The role of performance engineering techniques in the context of the Grid

Abstract

SUMMARYPerformance engineering can be described as a collection of techniques and methodologies whose aim is to provide reliable prediction, measurement and validation of the performance of applications on a variety of computing platforms. This paper reviews techniques for performance estimation and performance engineering developed at the University of Southampton and presents application case studies in task scheduling for engineering meta-applications, and capacity engineering for a financial transaction processing system. These show that it is important to describe performance in terms of a resource model, and that the choice of models may have to trade accuracy for utility in addressing the operational issues. We then present work from the on-going EU funded Grid project GRIA, and show how lessons learned from the earlier work have been applied to support a viable business model for Grid service delivery to a specified quality of service level. The key in this case is to accept the limitations of performance estimation methods, and design business models that take these limitations into account rather than attempting to provide hard guarantees over performance. We conclude by identifying some of the key lessons learned in the course of our work over many years and suggest possible directions for future investigations. Copyright

Grid benchmarking: vision, challenges, and current status

“…Consequently, the proper interpretation of Grid benchmarking metrics is a challenging task, which requires the combination of benchmarking metrics with appropriate models for the Grid and its applications. To the best of our knowledge, however, the field of Grid modeling is still at its infancy, although some promising results have already appeared in the literature [31].…”

A Study on the Effect of Application and Resource Characteristics on the QoS in Service Provisioning Environments

“…These models can be used to compare tasks prior to making scheduling decisions about the selection of the machine on which the service will be executed. The accuracy of performance predictions obtained by this technique was illustrated in several case studies drawn from the domain of mechanical simulations (Hey, 2005). The advantage of analytical approach is that it provides simple mathematical expressions that include the key parameters governing the performance of the application, however in the case of commercial software codes, the source code for the application is not available for instrumentation and all analytical models have therefore to be derived from benchmarking the application.…”