Query based performance analysis of row and column storage data warehouse

Abstract

Row based relational database management systems (R-RDBMS) are the most common choice for data warehouse implementations. Row based storage is useful in online transaction processing (OLTP) to insert and update data while column oriented RDBMS (C-RDBMS) in online analytical processing (OLAP) to access data from data warehouse. This paper analyses the best suited mode of storage (row or column based storage) for different type of data manipulation language (DML) queries in data warehouse. It also evaluates and compares the performance of row and column oriented data structures based on elapsed time, CPU, I/O and operator costs; for different types of DML queries. A data warehouse has been designed for simulation purpose using Red Gate Data Generator tool along with Microsoft SQL Server 2012. © 2014 IEEE.