From owner-freebsd-fs@FreeBSD.ORG Sat Feb 25 15:56:57 2012 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 38C30106566C for ; Sat, 25 Feb 2012 15:56:57 +0000 (UTC) (envelope-from bfriesen@simple.dallas.tx.us) Received: from blade.simplesystems.org (blade.simplesystems.org [65.66.246.74]) by mx1.freebsd.org (Postfix) with ESMTP id ECBE98FC08 for ; Sat, 25 Feb 2012 15:56:56 +0000 (UTC) Received: from freddy.simplesystems.org (freddy.simplesystems.org [65.66.246.65]) by blade.simplesystems.org (8.14.4+Sun/8.14.4) with ESMTP id q1PFuqn6015039; Sat, 25 Feb 2012 09:56:52 -0600 (CST) Date: Sat, 25 Feb 2012 09:56:52 -0600 (CST) From: Bob Friesenhahn X-X-Sender: bfriesen@freddy.simplesystems.org To: Peter Maloney In-Reply-To: <4F48A402.70009@brockmann-consult.de> Message-ID: References: <3E3E4094-77E2-490B-9574-5B95ECDED447@pean.org> <4F48A402.70009@brockmann-consult.de> User-Agent: Alpine 2.01 (GSO 1266 2009-07-14) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.2.2 (blade.simplesystems.org [65.66.246.90]); Sat, 25 Feb 2012 09:56:52 -0600 (CST) Cc: freebsd-fs@freebsd.org Subject: Re: glabel, gpart and zfs confusion. 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: Sat, 25 Feb 2012 15:56:57 -0000 On Sat, 25 Feb 2012, Peter Maloney wrote: > In Solaris, I've read that the IO system is designed such that a some > commands (eg. flush of a partition) does not necessarily flush the > disk's write cache... like the command can't move up the chain. So if > you put zfs on a partition, you can get data loss (eg. transaction > rollback required and probably no corruption). I wonder where you read that since it seems like bad information? In Solaris, if zfs uses a partition (rather than the whole disk), the disk write cache is not enabled by default due to the possibility that some other partition uses a legacy filesystem like UFS, which could become inconsistent and corrupted if the write cache is enabled. The drawback then becomes that zfs writes are likely to incur more latency. > In FreeBSD, things are different I am told, without the above > limitation. So you can happily put zfs on partitions, and the zfs code > can keep your data safe. I haven't had data loss with system panics > during sync writes with my ZIL on a partition, so I guess this must be true. It seems unlikely that FreeBSD zfs is somehow "safer" than Solaris zfs. Both rely on a disk cache flush request to write buffered data to disk. Synchronous writes necessarily require that the zil (zfs intent log) be flushed to disk before write returns success to the user. Bob -- Bob Friesenhahn bfriesen@simple.dallas.tx.us, http://www.simplesystems.org/users/bfriesen/ GraphicsMagick Maintainer, http://www.GraphicsMagick.org/