From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1755730Ab3A3QXO (ORCPT <rfc822;w@1wt.eu>);
	Wed, 30 Jan 2013 11:23:14 -0500
Received: from zene.cmpxchg.org ([85.214.230.12]:38843 "EHLO zene.cmpxchg.org"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1754325Ab3A3QXM (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Wed, 30 Jan 2013 11:23:12 -0500
Date: Wed, 30 Jan 2013 11:22:57 -0500
From: Johannes Weiner <hannes@cmpxchg.org>
To: Michal Hocko <mhocko@suse.cz>
Cc: Ying Han <yinghan@google.com>, Andrew Morton <akpm@linux-foundation.org>,
        linux-kernel@vger.kernel.org,
        KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
        Tejun Heo <htejun@gmail.com>, Glauber Costa <glommer@parallels.com>,
        linux-mm@kvack.org, Li Zefan <lizefan@huawei.com>
Subject: Re: [PATCH] mmotm:
 memcgvmscan-do-not-break-out-targeted-reclaim-without-reclaimed-pages.patch
 fix
Message-ID: <20130130162257.GB21614@cmpxchg.org>
References: <20130103180901.GA22067@dhcp22.suse.cz>
 <20130129085104.GA30322@dhcp22.suse.cz>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20130129085104.GA30322@dhcp22.suse.cz>
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Tue, Jan 29, 2013 at 09:51:04AM +0100, Michal Hocko wrote:
> Ying has noticed me (via private email) that the patch is bogus because
> the break out condition is incorrect. She said she would post a fix
> but she's been probably too busy. If she doesn't oppose, could you add
> the follow up fix, please?
> 
> I am really sorry about this mess.
> ---
> >From 6d23b59e96b8173fae2d0d397cb5e99f16899874 Mon Sep 17 00:00:00 2001
> From: Ying Han <yinghan@google.com>
> Date: Tue, 29 Jan 2013 09:42:28 +0100
> Subject: [PATCH] mmotm:
>  memcgvmscan-do-not-break-out-targeted-reclaim-without-reclaimed-pages.patch
>  fix
> 
> We should break out of the hierarchy loop only if nr_reclaimed exceeded
> nr_to_reclaim and not vice-versa. This patch fixes the condition.
> 
> Signed-off-by: Ying Han <yinghan@google.com>
> ---
>  mm/vmscan.c |    2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index d75c1ec..7528eae 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -1985,7 +1985,7 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc)
>  			 * whole hierarchy is not sufficient.
>  			 */
>  			if (!global_reclaim(sc) &&
> -					sc->nr_to_reclaim >= sc->nr_reclaimed) {
> +					sc->nr_to_reclaim <= sc->nr_reclaimed) {

This is just a really weird ordering of the operands, isn't it?  You
compare the constant to the variable, like if (42 == foo->nr_pages).

    if (sc->nr_reclaimed >= sc->nr_to_reclaim)

would be less surprising.