Evaluating the performance of cloud services in a browser-based network measurement platform

Abstract

The emerging cloud services are often provisioned as web applications. Web browsers provide user-friendly interfaces for users to interact with different Internet contents with flexible and rich plug-in environments. Due to their ubiquitous and flexible nature, we propose to evaluate the performance of cloud services in a browser-based network measurement platform. Delay is one of the fundamental performance metrics of cloud services. The quality-of-experience (QoE) of end-users of cloud services is largely determined by the end-to-end delay between cloud servers and end-hosts at the application layer. Nevertheless, network measurement tools usually only measure network delay and it may be difficult to infer QoE using only network layer measurement approaches. In this paper, we conducted a delay measurement study using engineered scripts in the proposed browser-based measurement platform. Our investigation included a comparison study of three delay measurement methods at the application layer, including King, JavaScript and Flash ActionScript which measured application layer delay in terms of accuracy, intrusiveness, deployment, scalability, and security. We developed a browser-based delay measurement testbed over the Internet so that different delay measurement tools could be evaluated in the same real network environment. Our measurement results revealed the properties of the application layer delay over real Internet paths, and how these properties varied from the underlying network layer delay.