Performance Evaluation of MySQL 5.0 and Berkeley DB XML as a Grid Resource Information Manager (GRIM) with a Benchmark/Workload

Abstract

A challenge in the distributed middleware that implements a grid envisioned to span the world, is the management of information about the resources available to the Grid. This paper describes an experimental study we undertook to better understanding the performance of the native XML database Berkeley DB XML, as a grid resource information manager system compare to MySQL 5.0. We run a benchmark set of queries along with several workload scenarios. These queries test a broad range of database functionalities through realistic questions asked on meaningful data. The scenarios are short synthetic workload that test query response time of a repository under a workload of concurrent query and update requests. Based on the results, we illuminate the strengths and weaknesses of a platform in its contribution to the requirements of a grid resource information manager.