From owner-freebsd-net Wed Jun 19 18: 7: 5 2002 Delivered-To: freebsd-net@freebsd.org Received: from tp.databus.com (p72-186.acedsl.com [66.114.72.186]) by hub.freebsd.org (Postfix) with ESMTP id 7776A37B414 for ; Wed, 19 Jun 2002 18:07:00 -0700 (PDT) Received: from databus.com (localhost.databus.com [127.0.0.1]) by tp.databus.com (8.12.3/8.12.3) with ESMTP id g5K16pGC036718; Wed, 19 Jun 2002 21:06:51 -0400 (EDT) (envelope-from barney@databus.com) Received: (from barney@localhost) by databus.com (8.12.3/8.12.3/Submit) id g5K16ktV036717; Wed, 19 Jun 2002 21:06:46 -0400 (EDT) Date: Wed, 19 Jun 2002 21:06:46 -0400 From: Barney Wolff To: "McKenna, Lee" Cc: "'Fabien THOMAS'" , paleph@pacbell.net, freebsd-net@FreeBSD.ORG Subject: Re: bge driver issue Message-ID: <20020619210646.A36559@tp.databus.com> References: <3EA88113DE92D211807300805FA7994209149EC2@chaplin.lodgenet.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.5.1i In-Reply-To: <3EA88113DE92D211807300805FA7994209149EC2@chaplin.lodgenet.com>; from lmckenna@lodgenet.com on Wed, Jun 19, 2002 at 01:46:40PM -0500 Sender: owner-freebsd-net@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Er, you would appear to be measuring the transfer rate of your disk, unless you actually have enough ram to cache a 1.2GB file. By coincidence, tonight I hooked my dual 1.0GHz PIII running fbsd 4.6-stable to a Mac G4 OS-X (also dual 1GHz cpus) using an Intel PRO/1000T desktop adapter on the fbsd side. Here's the result of the Mac doing an ftp get from fbsd: ftp> get X11R6-011112.tgz /dev/null local: /dev/null remote: X11R6-011112.tgz 200 PORT command successful. 150 Opening BINARY mode data connection for 'X11R6-011112.tgz' (194432456 bytes). 226 Transfer complete. 194432456 bytes received in 6.45 seconds (30123284 bytes/s) ftp> get X11R6-011112.tgz /dev/null local: /dev/null remote: X11R6-011112.tgz 200 PORT command successful. 150 Opening BINARY mode data connection for 'X11R6-011112.tgz' (194432456 bytes). 226 Transfer complete. 194432456 bytes received in 1.76 seconds (110555016 bytes/s) The first transfer shows the speed of my disk. The second is really pretty good. Adding in the header overhead, we're over 920 Mbps. Going in the other direction I never got over 500 Mbps, don't yet know why. Windows were 65535 on both sides. Bumping the window over 100KB resulted in a sharp drop in performance, also as yet unexplained. Setting the send window above about 200KB resulted in failure to open a connection - no bufs available. That too will need some investigation. The test was run through a Dell 2508 switch - I could not get 1000baseTX with a crossover cable, but perhaps it was not good enough, although marked cat5. On Wed, Jun 19, 2002 at 01:46:40PM -0500, McKenna, Lee wrote: > I just loaded 4.5-RELEASE, and cvsup/make world upgraded to 4.6-STABLE dated > June 17, and have 2 machines with 3C996B-T cards using the bge driver with > the two machines connected directly to each other using a crossover cable. > Machines are both "home made" with Supermicro mobos with 1.2GHz CPUs. > > Using /dev/zero I created a file some 1.2 GBytes in size. I am getting 7 > MBytes/s using scp and 30 MBytes/s using ftp. So, it looks like the max is > about 240 Mbits/s. This is why we affectionately call gigabit Ethernet "a > couple-hundred megabit ethernet", and we cant wait for Ken's zero copy code > to reach -STABLE :) > > This test also includes tweaking the tcp and udp send and recv space buffers > to 512K, by the way... To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message