A Taxonomy and Performance Model of Data Skew Effects in Parallel Joins
VLDB '91 Proceedings of the 17th International Conference on Very Large Data Bases
Hi-index | 0.00 |
Data distributions are presented for relations in two databases: stock trading data and message traffic in a military communications system. This report makes two research contributions. Formal definitions of skew parameters are added to the relative partition model of data skew. Finally, although the observed databases reside on a single node system, skew parameters for three types of data skew are estimated for a worst case partitioning.