Workload-Based Placement and Join Processing in Node-Partitioned Data Warehouses

摘要

Data warehouses (DW) with enormous quantities of data put major performance and scalability challenges. The Node-Partitioned Data Warehouse (NPDW) divides the DW into cheap computer nodes for scalability. Partitioning and data placement strategies are relevant to the performance of complex queries on the NPDW. In this paper we propose a partitioning placement and join processing strategy to boost the performance of costly joins in NPDW, compare alternative strategies using the performance evaluation benchmark TPC-H and draw conclusions.