mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Stephen Frost <sfrost@snowman.net>
To: Jakob Oestergaard <jakob@unthought.net>,
	Christoph Pleger <Christoph.Pleger@uni-dortmund.de>,
	linux-kernel@vger.kernel.org
Subject: Re: 10 GB in Opteron machine
Date: Fri, 22 Jul 2005 08:57:32 -0400	[thread overview]
Message-ID: <20050722125732.GN24207@ns.snowman.net> (raw)
In-Reply-To: <20050722103955.GI30510@unthought.net>

[-- Attachment #1: Type: text/plain, Size: 1232 bytes --]

* Jakob Oestergaard (jakob@unthought.net) wrote:
> This is really the clever way to run a 64-bit system - 99% of what is
> commonly run on most systems only gains overhead from the 64-bit address
> space - tools like postfix, cron, syslog, apache, ... will not gain from
> being native 64-bit.

For most 64-bit systems, sure.  For amd64 it's a little different
because there are additional changes to the architecture (as compared to
ia32/x86) which can more than make up for the difference for many
applications.  Then there's also things like encryption (postfix/tls,
apache/ssl, etc) which can benefit greatly from better handling of
64bit (and larger) types.

So, basically, it's not nearly so clear-cut as you portray it. :)

> Solaris has done this for ages - maintaining a mostly 32-bit user space,
> a 64-bit kernel, and then allowing for certain memory intensive
> applications to run natively 64-bit.

The differences between a 64bit sparc chip in 32bit and 64bit are quite
a bit less than the differences between an amd64 chip in 32bit and
64bit.  Thus, this makes alot more sense for sparc.

> It's a nice way to run a Linux based system too, IMO.

Perhaps on sparc or mips; it's much less clear-cut on amd64.

	Stephen

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 189 bytes --]

      parent reply	other threads:[~2005-07-22 12:57 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-07-22  8:55 Christoph Pleger
2005-07-22  9:05 ` Jeff Garzik
2005-07-22  9:31   ` Christoph Pleger
2005-07-22 10:17     ` Bernd Petrovitsch
2005-07-22 10:17     ` Bernd Petrovitsch
2005-07-22 10:39     ` Jakob Oestergaard
2005-07-22 11:37       ` Christoph Pleger
2005-07-22 13:55         ` Jakob Oestergaard
2005-07-25 10:41           ` Christoph Pleger
2005-07-22 12:57       ` Stephen Frost [this message]

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=20050722125732.GN24207@ns.snowman.net \
    --to=sfrost@snowman.net \
    --cc=Christoph.Pleger@uni-dortmund.de \
    --cc=jakob@unthought.net \
    --cc=linux-kernel@vger.kernel.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

all inboxes | Powered by JetHome®