Hybrid clouds for web systems: Usability and performance

Abstract

The user requests of Web systems are often mutually independent, thus can be processed by processors at separate servers/sites. Irregular and/or burst workloads may occur sometimes. Hybrid Clouds could well be suitable for these kinds of Web systems. This research studies the usability and performance of hybrid Clouds for Web systems. Performance metrics measured are response time (RT), throughput and CPU utilization. Analytical results verify that hybrid Clouds can reach the performance level of private Clouds. They also indicate that both the inverse of RT reduction rate and throughput gain are smaller than the corresponding vCPU gain. The network latency of hybrid Clouds obviously affects CPU utilization and performance in some cases. Public Cloud providers offer various deployment models with different price policies. The performancecost relation of hybrid Clouds is derived from experimental data. It offers a guideline for selecting suitable deployment model for performance requirements under a cost constraint. For an arbitrary upper bound of cost, the system using the model of less computing capacities performs better than the one using the model of more computing capacities. This paper presents a novel method to adopt Cloud technology to achieve the balance of security, performance, server sprawl, and CPU utilization.