On 10/12/2018 12:23, Andrii Anisov wrote:
Hello Julien,
On 10.12.18 13:54, Julien Grall wrote:
What are the numbers without Xen?
Good question. Didn't try. At least putchar should be implemented for that.
I think we need the baremetal numbers to be able to compare properly the old and
new vGIC.
Which version of Xen are you using?
This morning's staging, commit-id 58eb90a9650a8ea73533bc2b87c13b8ca7bbe35a.
This also tells you that in the trap case the vGIC is not the bigger overhead.
Indeed, not the bigger. But significant even in this trivial case (receiving an
interrupt twice a second).
To confirm, in your use-case you have the interrupt firing every 500ms, right?
But I am not sure what you are trying to argue here... I never said it was
insignificant, I only pointed out that the context switch/trap has a strong
impact. This means that focusing on optimizing context/switch is probably more
worth it at the moment than trying to micro-optimizing the vGIC.
What matters at the end is the overhead of virtualization (i.e Xen). Without
those baremetal numbers, it is quite difficult to make an idea whether this is
significant.
This is with all your series applied but [4], correct?
Right.
Did you try to see the perfomance improvement patch by patch?
No. Not yet.
I would like to have performance per patch so we can make the decisions whether
the implementation cost is worth it for upstream.
Cheers,
--
Julien Grall
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
