From mboxrd@z Thu Jan 1 00:00:00 1970 From: Konrad Rzeszutek Wilk Subject: Re: [Xen-users] Re: VM disk I/O limit patch Date: Wed, 22 Jun 2011 09:07:10 -0400 Message-ID: <20110622130710.GA8216@dumpdata.com> References: <20110621162935.F4A1.3A8D29D5@cloudex.cn> <20110621133337.GD5650@dumpdata.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: Florian Heigl Cc: Andrew Xu , xen-devel@lists.xensource.com, xen-users@lists.xensource.com List-Id: xen-devel@lists.xenproject.org On Wed, Jun 22, 2011 at 02:16:09PM +0200, Florian Heigl wrote: > Hi, > > relying on DM is not advisable since this is yet another layer that > breaks write barriers, plus it kills portability to non-linux OS. How so? And write barriers don't exist anymore - I think you mean flush support. And I believe they are fixed now - flush requests are passed through to the bottom layer (the real disk). But let me double check that shortly. Portability to non-linux OS? ? What do you mean by that? As in using this patch on NetBSD or OpenSolaris backend? The backend in those OS-es is quite different so it wouldn't be "portable" > > btw: > It would be cool if a block shaping patch finally made it in the Xen > mainline, since the last one that was submitted in 2009 was apparently > forgotten... Why can't dm-ioband do this for you? Hm, I don't remember seeing that patch at all?