Re: [Discuss-gnuradio] oprofile inband code results

[Brian Padalino]

I really don't know much about oprofile and haven't done much
profiling, but I do have a question or two.

Q. Since the profiler looks at the lowest function that is taking so
much time, I find it strange that pmt_nthcdr is the second method
listed there.  Intuitively, pmt_nthcdr should just run a tight loop of
pmt_cdr in which case I would assume pmt_cdr would be higher on the
list but it is not.  Same with pmt_nth.  What might be taking so long
within those functions that is NOT taking as long within
pmt_cdr/pmt_car?  Is something turning into an inline function which
really yields a false profile?

Q. I am surprised to see a destructor (pmt_pair::~pmt_pair())
utilizing so much time.  Are there that many pmt_pairs that have to
get destroyed?  To answer my own question, I suppose so since every
call to pmt_cons actually creates a new pmt_pair - which might be a
good reason why the malloc and frees are high on the list.  Any idea
why so many pmt_cons are used?

Sorry if these seem naive or silly to answer, but it really just makes
me wonder.

Thanks,
Brian