From owner-freebsd-hackers  Wed Dec 17 11:59:39 1997
Return-Path: <owner-freebsd-hackers>
Received: (from root@localhost)
          by hub.freebsd.org (8.8.7/8.8.7) id LAA07795
          for hackers-outgoing; Wed, 17 Dec 1997 11:59:39 -0800 (PST)
          (envelope-from owner-freebsd-hackers)
Received: from verdi.nethelp.no (verdi.nethelp.no [195.1.171.130])
          by hub.freebsd.org (8.8.7/8.8.7) with SMTP id LAA07783
          for <hackers@freebsd.org>; Wed, 17 Dec 1997 11:59:25 -0800 (PST)
          (envelope-from sthaug@nethelp.no)
From: sthaug@nethelp.no
Received: (qmail 24912 invoked by uid 1001); 17 Dec 1997 19:59:15 +0000 (GMT)
To: tlambert@primenet.com
Cc: hackers@freebsd.org
Subject: Re: 3com 3c509 card
In-Reply-To: Your message of "Wed, 17 Dec 1997 19:25:10 +0000 (GMT)"
References: <199712171925.MAA04539@usr02.primenet.com>
X-Mailer: Mew version 1.05+ on Emacs 19.28.2
Mime-Version: 1.0
Content-Type: Text/Plain; charset=us-ascii
Date: Wed, 17 Dec 1997 20:59:15 +0100
Message-ID: <24910.882388755@verdi.nethelp.no>
Sender: owner-freebsd-hackers@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk

> > If you're trying to measure measure network performance, why don't you
> > use a tool which is suitable for the job? FTP is definitely not a good
> > tool for this job. I'd suggest ttcp or NetPerf.
> 
> Uh, if "typical usage" is FTP, then how is that going to reflect what
> he can expect in typical usage?

If you're trying to solve a problem, it's much easier if you can look
at smaller parts of the problem in isolation. Using ttcp or NetPerf is
an effective way of removing the disk subsystem from the chain.

If you're getting 1 MByte/s with ttcp/NetPerf, combined with reasonable
CPU usage, *then* it may be time to look at why the CPU usage is not
reasonable with FTP.

Steinar Haug, Nethelp consulting, sthaug@nethelp.no