User:Todd Bezenek/Little's Law Applications

Applications

• Perhaps suggest a new article.

• Add a comment about the definition of service time, response time, and wait time.

• Add these uses of Little's Law:
  • Average queue length = arrival rate = throughput * wait time (N = lambda * W = XW)
    • Restated: number of customers in the system = throughput * response time (N = lambda * R = XR)
    • Reference: http://www.shmula.com/queueing-theory/
    • Reference: Guerrilla Capacity Planning
    • Reference: Ed Lazowska's text on his Web page at UW.
  • Average utilization = throughput * service time (U = XS)

Software-performance testers have used Little's law to ensure that the observed performance results are not due to bottlenecks imposed by the testing apparatus. See:

• Software Infrastructure Bottlenecks in J2EE by Deepak Goel
• Benchmarking Blunders and Things That Go Bump in the Night by Neil Gunther
• Appears to be a good reference.