From owner-freebsd-hackers  Wed Mar 22 15:22:50 1995
Return-Path: hackers-owner
Received: (from majordom@localhost) by freefall.cdrom.com (8.6.10/8.6.6) id PAA18232 for hackers-outgoing; Wed, 22 Mar 1995 15:22:50 -0800
Received: from star-gate.com (hasty.vip.best.com [204.156.141.143]) by freefall.cdrom.com (8.6.10/8.6.6) with ESMTP id PAA18226 for <hackers@FreeBSD.org>; Wed, 22 Mar 1995 15:22:47 -0800
Received: from localhost (localhost [127.0.0.1]) by star-gate.com (8.6.9/8.6.9) with SMTP id PAA01780 for <hackers@FreeBSD.org>; Wed, 22 Mar 1995 15:18:04 GMT
Message-Id: <199503221518.PAA01780@star-gate.com>
X-Authentication-Warning: star-gate.com: Host localhost didn't use HELO protocol
X-Mailer: exmh version 1.6alpha 2/16/95
To: hackers@FreeBSD.org
Subject: Re: Why IDE is bad 
In-reply-to: Your message of "Wed, 22 Mar 1995 11:15:44 PST."
             <199503221915.LAA09736@gndrsh.aac.dev.com> 
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Date: Wed, 22 Mar 1995 15:18:02 +0000
From: Amancio Hasty <hasty@star-gate.com>
Sender: hackers-owner@FreeBSD.org
Precedence: bulk


Well to check out the assumption that synchronous updates affect the
performace of normal file copies, I did a simple test:

/bg is mounted normally

 time cp -R /bg/sys /bg/test
0.211u 8.486s 2:56.21 4.9% 62+413k 3634+8707io 3pf+0w

Now with /bg mounted asynchronously:

 /bg > mount
/dev/sd0a on / (local)
/dev/sd0f on /usr (local)
/dev/sd0e on /var (local)
procfs on /proc (local)
/dev/sd1f on /bg (asynchronous, local)
 /bg > time cp -R /bg/sys /bg/test1
0.204u 8.544s 2:51.12 5.1% 63+427k 3669+8706io 0pf+0w

Is only 5 secondes faster...

Amancio