From mboxrd@z Thu Jan 1 00:00:00 1970 From: Keir Fraser Subject: Re: [PATCH] x86/S3: Restore broken vcpu affinity on resume (v4) Date: Wed, 03 Apr 2013 15:29:56 +0100 Message-ID: References: <515AA9BE02000078000C9FEE@nat28.tlf.novell.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <515AA9BE02000078000C9FEE@nat28.tlf.novell.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Jan Beulich , Ben Guthro Cc: George Dunlap , "xen-devel@lists.xen.org" List-Id: xen-devel@lists.xenproject.org On 02/04/2013 08:49, "Jan Beulich" wrote: >>> Thanks George. >>> >>> Jan, >>> >>> Is this a sufficient Ack, or does Kier need to weigh in as well? >> >> Acked-by: Keir Fraser >> >> I kind of feel this sort of thing should be done in dom0 userspace but, >> pragmatically, I know that's not really going to happen! > > How would that work, considering the Dom0's vCPU affinities are > equally affected, and considering that all domains get thawed at > once? Minimally you'd have a burst of (overcommit) load on pCPU0 > right after resume, and whether the system would survive that is > impossible to predict. Ha, yes, well you'd put freeze/thaw in dom0 too. Well, it wasn't really a serious suggestion on my part, what we have works, this new patch will also work, and I'm happy. :) -- Keir