From owner-freebsd-chat  Tue Oct  6 16:08:10 1998
Return-Path: <owner-freebsd-chat@FreeBSD.ORG>
Received: (from majordom@localhost)
          by hub.freebsd.org (8.8.8/8.8.8) id QAA22713
          for freebsd-chat-outgoing; Tue, 6 Oct 1998 16:08:10 -0700 (PDT)
          (envelope-from owner-freebsd-chat@FreeBSD.ORG)
Received: from ns1.yes.no (ns1.yes.no [195.204.136.10])
          by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id QAA22663
          for <freebsd-chat@FreeBSD.ORG>; Tue, 6 Oct 1998 16:07:42 -0700 (PDT)
          (envelope-from eivind@bitbox.follo.net)
Received: from bitbox.follo.net (bitbox.follo.net [195.204.143.218])
	by ns1.yes.no (8.9.1a/8.9.1) with ESMTP id BAA27864;
	Wed, 7 Oct 1998 01:07:36 +0200 (CEST)
Received: (from eivind@localhost)
	by bitbox.follo.net (8.8.8/8.8.6) id BAA13466;
	Wed, 7 Oct 1998 01:07:34 +0200 (MET DST)
Message-ID: <19981007010733.53798@follo.net>
Date: Wed, 7 Oct 1998 01:07:33 +0200
From: Eivind Eklund <eivind@yes.no>
To: "Jason C. Wells" <jcwells@u.washington.edu>,
        Reginald Perry <perry@zso.dec.com>
Cc: freebsd-chat@FreeBSD.ORG
Subject: Re: PC Magazine 10/20/1998 Article about FreeBSD
References: <69CAF7F9AF57D2118D9A0000F881B4DD02F304@zsoexc1.zso.dec.com> <Pine.BSF.4.02A.9810061023240.1431-100000@s8-37-26.student.washington.edu>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
X-Mailer: Mutt 0.89.1i
In-Reply-To: <Pine.BSF.4.02A.9810061023240.1431-100000@s8-37-26.student.washington.edu>; from Jason C. Wells on Tue, Oct 06, 1998 at 10:23:57AM -0700
Sender: owner-freebsd-chat@FreeBSD.ORG
Precedence: bulk
X-Loop: FreeBSD.org

On Tue, Oct 06, 1998 at 10:23:57AM -0700, Jason C. Wells wrote:
> On Mon, 5 Oct 1998, Reginald Perry wrote:
> 
> >room before network saturation! So who is going to write the author and
> >request a correction?
> 
> Sounds like you just volunteered. :)

I have already mailed quite a bit back and forth with him, and we're
trying to track down if something could be done to better the results.

It averaged out around 27Mb/s, which I think sound a little low (but
that might be wrong).

My present suspicion is atime updates; it seems the server was not
configured noatime, which seem like it would strange the disk with
synchronous write requests.  That would be reasonably consistent with
the numbers.

However, it may also be that the test is fair - IIS has done a lot to
optimize this, including (if I understand correctly) NT kernel support
just to serve static pages faster.

Eivind.

To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-chat" in the body of the message