Baseline definition parameters and results

These are the parameters used in the baseline testcase, and the results in terms of throughput and CPU utilization.

This test case uses the four node cluster with Distributed Map Caching mode and the number of workload generating clients were scaled from 25 to 65 to define the base line. The client workload was scaled by increasing the number of users from 25 in increments of 5, until the throughput observed for the cluster peaked.

All runs were done with the standard configuration using the WebSphere® Edge Services Caching Proxy Server, described in Table 1.

Table 1. Cache definitions - baseline parameters
DynaCache size	Caching mode	Servlet caching	Replication domain	Replication type
20000	Distribute map	Disabled	Entire domain	Not shared

Figure 1 illustrates the throughput results for the baseline tests. Figure 2 illustrates the CPU utilization results for the baseline tests.

This figure show the base throughput for the Distributed Map Caching, WebSphere Edge Services Caching Proxy results. — Figure 1. Throughput - Distributed Map Caching, WebSphere Edge Services Caching Proxy

This figure shows the base for client scaling of CPU utilization for Distributed Map Caching and WebSphere Edge Services Caching Proxy. — Figure 2. CPU utilization - Distributed Map Caching, WebSphere Edge Services Caching Proxy

Observations

Throughput peaked at 60 workload clients and drops at 65 workload clients. Total CPU utilization is still increasing through 65 workload clients. Total CPU utilization for z/VM® is greater than 740% at 55 clients, and increases to 751% at 65 clients. This is approaching CPU saturation.

Conclusions

Increasing the number of workload generating clients increases the throughput until the system is fully utilized.