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 S1754699AbbGaXYO (ORCPT <rfc822;w@1wt.eu>);
	Fri, 31 Jul 2015 19:24:14 -0400
Received: from mga14.intel.com ([192.55.52.115]:35244 "EHLO mga14.intel.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1753141AbbGaXYL (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Fri, 31 Jul 2015 19:24:11 -0400
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="5.15,587,1432623600"; 
   d="scan'208";a="775520796"
Message-ID: <55BC0392.2070205@intel.com>
Date: Fri, 31 Jul 2015 16:24:02 -0700
From: Dave Hansen <dave.hansen@intel.com>
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.8.0
MIME-Version: 1.0
To: Xishi Qiu <qiuxishi@huawei.com>, Andrew Morton <akpm@linux-foundation.org>,
        Mel Gorman <mgorman@suse.de>, Vlastimil Babka <vbabka@suse.cz>,
        Johannes Weiner <hannes@cmpxchg.org>, Michal Hocko <mhocko@suse.cz>,
        iamjoonsoo.kim@lge.com, alexander.h.duyck@redhat.com,
        sasha.levin@oracle.com
CC: Linux MM <linux-mm@kvack.org>, LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] mm: add the block to the tail of the list in expand()
References: <55BB4027.7080200@huawei.com>
In-Reply-To: <55BB4027.7080200@huawei.com>
Content-Type: text/plain; charset=windows-1252
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On 07/31/2015 02:30 AM, Xishi Qiu wrote:
> __free_one_page() will judge whether the the next-highest order is free,
> then add the block to the tail or not. So when we split large order block, 
> add the small block to the tail, it will reduce fragment.

It's an interesting idea, but what does it do in practice?  Can you
measure a decrease in fragmentation?

Further, the comment above the function says:
 * The order of subdivision here is critical for the IO subsystem.
 * Please do not alter this order without good reasons and regression
 * testing.

Has there been regression testing?

Also, this might not do very much good in practice.  If you are
splitting a high-order page, you are doing the split because the
lower-order lists are empty.  So won't that list_add() be to an empty
list most of the time?  Or does the __rmqueue_fallback()
largest->smallest logic dominate?