From owner-freebsd-questions@FreeBSD.ORG Mon May 9 18:07:41 2005 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 55B2C16A4EA for ; Mon, 9 May 2005 18:07:41 +0000 (GMT) Received: from cartman.xxiii.com (cartman.xxiii.com [208.62.177.45]) by mx1.FreeBSD.org (Postfix) with ESMTP id 86D3C43D55 for ; Mon, 9 May 2005 18:07:40 +0000 (GMT) (envelope-from wc_fbsd@xxiii.com) Received: from PC02.xxiii.com (lan23.xxiii.com [208.62.177.50]) by cartman.xxiii.com (8.12.10/8.12.10) with ESMTP id j49I7Wva024841; Mon, 9 May 2005 14:07:32 -0400 (EDT) (envelope-from wc_fbsd@xxiii.com) Message-Id: <6.0.1.1.2.20050509135612.028498f8@mailsvr.xxiii.com> X-Sender: (Unverified) X-Mailer: QUALCOMM Windows Eudora Version 6.0.1.1 Date: Mon, 09 May 2005 14:07:32 -0400 To: Chris Fedde , freebsd-questions@freebsd.org From: WMC In-Reply-To: <200505091720.j49HKHAM097093@fedde.littleton.co.us> References: <200505091720.j49HKHAM097093@fedde.littleton.co.us> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed X-Content-Filtered-By: Mailman/MimeDel 2.1.1 Subject: Re: swap space problems X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 09 May 2005 18:07:41 -0000 At 01:20 PM 5/9/2005, Chris Fedde wrote: >Occasionaly my system hangs for a few seconds while loading a process >from swap that has been idle for some time. > ad0: TIMEOUT - WRITE_DMA retrying (2 retries left) LBA=161663 What type of driver interface and controller is this? And what FBSD version? I used to get this error when I was trying to get a SATA drive working last summer. There were bugs in the ata driver (circa 5.2.1) that are about 96% fixed in 5.3. It would happen under heavy disk IO doing a lot of random seeks. The hang really is a hang, not just a delay from the swapping activity. 40 or 50% of the time, it resulted in a "hard" full system hang (ie: had to power cycle or hit the reset button.) Often there was severe data corruption, also. -Wayne