On 15.06.2011, at 01:34, Scott Wood wrote:
> This is a shared page used for paravirtualization. It is always present
> in the guest kernel's effective address space at the address indicated
> by the hypercall that enables it.
>
> The physical address specified by the hypercall is not used, as
> e500 does not have real mode.
What are your results when using the magic page? I have the following numbers with your patches applied:
== bare metal ==
root@e500:~/kvm# time for i in {1..1000}; do /bin/echo > /dev/null; done
real 0m5.445s
user 0m0.204s
sys 0m0.572s
== no hypervisor node (magic page not used) ==
debian-powerpc:~# time for i in {1..1000}; do /bin/echo > /dev/null; done
real 1m36.362s
user 0m13.224s
sys 1m11.084s
== with hypervisor node (magic page used) ==
debian-powerpc:~# time for i in {1..1000}; do /bin/echo > /dev/null; done
real 2m28.888s
user 0m9.248s
sys 1m4.016s
This seems rather irritating to me. I haven't tried to trace what's going on, but trapping instructions really shouldn't be much better than mapping the magic page, plus the magic page should stay in memory.
... unless of course we're in the dynamically generated code paths. Then we get plenty of TLB misses instead of instruction emulation traps.
Either way, certainly something to check before we enable the magic page in Qemu.
Alex
--
To unsubscribe from this list: send the line "unsubscribe kvm-ppc" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
