From mboxrd@z Thu Jan 1 00:00:00 1970 From: Paolo Bonzini Subject: Re: Live migration locks up 3.2 guests in do_timer(ticks ~ 500000) Date: Tue, 16 Sep 2014 10:42:41 +0200 Message-ID: <5417F801.20408@redhat.com> References: <20140908055416.GE23305@hydra.tuxags.com> <540D663E.2070905@redhat.com> <20140908155642.GF23305@hydra.tuxags.com> <540DD6E6.70409@redhat.com> <20140910065349.GM23305@hydra.tuxags.com> <20140915181441.GN23305@hydra.tuxags.com> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit To: kvm@vger.kernel.org Return-path: Received: from mx1.redhat.com ([209.132.183.28]:51161 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751071AbaIPImo (ORCPT ); Tue, 16 Sep 2014 04:42:44 -0400 Received: from int-mx14.intmail.prod.int.phx2.redhat.com (int-mx14.intmail.prod.int.phx2.redhat.com [10.5.11.27]) by mx1.redhat.com (8.14.4/8.14.4) with ESMTP id s8G8ghgP022742 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=FAIL) for ; Tue, 16 Sep 2014 04:42:44 -0400 Received: from yakj.usersys.redhat.com (ovpn-112-37.ams2.redhat.com [10.36.112.37]) by int-mx14.intmail.prod.int.phx2.redhat.com (8.14.4/8.14.4) with ESMTP id s8G8gg11021980 for ; Tue, 16 Sep 2014 04:42:43 -0400 In-Reply-To: <20140915181441.GN23305@hydra.tuxags.com> Sender: kvm-owner@vger.kernel.org List-ID: Il 15/09/2014 20:14, Matt Mullins ha scritto: > On Tue, Sep 09, 2014 at 11:53:49PM -0700, Matt Mullins wrote: >> On Mon, Sep 08, 2014 at 06:18:46PM +0200, Paolo Bonzini wrote: >>> What version of QEMU? Can you try the 12.04 qemu (which IIRC is 1.0) on >>> top of the newer kernel? >> >> I did reproduce this on qemu 1.0.1. >> >> What would you like me to test next? I've got both VM hosts currently running >> 3.17-rc4, so I'll know tomorrow if that works. >> >> I've been looking into this off-and-on for a while now, and this time around I >> may have found other folks experiencing the same issue: >> https://issues.apache.org/jira/browse/CLOUDSTACK-6788 >> That one's a little empty on the details (do y'all know more about to whom that >> bug was "known" than I do?), but >> https://bugs.launchpad.net/ubuntu/+source/libvirt/+bug/1297218 >> sees similar symptoms due to running NTP on the host. I may try disabling that >> after the current round of testing-3.17-rc4 finishes up. > > A summary of my testing from last week: > * 3.17-rc4 (with qemu 2.0) seems to have had the same problem as well. > * Disabling ntpd didn't help either. > * _does_ seem to make my VM migrate > without issue. > > I'm not really sure what to look at from here. I suppose leaving kvmclock > disabled is a workaround for now, but is there a major disadvantage to doing > so? Sorry for not following up. I think we have QEMU patches to fix this issue. I'll reply as soon as they are available in a git tree. Paolo