Effective clustering of complex objects in object-oriented databases

Abstract

Clustering is an effective mechanism for retrieving complex objects. Many object-oriented database management systems have suggested variant clustering schemes to improve their performance. Two issues may compromise the effectiveness of a clustered structure, i.e., object updates and multiple relationships. Updates may destroy the initially clustered structure, and in a multiple relationship environment, clustering objects based on one relationship may sacrifice others. This paper investigates the updating effects and suggests a dynamic reclustering scheme to reorganize related objects on the disk. A cost model is introduced to estimate the benefit and overhead of reclustering. Reorganizations are performed only when the overhead can be justified. For environments in which multiple relationships among objects exist, the paper proposes a leveled clustering scheme to order related objects into a clustering sequence. Our simulation results show that the leveled clustering scheme has a better access time compared with a single-level clustering scheme.