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

Re: [Xen-devel] RFC: [0/2] Remove netloop by lazy copying in netback



On Tue, Mar 27, 2007 at 09:10:40AM +0100, Keir Fraser wrote:
>
> > Even with this we could still keep the large pages by using page
> > faults on the host page table rather than the guest page table.
> 
> Sure. How would you expose those to the guest? If that can be solved we can
> define grant-table unmap to switch the p2m entry into an explicitly invalid
> state and we're away.

I was actually thinking of Jose's scheme where it's mapped in on
demand.  So you would still do your grant table map operation,
but instead of mapping it in as we do now it would simply notify
the hypervisor of the intention to map this page, and the hypervisor
can then map it in when it actually faults.

Cheers,
-- 
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <herbert@xxxxxxxxxxxxxxxxxxx>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel


 


Rackspace

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