Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753854AbYKQQWn (ORCPT ); Mon, 17 Nov 2008 11:22:43 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752083AbYKQQWf (ORCPT ); Mon, 17 Nov 2008 11:22:35 -0500 Received: from smtp1.linux-foundation.org ([140.211.169.13]:38082 "EHLO smtp1.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751974AbYKQQWe (ORCPT ); Mon, 17 Nov 2008 11:22:34 -0500 Date: Mon, 17 Nov 2008 08:22:13 -0800 (PST) From: Linus Torvalds To: KAMEZAWA Hiroyuki cc: KOSAKI Motohiro , Andrew Morton , Rik van Riel , LKML , linux-mm , Gene Heskett Subject: Re: [PATCH] mm: evict streaming IO cache first In-Reply-To: <20081117155417.5cc63907.kamezawa.hiroyu@jp.fujitsu.com> Message-ID: References: <20081115181748.3410.KOSAKI.MOTOHIRO@jp.fujitsu.com> <20081115210039.537f59f5.akpm@linux-foundation.org> <49208E9A.5080801@redhat.com> <20081116204720.1b8cbe18.akpm@linux-foundation.org> <20081117153012.51ece88f.kamezawa.hiroyu@jp.fujitsu.com> <2f11576a0811162239w58555c6dq8a61ec184b22bd52@mail.gmail.com> <20081117155417.5cc63907.kamezawa.hiroyu@jp.fujitsu.com> User-Agent: Alpine 2.00 (LFD 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1383 Lines: 34 On Mon, 17 Nov 2008, KAMEZAWA Hiroyuki wrote: > > How about resetting zone->recent_scanned/rotated to be some value calculated from > INACTIVE_ANON/INACTIVE_FILE at some time (when the system is enough idle) ? .. or how about just considering the act of adding a new page to the LRU to be a "scan" event? IOW, "scanning" is not necessarily just an act of the VM looking for pages to free, but would be a more general "activity" meter. IOW, when we calculate the percentages of anon-vs-file in get_scan_ratio() we take into account how much anon-page activity vs how much file cache activity there has been. So if we've seen a lot of filesystem activity ("streaming"), we would tend to prefer to scan the page cache. If we've seen a lot of anon page mapping, we'd tend to prefer to scan the anon side. That would seem to be the right kind of thing to do: if we literally have a load that only does streaming and pages never get moved to the active LRU, it should basically keep the page cache close to constant size - which is just another way of saying that we should only be scanning page cache pages. Hmm? Linus -- 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/