An Examination Method of Mergeable Memory Page Distribution for Memory Deduplication
Masahito Shiba · 2019
When multiple virtual machines run in a single physical machine, the same libraries and applications are often used and these virtual machines have memory pages of the same contents. Memory deduplication, which merge such memory pages that have the same contents into one physical memory page, can improve the efficiency of the memory usage. However, the cost of finding mergeable pages is significantly expensive. This paper describes a method to investigate how mergeable memory pages are distributed in address spaces. The method classifies the pages by state of consecutive pages and measures the proportion of the pages in each state. This paper also describes that the actual page distribution measured by the proposed method on environment that virtual machines run. It shows that measuring the distribution is useful for estimating the probability of merging pages for memory deduplication.