外文文献—并行处理系统的sql优化.docxVIP

余景标：基于Java Web的音乐网站life-listening设计与实现 华东交通大学毕业设计 PAGE 56 PAGE 57 附录A 外文翻译—原文部分 SQL OPTIMIZATION IN A PARALLEL PROCESSING DATABASE SYSTEM Item type Conference Paper Authors Nayem Rahman Citation Rahman N. SQL optimization in a parallel processing database system[C]// Electrical Computer Engineering. 2013. Publisher IEEE Link to item /document/6567832 华东交通大学毕业设计 PAGE 73 SQL OPTIMIZATION IN A PARALLEL PROCESSING DATABASE SYSTEM Nayem Rahman Intel Corporation, Email: nayem.rahman@ Abstract—A database management system (DBMS) with a parallel processing database system is different from conventional database systems. Accordingly, writing SQL for a parallel processing DBMS requires special attention to maintain parallel efficiency in DBMS resources usage such as CPU and I/O. This paper discusses the techniques in SQL writing, tuning, utilization of index, data distribution techniques in a parallel processing DBMS architecture. The resource savings statistics based on several experiments show significant reduction of computing resources usage and improvement of parallel efficiency (PE) can be achieved by using different optimization techniques. Index Terms — Database System; DBMS; Computing Resources; CPU; I/O;Data Warehouse; Parallel Processing I. INTRODUCTION Data warehouse systems resources are destined for use by reporting, analytical and Business Intelligence (BI) tools, enabling business people to make all sorts of decisions based on data warehouse information. It is critical that enough computing resources be available for use by the analytical community to retrieve and process information into intuitive presentations (i.e., reads). This means that the data warehouse batch processing should use the minimum resources possible. There are two aspects that we need take into consideration in maintaining parallel processing capability in a data warehouse. First, in the load process we need to make sure that the database system resources such as CPU time an