From mboxrd@z Thu Jan  1 00:00:00 1970
From: Gordan Bobic <gordan@bobich.net>
Subject: KSM For All Via LD_PRELOAD?
Date: Tue, 08 Jun 2010 19:43:07 +0100
Message-ID: <4C0E8F3B.5060501@bobich.net>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
To: kvm@vger.kernel.org
Return-path: <kvm-owner@vger.kernel.org>
Received: from 78-86-195-86.zone2.bethere.co.uk ([78.86.195.86]:54891 "EHLO
	sentinel1.shatteredsilicon.net" rhost-flags-OK-OK-OK-OK)
	by vger.kernel.org with ESMTP id S1754087Ab0FHSxO (ORCPT
	<rfc822;kvm@vger.kernel.org>); Tue, 8 Jun 2010 14:53:14 -0400
Received: from thinkpad.shatteredsilicon.net (unknown [10.255.20.6])
	by sentinel1.shatteredsilicon.net (Postfix) with ESMTP id 107A3F87C4
	for <kvm@vger.kernel.org>; Tue,  8 Jun 2010 19:43:09 +0100 (BST)
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

Is this plausible?

I'm trying to work out if it's even worth considering this approach to 
enable all memory used by in a system to be open to KSM page merging, 
rather than only memory used by specific programs aware of it (e.g. 
kvm/qemu).

Something like this would address the fact that container based 
virtualization (OpenVZ, VServer, LXC) cannot benefit from KSM.

What I'm thinking about is somehow intercepting malloc() and wrapping it 
so that all malloc()-ed memory gets madvise()-d as well.

Has this been done?

Or is this too crazy an idea?

Gordan