From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner+w=401wt.eu-S1756420AbYKDVVn@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1756420AbYKDVVn (ORCPT <rfc822;w@1wt.eu>);
	Tue, 4 Nov 2008 16:21:43 -0500
Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755576AbYKDVV3
	(ORCPT <rfc822;linux-kernel-outgoing>);
	Tue, 4 Nov 2008 16:21:29 -0500
Received: from nlpi053.sbcis.sbc.com ([207.115.36.82]:47036 "EHLO
	nlpi053.prodigy.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1755100AbYKDVV3 (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Tue, 4 Nov 2008 16:21:29 -0500
Date: Tue, 4 Nov 2008 15:20:56 -0600 (CST)
From: Christoph Lameter <cl@linux-foundation.org>
X-X-Sender: cl@quilx.com
To: Andrew Morton <akpm@linux-foundation.org>
cc: David Rientjes <rientjes@google.com>, npiggin@suse.de,
       peterz@infradead.org, menage@google.com, dfults@sgi.com,
       linux-kernel@vger.kernel.org
Subject: Re: [patch 1/7] cpusets: add dirty map to struct address_space
In-Reply-To: <20081104130918.bee16cff.akpm@linux-foundation.org>
Message-ID: <Pine.LNX.4.64.0811041513490.23418@quilx.com>
References: <alpine.DEB.2.00.0810292337170.23858@chino.kir.corp.google.com>
 <alpine.DEB.2.00.0810300310180.18283@chino.kir.corp.google.com>
 <20081104130918.bee16cff.akpm@linux-foundation.org>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed
X-Spam-Score: -2.6
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Tue, 4 Nov 2008, Andrew Morton wrote:

>> +#ifdef CONFIG_CPUSETS
>> +#if MAX_NUMNODES <= BITS_PER_LONG
>> +	nodemask_t		dirty_nodes;	/* nodes with dirty pages */
>> +#else
>> +	nodemask_t		*dirty_nodes;	/* pointer to mask, if dirty */
>> +#endif
>> +#endif
>>  } __attribute__((aligned(sizeof(long))));
>
> eek.  Increasing the size of the address_space (and hence of the inode)
> is a moderately big deal - there can be millions of these in memory.

Well this is adding only a single word to the inode structure.

>> @@ -72,6 +72,8 @@ struct writeback_control {
>>  	 * so we use a single control to update them
>>  	 */
>>  	unsigned no_nrwrite_index_update:1;
>> +
>> +	nodemask_t *nodes;		/* Nodemask to writeback */
>
> This one doesn't get ifdefs?

The structure is typically allocated temporarily on the stack.

>> +	nodemask_t *nodes = mapping->dirty_nodes;
>> +	int node = page_to_nid(page);
>> +
>> +	if (!nodes) {
>> +		nodes = kmalloc(sizeof(nodemask_t), GFP_ATOMIC);
>
> erk, OK, called from __set_page_dirty, needs to be atomic.
>
> What are the consequences when this allocation fails?

Dirty tracking will not occur. All nodes are assumed to be dirty.

We discussed this earlier 
http://www.ussg.iu.edu/hypermail/linux/kernel/0709.1/2291.html