Cache Conscious Indexing for Decision-Support in Main Memory

As random access memory gets cheaper, it becomes increasingly affordable to build computers with large main memories. We consider decision support workloads within the context of a main memory database system, and consider ways to enhance the performance of query evaluation. Indexes can potentially speed up a variety of operations in a database system. In our context, we are less concerned about incremental updating of the index, since we can rebuild indexes in response to batch updates relatively quickly. Our primary concerns are the time taken for a lookup, and the space occupied by the index structure. We study indexing techniques for main memory, including hash indexes, binary search trees, T-trees, B+-trees, interpolation search, and binary search on arrays. At one extreme, hash-indexes provide fast lookup but require a lot of space. At another extreme, binary search on an array requires no additional space beyond the array, but performs relatively poorly. An analysis of binary ...

• Type: Conference
• Year: 1999
• Where: VLDB
• Authors: Jun Rao, Kenneth A. Ross
• Keywords: Binary Search, Binary Search Trees, Database, Search Tree, VLDB 1999