Object Placement in Parallel Object-Oriented Database Systems

Parallelism is a viable solution to constructing high performance object-oriented database systems. In parallel systems based on a shared-nothing architecture, the database is horizontally declustered across multiple processors, enabling the system to employ multiple processors to speedup the execution time of a query. The placement of objects across the processors has a significant impact on the performance of queries that traverse a few objects. This is because the execution time of these queries is fairly small and if they access a large number of processors for the relevant data, the overhead of parallelism may become significant, reducing the overall performance of the system and diminishing its capability to scale to a large number of processors. This paper describes and evaluates a greedy algorithm for the placement of objects across the processors of a system. Moreover, it describes two alternative availability strategies: LOBO and SIRE. Both strategies are targeted towards a s..