RE: [PATCH v1 01/11] perf/x86/core: Support KVM to assign a dedicated counter for guest PEBS

[Kang, Luwei]

> >> In the new proposal, KVM user is treated the same as other host
> >> events with event constraint. The scheduler is free to choose whether
> >> or not to assign a counter for it.
> > That's what it does, I understand that. I'm saying that that is
> > creating artificial contention.
> >
> >
> > Why is this needed anyway? Can't we force the guest to flush and then
> > move it over to a new counter?
> 
> KVM only traps the MSR access. There is no MSR access during the scheduling
> in guest.
> KVM/host only knows the request counter, when guest tries to enable the
> counter. It's too late for guest to start over.
> 
> Regarding to the artificial contention, as my understanding, it should rarely
> happen in practical.
> Cloud vendors have to explicitly set pebs option in qemu to enable PEBS
> support for guest. They knows the environment well. They can avoid the
> contention. (We may implement some patches for qemu/KVM later to
> temporarily disable PEBS in runtime if they require.)
> 
> For now, I think we may print a warning when both host and guest require the
> same counter. Host can get a clue from the warning.

Hi Peter,
    What is your opinion? We can treat the guest PEBS event as an event from the user. A little different from other events is the need of pin to the specific counter because the counter index will be included in the Guest PEBS record. The guest counter can't be forced disabled/released as well, otherwise, the end-user will complain. Can we add a warning when the contention is detected or add some description in the document or...?

Thanks,
Luwei Kang