Re: [Xen-devel] Xen optimization

[Andrii Anisov <andrii.anisov@xxxxxxxxx>]

On 12.12.18 19:59, Dario Faggioli wrote:
> Yeah, and although difficult to admit/see the reason why, I think this
> looks like it is coming from something we do in Xen. And since you say
> you have an old Xen version that works, I really see bisection as the
> way to go...
> Not sure I'm getting. Are you saying that you somehow verified that on
> 4.10 vcpus don't move? But on 4.10 you have pinning that works, don't
> you?
Yes, the pinning works (and is reasonably used) in our setup we are providing 
to a customer. That setup is based on 4.10 release.
For my IRQ latency work, I used a simplified setup with the only Dom0 and the 
same XEN as in the customer's setup.
I was too lazy to set up pinning for my experimental setup from the beginning 
and later I found out that VCPUs were not migrating.

> Or are you saying you've verified that vcpus don't move, on 4.10, even
> without doing the pinning? If yes, can I ask how?
Yeh, it took me some time to recall that from my memory:)
When I tried using xentrace to profile interrupt path, I noticed that `current` 
non-idle VCPU is not changed for a particular PCPU.

--
Sincerely,
Andrii Anisov.

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel