An Experimental Performance Evaluation of Join Algorithms for Parallel Object Databases

Abstract. Parallel relational databases have been successful in providing scalable performance for data intensive applications, and much work has been carried out on query processing techniques in such systems. However, although many applications associated with object databases also have stringent performance requirements, there has been much less work investigating parallel object database systems. An important feature for the performance of object databases is the speed at which relationships can be explored. In queries, this depends upon the effectiveness of different join algorithms into which queries that follow relationships can be compiled. This paper presents the results of empirical evaluations of four parallel join algorithms, two value based and two pointer based. The experiments have been run on Polar, a parallel ODMG object database system.

• Type: Conference
• Year: 2001
• Where: EUROPAR
• Authors: Sandra de F. Mendes Sampaio, Jim Smith, Norman W. Paton, Paul Watson
• Keywords: EUROPAR 2001, Object Database, Object Database System, Parallel Relational Databases