[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <4A794008.6030204@redhat.com>
Date: Wed, 05 Aug 2009 11:17:12 +0300
From: Avi Kivity <avi@...hat.com>
To: Wu Fengguang <fengguang.wu@...el.com>
CC: Rik van Riel <riel@...hat.com>,
"Dike, Jeffrey G" <jeffrey.g.dike@...el.com>,
"Yu, Wilfred" <wilfred.yu@...el.com>,
"Kleen, Andi" <andi.kleen@...el.com>,
Andrea Arcangeli <aarcange@...hat.com>,
Hugh Dickins <hugh.dickins@...cali.co.uk>,
Andrew Morton <akpm@...ux-foundation.org>,
Christoph Lameter <cl@...ux-foundation.org>,
KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>,
Mel Gorman <mel@....ul.ie>,
LKML <linux-kernel@...r.kernel.org>,
linux-mm <linux-mm@...ck.org>,
Andrea Arcangeli <aarcange@...hat.com>,
KVM list <kvm@...r.kernel.org>
Subject: Re: [RFC] respect the referenced bit of KVM guest pages?
On 08/05/2009 10:58 AM, Avi Kivity wrote:
> On 08/05/2009 05:40 AM, Wu Fengguang wrote:
>> Greetings,
>>
>> Jeff Dike found that many KVM pages are being refaulted in 2.6.29:
>>
>> "Lots of pages between discarded due to memory pressure only to be
>> faulted back in soon after. These pages are nearly all stack pages.
>> This is not consistent - sometimes there are relatively few such pages
>> and they are spread out between processes."
>>
>> The refaults can be drastically reduced by the following patch, which
>> respects the referenced bit of all anonymous pages (including the KVM
>> pages).
>>
>> However it risks reintroducing the problem addressed by commit 7e9cd4842
>> (fix reclaim scalability problem by ignoring the referenced bit,
>> mainly the pte young bit). I wonder if there are better solutions?
>
> How do you distinguish between kvm pages and non-kvm anonymous pages?
> More importantly, why should you?
>
> Jeff, do you see the refaults on Nehalem systems? If so, that's
> likely due to the lack of an accessed bit on EPT pagetables. It would
> be interesting to compare with Barcelona (which does).
>
> If that's indeed the case, we can have the EPT ageing mechanism give
> pages a bit more time around by using an available bit in the EPT PTEs
> to return accessed on the first pass and not-accessed on the second.
>
The attached patch implements this.
--
error compiling committee.c: too many arguments to function
View attachment "ept-emulate-accessed-bit.patch" of type "text/x-patch" (2116 bytes)
Powered by blists - more mailing lists