From mboxrd@z Thu Jan 1 00:00:00 1970 Date: Thu, 15 Feb 2007 07:21:50 -0800 (PST) From: Christoph Lameter Subject: Re: [PATCH 4/7] Logic to move mlocked pages In-Reply-To: <20070214213925.13b1111a.akpm@linux-foundation.org> Message-ID: References: <20070215012449.5343.22942.sendpatchset@schroedinger.engr.sgi.com> <20070215012510.5343.52706.sendpatchset@schroedinger.engr.sgi.com> <20070214213925.13b1111a.akpm@linux-foundation.org> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-linux-mm@kvack.org Return-Path: To: Andrew Morton Cc: Christoph Hellwig , Arjan van de Ven , Nigel Cunningham , "Martin J. Bligh" , Peter Zijlstra , Nick Piggin , linux-mm@kvack.org, Matt Mackall , Rik van Riel , KAMEZAWA Hiroyuki List-ID: On Wed, 14 Feb 2007, Andrew Morton wrote: > There are various proposals and patches floating about to similarly leave > anonyous pages off the LRU if there's no swap available: CONFIG_SWAP=n, no > swapfiles online or even no-swapspace-left. Handling this is probably more > useful to more people than handling the munlock case, frankly. Hmmm.. Okay but then we need to account for these pages during writeback ratio calculation. > I think that modifying this code to also provide that function is pretty > darn simple, and that this code should perhaps be designed with that > extension in mind. Yes should be easy to add. > In which case it might be better to rename at least the user-visible > meminfo fields (so we don't have to change them later) and perhaps things > like PG_mlocked and NR_MLOCKED. To PG_nonlru and NR_NONLRU, perhaps. I look into it. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org