From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner+w=401wt.eu-S1755215AbYE1XXT@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1755215AbYE1XXT (ORCPT <rfc822;w@1wt.eu>);
	Wed, 28 May 2008 19:23:19 -0400
Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753467AbYE1XXI
	(ORCPT <rfc822;linux-kernel-outgoing>);
	Wed, 28 May 2008 19:23:08 -0400
Received: from smtp1.linux-foundation.org ([140.211.169.13]:56264 "EHLO
	smtp1.linux-foundation.org" rhost-flags-OK-OK-OK-OK)
	by vger.kernel.org with ESMTP id S1753220AbYE1XXG (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Wed, 28 May 2008 19:23:06 -0400
Date: Wed, 28 May 2008 16:23:02 -0700
From: Andrew Morton <akpm@linux-foundation.org>
To: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp>
Cc: linux-kernel@vger.kernel.org
Subject: Re: [PATCH] VFS: Pagecache usage optimization onpagesize!=blocksize
 environment
Message-Id: <20080528162302.d2924861.akpm@linux-foundation.org>
In-Reply-To: <6.0.0.20.2.20080527175418.0554f348@172.19.0.2>
References: <6.0.0.20.2.20080513205758.03a7a6b0@172.19.0.2>
	<20080521001930.202446eb.akpm@linux-foundation.org>
	<6.0.0.20.2.20080522160939.051ca938@172.19.0.2>
	<20080522010355.32590474.akpm@linux-foundation.org>
	<6.0.0.20.2.20080527172732.05447770@172.19.0.2>
	<20080527015135.561eeb6d.akpm@linux-foundation.org>
	<6.0.0.20.2.20080527175418.0554f348@172.19.0.2>
X-Mailer: Sylpheed version 2.2.4 (GTK+ 2.8.20; i486-pc-linux-gnu)
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
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 Tue, 27 May 2008 18:34:02 +0900
Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> wrote:

> When we read some part of a file through pagecache, if there is a pagecache 
> of corresponding index but this page is not uptodate, read IO is issued and
> this page will be uptodate.
> I think this is good for pagesize == blocksize environment but there is room
> for improvement on pagesize != blocksize environment. Because in this case
> a page can have multiple buffers and even if a page is not uptodate, some buffers 
> can be uptodate. So I suggest that when all buffers which correspond to a part
> of a file that we want to read are uptodate, use this pagecache and copy data
> from this pagecache to user buffer even if a page is not uptodate. This can
> reduce read IO and improve system throughput.
> 
> v2: add new address_space_operations member is_partially_uptodate, and 
>      block_is_partially_uptodate was registered to ext2/3/4's aops.
>      modify do_generic_file_read to use this aops callback.
> v3: use unsigned instead of unsigned long in block_is_partially_uptodate.
>      cleaned up and simplified page buffer iteration code in block_is_partially_uptodate.
> 
> Signed-off-by :Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp>

OK, thanks, let's give it a try.

It would be excellent if we had some benchmark numbers which justify
this change.

It also would be good if we can think up some workload which might be
slowed down by the change, and then demonstrate that this is not a
significant problem.

After all, it _is_ a performance patch...