From owner-freebsd-current@FreeBSD.ORG Wed Nov 10 09:41:32 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 96E2B16A4CE; Wed, 10 Nov 2004 09:41:32 +0000 (GMT) Received: from spider.deepcore.dk (cpe.atm2-0-53484.0x50a6c9a6.abnxx9.customer.tele.dk [80.166.201.166]) by mx1.FreeBSD.org (Postfix) with ESMTP id DFB1D43D49; Wed, 10 Nov 2004 09:41:31 +0000 (GMT) (envelope-from sos@DeepCore.dk) Received: from [194.192.25.143] (laptop.deepcore.dk [194.192.25.143]) by spider.deepcore.dk (8.12.11/8.12.10) with ESMTP id iAA9fR5g034663; Wed, 10 Nov 2004 10:41:29 +0100 (CET) (envelope-from sos@DeepCore.dk) Message-ID: <4191E21C.5040307@DeepCore.dk> Date: Wed, 10 Nov 2004 10:40:44 +0100 From: =?ISO-8859-1?Q?S=F8ren_Schmidt?= User-Agent: Mozilla Thunderbird 0.7.2 (X11/20040802) X-Accept-Language: en-us, en MIME-Version: 1.0 To: Robert Watson References: In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: quoted-printable X-mail-scanned: by DeepCore Virus & Spam killer v1.4 cc: Zoltan Frombach cc: freebsd-current@freebsd.org Subject: Re: 5.3-RELEASE: WARNING - WRITE_DMA interrupt timout - what does it mean? 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: Wed, 10 Nov 2004 09:41:32 -0000 Robert Watson wrote: >>It means that the disk has processed the write request (interrupt seen)= , >>but that the system (the bio_taskqueue) hasn't been able to get the >>result returned to the kernel.=20 >> >>Your disk is not involved in this problem since it has done its part, >>but the rest of the system is either busy with something else, or there= >>are bugs lurking that prohibits the bio_taskqueue from running.=20 >> >>Either way its a WARNING not a FAILURE :)=20 >=20 >=20 > I'm still a bit skeptical that the task queue is at fault -- I run my > notebook with continuous measurement of the latency to schedule tasks, > generating a warning for any latency > .5 seconds, and the only time I > ever see that sort of latency is during the boot process when ACPI has > scheduled a task to run, but the task queue thread has not yet been > allowed to run: Right, the timeout is 5 secs. I havn't looked into how the taskqueues=20 are handled recently, but in case of ATA read/writes it is the=20 bio_taskqueue handled by geom thats in use not the catchall ones, does=20 your timing cover that as well? There are several explanations for what happens: 1. the bio_taskqueue is not pushing requests through. 2. the disks takes long to respond and uses almost all of the 5 secs 3. timeouts are not working and fireing at random. I cannot reproduce the symptoms on any of my HW no matter how hard I hit = it, and I dont really belive in items 2 and 3 above, however I've been=20 proven wrong before :) --=20 -S=F8ren