From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:55239) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1WBhWv-00088l-1v for qemu-devel@nongnu.org; Fri, 07 Feb 2014 04:15:29 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1WBhWq-0006sd-Nx for qemu-devel@nongnu.org; Fri, 07 Feb 2014 04:15:24 -0500 Received: from mx1.redhat.com ([209.132.183.28]:52946) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1WBhWq-0006r6-F3 for qemu-devel@nongnu.org; Fri, 07 Feb 2014 04:15:20 -0500 Date: Fri, 7 Feb 2014 09:15:14 +0000 From: "Dr. David Alan Gilbert" Message-ID: <20140207091513.GC2374@work-vm> References: <50562927-0498-460b-8f29-98722e332149@mailpro> <52F496B4.5030505@profihost.ag> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable In-Reply-To: <52F496B4.5030505@profihost.ag> 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: Stefan Priebe - Profihost AG Cc: qemu-devel , Alexandre DERUMIER * Stefan Priebe - Profihost AG (s.priebe@profihost.ag) wrote: > Am 07.02.2014 09:15, schrieb Alexandre DERUMIER: > >=20 > > do you use xbzrle for live migration ? >=20 > no - i'm really stucked right now with this. Biggest problem i can't > reproduce with test machines ;-( Only being able to test on your production VMs isn't fun; is it possible or you to run an extra program on these VMs - e.g. if we came up with a simple (userland) memory test? Dave >=20 > Stefan >=20 >=20 > >=20 > > ----- Mail original -----=20 > >=20 > > De: "Stefan Priebe" =20 > > =C0: "Dr. David Alan Gilbert" =20 > > Cc: "Alexandre DERUMIER" , "qemu-devel" =20 > > Envoy=E9: Jeudi 6 F=E9vrier 2014 21:00:27=20 > > Objet: Re: [Qemu-devel] [pve-devel] QEMU LIve Migration - swap_free: Ba= d swap file entry=20 > >=20 > > Hi,=20 > > Am 06.02.2014 20:51, schrieb Dr. David Alan Gilbert:=20 > >> * Stefan Priebe - Profihost AG (s.priebe@profihost.ag) wrote:=20 > >>> some more things which happen during migration:=20 > >>> > >>> php5.2[20258]: segfault at a0 ip 0000000000740656 sp 00007fff53b694a0= =20 > >>> error 4 in php-cgi[400000+6d7000]=20 > >>> > >>> php5.2[20249]: segfault at c ip 00007f1fb8ecb2b8 sp 00007fff642d9c20= =20 > >>> error 4 in ZendOptimizer.so[7f1fb8e71000+147000]=20 > >>> > >>> cron[3154]: segfault at 7f0008a70ed4 ip 00007fc890b9d440 sp=20 > >>> 00007fff08a6f9b0 error 4 in libc-2.13.so[7fc890b67000+182000]=20 > >> > >> OK, so lets just assume some part of memory (or CPU state, or memory= =20 > >> loaded off disk...)=20 > >> > >> You said before that it was happening on a 32GB image - is it *only*= =20 > >> happening on a 32GB or bigger VM, or is it just more likely?=20 > >=20 > > Not image, memory. I've only seen this with vms having more than 16GB o= r=20 > > 32GB memory. But maybe this also indicates that just the migration take= s=20 > > longer.=20 > >=20 > >> I think you also said you were using 1.7; have you tried an older=20 > >> version - i.e. is this a regression in 1.7 or don't we know?=20 > > Don't know. Sadly i cannot reproduce this with test VMs only with=20 > > production ones.=20 > >=20 > > Stefan=20 > >=20 > >> Dave=20 > >> --=20 > >> Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK=20 > >> >=20 -- Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK