A Multi-factor Paging Experiment: I. The Experiment and the Conclusions

This paper reports on a statistically designed and analyzed experiment performed to study the effects of four factors, memory size, problem program, load sequence of system program subroutines and replacement algorithm, upon the paging process. The usefulness of the number of page swaps as a measure for comparing replacement algorithms is evaluated and alternative measures are proposed. The experiment and the conclusions drawn are presented in this paper, while the statistical methodology used to derive these conclusions is presented in a companion paper.