Dynamic Declustering Methods for Parallel Grid Files

Several declustering functions for distributing multi-attribute data on a set of disks have been proposed in recent years. Since these functions map grid regions to disks in a static way, performance deteriorates in case of dynamic datasets and/or non-stationary data distributions. We first analyze how declustering functions can be extended in order to deal with dynamic datasets without requiring periodic reorganizations. In order to support dynamic declustering, we propose to organize the directory as a parallel Multilevel Grid File. On this structure we experiment five dynamic declustering functions and two index-based allocation methods that only use locally available information. This first comparison among the two approaches reveals that methods based on local criteria always yield better results.