From: Christoph Hellwig Subject: Re: [RFC] basic delayed allocation in VFS Date: Sat, 28 Jul 2007 20:57:14 +0100 Message-ID: <20070728195714.GD5952@infradead.org> References: <46A8628D.6070103@clusterfs.com> <46A87858.40005@garzik.org> <46A878FC.5040600@clusterfs.com> <46A88DFD.7030609@garzik.org> <46A8A294.2070106@clusterfs.com> <20070727050714.GS12413810@sgi.com> <46A9E754.5070904@clusterfs.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: David Chinner , Jeff Garzik , ext4 development , linux-fsdevel@vger.kernel.org, Christoph Hellwig To: Alex Tomas Return-path: Received: from pentafluge.infradead.org ([213.146.154.40]:34973 "EHLO pentafluge.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753328AbXG1T5S (ORCPT ); Sat, 28 Jul 2007 15:57:18 -0400 Content-Disposition: inline In-Reply-To: <46A9E754.5070904@clusterfs.com> Sender: linux-ext4-owner@vger.kernel.org List-Id: linux-ext4.vger.kernel.org On Fri, Jul 27, 2007 at 04:38:44PM +0400, Alex Tomas wrote: > I just realized that you're talking about data=ordered mode in ext4, > where care is taken to prevent on-disk references to no-yet-written > blocks. Any reference to non-written blocks is a bug.