AnsweredAssumed Answered

compare CEM and Loadrunner Metrics

Question asked by paul_saivetz on May 22, 2013
Latest reply on Jun 5, 2013 by paul_saivetz
i know this is a somewhat unusual question. we have noticed large and
irregular differences in average response time and 95th percentile response
time metrics when comparing cem and loadrunner. the loadrunner metric values are
much longer than the cem metrics. of course, these are two different tools
measuring from different locations:

- loadrunner measures from the equivalent of a client desktop, though
rendering time is not included in the metric measurements.
- cem measures from the TIM of course which in our case is between the LB and
web servers. some rendering time may be included depending on how the browser
works before the last packet of the response crosses the tim.

The challenge for us is that we use loadrunner for our key performance
indicators in staging and cem in production. i was trying to develop a
multiplier that would adjust for the differences in the two tools; however,
the differences are large and irregular. I am going to do some more testing but i wanted to know if anyone has
encountered this issue before?