[<prev] [next>] [day] [month] [year] [list]
Message-ID: <20090630010302.GD21254@sli10-desk.sh.intel.com>
Date: Tue, 30 Jun 2009 09:03:02 +0800
From: Shaohua Li <shaohua.li@...el.com>
To: Christoph Lameter <cl@...ux-foundation.org>
Cc: "akpm@...ux-foundation.org" <akpm@...ux-foundation.org>,
linux-mm@...ck.org, linux-kernel@...r.kernel.org,
"mel@....ul.ie" <mel@....ul.ie>,
"Zhao, Yakui" <yakui.zhao@...el.com>
Subject: Re: +
memory-hotplug-exclude-isolated-page-from-pco-page-alloc.patch
added to -mm tree
On Tue, Jun 30, 2009 at 06:20:00AM +0800, Christoph Lameter wrote:
> On Mon, 29 Jun 2009, akpm@...ux-foundation.org wrote:
>
> > Pages marked as isolated should not be allocated again. If such pages
> > reside in pcp list, they can be allocated too, so there is a ping-pong
> > memory offline frees some pages to pcp list and the pages get allocated
> > and then memory offline frees them again, this loop will happen again and
> > again.
>
> Isolated pages are freed? Could they not be kept on a separate
> list with refcount elevated until the isolation procedure is complete?
Yes, they can be freed and add into pcp list. Moving them to a separate list
is feasible, but the approach is more intrusive to me. As I explained in the
patch, adding check in buffered_rmqueue() should hasn't impact for normal path.
Thanks,
Shaohua
--
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