Figure 9-25. Shown is a response-time graph created using OraPub's response-time graph template based solely on data shown in this example's related figures. This response-time graph focuses on the CPU subsystem, so we chose logical IO as our workload metric. As expected, the system is not operating in the elbow of the curve. Since there is virtually no queue time per logical IO processed, improving performance will be the result of decreasing service time or the number of logical IOs a SQL statement consumes.

Figure 9-25 shows the response-time graph based on logical IO processing during our reporting interval. The response-time graphs for this example were created as described previously in this chapter, using OraPub's response-time graph template. The logical IO workload metric was chosen, since it typically has a high correlation to CPU consumption.

Because there is virtually no queue time related to servicing a logical IO, to reduce CPU consumption, we will need to reduce pure logical IO service time (typically, a buy strategy), the number of logical IO requests a SQL statement makes (tune strategy), or the rate of SQL statement executions (balance strategy). During the second analysis cycle, we will focus on this tuning approach.