The argument that the 1% perfomance hit for native kernels requires extra work for
package maintainers because they have to make a seperate package for native
(without the performance hit) and a xen version (with paravirt_ops) seems
bogus.
At the moment they also have to provide the 2 packages, 1 native recent
kernel, and 1 older back or forward ported xen kernel (2.6.18 or 2.6.26 for
debian)
So this probably wouldn't change much, although it would be nice for
paravirt_ops to perform like native, i think it shouldn't have to be a show
stopper for inclusion of Xen in mainline.
--
Sander