Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934343Ab0D3T24 (ORCPT ); Fri, 30 Apr 2010 15:28:56 -0400 Received: from e5.ny.us.ibm.com ([32.97.182.145]:39829 "EHLO e5.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757436Ab0D3Qrr (ORCPT ); Fri, 30 Apr 2010 12:47:47 -0400 Subject: RE: Frontswap [PATCH 0/4] (was Transcendent Memory): overview From: Dave Hansen To: Dan Magenheimer Cc: Avi Kivity , Pavel Machek , linux-kernel@vger.kernel.org, linux-mm@kvack.org, jeremy@goop.org, hugh.dickins@tiscali.co.uk, ngupta@vflare.org, JBeulich@novell.com, chris.mason@oracle.com, kurt.hackel@oracle.com, dave.mccracken@oracle.com, npiggin@suse.de, akpm@linux-foundation.org, riel@redhat.com, Martin Schwidefsky In-Reply-To: <084f72bf-21fd-4721-8844-9d10cccef316@default> References: <4BD16D09.2030803@redhat.com> > > <4BD1A74A.2050003@redhat.com> > <4830bd20-77b7-46c8-994b-8b4fa9a79d27@default> > <4BD1B427.9010905@redhat.com> <4BD1B626.7020702@redhat.com> > <5fa93086-b0d7-4603-bdeb-1d6bfca0cd08@default> > <4BD3377E.6010303@redhat.com> > <1c02a94a-a6aa-4cbb-a2e6-9d4647760e91@default4BD43033.7090706@redhat.com> > > <20100428055538.GA1730@ucw.cz> <1272591924.23895.807.camel@nimitz 4BDA8324.7090409@redhat.com> <084f72bf-21fd-4721-8844-9d10cccef316@default> Content-Type: text/plain Date: Fri, 30 Apr 2010 09:08:00 -0700 Message-Id: <1272643680.23895.2537.camel@nimitz> Mime-Version: 1.0 X-Mailer: Evolution 2.26.1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 933 Lines: 21 On Fri, 2010-04-30 at 08:59 -0700, Dan Magenheimer wrote: > Dave or others can correct me if I am wrong, but I think CMM2 also > handles dirty pages that must be retained by the hypervisor. The > difference between CMM2 (for dirty pages) and frontswap is that > CMM2 sets hints that can be handled asynchronously while frontswap > provides explicit hooks that synchronously succeed/fail. Once pages were dirtied (or I guess just slightly before), they became volatile, and I don't think the hypervisor could do anything with them. It could still swap them out like usual, but none of the CMM-specific optimizations could be performed. CC'ing Martin since he's the expert. :) -- Dave -- 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/