From mboxrd@z Thu Jan 1 00:00:00 1970 From: Miles Fidelman Subject: Re: ceph for small cluster? Date: Mon, 31 Dec 2012 09:21:50 -0500 Message-ID: <50E19F7E.2000805@meetinghouse.net> References: <50E19E34.7080005@meetinghouse.net> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from server1.neighborhoods.net ([207.154.13.48]:36562 "EHLO server1.neighborhoods.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751187Ab2LaOVw (ORCPT ); Mon, 31 Dec 2012 09:21:52 -0500 Received: from localhost (localhost.localdomain [127.0.0.1]) by server1.neighborhoods.net (Postfix) with ESMTP id E59FECC0EA for ; Mon, 31 Dec 2012 09:21:51 -0500 (EST) Received: from server1.neighborhoods.net ([127.0.0.1]) by localhost (server1.neighborhoods.net [127.0.0.1]) (amavisd-new, port 10024) with LMTP id R87lt98kpZu5 for ; Mon, 31 Dec 2012 09:21:50 -0500 (EST) Received: from new-host-2.home (pool-71-184-234-147.bstnma.fios.verizon.net [71.184.234.147]) by server1.neighborhoods.net (Postfix) with ESMTPSA id 8BB54CC0DE for ; Mon, 31 Dec 2012 09:21:50 -0500 (EST) In-Reply-To: <50E19E34.7080005@meetinghouse.net> Sender: ceph-devel-owner@vger.kernel.org List-ID: To: ceph-devel Wido, Thanks for the comment, a follow-up if I might (below)? Wido den Hollander wrote: > > I build some small Ceph cluster with sometimes just 3 nodes. It works, > but you have to keep in mind that when one node in a 4 node cluster > fails you will loose 25% of the capacity. > > This will lead to a heavy recovery within the Ceph cluster which will > but a lot of pressure on that Gbit links and the CPUs and memory of > the nodes. > > With RBD you might want to consider adding an SSD for the journaling > of the OSDs, that will give you a pretty nice performance boost. > Would not journalling alone, say on a separate hard disk volume, help with recovery? Thanks, Miles -- In theory, there is no difference between theory and practice. In practice, there is. .... Yogi Berra