[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20091228035639.GG3601@balbir.in.ibm.com>
Date: Mon, 28 Dec 2009 09:26:39 +0530
From: Balbir Singh <balbir@...ux.vnet.ibm.com>
To: Rik van Riel <riel@...hat.com>
Cc: Minchan Kim <minchan.kim@...il.com>,
Andrew Morton <akpm@...ux-foundation.org>,
lkml <linux-kernel@...r.kernel.org>,
linux-mm <linux-mm@...ck.org>,
Hugh Dickins <hugh.dickins@...cali.co.uk>,
KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
Subject: Re: [PATCH -mmotm-2009-12-10-17-19] Prevent churning of zero page in
LRU list.
* Rik van Riel <riel@...hat.com> [2009-12-27 22:22:20]:
> On 12/27/2009 09:53 PM, Minchan Kim wrote:
> >
> >VM doesn't add zero page to LRU list.
> >It means zero page's churning in LRU list is pointless.
> >
> >As a matter of fact, zero page can't be promoted by mark_page_accessed
> >since it doesn't have PG_lru.
> >
> >This patch prevent unecessary mark_page_accessed call of zero page
> >alghouth caller want FOLL_TOUCH.
> >
> >Signed-off-by: Minchan Kim<minchan.kim@...il.com>
>
> The code looks correct, but I wonder how frequently we run into
> the zero page in this code, vs. how much the added cost is of
> having this extra code in follow_page.
>
> What kind of problem were you running into that motivated you
> to write this patch?
>
Frequent moving of zero page should ideally put it to the head of the
LRU list, leaving it untouched is likely to cause it to be scanned
often - no? Should this be moved to the unevictable list?
--
Balbir
--
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