Re: hi-res profiling

On Wed, 2002-10-02 at 17:26, Henrik Nordstrom wrote:

> A more interesting example is
>
> foo (int n)
> {
> PROF_START (foo);
> if (n)
> foo (--n):
> // do some time consuming task
> PROF_STOP (foo);
> }
>
> but I am not sure we have many of these conditions..

Yes, was just poking for holes on the fly.
 
> >From reading the source it seems nesting is not supported very well
> within the same performance counter. If you do the readings will be
> somewhat screwed up usually giving more time spent in the counter
> than actual, counting the time from last start to each stop.
>
> Extending it to support nesting would not be too hard, but involves
> overhead so counters needing nesting should perhaps use other calls.
> Knowing which sections need nesting is not too hard. For such
> counters I propose measuring the time from first start to last stop.

I came to the same conclusion from the source, and am glad to have it
confirmed. For now, I agree with you on the timing of such recursion.
I'm actually concerned about a much more complex case:
something () {
  call cb function.
}

callback() {
}

where the callback occurs for a different instance of something(). We
need to be very sure to PROF_STOP (something) before calling out of it
IMO.
 
> Some suggestions for optimizations:

Thanks - I'll do a few of these.

Whats your take on putting this in HEAD? It's quite non intrusive, and
could be of assistance with various developments.. like commloops and
ESI.

Rob