From owner-freebsd-hackers Fri Mar 13 19:36:29 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id TAA23256 for freebsd-hackers-outgoing; Fri, 13 Mar 1998 19:36:29 -0800 (PST) (envelope-from owner-freebsd-hackers@FreeBSD.ORG) Received: from implode.root.com (implode.root.com [198.145.90.17]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id TAA23185 for ; Fri, 13 Mar 1998 19:36:17 -0800 (PST) (envelope-from root@implode.root.com) Received: from implode.root.com (localhost [127.0.0.1]) by implode.root.com (8.8.5/8.8.5) with ESMTP id TAA29649; Fri, 13 Mar 1998 19:29:24 -0800 (PST) Message-Id: <199803140329.TAA29649@implode.root.com> To: Karl Denninger cc: mika ruohotie , hackers@FreeBSD.ORG Subject: Re: "Best" Fast Ethernet Card In-reply-to: Your message of "Fri, 13 Mar 1998 14:17:11 CST." <19980313141711.30263@mcs.net> From: David Greenman Reply-To: dg@root.com Date: Fri, 13 Mar 1998 19:29:24 -0800 Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG >Note that the Pro/100+ *AS WELL AS* the newer SMC cards have serious trouble >with TYN EISA/PCI motherboards when run in 100BaseT mode. It appears that >the motherboard is unable to keep up *on receive* with the data stream; >the result is a lot of input errors and horrible performance. Downshifting >those to 10Mbps fixes that (but obviously negates the point of a fast >ethernet card). The same problem does *NOT* show up on the Natoma >motherboards. Sounds like an older Orion chipset with the PCI write buffer bug. Maximum throughput will be about 4.2MB/sec on those - far less than the 10MB/sec that is required for fast ethernet. The Orion 'C' stepping and Natoma do not have this problem. -DG David Greenman Core-team/Principal Architect, The FreeBSD Project To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message