The first form simply states that response is the sum of service time and queue time. The second is the classic response time formula. The third replaces the utilization symbol with the utilization formula, which can be handy if the utilization is unknown.6

Figure 9-13 is the response-time graph based on the Statspack report used throughout this chapter and on which many of the preceding values and calculations are based (including the queuing theory calculations shown in this section). The actual graph was constructed by inputting the core statistics of sample interval timer, total workload units, total CPU consumption, number of CPU cores, and total non-idle wait time into OraPub's response-time graph template (a Microsoft Excel-based tool).7

Figure 9-13. Shown is the response-time graph created using OraPub's response-time graph template. This particular graph is based on the data shown in the calculations in this section. The peak arrival rate is clearly beyond what the system can process, and as we would expect, severe performance problems are occurring.