From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Michael S. Tsirkin" Subject: Re: hotplug: VM got stuck when attaching a pass-through device to the non-pass-through VM for the first time Date: Tue, 18 Feb 2014 13:16:15 +0200 Message-ID: <20140218111615.GE8114@redhat.com> References: <20140218103828.GB8114@redhat.com> <5303390B.50903@redhat.com> <20140218105159.GD8114@redhat.com> <53033E6F.60700@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: "Zhanghaoyu (A)" , "qemu-devel@nongnu.org" , KVM , Gleb Natapov , Avi Kivity , Eric Blake , Luonengjun , "Huangweidong (C)" , "Gonglei (Arei)" , "Gaowei (UVP)" , "chenliang (T)" To: Paolo Bonzini Return-path: Received: from mx1.redhat.com ([209.132.183.28]:30982 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754466AbaBRLL1 (ORCPT ); Tue, 18 Feb 2014 06:11:27 -0500 Content-Disposition: inline In-Reply-To: <53033E6F.60700@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: On Tue, Feb 18, 2014 at 12:05:19PM +0100, Paolo Bonzini wrote: > Il 18/02/2014 11:51, Michael S. Tsirkin ha scritto: > >>> I agree it's either COW breaking or (similarly) locking pages that > >>> the guest hasn't touched yet. > >>> > >>> You can use prealloc or "-rt mlock=on" to avoid this problem. > >>> > >>> Paolo > >Or the new shared flag - IIRC shared VMAs don't do COW either. > > Only if the problem isn't locking and zeroing of untouched pages > (also, it is not upstream is it?). No but it's a small patch - part of vhost user patchset. > Can you make a profile with perf? > > Paolo