From mboxrd@z Thu Jan 1 00:00:00 1970 From: Konrad Rzeszutek Wilk Subject: Re: quick question re blkback/blkfront w/ Xen 4.1.2 Date: Thu, 22 Mar 2012 17:55:04 -0400 Message-ID: <20120322215504.GC12985@phenom.dumpdata.com> References: <20120319174325.GA5063@phenom.dumpdata.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Content-Disposition: inline In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Steven Noonan Cc: xen-devel@lists.xensource.com List-Id: xen-devel@lists.xenproject.org On Mon, Mar 19, 2012 at 10:51:22AM -0700, Steven Noonan wrote: > On Mon, Mar 19, 2012 at 10:43 AM, Konrad Rzeszutek Wilk > wrote: > > On Tue, Feb 28, 2012 at 04:41:44PM -0800, Steven Noonan wrote: > >> With a PV guest on Xen 4.1.2 (Linux 3.2.2 dom0), I'm noticing that while > >> block I/O is happening the event channel interrupt count in > >> dom0:/proc/interrupts isn't incrementing at all. How can this be? > > > > Hey Steven, > > > > Sorry about late response - was on paternity leave (and is a bit this > > week). I am CC-ing the xen-devel on this. > > > > I tried it and the numbers do seem to increment on my side. > > You were looking at the blkif numbers right? Is this with a 2.6.18 guest > > or a 3.2? > > > > Yeah, I got your message about paternity leave. Congrats! :) > > It's a Linux 3.2 dom0 (I believe it's untouched vanilla) and Linux 3.2 > domU (Ubuntu 12.04 beta, with 3.2.0-based Ubuntu kernel, PV). OK, let me try to reproduce this. > > And yes, blkif-backend. It's strange, because I/O seems to happen just > fine (and it's definitely not going through QEMU, since it's a PV > guest and the devices are clearly registered as VBDs), but the > interrupt counts are frozen. > > _______________________________________________ > Xen-devel mailing list > Xen-devel@lists.xen.org > http://lists.xen.org/xen-devel