From mboxrd@z Thu Jan 1 00:00:00 1970 From: =?ISO-8859-1?Q?Micka=EBl_Can=E9vet?= Subject: Multiple disks per server. Date: Tue, 04 May 2010 14:18:25 +0200 Message-ID: <4BE01091.7040103@embl.fr> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: Received: from emblmta1.embl.fr ([193.49.43.176]:38949 "EHLO emblmta1.embl.fr" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758556Ab0EDM2G (ORCPT ); Tue, 4 May 2010 08:28:06 -0400 Sender: ceph-devel-owner@vger.kernel.org List-ID: To: ceph-devel@vger.kernel.org Hi, I'm testing ceph on 4 old servers. As there is more then one disk per server available for data (2 with 6=20 disks and 2 with 10 disks for a total of 32 disks over 4 nodes), I was=20 wondering how to define OSDs. I have choice between one OSD per disk (32 OSDs on the cluster) or one=20 OSD per server with one btrfs filesystem over all disks of the server (= 4=20 OSDs on the cluster). Which one is the best solution ? In the first case, if I lose one disk, I lose only a small part of=20 available space. In the other case, if I lose one disk, I lose the whol= e=20 server (as btrfs filesystem is in stripping) much more space. On the other hand, if I lose the whole server in the first case, I can=20 lose all replicates of a data because they may be on two different OSD=20 on the same server. Is there a way to define OSD groups so that we can be sure that 2=20 replicates are not on OSDs of the same group (could be usefull for=20 multiple OSDs per server, but also mutliple server per computing room -= =20 if I lose one whole room, a lot of server, I will be sure that I have=20 not lost every replicates). Thanks a lot. Micka=EBl -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" i= n the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html