From owner-freebsd-stable@FreeBSD.ORG Thu Feb 23 08:56:31 2012 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 28FAF1065670 for ; Thu, 23 Feb 2012 08:56:31 +0000 (UTC) (envelope-from ask@develooper.com) Received: from mbox1.develooper.com (mbox1.develooper.com [207.171.7.178]) by mx1.freebsd.org (Postfix) with ESMTP id 0ABDE8FC0C for ; Thu, 23 Feb 2012 08:56:30 +0000 (UTC) Received: (qmail 3670 invoked from network); 23 Feb 2012 08:56:26 -0000 Received: from cpe-76-172-28-38.socal.res.rr.com (HELO embla.bn.dev) (ask@mail.dev@76.172.28.38) by smtp.develooper.com with ESMTPA; 23 Feb 2012 08:56:26 -0000 Mime-Version: 1.0 (Apple Message framework v1257) Content-Type: text/plain; charset=iso-8859-1 From: =?iso-8859-1?Q?Ask_Bj=F8rn_Hansen?= In-Reply-To: Date: Thu, 23 Feb 2012 00:56:24 -0800 Content-Transfer-Encoding: quoted-printable Message-Id: <1E0D6546-49DE-478C-9759-FE496B1F0DB8@develooper.com> References: <770EEEFF-B41D-4851-AD74-C3F96FFB1683@develooper.com> To: Artem Belevich X-Mailer: Apple Mail (2.1257) Cc: freebsd-stable@freebsd.org, freebsd-zfs@freebsd.org Subject: Re: Can't read a full block, only got 8193 bytes. X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 23 Feb 2012 08:56:31 -0000 On Feb 19, 2012, at 12:10, Artem Belevich wrote: [...] >> "Can't read a full block, only got 8193 bytes." >=20 > That's probably just a side effect of ZFS checksum errors. ZFS will > happily read the file until it hits a record with checksum. If > redundant info is available (raidz or mirror), ZFS will attempt to > recover your data. If there's no redundancy you will get read error. > If you do "zpool status -v" you should see list of files affected by > corruption. Hi Artem, Thank you for the reply and the tips! =20 That makes sense and explains why we'd just get checksum errors on a = raidz1 test (but bonnie++ was happy except things were slow), but had = the weird errors on a single disk pool. >> This seems to only be when testing a single ZFS disk or a UFS = partition. Testing a raidz1 we just get checksum errors noted in zpool = status, but no errors reading (though read speeds are ~10MB/second = across four disks -- writing sequentially was ~230MB/second). >>=20 >> Any ideas where to start look? >=20 > You need to figure out why you're getting checksum errors. Alas > there's probably no easy way to troubleshoot it. The issue could be > hardware related and possible culprits may include bad RAM, bad SATA > cables, quirks of particular firmware revision on disk controller > and/or hard drive. Replacing the 3ware controller with a basic LSI controller fixed the = problems and improved performance, so I guess the 3ware controller = doesn't play nice with the Seagate 3TB disks (they're not on their = compatibility list). Ask