From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ray Van Dolson Subject: Re: Data De-duplication Date: Wed, 10 Dec 2008 13:19:03 -0800 Message-ID: <20081210211903.GA29002@bludgeon.org> References: <1228862899.8130.1.camel@mattos-laptop> <1228915802.11900.8.camel@think.oraclecorp.com> <32809.2001:470:e828:1::2:2.1228939660.squirrel@avalon.arbitraryconstant.com> <1228943437.7571.1.camel@mattos-laptop> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: btrfs-devel@arbitraryconstant.com, Chris Mason , linux-btrfs@vger.kernel.org To: Oliver Mattos Return-path: In-Reply-To: <1228943437.7571.1.camel@mattos-laptop> List-ID: I lost the original post so I'm jumping in at the wrong thread-point :) Someone mentioned that the primary usage of de-dup is in the backup realm. True perhaps currently, but de-dup IMO is *the* killer app in the world of virtualization and is a huge reason why we're picking NetApp at work to back our NFS VMware DataStores. We easily see 50% savings in space. I know of only one other production filesystem implementation of data-dedup -- GreenBytes has it in their ZFS-based storage product. I'm not sure why this hasn't caught on, but as soon as a solid and fast implementation of it exists in the Linux world I really think it can catch on for VM datastores.... I know we've hollered at Sun as to why they haven't rolled it out for ZFS yet! Anyways, I know it's on the roadmap, just like throwing my $0.02 once in a while on how big a feature I think this could be...... Great job all :) Ray