From owner-freebsd-current  Tue Nov 12 15:37:16 1996
Return-Path: owner-current
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.5/8.7.3) id PAA04507
          for current-outgoing; Tue, 12 Nov 1996 15:37:16 -0800 (PST)
Received: from vader.cs.berkeley.edu (vader.CS.Berkeley.EDU [128.32.38.234])
          by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id PAA04497
          for <freebsd-current@FreeBSD.org>; Tue, 12 Nov 1996 15:36:48 -0800 (PST)
Received: (from asami@localhost) by vader.cs.berkeley.edu (8.8.2/8.7.3) id PAA14170; Tue, 12 Nov 1996 15:36:39 -0800 (PST)
Date: Tue, 12 Nov 1996 15:36:39 -0800 (PST)
Message-Id: <199611122336.PAA14170@vader.cs.berkeley.edu>
To: danj@3skel.com
CC: gibbs@freefall.freebsd.org, freebsd-current@FreeBSD.org
In-reply-to: <199611122320.SAA25982@fnur.3skel.com> (message from Dan Janowski on Tue, 12 Nov 1996 18:20:09 -0500 (EST))
Subject: Re: ufs is too slow?
From: asami@FreeBSD.org (Satoshi Asami)
Sender: owner-current@FreeBSD.org
X-Loop: FreeBSD.org
Precedence: bulk

 * Justin T. Gibbs writes:
 *  > 
 *  > The main reason MS is looking to Veritas is that NTFS just doesn't perform
 *  > when striped or mirrored.  The NOW project at Cal did I/O comparison studies
 *  > on x86 platforms using Solaris, FreeBSD, Linux and NT and found that while
 *  > FreeBSD and Solaris could achieve upwards of 30MB/s through a striped file
 *  > system, NT topped out at around 9MB/s.  This was NT3.51 - they may have
 *  > improved things for 4.0.

Uh, are you talking about us? ;)

Yes, we did, but Solaris didn't perform nearly that well.  It was more 
like 13MB/s.  You are right about FreeBSD and Windows NT.

 * where did the Linux ext2fs fall?

It didn't install on our PC with 2940UW. :(  (We spent 2 weeks trying
to install that crap, ugh.)

Satoshi