Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760395Ab0FKNqy (ORCPT ); Fri, 11 Jun 2010 09:46:54 -0400 Received: from cn.fujitsu.com ([222.73.24.84]:49639 "EHLO song.cn.fujitsu.com" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1760322Ab0FKNqx (ORCPT ); Fri, 11 Jun 2010 09:46:53 -0400 Message-ID: <4C123D78.5040705@cn.fujitsu.com> Date: Fri, 11 Jun 2010 21:43:20 +0800 From: Xiao Guangrong User-Agent: Thunderbird 2.0.0.24 (Windows/20100228) MIME-Version: 1.0 To: Avi Kivity CC: Marcelo Tosatti , LKML , KVM list Subject: Re: [PATCH 7/7] KVM: MMU: don't walk every parent pages while mark unsync References: <4C1239EE.3090904@cn.fujitsu.com> <4C123B93.7060803@cn.fujitsu.com> In-Reply-To: <4C123B93.7060803@cn.fujitsu.com> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 738 Lines: 19 Xiao Guangrong wrote: > While we mark the parent's unsync_child_bitmap, if the parent is already > unsynced, it no need walk it's parent, it can reduce some unnecessary > workload > Hi Avi, Marcelo, About two months ago, i have sent this optimization, it just a little performance improved (~0.5%) at that time, now, we allow more page become unsync, this path is called higher frequency, during my test, kernelbench show the performance improved ~2%, so, i think we may apply it now :-) -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/