From owner-freebsd-amd64@FreeBSD.ORG Sat May 8 11:26:02 2004 Return-Path: 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 75E5016A4CE for ; Sat, 8 May 2004 11:26:02 -0700 (PDT) Received: from transport.cksoft.de (transport.cksoft.de [62.111.66.27]) by mx1.FreeBSD.org (Postfix) with ESMTP id B138243D2D for ; Sat, 8 May 2004 11:26:01 -0700 (PDT) (envelope-from bzeeb-lists@lists.zabbadoz.net) Received: from transport.cksoft.de (localhost [127.0.0.1]) by transport.cksoft.de (Postfix) with ESMTP id F0A6B1FFDD4; Sat, 8 May 2004 20:25:59 +0200 (CEST) Received: by transport.cksoft.de (Postfix, from userid 66) id 134631FFDC1; Sat, 8 May 2004 20:25:58 +0200 (CEST) Received: by mail.int.zabbadoz.net (Postfix, from userid 1060) id 7F0D31566B; Sat, 8 May 2004 18:25:25 +0000 (UTC) Received: from localhost (localhost [127.0.0.1]) by mail.int.zabbadoz.net (Postfix) with ESMTP id 74413154E2; Sat, 8 May 2004 18:25:26 +0000 (UTC) Date: Sat, 8 May 2004 18:25:26 +0000 (UTC) From: "Bjoern A. Zeeb" X-X-Sender: bz@e0-0.zab2.int.zabbadoz.net To: =?ISO-8859-1?Q?S=F8ren_Schmidt?= In-Reply-To: <4044297F.1080701@DeepCore.dk> Message-ID: References: <20040302031226.GA670@xor.obsecurity.org> <4044297F.1080701@DeepCore.dk> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Virus-Scanned: by AMaViS cksoft-s20020300-20031204bz on transport.cksoft.de cc: freebsd-amd64@freebsd.org Subject: Re: NFS or ATA driver causes FS corruption? X-BeenThere: freebsd-amd64@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Porting FreeBSD to the AMD64 platform List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 08 May 2004 18:26:02 -0000 On Mon, 1 Mar 2004, it was written: Hi, > Kris Kennaway wrote: > > ad0: WARNING - WRITE_DMA interrupt was seen but timeout fired LBA=9440 > > ad0: WARNING - WRITE_DMA interrupt was seen but timeout fired LBA=20904 > > ad0: WARNING - WRITE_DMA interrupt was seen but timeout fired LBA=117560 > > ad0: WARNING - WRITE_DMA interrupt was seen but timeout fired LBA=206664 > > ad0: WARNING - WRITE_DMA interrupt was seen but timeout fired LBA=30312 > > The above means that *something* is stomping on the taskqueue that > should take care of returning finished requests to the system (they are > finished as the interrupt has been seen). I can avoid this by putting it > all back in interrupt context again as it was before, but it would be > better to get whatever it is that causes this fixed.. I have just setup my new amd64 machine and started to copy srces of HEAD over to it when it suddenly stopped responding (pings still worked). Didn't use NFS but a tar pipe over ssh for some reason. I am not yet on serial console so I went to the screen and got s.th. like the above plus some ad10: WARNING - WRITE_DMA interrupt was seen but taskqueue stalled LBA=... from time to time; the machine is running a 5.2.1 Release (as initial installation). Is there any way to temporary disable s.th. so I can get a HEAD srces copied, built and installed ? would changing hw.ata.ata_dma=0 help ? And is this problem already fix in HEAD at all ? Some specs (if it helps): atapci0: port 0xcc00-0xcc7f,0xdc00-0xdc0f,0xec00-0xec3f mem 0xf3a00000-0xf3a1ffff,0xf3b00000-0xf3b00fff irq 18 at device 8.0 on pci0 and atapci1: port 0xd000-0xd0ff,0xd400-0xd40f,0xd800-0xd803,0xe000-0xe007,0xe400-0xe403,0xe800-0xe807 irq 20 at device 15.0 on pci0 both on board. ad10: 156334MB [317632/16/63] at ata5-master UDMA100 the disk should be attached to the VIA controller. -- Greetings Bjoern A. Zeeb bzeeb at Zabbadoz dot NeT 56 69 73 69 74 http://www.zabbadoz.net/