Re: [Qemu-devel] pert stat in KVM guest can not get LLC-loads hardware cache event

[Liang, Kan]

> > Hi, Kan,
> >
> > The dTLB-load-misses is 0, but it shows 80.00%hit, does that mean the
> > TLB- load miss is 0.8 * (dTLB-loads). Thanks.
> >
> >  Performance counter stats for './parsecmgmt -a run -i native -c
> > gcc-hooks -n
> > 1 -p freqmine':     

I'm not familiar with parsecmgmt. What’s the perf commands it calls?

> >
> >
> >                  0 dTLB-load-misses          #    0.00% of all dTLB
> > cache hits  [80.00%]
> >
> >    782,565,273,315 dTLB-loads
> >          [80.00%]
> >
> >    782,552,911,616 L1-dcache-loads
> >          [80.00%]
> >
> >      5,810,697,456 L1-dcache-load-misses     #    0.74% of all
> > L1-dcache hits   [80.00%]
> >
> >      2,145,907,209 L1-dcache-prefetch-misses
> >          [80.00%]
> >
> > - Hui
> >
> > On Wed, Aug 27, 2014 at 9:05 AM, Liang, Kan <address@hidden> wrote:
> > >
> > >
> > >>
> > >> Dear KVM developers:
> > >> I am trying use perf stat inside a VM to obtain some hardware cache
> > >> performance counter values.
> > >> The perf stat can report some numbers for L1 and TLB related
> > >> counters. But for the LLC-loads and LLC-load-misses, the numbers
> > >> are always 0. It seems that the these offcore events are not
> > >> exposed to the
> > guest.
> > >>
> > >> Is this a bug in Qemu or KVM?
> > >>
> > >
> > > There is no offcore virtualization support in KVM yet.
> > > For you case, I guess you are using paravirt for guest, so it should be 0.
> > > Otherwise, you should get #GP in guest.
> > >
> > >
> > >> My testbed is
> > >>
> > >> Host kernel: 3.12.26
> > >> Qemu: 2.1.0
> > >> CPU: Intel Ivy bridge 2620
> > >> VM boosted by qemu, with -cpu host.
> > >>
> > >> Thanks.
> > >>
> > >> - Hui Kang