From owner-freebsd-current@FreeBSD.ORG Mon Feb 9 23:20:24 2004 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 62FF516A4D0 for ; Mon, 9 Feb 2004 23:20:24 -0800 (PST) Received: from fed1mtao02.cox.net (fed1mtao02.cox.net [68.6.19.243]) by mx1.FreeBSD.org (Postfix) with ESMTP id E0F9943D39 for ; Mon, 9 Feb 2004 23:20:06 -0800 (PST) (envelope-from housel@acm.org) Received: from ip68-4-96-119.oc.oc.cox.net ([68.4.96.119]) by fed1mtao02.cox.netESMTP <20040210072006.ZFEF23539.fed1mtao02.cox.net@ip68-4-96-119.oc.oc.cox.net>; Tue, 10 Feb 2004 02:20:06 -0500 Received: from NOMAD (housel@ip68-4-96-119.oc.oc.cox.net [68.4.96.119]) i1A7K44n001077; Mon, 9 Feb 2004 23:20:05 -0800 (PST) (envelope-from housel@acm.org) Message-ID: <002801c3efa6$4e8cb640$0300000a@NOMAD> From: "Peter S. Housel" To: "Axel Gonzalez" , References: <200402090722.19717.loox@e-shell.net> Date: Mon, 9 Feb 2004 23:20:03 -0800 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2800.1158 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1165 Subject: Re: sata drive problem X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.1 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: Tue, 10 Feb 2004 07:20:24 -0000 "Axel Gonzalez" wrote: > When under heavy load, i get the error (just tested from a cvsup 09/02/2004 > src): > ad4: TIMEOUT - WRITE_DMA retrying (2 retries left) LBA=... > ad4: TIMEOUT - WRITE_DMA retrying (2 retries left) LBA=... > sometimes it crashes right away, sometimes it waits a little. > can't get the exact LBA sectors because the system crashes cold, and its not > logged (i've seen the error before a crash) I've seen the exact same problem with the same controller (Intel ICH5 SATA150). The problem went away when I turned off hyperthreading. With WITNESS turned on, the TIMEOUT messages were accompanied with some locking message or other, but I haven't had a chance to reproduce the problem and record the exact message. Given this, and the fact that it goes away when running UP, I speculate that it may be a locking problem somewhere. -Peter-