From owner-freebsd-net Fri Nov 23 7:22:27 2001 Delivered-To: freebsd-net@freebsd.org Received: from verdi.nethelp.no (verdi.nethelp.no [158.36.41.162]) by hub.freebsd.org (Postfix) with SMTP id 01FC037B416 for ; Fri, 23 Nov 2001 07:22:24 -0800 (PST) Received: (qmail 41890 invoked by uid 1001); 23 Nov 2001 15:22:21 +0000 (GMT) To: tlegvold@hotmail.com Cc: freebsd-net@freebsd.org Subject: Re: Maximum throughput of Intel Pro 100/S NIC? From: sthaug@nethelp.no In-Reply-To: Your message of "Fri, 23 Nov 2001 09:07:50 " References: X-Mailer: Mew version 1.05+ on Emacs 19.34.2 Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Date: Fri, 23 Nov 2001 16:22:21 +0100 Message-ID: <41888.1006528941@verdi.nethelp.no> 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 > >I have got 96% of 100Mbps under real production load. > > Wouldn't the TCP/IP overhead + ethernet design (collisions) reduce this > figure to more like 70Mbs max in the real world? As has been pointed out, a lot of people run full duplex these days. With FD ethernet, the maximum achievable bandwidth is easy to compute, but depends on which protocol level you're looking at: - 1500 byte Ethernet payload: Maximum is 1500 / (1500 + 18 + 8 + 12) = 97.53% (ie. 97.53 Mbps for 100 Mbps Ethernet). - 1460 byte TCP payload: Maximum is 1460 / (1500 + 18 + 8 + 12) = 94.93% (ie. 94.93 Mbps for 100 Mbps Ethernet). FreeBSD can get extremely close to these limits. Steinar Haug, Nethelp consulting, sthaug@nethelp.no To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message