From owner-freebsd-current@FreeBSD.ORG Thu Nov 29 07:10:58 2007 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 48D4C16A417; Thu, 29 Nov 2007 07:10:58 +0000 (UTC) (envelope-from sos@deepcore.dk) Received: from spider.deepcore.dk (cpe.atm2-0-70484.0x50a6c9a6.abnxx16.customer.tele.dk [80.166.201.166]) by mx1.freebsd.org (Postfix) with ESMTP id DBD6313C4E5; Thu, 29 Nov 2007 07:10:57 +0000 (UTC) (envelope-from sos@deepcore.dk) Received: from ws.local (ws.deepcore.dk [194.192.25.137]) by spider.deepcore.dk (8.13.8/8.13.8) with ESMTP id lAT7AECZ090439; Thu, 29 Nov 2007 08:10:14 +0100 (CET) (envelope-from sos@deepcore.dk) Message-ID: <474E65D6.4040403@deepcore.dk> Date: Thu, 29 Nov 2007 08:10:14 +0100 From: =?ISO-8859-1?Q?S=F8ren_Schmidt?= User-Agent: Thunderbird 2.0.0.9 (Macintosh/20071031) MIME-Version: 1.0 To: "Andrey V. Elsukov" References: <73807.10710.qm@web63912.mail.re1.yahoo.com> <200711280842.09340.jhb@freebsd.org> <474D726A.8080807@deepcore.dk> <200711280938.38545.jhb@freebsd.org> <474E5B69.7070406@yandex.ru> In-Reply-To: <474E5B69.7070406@yandex.ru> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: quoted-printable Cc: Barney Cordoba , freebsd-current@freebsd.org, Anton Yuzhaninov Subject: Re: Any successful installs on a Broadcom HT1000 chipset? X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Nov 2007 07:10:58 -0000 Andrey V. Elsukov wrote: > John Baldwin wrote: >> Again, on the machines I'm seeing this on it was totally disabled. I = >> don't think >> I can totally disable DMA (NICs etc. must use DMA) on the machines=20 >> and since they >> are in production and I only see the corruption as an after-effect=20 >> when the boxes >> panic or deadlock for another reason I'm not easily able to reproduce = >> this. Also, >> we do disable MSI for devices behind HT2000 chipsets because of a=20 >> chip bug, but >> not on HT1000 currently. However, MSI isn't on on 6.x anyway. > > Hi, John. > > Anton Yuzhaninov has mentioned in the top of this thread that > this bug may be easy reproduced by using external PCI-X card. > He tried use PCI-X Marvell card and got lots of corruptions on > the integrated HT1000. Can you or Soren try the same way to > reproduce? As I told earlier the fileserver I have here with the HT1000 chip also=20 has a marvel 6081 and it is on PCI-X. There are 4 disks on each and it=20 moves lots of data around on a daily basis, no problems whatsoever. I=20 have planned downtime today on it and will experiment with it, but I=20 can't hold it off for too long... -S=F8ren