[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] Re: [PATCH] Add hypercall to mark superpages to improve performance

  • To: Dave McCracken <dcm@xxxxxxxx>
  • From: Keir Fraser <keir.fraser@xxxxxxxxxxxxx>
  • Date: Sun, 2 May 2010 17:03:23 -0700
  • Cc: Jeremy Fitzhardinge <jeremy@xxxxxxxx>, Xen Developers List <xen-devel@xxxxxxxxxxxxxxxxxxx>
  • Delivery-date: Sun, 02 May 2010 17:04:28 -0700
  • List-id: Xen developer discussion <xen-devel.lists.xensource.com>
  • Thread-index: AcrqP4Trj5SNGNzgTO6NvnO23nvajwAE1i3/AABLjLU=
  • Thread-topic: [Xen-devel] Re: [PATCH] Add hypercall to mark superpages to improve performance

On 02/05/2010 16:54, "Keir Fraser" <keir.fraser@xxxxxxxxxxxxx> wrote:

>> What are your thoughts?  It seems fairly simple and elegant to me, and at
>> this
>> point I don't see any big holes in it.
> It does mean that creating/destroying pagetable pages causes an extra locked
> read-modify-write cycle on a non-local cacheline (superpage_info refcount).
> Would this be significant? Not sure. I guess we'd only be doing it for
> guests with the superpage capability configured, and we could do some
> performance comparisons with the capability enabled/disabled. I think
> overall I quite like your suggestion.

Oh, now I think about it, although your suggestion deals with type
conflicts, it doesn't handle page lifetimes. What if a page is only mapped
as a superpage? The page->count_info would not be incremented by the
superpage mappings, and the page would be erroneously freed to the Xen free
pools? So I'm not so sure we can so easily avoid the
mess-with-every-page's-refcount on first mapping of a superpage... :-(

 -- Keir

Xen-devel mailing list



Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.