From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:53252) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1flIzl-0005Td-IO for qemu-devel@nongnu.org; Thu, 02 Aug 2018 15:10:46 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1flIzk-0006pY-Oe for qemu-devel@nongnu.org; Thu, 02 Aug 2018 15:10:45 -0400 References: <20180626135035.133432-5-vsementsov@virtuozzo.com> <700dffe4-f3a8-8f70-052c-9f6f8ffbe3d3@redhat.com> <20180801102031.GC2691@work-vm> <64aad02b-3d5c-70d6-0f5a-93dd5b88e4bc@redhat.com> <20180801174005.GD2691@work-vm> <20180801185515.GE2691@work-vm> <6bfdc952-fb17-feae-f367-be710853d829@openvz.org> <20180802092907.GA2523@work-vm> <202065a2-f9d1-ce31-b12b-437d57095ac1@openvz.org> <20180802095056.GB2523@work-vm> <86304a35-efd8-a605-f684-2bd3fb3b9815@openvz.org> From: John Snow Message-ID: <1e41d103-6d56-71e8-ef60-fc4c9343a06e@redhat.com> Date: Thu, 2 Aug 2018 15:10:36 -0400 MIME-Version: 1.0 In-Reply-To: <86304a35-efd8-a605-f684-2bd3fb3b9815@openvz.org> Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCH 4/6] dirty-bitmaps: clean-up bitmaps loading and migration logic List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: "Denis V. Lunev" , "Dr. David Alan Gilbert" Cc: Vladimir Sementsov-Ogievskiy , qemu-devel@nongnu.org, qemu-block@nongnu.org, quintela@redhat.com, stefanha@redhat.com, famz@redhat.com, mreitz@redhat.com, kwolf@redhat.com, Eric Blake On 08/02/2018 03:05 PM, Denis V. Lunev wrote: > On 08/02/2018 12:50 PM, Dr. David Alan Gilbert wrote: >> * Denis V. Lunev (den@openvz.org) wrote: >> >> >>>> I don't quite understand the last two paragraphs. >>> we are thinking right now to eliminate delay on regular IO >>> for migration. There is some thoughts and internal work in >>> progress. That is why I am worrying. >> What downtime are you typicaly seeing and what are you aiming for? >> >> It would be good if you could explain what you're planning to >> fix there so we can get a feel for it nearer the start of it >> rather than at the end of the reviewing! >> >> Dave > The ultimate goal is to reliable reach 100 ms with ongoing IO and > you are perfectly correct about reviewing :) > > Though the problem is that right now we are just trying to > invent something suitable :( > > Den > Yeah, I gotcha -- please give me just a little time. I'm not against using Vlad's series, it just surprised me. David and I have talked about what you're trying to do and we are in agreement that it is the right thing to do for now. I have some more questions about Vlad's series, but I want to test it a bit myself before I waste time asking them. I'll stage a working version as soon as I can. --js