From owner-freebsd-amd64@FreeBSD.ORG Thu Feb 23 16:28:25 2006 Return-Path: X-Original-To: freebsd-amd64@freebsd.org Delivered-To: freebsd-amd64@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 46C0B16A420 for ; Thu, 23 Feb 2006 16:28:25 +0000 (GMT) (envelope-from vivek@khera.org) Received: from yertle.kcilink.com (yertle.kcilink.com [65.205.34.180]) by mx1.FreeBSD.org (Postfix) with ESMTP id E696A43D46 for ; Thu, 23 Feb 2006 16:28:24 +0000 (GMT) (envelope-from vivek@khera.org) Received: from [192.168.7.103] (host-103.int.kcilink.com [192.168.7.103]) by yertle.kcilink.com (Postfix) with ESMTP id 3C502B80D for ; Thu, 23 Feb 2006 11:28:24 -0500 (EST) Mime-Version: 1.0 (Apple Message framework v746.2) In-Reply-To: <20060223090534.065f3cd1.kgunders@teamcool.net> References: <43FCEF9C.5050308@bluelight.org.uk> <43FD3B83.2040109@rtl.fmailbox.com> <20060223090534.065f3cd1.kgunders@teamcool.net> Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Message-Id: Content-Transfer-Encoding: 7bit From: Vivek Khera Date: Thu, 23 Feb 2006 11:28:23 -0500 To: FreeBSD AMD list X-Mailer: Apple Mail (2.746.2) Subject: Re: AMD 64 stability X-BeenThere: freebsd-amd64@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Porting FreeBSD to the AMD64 platform List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 23 Feb 2006 16:28:25 -0000 On Feb 23, 2006, at 11:05 AM, Ken Gunderson wrote: >> still), Sun X4100 dual CPU. The Dells are Intel EM64T and the Sun is >> true Opteron. >> > > Did you ever test drive the x2100?? > no, but someone posted to me the dmesg from an X2100 and it seems everything worked ok. however one of the onboard ethernet is nvidia so that could cause problems if you needed both like I do. > I have a few Tyan Transport TA26's wh/ use the S2882 board. The one > MAJOR PITA issue I had w/them is w/LSI 320-1 MegaRAID cards. A mirror > using "slot 1" degrades under moderate load and cannot be recovered. > The problem goes away w/320-2x. Tyan and LSI are investigating. Tyan > reports "unable to reproduce/no problem found". Right.... LSI > support, by contrast, rocks and they are investigating further. > interesting.... I have a 320-2x card I wanted to use with the X4100, except it doesn't fit the low-profile slot that it has. So I tried it in a Dell 1425SC server... it reports random failures at different times on different disks on two different Dell powervault arrays which otherwise work flawlessly with an Adaptec 2230SLP card. If I run the 320-2X in Ultra 160 mode it has no complaints but that is stupid.... Of course everyone points the finger at everyone else... and I'm stuck in the middle with a bunch of expensive crap that won't work together. Anyhow.... I just (literally 15 minutes ago) got an IBM e326m evaluation unit. Watch for results shortly on that... I hope the 320-2x works fine with this box. > Doesn't the Sun use a Tyan board? It is based on a Tyan design, but significantly modified. The X4100 (and other X series) has no internal cables. Everything is plugged together more or less directly. There is one small flat 4" long ribbon cable hooking up something, but that's it. It is absolutely amazingly engineered. They also seem to have better QC than the OEM boards. However, the BIOS comes configured stupidly -- you have to turn on some options to make it bypass the BIOS 4GB hole, etc. Why not just do that by default?!?!?!!?!?!?!?!?!?