[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20090323101632.69E7.A69D9226@jp.fujitsu.com>
Date: Mon, 23 Mar 2009 10:20:18 +0900 (JST)
From: KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
Cc: kosaki.motohiro@...fujitsu.com,
"linux-mm@...ck.org" <linux-mm@...ck.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"balbir@...ux.vnet.ibm.com" <balbir@...ux.vnet.ibm.com>,
mel@....ul.ie, riel@...hat.com,
"akpm@...ux-foundation.org" <akpm@...ux-foundation.org>
Subject: Re: [PATCH] fix vmscan to take care of nodemask
> Kosaki pointed out it's not necessary to initialize struct member value by NULL.
> Remvoed it.
>
> Regards,
> -Kame
> ==
> From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
>
> try_to_free_pages() scans zonelist but don't take care of nodemask which is
> given to alloc_pages_nodemask(). This makes try_to_free_pages() less effective.
Yes, ignore nodemask make unnecessary reclaim. it decrease try_to_free_pages()
performance.
Note: currently, try_to_free_pages() stop to process reclaim after 32 pages reclaimed.
then, non intentional node scanning can cause large performance degression.
>
> Changelog: v1 -> v2
> - removed unnecessary nodemask=NULL initialization.
>
> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
thanks.
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists