Short-term performance management by priority-based queueing

Service-based IT infrastructures serve many different business processes on a shared infrastructure in parallel. The automated request execution on the interconnected software components, hosted on heterogeneous hardware resources, is typically orchestrated by distributed transaction processing (DTP) systems. While pre-defined quality-of-service metrics must be met, IT providers have to deal with short-term demand fluctuations. Adaptive prioritization is a way to react to short-term demand variances. Performance modelling can be applied to predict the impact of prioritization on the overall performance of the system. In this paper we describe the workload characteristics and particularities of two realworld DTP systems and evaluate the effects of prioritization regarding overall load and end-to-end performance measures.

• Type: Journal
• Year: 2010
• Where: SOCA
• Authors: Christian Markl, Oliver Hühn, Martin Bichler
• Keywords: Applied Computing, Short-term Demand, Short-term Demand Fluctuations, Short-term Demand Variances, SOCA 2010