From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:43005) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1d6GYF-0003jO-Nd for qemu-devel@nongnu.org; Thu, 04 May 2017 09:12:12 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1d6GYB-0004wI-P1 for qemu-devel@nongnu.org; Thu, 04 May 2017 09:12:11 -0400 Received: from mx1.redhat.com ([209.132.183.28]:59206) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1d6GYB-0004vk-IT for qemu-devel@nongnu.org; Thu, 04 May 2017 09:12:07 -0400 References: <20170504084135.7488.24715.stgit@PASHA-ISP> <20170504084210.7488.37561.stgit@PASHA-ISP> <000401d2c4c7$6d5b6d50$481247f0$@ru> <000801d2c4cd$3d3af720$b7b0e560$@ru> <58398574-88b5-3382-65e2-7208beccc09a@redhat.com> <000f01d2c4cf$7479f630$5d6de290$@ru> <001101d2c4d2$bb44a4e0$31cdeea0$@ru> <001201d2c4d6$c26bdd20$47439760$@ru> From: Paolo Bonzini Message-ID: Date: Thu, 4 May 2017 15:12:01 +0200 MIME-Version: 1.0 In-Reply-To: <001201d2c4d6$c26bdd20$47439760$@ru> Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCH v9 06/10] replay: fix save/load vm for non-empty queue List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Pavel Dovgalyuk , 'Pavel Dovgalyuk' , qemu-devel@nongnu.org Cc: kwolf@redhat.com, peter.maydell@linaro.org, mst@redhat.com, jasowang@redhat.com, quintela@redhat.com, kraxel@redhat.com On 04/05/2017 15:02, Pavel Dovgalyuk wrote: >> Understood. And what checkpoint will you be waiting for during drain, >> causing a deadlock? > Every checkpoint processes the queue, but none of them are invoked, > because iothread (which invokes all the checkpoints) is waiting for the end of the drain. > > And we cannot add a checkpoint into the drain, because then vmstop will > affect the behavior of the guest. But it does affect the behavior already when RR is off. And it shouldn't be a problem if it does in record mode (as long as the effect can be replayed). If RR cannot do drain reliably, not even in record mode, that is a huge problem because a lot of block layer operations assume they can. Paolo