Performance comparison of three alternatives of distributed multidatabase systems: a global query perspective

Diversity and evolution in database applications often result in a multidatabase environment in which corporate data are stored in multiple distributed data sources, each managed by an independent database management system. One of the essential functions of a multidatabase system is to provide inter database access: the capability of evaluating global queries that require access to multiple data sources. The paper compares three common relational multidatabase approaches: the federated approach, the gateway approach, and the middleware approach from the perspective of global query performance. In particular, we examine their architectural impact on the applicability of pipelined query processing techniques and load balancing. We present a performance comparison based on a detailed simulation. The study suggests that the middleware approach, which is the most cost effective solution among the three, provides better or comparable performance to the other two approaches.