From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andy Subject: Re: Re: IO scheduler based IO controller V10 Date: Wed, 7 Oct 2009 15:23:56 -0500 Message-ID: <20091007202356.GA2624@thumper2> References: <20091006.161744.189719641.ryov@valinux.co.jp> <20091006112201.GA27866@redhat.com> <20091007.233805.183040347.ryov@valinux.co.jp> <4ACCC4B7.4050805@redhat.com> Reply-To: device-mapper development Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <4ACCC4B7.4050805@redhat.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: dm-devel-bounces@redhat.com Errors-To: dm-devel-bounces@redhat.com To: device-mapper development List-Id: dm-devel.ids On Wed, Oct 07, 2009 at 12:41:27PM -0400, Rik van Riel wrote: > Ryo Tsuruta wrote: > > >If once dm-ioband is integrated into the LVM tools and bandwidth can > >be assigned per device by lvcreate, the use of dm-tools is no longer > >required for users. > > A lot of large data center users have a SAN, with volume management > handled SAN-side and dedicated LUNs for different applications or > groups of applications. > > Because of alignment issues, they typically use filesystems directly > on top of the LUNs, without partitions or LVM layers. We cannot rely > on LVM for these systems, because people prefer not to use that. > I am one of these people that does not use LVM, because I have no need to with the SAN. The SAN spreads the volume across many disks, I do not need to do it. LVM would add layers of complexity than I do not need. I do use currently use EVMS to allow me to expand volumes without rebooting. But, with the newer kernels I do not even need that since I can just expand the LUN and the the filesystem (I do not use partitions either). Why was device-mapper stuff moved into LVM2? IMHO it should have stayed separate. Andy