From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:43729) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1WxeJ5-0000gW-9P for qemu-devel@nongnu.org; Thu, 19 Jun 2014 11:31:26 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1WxeIx-00060n-QC for qemu-devel@nongnu.org; Thu, 19 Jun 2014 11:31:19 -0400 Received: from mx1.redhat.com ([209.132.183.28]:64871) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1WxeIx-00060i-IA for qemu-devel@nongnu.org; Thu, 19 Jun 2014 11:31:11 -0400 Message-ID: <53A3023A.5030800@redhat.com> Date: Thu, 19 Jun 2014 17:31:06 +0200 From: Paolo Bonzini MIME-Version: 1.0 References: <53693FA4.3000306@windriver.com> <5369D504.2070101@redhat.com> <536AB2EE.6010504@windriver.com> <20140508130231.GA24978@grmbl.mre> <536B8332.9070705@redhat.com> <20140508133052.GA25602@grmbl.mre> <536B884D.6080504@redhat.com> <20140508134738.GB25602@grmbl.mre> <536BA579.10604@windriver.com> <536C2712.3030803@windriver.com> <536C8F7D.2050302@redhat.com> <53A2FF73.1080201@windriver.com> In-Reply-To: <53A2FF73.1080201@windriver.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] virtio-serial-pci very expensive during live migration List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Chris Friesen , Amit Shah Cc: qemu-devel@nongnu.org, armbru@redhat.com Il 19/06/2014 17:19, Chris Friesen ha scritto: > On 05/09/2014 02:19 AM, Paolo Bonzini wrote: >> Il 09/05/2014 02:53, Chris Friesen ha scritto: >>> >>> >>> Turns out I spoke too soon. With the patch applied, it boots, but if I >>> try to do a live migration both the source and destination crash. This >>> happens for both the master branch as well as the stable-1.4 branch. >> >> The destination doesn't crash, it simply stops because it got an >> incomplete migration stream. Thanks for the report, the patch seems >> correct so it's worthwhile looking at it more closely. >> >>> If I back out the patch, it works fine. If I leave the patch in and >>> disable kvm acceleration it works fine. >> >> Indeed, non-KVM doesn't use ioeventfd at all. > > Did anyone ever figure out why wrapping the whole thing in > memory_region_transaction_begin()/memory_region_transaction_commit() > caused problems? No, sorry, I didn't have time. On the other hand patches went in that avoided unnecessary work on ioeventfds, so you may want to test again with the latest master branch. Paolo