From owner-freebsd-current@FreeBSD.ORG Fri Dec 18 11:48:48 2009 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id AAD7D1065676 for ; Fri, 18 Dec 2009 11:48:48 +0000 (UTC) (envelope-from alexz@visp.ru) Received: from mail.visp.ru (srv1.visp.ru [91.215.204.2]) by mx1.freebsd.org (Postfix) with ESMTP id 590A58FC13 for ; Fri, 18 Dec 2009 11:48:48 +0000 (UTC) Received: from 91-215-205-255.static.visp.ru ([91.215.205.255] helo=zagrebin) by mail.visp.ru with esmtp (Exim 4.66 (FreeBSD)) (envelope-from ) id 1NLbK9-0009UP-WC; Fri, 18 Dec 2009 14:48:46 +0300 From: "Alexander Zagrebin" To: "'Andriy Gapon'" References: <39309F560B98453EBB9AEA0F29D9D80E@vosz.local><4C1C2598-4157-4B04-8DB8-C84F353AB8B8@nevada.net.nz><6FAA390A-1E40-4D7A-AAD5-DC72578CE974@nevada.net.nz> <200912182027.11632.doconnor@gsoft.com.au><5C4BD0F81D1348B287B2ECD55EF283E1@vosz.local> <4B2B67FB.80705@icyb.net.ua> Date: Fri, 18 Dec 2009 14:48:45 +0300 Keywords: freebsd-current Message-ID: <4F5E9203FBE0440780E31C376646F5B0@vosz.local> MIME-Version: 1.0 Content-Type: text/plain; charset="koi8-r" Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Office Outlook 11 Thread-Index: Acp/1bhIM7OemahPRHmeyGWtuJPGLAAAWbmQ X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.5512 In-Reply-To: <4B2B67FB.80705@icyb.net.ua> Cc: freebsd-current@freebsd.org Subject: RE: 8.0-RELEASE: disk IO temporarily hangs up (ZFS or ATA related problem) X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 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: Fri, 18 Dec 2009 11:48:48 -0000 > >> I doubt this is the problem, I have WD10EADS disks in my ZFS > >> array and I > >> see the same issue. > >> > >> It strikes me as extremely unlikely that both of us would have dud > >> disks.. > >> > >> In any case it seems to be a general problem not limited to > >> one area of > >> the disk so a dud sector is an unlikely reason. > > > > Big thanks for confirmation! > > Your confirmation is important for me. > > There should be a way to define where the bug is: in the > ata (or filesystem) > > driver or in the drive's firmware.... > > Just another 'me too'. > >From the moment I started using zfs and till this day I saw > this pattern when > writing lots data to zfs - first high throughput and then > idle pause, and so on. May be it usual write caching? See gstat or iostat output. At my case gstat shows abnormal value of %busy (usually approx. 180%) and very long ms/r and ms/w. -- Alexander Zagrebin