Controlling probe overhead

[Stone, Joshua I]

Frank Ch. Eigler wrote:
> On Mon, Mar 12, 2007 at 05:01:32PM -0700, Stone, Joshua I wrote:
> 
>> [...]  And since I like convoluted corner cases -- what do you do if
>> an end probe triggers an error?
> 
> Why, my dear Watson, we allow sequence numbering also on the error
> probes.  That way they logically interleave with end probes.  Any end
> probes with a larger sequence number will not be run and error probes
> will.  (An error that occurs during an error probe is actually easy to
> handle: that probe handler will unwind, but subsequent ones can run.)

Ok -- should there be a defined order for end/error probes with the same
sequence number?  We could leave that ambiguous, but it would be just as
easy to impose one before the other.

Josh