Assume a M/M/1 system is in it's steady state, given the capacity of the system is 200 req/sec at the maximum clock speed of 1 GHz, I'm confused how to get the service time for it? Does the capacity equal to the service rate in this scenario? So can I let the Capacity = μ = 1 / Ts?

Also, knowing the Ts, and given a desired throughput = 60 req/sec, with average per-request latency = 10 ms, do I able to get a response time/Tq with this parameters, and hence compare it to the desired throughput to see if the system can satisfy the customer?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.