Re: [PATCH] perfcounters: Support for ftrace event records sampling

[Ingo Molnar]

* Peter Zijlstra <a.p.zijlstra@xxxxxxxxx> wrote:

> On Fri, 2009-08-07 at 01:25 +0200, Frederic Weisbecker wrote:
> > This patch brings the kernel side support for ftrace event record
> > sampling.
> > 
> > A new counter attribute is added: PERF_SAMPLE_TP_RECORD which requests
> > ftrace events record sampling.
> > 
> 
> > +	PERF_SAMPLE_TP_RECORD			= 1U << 10,
> 
> I'd really want this thing called PERF_SAMPLE_RAW

yeah, i'd agree. I suggested to Frederic to use TP_RECORD but in 
hindsight we are better off to handle PERF_SAMPLE_RAW as a 'non-ABI' 
embelishment of samples, of not firmly defined content.

In the tracepoint case, that extra raw content is defined by:

   /debug/tracing/events/*/format

and subject to changes.

	Ingo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/