From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:56806) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1WCvz9-00074m-CQ for qemu-devel@nongnu.org; Mon, 10 Feb 2014 13:53:44 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1WCvz4-00028U-Cu for qemu-devel@nongnu.org; Mon, 10 Feb 2014 13:53:39 -0500 Received: from mail-ph.de-nserver.de ([85.158.179.214]:52530) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1WCvz3-00028M-V3 for qemu-devel@nongnu.org; Mon, 10 Feb 2014 13:53:34 -0500 Message-ID: <52F92035.5040402@profihost.ag> Date: Mon, 10 Feb 2014 19:53:41 +0100 From: Stefan Priebe MIME-Version: 1.0 References: <52F4D1CA.6030501@profihost.ag> <52F4D523.9040809@redhat.com> <52F4D9E2.4010600@profihost.ag> <52F4DD77.7000209@redhat.com> <52F4E211.9080808@profihost.ag> <52F4E37D.4050204@profihost.ag> <52F5321C.4090605@profihost.ag> <20140207200204.GA5013@work-vm> <52F53DBC.8000209@profihost.ag> <52F68438.9050300@profihost.ag> <20140210160706.GK3545@work-vm> In-Reply-To: <20140210160706.GK3545@work-vm> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [pve-devel] QEMU LIve Migration - swap_free: Bad swap file entry List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: "Dr. David Alan Gilbert" Cc: Paolo Bonzini , qemu-devel , Alexandre DERUMIER Am 10.02.2014 17:07, schrieb Dr. David Alan Gilbert: > * Stefan Priebe (s.priebe@profihost.ag) wrote: >> i could fix it by explicitly disable xbzrle - it seems its >> automatically on if i do not set the migration caps to false. >> >> So it seems to be a xbzrle bug. > > Stefan can you give me some more info on your hardware and > migration setup; that stressapptest (which is a really nice > find!) really batters the memory and it means the migration > isn't converging for me, so I'm curious what your setup is. That one is devlopment by google and known to me since a few years. Google has detected that memtest and co are not good enough to stress test memory. > What CPU have you got? Dual Xeon E5-2695v2 > How many cores are you giving each guest? 16 > What network technology are you migrating over? 10Gb/s > Other than xbzrle what else do you have enabled? nothing > How long is the migrate taking for you? with migration_downtime => 4s around 10s Stefan > Thanks, > > Dave > -- > Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK >