Parallel relational database algorithms revisited for range declustered data sets

Abstract

Today available parallel database systems use conventional parallel hardware architectures employing a highly parallel software architecture. It is an emerging technique to speed up the execution by declustering the stored data sets among a number of parallel and independent disk drives. In this paper we revisit parallel relational database algorithms for range declustering. We adapt the conventional known and well studied parallel algorithms for declustered data, exploit the inherent order property of the partitioned data sets and compare analytically the performance of the algorithms. It is shown that the parallel range declustered variants generally outperform their conventional parallel counterparts.<>