All of lore.kernel.org
 help / color / mirror / Atom feed
From: ralf@uni-koblenz.de
To: Andi Kleen <ak@muc.de>
Cc: linux@cthulhu.engr.sgi.com, lm@bitmover.com
Subject: Re: [lm@bitmover.com: Linux performance vs IRIX performance]
Date: Sun, 19 Jul 1998 03:05:05 +0200	[thread overview]
Message-ID: <19980719030505.B489@uni-koblenz.de> (raw)
In-Reply-To: <k21zrjqh9q.fsf@zero.aec.at>; from Andi Kleen on Sat, Jul 18, 1998 at 06:02:25PM +0200

On Sat, Jul 18, 1998 at 06:02:25PM +0200, Andi Kleen wrote:

> ralf@uni-koblenz.de writes:
> 
> > A factor of 4.4 difference.  It's not fair to actually expect that good of
> > a result - the SGI OS is an SMP OS that scales up to approximately 128 
> > processors, has all sorts of useful and not so useful features that Linux
> > doesn't have, etc, etc.  None the less, it is likely that Linux on the same
> > hardware would be about 3 times faster than IRIX.  
> 
> Larry did not say what kind of FS he used on the Irix box (XFS or EFS), but
> for me it looks like a typical sync metadata/async metadata comparison.

Whatever - the impact of the dcache on the performance is sometimes really
amazing.  As long as Linux doesn't hit the disk on an Indy it is _much_
faster than IRIX.  For the normal case XFS and ext2 aren't too far from
each other.  Finally when Linux hits the disk it looses badly, the current
wd33c93 driver performs pretty badly.

  Ralf

  parent reply	other threads:[~1998-07-19  1:06 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
1998-07-18  3:27 [lm@bitmover.com: Linux performance vs IRIX performance] ralf
     [not found] ` <k21zrjqh9q.fsf@zero.aec.at>
1998-07-19  1:05   ` ralf [this message]
  -- strict thread matches above, loose matches on Subject: below --
1998-07-18 16:34 Larry McVoy

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=19980719030505.B489@uni-koblenz.de \
    --to=ralf@uni-koblenz.de \
    --cc=ak@muc.de \
    --cc=linux@cthulhu.engr.sgi.com \
    --cc=lm@bitmover.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.