From owner-freebsd-fs@FreeBSD.ORG Wed Sep 29 15:19:10 2010 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 07EDA106566C for ; Wed, 29 Sep 2010 15:19:10 +0000 (UTC) (envelope-from kpielorz_lst@tdx.co.uk) Received: from mail.tdx.com (mail.tdx.com [62.13.128.18]) by mx1.freebsd.org (Postfix) with ESMTP id 983FA8FC0C for ; Wed, 29 Sep 2010 15:19:09 +0000 (UTC) Received: from HexaDeca64.dmpriest.net.uk (HPQuadro64.dmpriest.net.uk [62.13.130.30]) (authenticated bits=0) by mail.tdx.com (8.14.3/8.14.3/Kp) with ESMTP id o8TFJ74e061126 (version=TLSv1/SSLv3 cipher=DHE-DSS-AES256-SHA bits=256 verify=NO); Wed, 29 Sep 2010 16:19:08 +0100 (BST) Date: Wed, 29 Sep 2010 16:18:21 +0100 From: Karl Pielorz To: Jeremy Chadwick Message-ID: <24249EBE70346EDE973308F6@HexaDeca64.dmpriest.net.uk> In-Reply-To: <20100929151111.GA91705@icarus.home.lan> References: <20100929151111.GA91705@icarus.home.lan> X-Mailer: Mulberry/4.0.8 (Win32) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline Cc: freebsd-fs@freebsd.org Subject: Re: FreeBSD 8.1-R/amd64 - zfs 'hangs' - help tracing? 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: Wed, 29 Sep 2010 15:19:10 -0000 --On 29 September 2010 08:11 -0700 Jeremy Chadwick wrote: > Can you provide (with the disks hooked to an ATA/SATA controller and > the system not wedged waiting for ZFS I/O) the output from smartctl > (you'll probably have to install ports/sysutils/smartmontools) as: > > smartctl -a /dev/adXX (one command per device) > > I can review these statistics to see if any of the disks look like they > may be misbehaving. > > It would also help if you could provide dmesg output associated with the > ATA/SATA controller which they're hooked to. I can do - I'll try to get all the relevant stuff up on a site and send you the URL (i.e. dmesg output, zpool status output, smartctl output etc.) The same system works fine under 7.2-Stable with the same drives, hardware etc. - But under 8.1 anything more than "a ZFS little I/O" (e.g. scrubs, copying lots of files etc.) - and it just hangs at a random point, with no error given - and anything that touches the zpool 'hangs next'. I already run smartmontools - though it's currently disabled (incase it was that causing issues). The drives on the whole look OK, I think two have picked up a couple of reallocated blocks (and failed reads) - but it's nothing that's increasing or anything - and like I said, 7.2-S is fine with the same setup... If I break to KDB with the current system, is there anything I can do to get a better look at what's hung up/where? -Karl