From mboxrd@z Thu Jan  1 00:00:00 1970
From: Andrew Morton <akpm@zip.com.au>
Subject: Re: [PATCH] smbfs async readpage
Date: Tue, 06 Aug 2002 21:57:56 -0700
Sender: linux-fsdevel-owner@vger.kernel.org
Message-ID: <3D50A8D4.AA31B1DD@zip.com.au>
References: <Pine.LNX.4.44.0208070051220.8176-100000@cola.enlightnet.local>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Cc: linux-fsdevel@vger.kernel.org
Return-path: <linux-fsdevel-owner@vger.kernel.org>
To: Urban Widmark <urban@teststation.com>
List-Id: linux-fsdevel.vger.kernel.org

Urban Widmark wrote:
> 
> This patch implements async readpage for smbfs. It seems to generate
> readahead judging from the network traffic and profile_readahead output
> from 2.4.
>

You'll find that each smbfs inode has its mapping->backing_dev_info
pointing at the global default_backing_dev_info.  Which is not
tunable.

What you can do (please, I'd be interested in checking that it's
workable) is to create an smbfs_backing_dev_info, and arrange
(in smb_iget) for each new inode's mapping->backing_dev_info
to point at it.

Then implement some way of diddling smbfs_backing_dev_info.ra_pages
and voila, tunable readahead.