From owner-freebsd-hackers Wed Dec 4 01:55:22 1996 Return-Path: owner-hackers Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id BAA21591 for hackers-outgoing; Wed, 4 Dec 1996 01:55:22 -0800 (PST) Received: from caipfs.rutgers.edu (root@caipfs.rutgers.edu [128.6.91.100]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id BAA21586 for ; Wed, 4 Dec 1996 01:55:20 -0800 (PST) Received: from jenolan.caipgeneral (jenolan.rutgers.edu [128.6.111.5]) by caipfs.rutgers.edu (8.7.6/8.7.3) with SMTP id EAA10664; Wed, 4 Dec 1996 04:55:19 -0500 (EST) Received: by jenolan.caipgeneral (SMI-8.6/SMI-SVR4) id EAA20107; Wed, 4 Dec 1996 04:54:55 -0500 Date: Wed, 4 Dec 1996 04:54:55 -0500 Message-Id: <199612040954.EAA20107@jenolan.caipgeneral> From: "David S. Miller" To: vode@snakemail.hut.fi CC: hackers@freebsd.org In-reply-to: (message from Kai Vorma on 04 Dec 1996 11:47:00 +0200) Subject: Re: TCP/IP bandwidth bragging Sender: owner-hackers@freebsd.org X-Loop: FreeBSD.org Precedence: bulk From: Kai Vorma Date: 04 Dec 1996 11:47:00 +0200 30 MB/s remote host TCP bandwidth :-) The machine is dirty old IBM SP2 with wide nodes (similar to RS/6000 590 which appeared in 1993, I think) and HPS2 switch. Okay, the HPS2 switch is quite a different animal than ethernet, but you asked.. :-) We'll see what my Gigabit ethernet numbers look like in two days. (I have an SP2 right here btw (15 feet away), and I have run several such benchmarks like the what you have shown already, the internal network switch on the SP2 is actually kind of neat)