Experimentation

After you read this document, you can better understand Capacity Advisor by experimenting, considering different configurations and workload placement, and by trying them out in what-if scenarios. A scenario identifies the workload demand profile that creates your experimental simulations.

When you do workload analysis on systems, you view graphs and reports that represent CPU or memory utilization by time. For example, Figure 2–2 shows a graph of CPU utilization for a single system over a one-month period.

Figure 2-2 CPU Utilization for node01

Similarly, Figure 2–3 shows CPU utilization for a second system over the same period.

Figure 2-3 CPU Utilization for node02

Comparing these two graphs shows that workload peaks on the two systems do not occur simultaneously. Also, on node01, CPU utilization has a peak of about 7 CPUs, while that for node02 has a peak of almost 8 CPUs. This suggests an opportunity to consider whether you can use both systems together to satisfy the needs of both workloads, while reducing the number of CPUs.

Figure 2–4 shows the result of using a Capacity Advisor what-if scenario to combine the workloads on both systems.

Figure 2-4 Combined What-If CPU Utilization for node01 and node02

From the graph, it is evident that the peak of the combined workloads is only 12 CPUs because workload peaks on both systems are not simultaneous. Therefore, you do not need 15 CPUs to meet this workload demand during the utilization period.