From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754222AbZHaUKW (ORCPT ); Mon, 31 Aug 2009 16:10:22 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752884AbZHaUKW (ORCPT ); Mon, 31 Aug 2009 16:10:22 -0400 Received: from mx1.redhat.com ([209.132.183.28]:45111 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751152AbZHaUKV (ORCPT ); Mon, 31 Aug 2009 16:10:21 -0400 Message-ID: <4A9C2E01.7080707@redhat.com> Date: Mon, 31 Aug 2009 16:09:37 -0400 From: Rik van Riel User-Agent: Thunderbird 2.0.0.21 (X11/20090320) MIME-Version: 1.0 To: "Dike, Jeffrey G" CC: "balbir@linux.vnet.ibm.com" , "Wu, Fengguang" , Avi Kivity , Andrea Arcangeli , "Yu, Wilfred" , "Kleen, Andi" , Hugh Dickins , Andrew Morton , Christoph Lameter , KOSAKI Motohiro , Mel Gorman , LKML , linux-mm Subject: Re: [RFC] respect the referenced bit of KVM guest pages? References: <4A7AAE07.1010202@redhat.com> <20090806102057.GQ23385@random.random> <20090806105932.GA1569@localhost> <4A7AC201.4010202@redhat.com> <20090806130631.GB6162@localhost> <4A7AD79E.4020604@redhat.com> <20090816032822.GB6888@localhost> <4A878377.70502@redhat.com> <20090816045522.GA13740@localhost> <9EECC02A4CC333418C00A85D21E89326B6611F25@azsmsx502.amr.corp.intel.com> <20090821182439.GN29572@balbir.in.ibm.com> <9EECC02A4CC333418C00A85D21E8932601841832F9@azsmsx502.amr.corp.intel.com> <4A9C2A17.3080802@redhat.com> <9EECC02A4CC333418C00A85D21E893260184183339@azsmsx502.amr.corp.intel.com> In-Reply-To: <9EECC02A4CC333418C00A85D21E893260184183339@azsmsx502.amr.corp.intel.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Dike, Jeffrey G wrote: >> This will be because the VM does not start aging pages >> from the active to the inactive list unless there is >> some memory pressure. > > Which is the reason I gave the VM a puny amount of memory. > We know the thing is under memory pressure because I've been > complaining about page discards. Page discards by the host, which are invisible to the guest OS. The guest OS thinks it has enough pages. The host disagrees and swaps out some guest memory.