From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stan Hoeppner Subject: Re: Raid 0+1 Date: Sat, 01 Dec 2012 20:10:17 -0600 Message-ID: <50BAB889.2090308@hardwarefreak.com> References: <50B8C26C.7000807@profitbricks.com> <50B8C55E.1050902@profitbricks.com> Reply-To: stan@hardwarefreak.com Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: Sender: linux-raid-owner@vger.kernel.org To: Oguz Yilmaz Cc: Sebastian Riemer , linux-raid@vger.kernel.org List-Id: linux-raid.ids On 12/1/2012 7:11 AM, Oguz Yilmaz wrote: > Why do we need another storage server. You don't. > IF I create > md0 Raid0 (sda1 + sda2) > md1 Raid0 (sdc1 + sdc2) > > then is it possible to create > md2 Raid1 (md0 + md1) > > like md? Sure, you can do this. One downside is you can never expand it WRT capacity or effective spindles. The only way to get there is to put the RAID1 device in a linear device and grow more of these 4 device RAID 0+1 devices into the linear device. This setup requires an allocation group based filesystem, XFS, to get anything near linear scaling across the drives. But for that your application must exhibit file level parallelism, i.e. reading/writing many dozens of files in parallel, and with inode64 mount, they must be in different directories. Otherwise you IO won't scale across your disks. -- Stan