PROJECT TITLE :

Optimization of Composite Cloud Service Processing with Virtual Machines

ABSTRACT:

By leveraging virtual machine (VM) technology, we have a tendency to optimize cloud system performance based on refined resource allocation, in processing user requests with composite services. Our contribution is three-fold. (1) We devise a VM resource allocation theme with a minimized processing overhead for task execution. (a pair of) We have a tendency to comprehensively investigate the simplest-suited task scheduling policy with different design parameters. (three) We tend to additionally explore the best-suited resource sharing theme with adjusted divisible resource fractions on running tasks in terms of Proportional-share model (PSM), which will be split into absolute mode (known as AAPSM) and relative mode (RAPSM). We tend to implement a prototype system over a cluster setting deployed with fifty six real VM instances, and summarized valuable expertise from our analysis. Because the system runs in short supply, lightest workload 1st (LWF) is largely suggested because it will minimize the general response extension ratio (RER) for each sequential-mode tasks and parallel-mode tasks. In an exceedingly competitive scenario with over-commitment of resources, the best one is combining LWF with each AAPSM and RAPSM. It outperforms different solutions in the competitive scenario, by sixteen % w.r.t. the worst-case response time and by 7.four % w.r.t. the fairness.