From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH v4 0/8] KVM paravirt remote flush tlb Date: Tue, 04 Sep 2012 13:37:52 +0300 Message-ID: <5045DA00.6090208@redhat.com> References: <20120821112346.3512.99814.stgit@abhimanyu.in.ibm.com> <5044BFCA.7060303@redhat.com> <87txveefrc.fsf@abhimanyu.in.ibm.com> <5045B2EA.2030301@redhat.com> <87ligqdxcp.fsf@abhimanyu.in.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: mtosatti@redhat.com, raghukt@linux.vnet.ibm.com, alex.shi@intel.com, kvm@vger.kernel.org, stefano.stabellini@eu.citrix.com, peterz@infradead.org, hpa@zytor.com, vsrivatsa@gmail.com, mingo@elte.hu To: Nikunj A Dadhania Return-path: Received: from mx1.redhat.com ([209.132.183.28]:20351 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752309Ab2IDKiN (ORCPT ); Tue, 4 Sep 2012 06:38:13 -0400 In-Reply-To: <87ligqdxcp.fsf@abhimanyu.in.ibm.com> Sender: kvm-owner@vger.kernel.org List-ID: On 09/04/2012 11:08 AM, Nikunj A Dadhania wrote: > On Tue, 04 Sep 2012 10:51:06 +0300, Avi Kivity wrote: >> On 09/04/2012 04:30 AM, Nikunj A Dadhania wrote: >> > On Mon, 03 Sep 2012 17:33:46 +0300, Avi Kivity wrote: >> >> On 08/21/2012 02:25 PM, Nikunj A. Dadhania wrote: >> >> > >> >> > kernbench(lower is better) >> >> > ========================== >> >> > base pvflushv4 %improvement >> >> > 1VM 48.5800 46.8513 3.55846 >> >> > 2VM 108.1823 104.6410 3.27346 >> >> > 3VM 183.2733 163.3547 10.86825 >> >> > >> >> > ebizzy(higher is better) >> >> > ======================== >> >> > base pvflushv4 %improvement >> >> > 1VM 2414.5000 2089.8750 -13.44481 >> >> > 2VM 2167.6250 2371.7500 9.41699 >> >> > 3VM 1600.1111 2102.5556 31.40060 >> >> > >> >> >> >> The regression is worrying. We're improving the contended case at the >> >> cost of the non-contended case, this is usually the wrong thing to do. >> >> Do we have any clear idea of the cause of the regression? >> >> >> > Previous perf numbers suggest that in 1VM scenario flush_tlb_others_ipi >> > is around 2%, while for contented case its around 10%. That is what is >> > helping contended case. >> >> But what is causing the regression for the uncontended case? >> > Haven't been able to nail that, any clue on how to profile would help. perf top, perf kvm top, kvm_stat should help. -- error compiling committee.c: too many arguments to function