Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754593Ab1C1P3U (ORCPT ); Mon, 28 Mar 2011 11:29:20 -0400 Received: from mail-pw0-f46.google.com ([209.85.160.46]:39636 "EHLO mail-pw0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753269Ab1C1P3T (ORCPT ); Mon, 28 Mar 2011 11:29:19 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=from:reply-to:organization:to:subject:date:user-agent:cc:references :in-reply-to:mime-version:content-type:content-transfer-encoding :message-id; b=DmufBtr3cIyAmphPKJc8OIPpGtkhANfwwhebJLbrwQ7EyXhqtH/7hBt9lqa/dSu2/A G0ptMl5gIqQNUdcdrATqBDJDiYBgBkdppJ6ww0hk+IYh8LglFlPbFWsmS0YfqX2SPJBm mSKjJFOPcMHY75JRQkVXZEzt3vXq3DVlKxx4M= From: Nai Xia Reply-To: nai.xia@gmail.com Organization: Nanjing University To: Izik Eidus Subject: Re: [PATCH 0/2] ksm: take dirty bit as reference to avoid volatile pages Date: Mon, 28 Mar 2011 23:29:03 +0800 User-Agent: KMail/1.13.5 (Linux/2.6.38.1; KDE/4.5.5; i686; ; ) Cc: "linux-kernel" , Andrew Morton , Hugh Dickins , Johannes Weiner , Chris Wright , Andrea Arcangeli , Rik van Riel , "linux-mm" References: <201103282214.19345.nai.xia@gmail.com> <4D90A236.9030200@ravellosystems.com> In-Reply-To: <4D90A236.9030200@ravellosystems.com> MIME-Version: 1.0 Content-Type: Text/Plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Message-Id: <201103282329.04184.nai.xia@gmail.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1121 Lines: 34 On Monday 28 March 2011 22:59:02 Izik Eidus wrote: > On 03/28/2011 04:14 PM, Nai Xia wrote: > > Currently, ksm uses page checksum to detect volatile pages. Izik Eidus > > suggested that we could use pte dirty bit to optimize. This patch series > > adds this new logic. > > > > Hi, > > One small note: > When kvm will use ksm on intel cpu with extended page tables support, > the cpu won`t track > dirty bit, therefore the calc_hash() logic should be used in such cases > (untill intel will fadd this support in their cpus)... > > Moreover I think that even though that AMD nested page tables does > update dirty bit, you still need > to sync it with the host page table using mmu notifiers ? > > (Not that on regular application use case of ksm any of this should be > an issue) > > Hmm, I will consider these two issues in the next version. Thanks for input! Nai -- 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/