From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752109AbZGDRgc (ORCPT ); Sat, 4 Jul 2009 13:36:32 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1750812AbZGDRgX (ORCPT ); Sat, 4 Jul 2009 13:36:23 -0400 Received: from mail-qy0-f193.google.com ([209.85.221.193]:58801 "EHLO mail-qy0-f193.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750773AbZGDRgW convert rfc822-to-8bit (ORCPT ); Sat, 4 Jul 2009 13:36:22 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; b=DNWHwpgKRsRf1+KFfr1fUQDPa+e6ur9mpKZ02NyOFOgyjYZ5fjRyYniJ7CHFQ20hnp 23VgFg4ozrtG2rkTwE4sGA39ARgd+V7uoQSdxs7aLo3NryT4teWpMHLYqIlFwkmjlJUr aRBN5LoNFcuiX+QyXj2C5pEIBUjag1iXLfYyk= MIME-Version: 1.0 In-Reply-To: <20090704141818.0afa877a.minchan.kim@gmail.com> References: <20090704141818.0afa877a.minchan.kim@gmail.com> Date: Sun, 5 Jul 2009 02:36:25 +0900 X-Google-Sender-Auth: 36a4f4c56aab5d6b Message-ID: <2f11576a0907041036i3585206bl475cc9f70176a0db@mail.gmail.com> Subject: Re: [PATCH][mmotm] don't attempt to reclaim anon page in lumpy reclaim when no swap space is available From: KOSAKI Motohiro To: Minchan Kim Cc: Andrew Morton , LKML , Linux MM , Mel Gorman , Rik van Riel , KAMEZAWA Hiroyuki Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 2009/7/4 Minchan Kim : > > This patch is based on mmotm 2009-07-02-19-57 reverted > 'vmscan: don't attempt to reclaim anon page in lumpy reclaim when no swap space is available.' > > This verssion is better than old one. > That's because enough swap space check is done in case of only lumpy reclaim. > so it can't degrade performance in normal case. > > == CUT HERE == > > VM already avoids attempting to reclaim anon pages in various places, But > it doesn't avoid it for lumpy reclaim. > > It shuffles lru list unnecessary so that it is pointless. > > Signed-off-by: Minchan Kim > Cc: Mel Gorman > Cc: KOSAKI Motohiro > Cc: Rik van Riel > Cc: KAMEZAWA Hiroyuki > --- >  mm/vmscan.c |    7 +++++++ >  1 files changed, 7 insertions(+), 0 deletions(-) > > diff --git a/mm/vmscan.c b/mm/vmscan.c > index 27558aa..977af15 100644 > --- a/mm/vmscan.c > +++ b/mm/vmscan.c > @@ -930,6 +930,13 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, >                        /* Check that we have not crossed a zone boundary. */ >                        if (unlikely(page_zone_id(cursor_page) != zone_id)) >                                continue; > +                       /* > +                        * If we don't have enough swap space, reclaiming of anon page > +                        * which don't already have a swap slot is pointless. > +                        */ > +                       if (nr_swap_pages <= 0 && (PageAnon(cursor_page) && > +                                               !PageSwapCache(cursor_page))) > +                               continue; >                        if (__isolate_lru_page(cursor_page, mode, file) == 0) { >                                list_move(&cursor_page->lru, dst); >                                mem_cgroup_del_lru(cursor_page); okey. this is definitely better. thanks. Reviewed-by: KOSAKI Motohiro