Experiment Replication Using ProtoGENI nodes

摘要

Repeatability of network experiments has long been a goal for networking researchers but the lack of a scientific process of experimentation has made this exercise difficult to achieve. In this paper, we demonstrate that, if conducted in a scientific manner, experiments can indeed be repeated in different networks to produce the same results. We ran experiments in our lab, and on two different network configurations in ProtoGENI and demonstrated that we get similar results for network and application performance evaluations. We believe that this is an important step as we take the process of measurementbased networking research from its ad hoc phase into the realm of a scientific process. We also present these experiments using GENI infrastructure as a demonstration for other experimenters to run similar realistic experiments on GENI testbeds. Furthermore, we believe this is the first set of experiments to emulate per-connection Round- Trip-Times in GENI-based experiments.