From mboxrd@z Thu Jan  1 00:00:00 1970
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Subject: Re: [PATCH 2/4] xen: introduce an "scrub" free page list
Date: Wed, 18 Jun 2014 09:18:14 -0400
Message-ID: <20140618131814.GD2788@laptop.dumpdata.com>
References: <1403005783-30746-1-git-send-email-bob.liu@oracle.com>
	<1403005783-30746-2-git-send-email-bob.liu@oracle.com>
	<53A05278020000780001B079@mail.emea.novell.com>
	<53A0E328.8070702@oracle.com>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Return-path: <xen-devel-bounces@lists.xen.org>
Received: from mail6.bemta4.messagelabs.com ([85.158.143.247])
	by lists.xen.org with esmtp (Exim 4.72)
	(envelope-from <konrad.wilk@oracle.com>) id 1WxFkx-0000ZB-4S
	for xen-devel@lists.xenproject.org; Wed, 18 Jun 2014 13:18:27 +0000
Content-Disposition: inline
In-Reply-To: <53A0E328.8070702@oracle.com>
List-Unsubscribe: <http://lists.xen.org/cgi-bin/mailman/options/xen-devel>,
	<mailto:xen-devel-request@lists.xen.org?subject=unsubscribe>
List-Post: <mailto:xen-devel@lists.xen.org>
List-Help: <mailto:xen-devel-request@lists.xen.org?subject=help>
List-Subscribe: <http://lists.xen.org/cgi-bin/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xen.org?subject=subscribe>
Sender: xen-devel-bounces@lists.xen.org
Errors-To: xen-devel-bounces@lists.xen.org
To: Bob Liu <bob.liu@oracle.com>
Cc: Bob Liu <lliubbo@gmail.com>, keir@xen.org, ian.campbell@citrix.com, George.Dunlap@eu.citrix.com, andrew.cooper3@citrix.com, Jan Beulich <JBeulich@suse.com>, xen-devel@lists.xenproject.org
List-Id: xen-devel@lists.xenproject.org

On Wed, Jun 18, 2014 at 08:54:00AM +0800, Bob Liu wrote:
> 
> On 06/17/2014 08:36 PM, Jan Beulich wrote:
> >>>> On 17.06.14 at 13:49, <lliubbo@gmail.com> wrote:
> >> Because of page scrubbing, it's very slow to destroy a domain with large 
> >> memory.
> >> It takes around 10 minutes when destroy a guest of nearly 1 TB of memory.
> >>
> >> This patch introduced a "scrub" free page list, pages on this list need to be
> >> scrubbed before use. During domain destory just mark pages "PGC_need_scrub"
> >> and then add them to this list, so that xl can return quickly.
> >>
> >> In alloc_domheap_pages():
> >>   - If there are pages on the normal "heap" freelist, allocate them.
> >>   - Try to allocate from the "scrub" free list with the same order and do
> >>     scrubbing synchronously.
> >>
> >> In order to not fail high order allocate request, merge page trunks for
> >> PGC_need_scrub pages.
> >> Note: PCG_need_scrub pages and normal pages are not mergeable
> > 
> > The whole series needs sync-ing logically both with Konrad's recent
> > boot time scrubbing changes (this change here really makes his
> > change unnecessary - the affected pages could quite well be simply
> > marked as needing scrubbing, getting dealt with by the logic added
> > here) and with XSA-100's change.
> > 
> 
> I agree. Konrad?

The patch is already in staging. See 7430a86de0c9bd126b441570e459f6e06413cbf6
and 4bd78937ec324bcef4e29ef951e0ff9815770de1.

Thanks!