Measuring performance

After you have defined the workload and estimated the resources required, you must reconcile the response that you want with what you consider attainable. Performance of a production system depends on the usage, paging rates, and virtual storage requirements placed on the main processor, the traffic to and from the disk devices, the traffic of messages throughout the network and a variety of other factors.

You should monitor all of these factors to determine when constraints in the system might develop. A variety of programs could be written to monitor all these resources. Some of these programs are currently supplied as part of products such as HCL Workload Automation for Z, or are supplied as separate products. This topic describes some of the programs that can give performance information on different components of a production system.

The list of products in this topic is far from being an exhaustive summary of performance monitoring tools, yet the data provided from these sources comprises a large amount of information. To monitor all this data is an extensive task. Furthermore, only a small subset of the information provided is important for identifying constraints and determining necessary tuning actions, and you must identify this specific subset. You often have to gather a lot of data before you can fully understand the behavior of your own system and determine where a tuning effort can provide the best overall performance improvement. You must be familiar with the analysis tools and the data they provide to successfully tune a system. But remember that all monitoring tools cost processing effort to use.