From owner-freebsd-fs@FreeBSD.ORG Mon Jun 7 16:55:38 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 D512B106567B for ; Mon, 7 Jun 2010 16:55:38 +0000 (UTC) (envelope-from martin@lispworks.com) Received: from lwfs1-cam.cam.lispworks.com (mail.lispworks.com [193.34.186.230]) by mx1.freebsd.org (Postfix) with ESMTP id 6719D8FC23 for ; Mon, 7 Jun 2010 16:55:34 +0000 (UTC) Received: from higson.cam.lispworks.com (IDENT:U2FsdGVkX1+YcVTcmnofzCojPtvAIFHitg0ZVF99qqI@higson [192.168.1.7]) by lwfs1-cam.cam.lispworks.com (8.14.3/8.14.3) with ESMTP id o57GtTne086545; Mon, 7 Jun 2010 17:55:29 +0100 (BST) (envelope-from martin@lispworks.com) Received: from higson.cam.lispworks.com by higson.cam.lispworks.com (8.13.1) id o57GtSxK029970; Mon, 7 Jun 2010 17:55:28 +0100 Received: (from martin@localhost) by higson.cam.lispworks.com (8.13.1/8.13.1/Submit) id o57GtSBg029967; Mon, 7 Jun 2010 17:55:28 +0100 Date: Mon, 7 Jun 2010 17:55:28 +0100 Message-Id: <201006071655.o57GtSBg029967@higson.cam.lispworks.com> From: Martin Simmons To: freebsd-fs@freebsd.org In-reply-to: <20100607121954.GA52932@icarus.home.lan> (message from Jeremy Chadwick on Mon, 7 Jun 2010 05:19:54 -0700) References: <4C0CAABA.2010506@icyb.net.ua> <20100607083428.GA48419@icarus.home.lan> <4C0CB3FC.8070001@icyb.net.ua> <20100607090850.GA49166@icarus.home.lan> <201006071112.o57BCGMf027496@higson.cam.lispworks.com> <20100607121954.GA52932@icarus.home.lan> Subject: Re: zfs i/o error, no driver error 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 Jun 2010 16:55:38 -0000 >>>>> On Mon, 7 Jun 2010 05:19:54 -0700, Jeremy Chadwick said: > > Which brings us to the topic of scrub interval... > > This exact question was asked on the ZFS OpenSolaris list[6] in late > 2008, and nobody there provided any concrete evidence either. The > closest thing to evidence is this: > > "...in normal operation, ZFS only checks data as it's read back from the > disks. If you don't periodically scrub, errors that happen over time > won't be caught until I next read that actual data, which might be > inconvenient if it's a long since the initial data was written". The question can't be answered with absolute numbers, because it depends on other factors such as environmental effects. > The topic of scrub intervals was also brought up a month later[7]. > Someone said: > > "We did a study on re-write scrubs which showed that once per year was a > good interval for modern, enterprise-class disks. However, ZFS does a > read-only scrub, so you might want to scrub more often". > > The first part conflicts with what the guide recommends (I'd also like > to see the results of the study!), while the last half of the paragraph > makes no sense ("because it reads, do it more often!"). So if you take > the first sentence and apply it to what the ZFS Best Practices Guide > says, you come out with... "scrub consumer-grade disks every 6 months". It doesn't conflict if you agree that freshly written data is more likely to be readable that data written long ago (with some curve in between). The re-write scrub they are talking about will write all of the data back to the disks during the scrubbing operation, which makes it fresher. ZFS OTOH performs read-only scrubs, i.e. it just checks that the data can be read. It only writes if there was a problem reading from one of the disks. I don't know if there is any science behind that theory... __Martin