From owner-freebsd-fs@FreeBSD.ORG Thu Jul 4 14:30:25 2013 Return-Path: Delivered-To: freebsd-fs@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) by hub.freebsd.org (Postfix) with ESMTP id E6B7A3FD for ; Thu, 4 Jul 2013 14:30:25 +0000 (UTC) (envelope-from bofh@terranova.net) Received: from tog.net (tog.net [IPv6:2605:5a00::5]) by mx1.freebsd.org (Postfix) with ESMTP id BC3F91914 for ; Thu, 4 Jul 2013 14:30:25 +0000 (UTC) Received: from [IPv6:2605:5a00:ffff::face] (unknown [IPv6:2605:5a00:ffff::face]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by tog.net (Postfix) with ESMTPSA id 3bmM6T2LlYz6x9 for ; Thu, 4 Jul 2013 10:30:25 -0400 (EDT) Message-ID: <51D586F9.7060508@terranova.net> Date: Thu, 04 Jul 2013 10:30:17 -0400 From: Travis Mikalson Organization: TerraNovaNet Internet Services User-Agent: Thunderbird 2.0.0.24 (Windows/20100228) MIME-Version: 1.0 To: freebsd-fs@FreeBSD.org Subject: Re: Report: ZFS deadlock in 9-STABLE References: <51D45401.5050801@terranova.net> <51D5776F.5060101@FreeBSD.org> <51D57C19.1080906@terranova.net> <51D5804B.7090702@FreeBSD.org> In-Reply-To: <51D5804B.7090702@FreeBSD.org> X-Enigmail-Version: 0.96.0 OpenPGP: url=http://www.terranova.net/pgp/bofh Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 04 Jul 2013 14:30:26 -0000 Andriy Gapon wrote: > on 04/07/2013 16:43 Travis Mikalson said the following: >> Yes, that helpful article is where I got the run-down on how best to >> report what was going on here. I still believe this is an actual >> deadlock bug and not a storage layer issue. >> >> I have not seen any indications of any problems with my storage layer. >> You'd think there would be some scary-looking complaint on the console >> during one of these deadlocks if it had suddenly lost the capability to >> communicate with most or all the disks, but I've deadlocked at least 10 >> times now in 2013 and never anything of the sort. Thanks to IPMI, I have >> actually viewed the console each time it has happened. > > Well, I do consider GEOM, CAM, drivers to be parts of the storage layer. > In other words, everything below ZFS. Ah, I believe I understand. It's not necessarily a hardware issue (which is what I took away from the original verbage), the deadlock may have occurred in other parts of the storage layer. FWIW, my simple UFS compact flash that I boot from also becomes inaccessible during these deadlocks. All UFS and ZFS storage goes dead simultaneously. If it were purely a ZFS issue, I suppose one might expect to still be able to read from their UFS filesystem.