From: Chris Wedgwood <cw@f00f.org>
To: Marvin Justice <mjustice@austin.rr.com>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>,
Benjamin LaHaise <bcrl@redhat.com>,
Gerrit Huizenga <gerrit@us.ibm.com>,
"M. Edward Borasky" <znmeb@aracnet.com>,
Harald Holzer <harald.holzer@eunet.at>,
linux-kernel@vger.kernel.org
Subject: Re: i686 SMP systems with more then 12 GB ram with 2.4.x kernel ?
Date: Mon, 7 Jan 2002 15:38:54 +1300 [thread overview]
Message-ID: <20020107023854.GA26751@weta.f00f.org> (raw)
In-Reply-To: <20020106032030.A27926@redhat.com> <E16NFxv-0005e4-00@the-village.bc.nu> <20020106233726.GA26491@weta.f00f.org> <200201070215.g072F0u3010729@sm14.texas.rr.com>
In-Reply-To: <200201070215.g072F0u3010729@sm14.texas.rr.com>
On Sun, Jan 06, 2002 at 08:18:33PM -0600, Marvin Justice wrote:
Here's my (probably simple minded) understanding. With the PSE bit
turned on in one of the x86 control registers (cr3?), page sizes
are 4MB instead of the usual 4KB. One advantage of large pages is
that there are fewer page tables and struct page's to store.
Ah, I knew 4MB pages were possible... I was under the impression _all_
pages had to be 4MB which would seem to suck badly as they would be
too coarse for many applications (but for certain large sci. apps. I'm
sure this would be perfect, less TLB thrashing too with sparse
data-sets).
On the whole, I'm not sure I can see how 4MB pages _everywhere_ in
user-space would be a win for many people at all...
--cw
next prev parent reply other threads:[~2002-01-07 2:36 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2001-12-29 18:18 i686 SMP systems with more then 12 GB ram with 2.4.x kernel ? Harald Holzer
2001-12-29 18:45 ` Alan Cox
2001-12-29 21:24 ` M. Edward (Ed) Borasky
2001-12-30 0:25 ` M. Edward (Ed) Borasky
2001-12-30 2:14 ` Harald Holzer
2001-12-30 2:33 ` M. Edward Borasky
2002-01-01 18:15 ` M. Edward Borasky
2002-01-01 18:46 ` Alan Cox
2002-01-01 19:02 ` M. Edward Borasky
2002-01-02 1:16 ` H. Peter Anvin
2002-01-02 21:17 ` Gerrit Huizenga
2002-01-06 8:20 ` Benjamin LaHaise
2002-01-06 16:16 ` Alan Cox
2002-01-06 20:23 ` Benjamin LaHaise
2002-01-06 23:37 ` Chris Wedgwood
2002-01-07 0:29 ` The COUGAR Project M. Edward Borasky
2002-01-07 2:18 ` i686 SMP systems with more then 12 GB ram with 2.4.x kernel ? Marvin Justice
2002-01-07 2:38 ` Chris Wedgwood [this message]
2002-01-07 4:40 ` T. A.
2002-01-07 16:20 ` Hugh Dickins
2002-01-02 17:30 ` Timothy D. Witham
[not found] ` <1009994687.12942.14.camel@hh2.hhhome.at>
[not found] ` <1009995669.1253.17.camel@wookie-laptop.pdx.osdl.net>
2002-01-02 23:50 ` Harald Holzer
2002-01-03 0:16 ` Alan Cox
2002-01-03 13:30 ` Rik van Riel
2002-01-04 12:09 ` Hugh Dickins
2002-01-04 12:15 ` Rik van Riel
2002-01-03 0:17 ` Mark Zealey
2002-01-03 13:28 ` Rik van Riel
2002-01-03 14:33 ` Stephan von Krawczynski
2002-01-03 16:38 ` Rik van Riel
2002-01-03 15:15 ` Anton Blanchard
-- strict thread matches above, loose matches on Subject: below --
2001-12-29 19:25 Dieter Nützel
2002-01-06 18:39 Daniel Freedman
2002-01-06 18:59 ` Marvin Justice
2002-01-06 19:45 ` Daniel Freedman
2002-01-06 20:15 ` Marvin Justice
2002-01-07 5:17 ` Daniel Freedman
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=20020107023854.GA26751@weta.f00f.org \
--to=cw@f00f.org \
--cc=alan@lxorguk.ukuu.org.uk \
--cc=bcrl@redhat.com \
--cc=gerrit@us.ibm.com \
--cc=harald.holzer@eunet.at \
--cc=linux-kernel@vger.kernel.org \
--cc=mjustice@austin.rr.com \
--cc=znmeb@aracnet.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