Skip to Main Content
Paging activity can be a major factor in determining whether a software workload will run on a given computer system. A program's paging behavior is difficult to predict because it depends not only on the workload processed by the program, but also on the level of storage contention of the processor. A program's fault rate function relates storage allocation to the page fault rate experienced while processing a given workload. Thus, with the workload defined, the fault rate function can be used to see how the program's storage allocation is affected by varying levels of storage contention, represented by varying fault rates. This paper presents a technique to represent program workloads and estimate the fault rate function, and describes how these results can be used in analyzing program performance.
Note: The Institute of Electrical and Electronics Engineers, Incorporated is distributing this Article with permission of the International Business Machines Corporation (IBM) who is the exclusive owner. The recipient of this Article may not assign, sublicense, lease, rent or otherwise transfer, reproduce, prepare derivative works, publicly display or perform, or distribute the Article.