From owner-freebsd-stable@FreeBSD.ORG Thu May 26 21:04:24 2005 Return-Path: X-Original-To: freebsd-stable@freebsd.org Delivered-To: freebsd-stable@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 661B116A424 for ; Thu, 26 May 2005 21:04:24 +0000 (GMT) (envelope-from freebsd-current@byrnehq.com) Received: from schubert.byrnehq.com (dsl-33-12.dsl.netsource.ie [213.79.33.12]) by mx1.FreeBSD.org (Postfix) with ESMTP id C75DE43D48 for ; Thu, 26 May 2005 21:04:23 +0000 (GMT) (envelope-from freebsd-current@byrnehq.com) Received: from localhost ([192.168.10.1]) by schubert.byrnehq.com (8.13.3/8.13.3) with ESMTP id j4QM3ABt057194 for ; Thu, 26 May 2005 22:03:11 GMT (envelope-from freebsd-current@byrnehq.com) Date: Thu, 26 May 2005 22:04:24 +0100 From: Tony Byrne Organization: ByrneHQ X-Priority: 3 (Normal) Message-ID: <1936063736.20050526220424@byrnehq.com> To: freebsd-stable@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-ByrneHQ-SA-Hits: -0.945 X-Scanned-By: MIMEDefang 2.51 on 192.168.10.254 Subject: ATA Timeouts X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Tony Byrne List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 26 May 2005 21:04:24 -0000 Folks, We have an up-to date FreeBSD 5.4 Stable server that has suddenly started experiencing timeouts while reading and writing its 200Gb Western Digital SATA hard disk. We see at least one read / write timeout with kernel message every fifteen minutes or so and the box becomes sluggish while the IO is retried. The server has an Intel ICH5 SATA disk controller. I temporarily moved the disk to a recent 5.4 desktop machine equipped with the same chipset and the timeouts stopped, so it appears that the problem is not with the disk. I also tried Soren's ATA mkIII patches on the server, but the problem remains. Since the controller is built onto the Intel server board, we're tempted to try another brand of SATA disk. Does anyone have any ideas as to what could cause a previously happy server to start behaving this way? Regards, Tony. -- Tony Byrne