performance analysis producer_consumer.cc TEST_T5

[law@redhat.com]

In message <40329DA9.8060604@redhat.com>, Will Cohen writes:
 >There is also a problem related to the threading with this particular 
 >performance test code. The uniprocessor machine the runtime was about 
 >1/30 the cpu time for the smp machine. If things were working correctly 
 >in the producer_consumer.cc code, the lists should be relatively short. 
 >That one function should not take 99.9% of the time (okay that is an 
 >exaggeration. it has 99.8996% of the samples for the test).
I'm not disputing that there's a deeper problem, it was just ironic
that we had just discussed the O(n) cost to count the members in a list
with customers.

jeff