From mboxrd@z Thu Jan 1 00:00:00 1970 From: Faidon Liambotis Subject: Re: porting fixes regarding kvm-clock and lost irqs to stable qemu-kvm 0.12.4 Date: Sat, 05 Jun 2010 04:34:55 +0300 Message-ID: <4C09A9BF.8090107@debian.org> References: <4C06751A.4080507@dlh.net> <20100604153102.GB11087@amt.cnet> <17DE5732-EDBF-4C7B-9C45-6BF66F200911@dlh.net> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Cc: Marcelo Tosatti , Avi Kivity , Anthony Liguori , "kvm@vger.kernel.org" To: Peter Lieven Return-path: Received: from mail.noc.grnet.gr ([83.212.9.3]:38944 "EHLO mail.noc.grnet.gr" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752130Ab0FEBom (ORCPT ); Fri, 4 Jun 2010 21:44:42 -0400 In-Reply-To: <17DE5732-EDBF-4C7B-9C45-6BF66F200911@dlh.net> Sender: kvm-owner@vger.kernel.org List-ID: Hi, Peter Lieven wrote: > i was looking for a generic way to disable it in the hypervisor > without the need to touch every guests kernel commandline. > this would be easy revertible once its all working as expected. This is a huge hack but for the same reason I've made an LD_PRELOAD wrapper that wraps ioctl masking the hsot kernel's kvmclock feature from userspace kvm. I'll be happy to share it if you're interested. Works like a charm, migration has worken reliably with qemu-kvm 0.11.3 + the wrapper. Regards, Faidon