Column Partitioning to Improve Data Warehouse Query Performance
Jong Wook Kim, Sae-Hong Cho, Il‐Min Kim · Advanced science and technology letters · 2015
In this paper, we propose a novel data partitioning scheme to im- prove data warehouse query performance in column-oriented data stores. The proposed partitioning method leverages column access patterns of a given workload in order to find the best multi-column partitions. Our proposed ap- proach is able to compute a set of multi-column partitions that yield the best performance for the given entire query workload, when storage is constrained.