Re: [Xen-devel] [PATCH v3 2/2] x86/Intel: virtualize support for cpuid faulting

[Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>]

On 10/24/2016 12:18 AM, Kyle Huey wrote:
>
> The anomalies we see appear to be related to, or at least triggerable
> by, the performance monitoring interrupt.  The following program runs
> a loop of roughly 2^25 conditional branches.  It takes one argument,
> the number of conditional branches to program the PMI to trigger on.
> The default is 50,000, and if you run the program with that it'll
> produce the same value every time.  If you drop it to 5000 or so
> you'll probably see occasional off-by-one discrepancies.  If you drop
> it to 500 the performance counter values fluctuate wildly.

Yes, it does change but I also see the difference on baremetal (although
not as big as it is in an HVM guest):
ostr@workbase> ./pmu 500
Period is 500
Counted 5950003 conditional branches
ostr@workbase> ./pmu 500
Period is 500
Counted 5850003 conditional branches
ostr@workbase> ./pmu 500
Period is 500
Counted 7530107 conditional branches
ostr@workbase>



>
> I'm not yet sure if this is specifically related to the PMI, or if it
> can be caused by any interrupt and it's only how frequently the
> interrupts occur that matters.

I have never used file interface to performance counters, but what are
we reporting here (in read_counter()) --- total number of events or
number of events since last sample? It is also curious to me that the
counter in non-zero after  PERF_EVENT_IOC_RESET (but again, I don't have
any experience with these interfaces).

Also, exclude_guest doesn't appear to make any difference, I don't know
if there are any bits in Intel counters that allow you to distinguish
guest from host (unlike AMD, where there is a bit for that).


-boris

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
https://lists.xen.org/xen-devel