Metric Dependent Performance Optimization of Virtual Machine Using Hyper Threading Concept

Abstract

Accurate estimate of resource demands is crucial for managing and planning resources in various computer systems. Any work done by computer system considered as a path in the potential field of resources. Metrics provide a quantitative basis for the development and validation of models in the development process. Virtual systems and virtualization technology are taking the momentum nowadays in data centers and IT infrastructure models. Performance analysis of such systems is very invaluable for enterprises but yet is not a deterministic process. n this paper we will present an overview of the key requirements and characteristics of virtual systems performance metrics and workload characterization which can be considered one step further in implementing virtual systems benchmark and performance. The benchmark tests are taken to describe the type of system scalability feature being tested, and describe observed behaviour based on the workload. In particular we explore how Hyper-Threading affects the throughput.

Keywords: Metric, Virtualization, Hyper-thread, Throughput, Virtual Machine