Persistently cached B-trees

This paper presents an approach to enhancing B-tree indexing performance by using a replication technique called persistent caching. A notable feature of the approach is its compatibility with ordinary B-trees; it exploits only the otherwise unused area of each B-tree page, and the basic behavior of B-trees need not be changed. This paper evaluates the performance of persistently cached B-trees by showing the result of mathematical analysis and of experimental investigations.