A Simple Linear Model of Demand Paging Performance Predicting the performance of a proposed automatically managed multilevel memory system requires a model of the patterns by which programs refer to the information stored in the memory. Some recent experimental measurements on the Multics virtual memory suggest that, for rough approximations, a remarkably simple program reference model will suffice. The simple model combines the effect of the information reference pattern with the effect of the automatic management algorithm to produce a single, composite statement: the mean number of memory references between paging exceptions increases linearly with the size of the paging memory. The resulting model is easy to manipulate, and is applicable to such diverse problems as choosing an optimum size for a paging memory, arranging for reproducible memory usage charges, and estimating the amount of core memory sharing. CACM April, 1974 Saltzer, J. H. paging, demand paging, memory models, program models, performance measurement, multilevel memory systems, virtual memory, associative memory, memory usage accounting, Multics 3.79 4.30 4.32 CA740401 JB January 18, 1978 10:41 AM 1892 4 2669 1901 4 2669 2085 4 2669 2095 4 2669 2218 4 2669 2277 4 2669 2319 4 2669 2319 4 2669 2329 4 2669 2358 4 2669 2377 4 2669 2373 4 2669 2374 4 2669 2380 4 2669 2434 4 2669 2499 4 2669 2481 4 2669 2501 4 2669 2582 4 2669 2582 4 2669 2625 4 2669 2626 4 2669 2669 4 2669 2669 4 2669 2669 4 2669 2669 4 2669 2828 4 2669 2863 4 2669 2863 4 2669 2881 4 2669 2928 4 2669 2996 4 2669 3006 4 2669 3016 4 2669 3052 4 2669 3054 4 2669 3067 4 2669 1751 5 2669 1901 5 2669 2017 5 2669 2358 5 2669 2669 5 2669 2669 5 2669 2669 5 2669