I don't know.
BUT I DO KNOW IF YOU DONT HAVE A REAL-TIME OPERATING SYSTEM AND A REAL-TIME PROGRAM YOU CANT DO IT.
P100 is the max latency of the response of network service, such as a HTTP request.
This metric is very variable, and it is not a good metric to measure the performance of majority of the services,
except it is a real-time service, such as the control system of nuclear missile / fighter aircraft, etc.