From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756120Ab0ECTcc (ORCPT ); Mon, 3 May 2010 15:32:32 -0400 Received: from ksp.mff.cuni.cz ([195.113.26.206]:40348 "EHLO atrey.karlin.mff.cuni.cz" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1754685Ab0ECTca (ORCPT ); Mon, 3 May 2010 15:32:30 -0400 Date: Mon, 3 May 2010 21:32:23 +0200 From: Pavel Machek To: Dan Magenheimer Cc: Avi Kivity , Jeremy Fitzhardinge , Dave Hansen , linux-kernel@vger.kernel.org, linux-mm@kvack.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 Subject: Re: Frontswap [PATCH 0/4] (was Transcendent Memory): overview Message-ID: <20100503193223.GA27796@elf.ucw.cz> References: <1272591924.23895.807.camel@nimitz> <4BDA8324.7090409@redhat.com> <084f72bf-21fd-4721-8844-9d10cccef316@default> <4BDB026E.1030605@redhat.com> <4BDB18CE.2090608@goop.org> <4BDB2069.4000507@redhat.com> <3a62a058-7976-48d7-acd2-8c6a8312f10f@default> <4BDD9BD3.2080301@redhat.com> <74c69226-4678-4b9b-bfeb-1490c8f5636d@default> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <74c69226-4678-4b9b-bfeb-1490c8f5636d@default> X-Warning: Reading this can be dangerous to your mental health. User-Agent: Mutt/1.5.20 (2009-06-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > > If block layer overhead is a problem, go ahead and optimize it instead > > of adding new interfaces to bypass it. Though I expect it wouldn't be > > needed, and if any optimization needs to be done it is in the swap > > layer. > > Optimizing swap has the additional benefit of improving performance on > > flash-backed swap. > > : > > What happens when no tmem is available? you swap to a volume. That's > > the disk size needed. > > : > > You're dynamic swap is limited too. And no, no guest modifications. > > You keep saying you are going to implement all of the dynamic features > of frontswap with no changes to the guest and no copying and no > host-swapping. You are being disingenuous. VMware has had a lot I don't see why no copying is a requirement. I believe requirement should be "it is fast enough". Pavel -- (english) http://www.livejournal.com/~pavelmachek (cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html