From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH 2/2] Remove -tdf Date: Sun, 27 Jul 2008 12:38:29 +0300 Message-ID: <488C4215.9010509@qumranet.com> References: <1216756217-21888-1-git-send-email-aliguori@us.ibm.com> <1216756217-21888-2-git-send-email-aliguori@us.ibm.com> <48865934.8070007@qumranet.com> <48868769.7050307@codemonkey.ws> <20080723055825.GA3196@minantech.com> <48874EBC.1050209@codemonkey.ws> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Gleb Natapov , Dor Laor , kvm@vger.kernel.org To: Anthony Liguori Return-path: Received: from il.qumranet.com ([212.179.150.194]:27353 "EHLO il.qumranet.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751113AbYG0Jib (ORCPT ); Sun, 27 Jul 2008 05:38:31 -0400 In-Reply-To: <48874EBC.1050209@codemonkey.ws> Sender: kvm-owner@vger.kernel.org List-ID: Anthony Liguori wrote: > > I think there's a healthy amount of scepticism about whether tdf > really is worth it. This is why I suggested that we need to better > quantify exactly how much this patch set helps things. For instance, > a time drift test for kvm-autotest would be perfect. > > tdf is ugly and deviates from how hardware works. A compelling case > is needed to justify it. > On real hardware, the processor won't go away randomly for lengthy periods. Since software assumes this, we must either provide a correction or live with guest time not corresponding to real time. -- error compiling committee.c: too many arguments to function