From owner-freebsd-net Mon Mar 29 22:32:13 1999 Delivered-To: freebsd-net@freebsd.org Received: from obie.softweyr.com (unknown [204.68.178.33]) by hub.freebsd.org (Postfix) with ESMTP id EEA8014F42 for ; Mon, 29 Mar 1999 22:32:10 -0800 (PST) (envelope-from wes@softweyr.com) Received: from softweyr.com (wes@zaphod.softweyr.com [204.68.178.35]) by obie.softweyr.com (8.8.8/8.8.8) with ESMTP id XAA00488; Mon, 29 Mar 1999 23:31:45 -0700 (MST) (envelope-from wes@softweyr.com) Message-ID: <37006FD1.45A2865A@softweyr.com> Date: Mon, 29 Mar 1999 23:31:45 -0700 From: Wes Peters Organization: Softweyr llc X-Mailer: Mozilla 4.5 [en] (X11; U; FreeBSD 3.1-RELEASE i386) X-Accept-Language: en MIME-Version: 1.0 To: Garrett Wollman Cc: freebsd-net@FreeBSD.ORG Subject: Re: FreeBSD as a router References: <14079.61724.162248.667212@avalon.east> <199903292322.XAA11026@inner.net> <199903300122.UAA14792@khavrinen.lcs.mit.edu> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-net@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Garrett Wollman wrote: > > < said: > > > I'd love to see well-done test data to substantiate or refute this sort of > > discussion; people know what the good and bad properties of the hardware and > > the software are and can take reasonably good guesses, but they're still just > > guesses and not measured performance numbers. I know that there is data out > > there, but I don't know how good it is. > > I actually did something like this a few years back. The tests we > were running were flat-out packet generation (because we needed to > know how fast we could send packets before we attempted to receive or > forward them). At that time, the fastest machine we had in the > hardware lab was a 200-MHz Pentium Pro with the Natoma chipset; with > the best hardware/driver combination (Intel 82557), we were able to > transmit at line rate at packet sizes down to about 80 bytes (excuse > me, octets) before the machine ran out of gas. With better chipsets > and faster memory subsystems, there should be plenty of headroom to > forward packets at line rate, particularly if you're doing VJ-style > fast forwarding. (Whether that leaves enough CPU to run a routing > protocol as well I can't say.) If somebody wants to write up some sketchy details as to what I should configure, I can do a couple of quick tests later this week. I have a PII-233 machine with 64MB RAM, one onboard EEPro100, and two 3C905B on PCI cards. I also have access to a SmartBits traffic generator that can do 2 or 3 full-duplex 100Base-TX streams without breaking a sweat, and gives really reliable numbers. If other network interfaces would be better, let me know and I'll see if I can scare up a couple of them. Another EEPro100 shouldn't be a problem to borrow, for instance. -- "Where am I, and what am I doing in this handbasket?" Wes Peters Softweyr LLC http://www.softweyr.com/~softweyr wes@softweyr.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message