Re: hi-res profiling

From: Henrik Nordstrom <hno@dont-contact.us>
Date: Wed, 2 Oct 2002 12:09:40 +0200

Andres Kroonmaa wrote:
> On 2 Oct 2002, at 9:26, Henrik Nordstrom <hno@marasystems.com> wrote:
> > > Can probes reenter?
> >
> > 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.
>
> you mean opposite, it shows less time than actual. Time between
> successive starts is lost.

While that is true, it also counts the time twice for each stop.

The time between consequtive START is lost.

The time between the last START and all STOP is counted twice, once per STOP.

Regards
Henrik
Received on Wed Oct 02 2002 - 04:09:45 MDT

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:16:51 MST