From owner-freebsd-fs@FreeBSD.ORG Mon Apr 7 08:52:01 2008 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 98F031065672 for ; Mon, 7 Apr 2008 08:52:01 +0000 (UTC) (envelope-from uspoerlein@gmail.com) Received: from acme.spoerlein.net (cl-43.dus-01.de.sixxs.net [IPv6:2a01:198:200:2a::2]) by mx1.freebsd.org (Postfix) with ESMTP id 2BD028FC1D for ; Mon, 7 Apr 2008 08:52:00 +0000 (UTC) (envelope-from uspoerlein@gmail.com) Received: from acme.spoerlein.net (localhost.spoerlein.net [127.0.0.1]) by acme.spoerlein.net (8.14.2/8.14.2) with ESMTP id m378pwwF030377 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Mon, 7 Apr 2008 10:51:58 +0200 (CEST) (envelope-from uspoerlein@gmail.com) Received: (from uqs@localhost) by acme.spoerlein.net (8.14.2/8.14.2/Submit) id m378puWe030376; Mon, 7 Apr 2008 10:51:56 +0200 (CEST) (envelope-from uspoerlein@gmail.com) Date: Mon, 7 Apr 2008 10:51:56 +0200 From: Ulrich Spoerlein To: Attila Nagy Message-ID: <20080407085156.GA30355@acme.spoerlein.net> References: <47F0D02B.8060504@fsn.hu> <20080331152251.62526181@peedub.jennejohn.org> <47F0EDD6.8060402@fsn.hu> <47F0F1E8.1080504@fsn.hu> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <47F0F1E8.1080504@fsn.hu> User-Agent: Mutt/1.5.17 (2007-11-01) Cc: freebsd-fs@freebsd.org Subject: Re: ZFS hangs very often X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 07 Apr 2008 08:52:01 -0000 On Mon, 31.03.2008 at 05:15:14 +0000, Attila Nagy wrote: > On 2008.03.31. 15:57, Attila Nagy wrote: > > My system completely locks up, I can't start new processes, but > > runnings ones -which don't do IO- can continue (for example a top). > > I don't know ZFS internals (BTW, /usr and others are of course > > different ZFS filesystems on the pool), but it might be, that > > something major gets locked and that's why it stops here. > > > > Anyways, if somebody can help to back this out, I'm here to try > > patches, or do experiments. > I forgot to tell -I don't know, maybe it's important-, that I have an > SMP box (but tried with UP kernel, the effect is the same) and > compression is enabled on every filesystems. Hi, I had frequent deadlocks as you just describe when using GMIRROR on SMP systems and running with PREEMPTION. Could you try a kernel without PREEMPTION? Or perhaps break the GMIRRORs for testing purposes? Cheers, Ulrich Spoerlein -- It is better to remain silent and be thought a fool, than to speak, and remove all doubt.