From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:45960) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1aO6ox-0003U5-8Y for qemu-devel@nongnu.org; Tue, 26 Jan 2016 11:50:27 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1aO6ou-0006I1-3C for qemu-devel@nongnu.org; Tue, 26 Jan 2016 11:50:23 -0500 Received: from mail-wm0-x22f.google.com ([2a00:1450:400c:c09::22f]:38508) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1aO6ot-0006Hh-SQ for qemu-devel@nongnu.org; Tue, 26 Jan 2016 11:50:20 -0500 Received: by mail-wm0-x22f.google.com with SMTP id b14so140734540wmb.1 for ; Tue, 26 Jan 2016 08:50:19 -0800 (PST) Sender: Paolo Bonzini References: <56A7A1A8.4060704@windriver.com> From: Paolo Bonzini Message-ID: <56A7A3C7.6090006@redhat.com> Date: Tue, 26 Jan 2016 17:50:15 +0100 MIME-Version: 1.0 In-Reply-To: <56A7A1A8.4060704@windriver.com> Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] high outage times for qemu virtio network links during live migration, trying to debug List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Chris Friesen , libvir-list@redhat.com, qemu-devel@nongnu.org On 26/01/2016 17:41, Chris Friesen wrote: > I'm using libvirt (1.2.12) with qemu (2.2.0) in the context of OpenStack. > > If I live-migrate a guest with virtio network interfaces, I see a > ~1200msec delay in processing the network packets, and several hundred > of them get dropped. I get the dropped packets, but I'm not sure why > the delay is there. > > I instrumented qemu and libvirt, and the strange thing is that this > delay seems to happen before qemu actually starts doing any > migration-related work. (i.e. before qmp_migrate() is called) > > Looking at my timestamps, the start of the glitch seems to coincide with > libvirtd calling qemuDomainMigratePrepareTunnel3Params(), and the end of > the glitch occurs when the migration is complete and we're up and > running on the destination. > > My question is, why doesn't qemu continue processing virtio packets > while the dirty page scanning and memory transfer over the network is > proceeding? QEMU (or vhost) _are_ processing virtio traffic, because otherwise you'd have no delay---only dropped packets. Or am I missing something? Paolo