Re: [RFC PATCH 1/1] smi_detector: A System Management Interrupt detector

[Ingo Molnar <mingo@elte.hu>]

* Andrew Morton <akpm@linux-foundation.org> wrote:

> On Sun, 31 May 2009 12:31:18 -0400 Jon Masters <jonathan@jonmasters.org> wrote:
> 
> > This patch introduces a new SMI (System Management Interrupt) detector module
> > that can be used to detect high latencies within the system. It was originally
> > written for use in the RT kernel, but has wider applications.
> > 
> 
> Neat-looking code.
> 
> AFACIT it can be used on any platform.  Suppose that powerpcs or ia64s
> also mysteriously go to lunch like PC's do - I think the code will work
> for them too?  In which case the "smi" name is excessively specific. 
> Not a big deal though.

Yes, i wondered about that too - this is really a generic method 
that detects and measures hardware latencies.

Many of the internal smi_ prefixes can go - such a prefix is really 
only needed within a .c module if the symbol is exported.

The rest (and the whole facility) could be renamed to hwlat_, 
hw_latency_ or so - prominently documenting that on x86 it can find 
SMI latencies, etc.?

	Ingo