Re: [RFC PATCH] perf: Add load latency monitoring on Intel Nehalem/Westmere

[Peter Zijlstra <a.p.zijlstra@chello.nl>]

On Thu, 2010-12-23 at 16:28 +0800, Lin Ming wrote:
> On Wed, 2010-12-22 at 18:45 +0800, Peter Zijlstra wrote:
> > On Wed, 2010-12-22 at 11:08 +0100, Stephane Eranian wrote:
> > > Yes, I think there is more to it than just data source, unfortunately.
> > > If you want to avoid returning an opaque u64 (PERF_SAMPLE_EXTRA), then
> > > you need to break it down: PERF_SAMPLE_DATA_SRC, PERF_SAMPLE_XX
> > > and so on. 
> > 
> > I guess we can do things like:
> > 
> > Satisfied by {L1, L2, L3, RAM}x{snoop, local, remote} + unknown, and
> > encode "Pending core cache HIT" as L2-snoop or something, whatever is
> > most appropriate.
> > 
> > But does that cover every architecture?
> > 
> > Also, since that doesn't require more that 4 bits to encode, we could
> > try and categorize what else is around and try and create a well
> > specified _EXTRA register, I mean, we still got 60bits left after this.
> 
> Could you tell more about this well specified _EXTRA register?

Like how we should look at other archs (like POWER) and try and figure
out what other useful information is available and come up with a
generic format for that?

We could of course leave the 59 bits as reserved and fill it in later,
and go with the data source bits only for now..