Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756842AbYKQIcp (ORCPT ); Mon, 17 Nov 2008 03:32:45 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752705AbYKQIce (ORCPT ); Mon, 17 Nov 2008 03:32:34 -0500 Received: from wa-out-1112.google.com ([209.85.146.181]:52942 "EHLO wa-out-1112.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752627AbYKQIcd (ORCPT ); Mon, 17 Nov 2008 03:32:33 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=message-id:date:from:sender:to:subject:cc:in-reply-to:mime-version :content-type:content-transfer-encoding:content-disposition :references:x-google-sender-auth; b=SXnBVB0coXiZDbsNTSxkZz6OU5sNpK5wF0deARY0ewnWM85qk89bRTjPmlo5FUkpHS 4JEXIX15HAw7Wp4RA/L/B2MQxG1xSuZRzUxwQUCOPToeLXJDnv5edeTYcHG35c+UZ18P lJLoPd7J/kiQ8e8uU1EdeOUw2BC1+xW+P5xoY= Message-ID: <2f11576a0811170032i6548e03die47f9e341f3ef9a@mail.gmail.com> Date: Mon, 17 Nov 2008 17:32:32 +0900 From: "KOSAKI Motohiro" To: "KAMEZAWA Hiroyuki" Subject: Re: [PATCH] mm: evict streaming IO cache first Cc: "Andrew Morton" , "Rik van Riel" , "Linus Torvalds" , LKML , linux-mm , "Gene Heskett" In-Reply-To: <20081117172202.343e1b35.kamezawa.hiroyu@jp.fujitsu.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline 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> <2f11576a0811162303t51609098o6cd765c04d791581@mail.gmail.com> <20081117172202.343e1b35.kamezawa.hiroyu@jp.fujitsu.com> X-Google-Sender-Auth: a76ceda83f29fd2d Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 921 Lines: 36 >> > 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) ? >> >> in get_scan_ratio() >> > But active/inactive ratio (and mapped_ratio) is not handled there. Yes. I think akpm pointed out just this point. > Follwoing 2 will return the same scan ratio. > ==case 1== > active_anon = 480M > inactive_anon = 32M > active_file = 2M > inactive_file = 510M > > ==case 2== > active_anon = 480M > inactive_anon = 32M > active_file = 480M > inactive_file = 32M > == Yes. the patch handle this situation by special priority. Umm.. Perhaps, I am missing your point? -- 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/