Parallel and Distributed Systems, International Conference on (2002)
Dec. 17, 2002 to Dec. 20, 2002
Yu-lung Lo , Chaoyang University of Technology
Yu-chen Huang , Chaoyang University of Technology
A consensus on parallel architecture for very large database management has emerged. This architecture is based on a shared-nothing hardware organization. The computation model is very sensitive to skew in tuple distribution, however. Sorting operation is frequently used for database processing. For example sorting may be requested by users through the use of Distinct, Order By and Group By clauses in SQL. Although load balancing incurs processing costs, and therefore can have a profound influence on the optimized execution plan of a query, only few of the existing parallel sorting execution consider this factor. In this article, we present two parallel sorting algorithms using the dynamic load balancing technique to address the data skew problem. Our performance study indicates that the proposed parallel sorting techniques can provide very impressive performance improvement over conventional approaches.
Parallel Sort, Load Balancing, Data Skew
Y. Huang and Y. Lo, "Effective Skew Handling for Parallel Sorting in Multiprocessor Database Systems," Parallel and Distributed Systems, International Conference on(ICPADS), Taiwan, ROC, 2002, pp. 151.