From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: KVM Test report, kernel e6a9246... qemu 94f964d... Date: Tue, 07 Sep 2010 15:31:30 +0300 Message-ID: <4C8630A2.9040706@redhat.com> References: <4C85F489.306@redhat.com> <201009071654.26156.sheng@linux.intel.com> <4C8621A4.6040805@redhat.com> <4C862A4C.8080002@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: kvm@vger.kernel.org, "Hao, Xudong" To: Sheng Yang Return-path: Received: from mx1.redhat.com ([209.132.183.28]:17509 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756295Ab0IGMbg (ORCPT ); Tue, 7 Sep 2010 08:31:36 -0400 In-Reply-To: <4C862A4C.8080002@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: On 09/07/2010 03:04 PM, Avi Kivity wrote: > On 09/07/2010 02:27 PM, Avi Kivity wrote: >> On 09/07/2010 11:54 AM, Sheng Yang wrote: >>> >>> BTW: the bad commit is: c94c3ba901f87115cf574044e7faabfb1d0251fb >>> "KVM: Don't >>> save/restore MSR_IA32_PERF_STATUS", but I haven't figured out the >>> reason yet. >> >> Confirmed. Strange! >> > > It's incredibly slow. Did we disable the cpu cache somehow? Maybe > through the page tables? > PAT = 0. -- error compiling committee.c: too many arguments to function