Empirical analyses of data on working set size are reported. The data do not support the hypothesis that working set sizes are normally distributed. The data suggest various algorithms for predicting working set size based on the program's past history. Several representative algorithms are discussed and evaluated.
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.