RE: [Xen-ia64-devel] Time for hybrid virtualization?

[tgingold@xxxxxxx]

Quoting "Xu, Anthony" <anthony.xu@xxxxxxxxx>:

> 1. Memory virtualization,
I agree.

> 2. CPU virtualization
I agree.

>       Accessing shadow register may be faster than accessing memory.
... or not.  Reading memory is faster than reading most AR or CR regs.

>       In summary, I think there are similar performance in terms of
> cpu vitualization.
I agree but this depends on your CPU generation.  I don't know VTi differences
between Montvale and Montecito.

> 3. Device vitualiztion
>       Both para-domain and VT-I domain can use same technology.
Ok.

4. Firmware
  Should we use a guest firmware for dom0 ?

> There were some issues we encounterd on building Vti-dom0( there is no
> modification for dom0 linux kernel at all),
> 1. need an interrupt vector to handle event channel,
>       how to reserve an interrupt vector?
>       What's the interrupt vector priority?

Almost resolved by PV on HVM drivers.

Tristan.

_______________________________________________
Xen-ia64-devel mailing list
Xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-ia64-devel