TBI: end-to-end network performance measurement testbed for empirical bottleneck detection

Recent advances in networking include new bandwidth-intensive applications, sophisticated protocols that enable real-time data and multimedia delivery and aspects of network security that were not conceived in the beginnings of the Internet. Given these advances and the rapid increase in the number of users accessing the Internet, today's networks need to deliver high levels of end-to-end performance in a reliable fashion. In this paper, we present our novel network measurement methodology which employs an application-specific measurement toolkit including a scaleable test scheduler and analysis module to empirically identify end-to-end bottleneck paths in monitored network routes. To show the utility of our proposed methodology, we present case-studies from a network measurement testbed between 3 University campus labs traversing regional and national academic network backbones. Our case-studies address identifying network measurement anomalies in routine ISP operations due to route changes, device misconfigurations and erroneous data from measurement tools. We also present a performance comparison of campus, regional, national-academic and national-commercial network paths based on the measurement data obtained from our testbed. Finally, we illustrate the requirements and potential of federated measurement testbeds to better characterize end-to-end network performance bottlenecks across multiple ISP domains.