:48 UTC|newest]
Thread overview: 118+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-09-04 14:51 RFC: i386: kill !4KSTACKS Alex Davis
2005-09-04 17:11 ` Stefan Smietanowski
2005-09-04 17:11 ` Dr. David Alan Gilbert
2005-09-04 17:19 ` Alan Cox
2005-09-06 4:37 ` Andi Kleen
2005-09-06 6:39 ` Denis Vlasenko
2005-09-06 7:13 ` Andi Kleen
2005-09-06 7:32 ` Nick Piggin
2005-09-06 7:50 ` Andi Kleen [this message]
2005-09-06 13:29 ` Diego Calleja
2005-09-06 13:25 ` Giridhar Pemmasani
2005-09-06 17:05 ` Jan Kiszka
2005-09-06 17:23 ` Giridhar Pemmasani
2005-09-06 18:42 ` linux-os (Dick Johnson)
2005-09-06 18:46 ` viro
2005-09-06 19:42 ` Jan Kiszka
2005-09-06 20:21 ` linux-os (Dick Johnson)
2005-09-07 17:46 ` Bill Davidsen
2005-09-07 17:54 ` Jan Kiszka
2005-09-07 19:52 ` Daniel Phillips
2005-09-07 20:17 ` Daniel Phillips
2005-09-07 20:29 ` Jan Kiszka
2005-09-07 20:28 ` Jan Kiszka
2005-09-07 21:57 ` Giridhar Pemmasani
2005-09-07 23:25 ` Jan Kiszka
2005-09-08 1:06 ` Giridhar Pemmasani
2005-09-08 19:43 ` Bill Davidsen
2005-09-06 22:19 ` Daniel Phillips
2005-09-06 22:21 ` Andi Kleen
2005-09-06 22:36 ` Daniel Phillips
2005-09-06 23:40 ` Steven Rostedt
2005-09-06 22:28 ` Roland Dreier
2005-09-07 0:04 ` Daniel Phillips
2005-09-06 22:42 ` Giridhar Pemmasani
2005-09-07 1:59 ` Mark Lord
2005-09-07 3:46 ` Lee Revell
2005-09-07 4:16 ` Daniel Phillips
2005-09-07 5:48 ` Daniel Phillips
2005-09-07 16:43 ` Bill Davidsen
2005-09-08 0:44 ` Alex Davis
-- strict thread matches above, loose matches on Subject: below --
2005-09-06 10:29 Chuck Ebbert
2005-09-05 2:00 Alex Davis
2005-09-05 2:07 ` Sean
2005-09-05 2:29 ` Alex Davis
2005-09-05 3:00 ` Sean
2005-09-05 3:41 ` Alex Davis
2005-09-05 3:51 ` Sean
2005-09-05 4:03 ` Alex Davis
2005-09-05 4:12 ` Sean
2005-09-05 4:36 ` Willy Tarreau
2005-09-05 4:47 ` Sean
2005-09-05 5:01 ` Willy Tarreau
2005-09-05 5:31 ` Sean
2005-09-05 6:04 ` Willy Tarreau
2005-09-05 6:20 ` Sean
2005-09-05 6:29 ` Pekka Enberg
2005-09-05 15:29 ` Horst von Brand
2005-09-08 20:18 ` Bill Davidsen
2005-09-08 22:51 ` Sean
2005-09-05 6:41 ` Sander
2005-09-05 8:01 ` Willy Tarreau
2005-09-08 20:01 ` Bill Davidsen
2005-09-08 20:24 ` Christopher Friesen
2005-09-05 3:54 ` Kyle Moffett
2005-09-05 4:26 ` Dave Jones
2005-09-05 4:48 ` Willy Tarreau
2005-09-06 17:04 ` Benjamin LaHaise
2005-09-05 1:30 Alex Davis
2005-09-05 1:41 ` Adrian Bunk
2005-09-05 1:56 ` dean gaudet
[not found] <4I7UM-M1-1@gated-at.bofh.it>
[not found] ` <4ITG4-8nH-1@gated-at.bofh.it>
[not found] ` <4J1DC-2NU-1@gated-at.bofh.it>
2005-09-04 17:33 ` Robert Hancock
[not found] <4IcUz-7H2-27@gated-at.bofh.it>
[not found] ` <4J2gx-3zf-3@gated-at.bofh.it>
[not found] ` <4J5R1-cH-21@gated-at.bofh.it>
[not found] ` <4J6ao-L9-21@gated-at.bofh.it>
[not found] ` <4J6jZ-Xg-11@gated-at.bofh.it>
[not found] ` <4J8vt-43Y-13@gated-at.bofh.it>
2005-09-02 6:08 ` Alex Davis
2005-09-04 12:49 ` Denis Vlasenko
2005-09-04 13:30 ` Ed Tomlinson
2005-09-04 14:49 ` Alan Cox
2005-09-04 16:44 ` Paul Misner
2005-09-04 17:07 ` Pekka Enberg
2005-09-04 17:12 ` Bas Westerbaan
2005-09-04 19:22 ` Horst von Brand
2005-09-04 19:33 ` Adrian Bunk
2005-09-04 20:13 ` Bas Westerbaan
2005-09-04 20:37 ` Dave Jones
2005-09-07 16:38 ` Bill Davidsen
2005-09-07 17:53 ` Mike Galbraith
2005-09-08 19:05 ` Bill Davidsen
2005-09-05 22:32 ` Thorild Selen
2005-09-05 23:06 ` Kyle Moffett
2005-09-02 0:39 Adrian Bunk
2005-09-02 5:33 ` Chris Wedgwood
2005-09-02 6:29 ` Nathan Scott
2005-09-02 6:40 ` Neil Brown
2005-09-13 8:05 ` Alexander Nyberg
2005-10-01 22:50 ` Adrian Bunk
2005-10-02 20:35 ` Nathan Scott
2005-09-02 6:55 ` Vladimir V. Saveliev
2005-09-02 21:58 ` Hans Reiser
2005-09-04 3:48 ` Lee Revell
2005-09-04 7:36 ` Stefan Smietanowski
2005-09-04 8:23 ` Lee Revell
2005-09-04 19:39 ` Adrian Bunk
2005-09-04 12:12 ` Guillaume Chazarain
2005-09-04 13:26 ` Sander
2005-06-08 12:35 Ian Kumlien
2005-06-08 13:14 ` Denis Vlasenko
2005-06-07 21:27 Adrian Bunk
2005-06-07 21:47 ` Alexander Nyberg
2005-06-08 10:03 ` Jörn Engel
2005-06-08 10:39 ` Denis Vlasenko
2005-06-08 11:12 ` Adrian Bunk
2005-06-08 12:13 ` Denis Vlasenko
2005-07-04 18:22 ` Adrian Bunk
2005-07-05 6:14 ` Denis Vlasenko
2005-07-05 13:46 ` Horst von Brand
2005-06-08 1:52 ` Ian Kent
2005-06-08 10:42 ` Denis Vlasenko
2005-06-08 14:28 ` raven
2005-06-08 12:00 ` Vladimir Saveliev
2005-06-10 15:18 ` Vladimir Saveliev
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=200509060950.16752.ak@suse.de \
--to=ak@suse.de \
--cc=alan@lxorguk.ukuu.org.uk \
--cc=linux-kernel@vger.kernel.org \
--cc=nickpiggin@yahoo.com.au \
--cc=vda@ilport.com.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