Simulation model driven performance evaluation for enterprise applications

Performance evaluations for enterprise applications running over IT systems are difficult to carry out given the multiplicity and variability of the operational components that constitute the dispersed IT infrastructures. To overcome this challenge, most of the approaches for performance assessment employ benchmarking strategies. While benchmarking methods provide exact indications on the performance capability of the measured facility, the results so obtained mostly apply to specific physical implementations considered in benchmark runs. The information provided by benchmark data thus restricts the ability to carry out meaningful performance analysis unless wide varieties of physical scenarios are generated for comparative studies. Given the logistical drawbacks associated with benchmarking techniques, we therefore propose a flexible model-based approach to determine quantitative performance for applications in IT systems by producing a range of performance models through the use of generic components that are easily assembled in simulation environments. Our approach initially considers a Tier 2 model framework whose components are derived from the SAP Sell-from-Stock application routine running on a multi-core processor server. The modelled framework is extensible enough to provide the definitions of resource consumptions patterns of different applications as well as the variety of server hardware systems. The simulations of our initial models developed so far generate results that are comparable to measurements obtained for scenarios in the low and moderate loading levels.