Re: [REDO PATCH v7] perf/x86/amd/power: Add AMD accumulated power reporting mechanism

[Huang Rui <ray.huang@amd.com>]

On Thu, Jun 16, 2016 at 01:38:13PM +0800, Huang Rui wrote:
> On Wed, Jun 15, 2016 at 09:13:59PM -0400, Vince Weaver wrote:
> > 
> > 2.  Unless I'm misunderstanding things, the code seems to be accumulating 
> > 	Power. (see chunk below) Power is an instantaneous measurement, it 
> > 	makes no sense to add values.  If you use 5W for 1ms and 10W for
> > 	1ms, the average power across the 2ms interval is not 15W.
> > 
> > 	You can add energy, but not power.
> > 
> > > +	delta *= cpu_pwr_sample_ratio * 1000;
> > > +	tdelta = new_ptsc - prev_ptsc;
> > > +
> > > +	do_div(delta, tdelta);
> > > +	local64_add(delta, &event->count);
> > 
> 
> You're right. Nice catch! The average power is per compute unit. We
> cannot add the power simplely for each processor/package.
> 
> So here, the average power per package should be (delta1 + delta2 + ... + deltaN)/(tdelta_avg).
> I will work out a fix. Thanks to point out.
> 

After considering carefully, the original method should be OK. 

      AMD nomenclature for CMT systems:

        [node 0] -> [Compute Unit 0] -> [Compute Unit Core 0] -> Linux CPU 0
                                     -> [Compute Unit Core 1] -> Linux CPU 1
                 -> [Compute Unit 1] -> [Compute Unit Core 0] -> Linux CPU 2
                                     -> [Compute Unit Core 1] -> Linux CPU 3

The deltaN is power per compute unit. Current one package has two CUs.
In the *same* interval, CU0's power is 10W, CU1's power is 15W. The
package (CU0 + CU1) power should be 15W, right? Because the interval
is the same.

Q = Q1 + Q2.  P = Q/t = (Q1 + Q2)/t = Q1/t + Q2/t = P1 + P2.

Is that clear?

Thanks,
Rui