Accuracy study and improvement of network simulation in the SimGrid framework

Distributed computing is a very broad and active research area comprising fields such as cluster computing, computational grids, desktop grids and peer-to-peer (P2P) systems. Studies in this area generally resort to simulations, which enable reproducible results and make it possible to explore wide ranges of platform and application scenarios. In this context, network simulation is certainly the most critical part. Many packet-level network simulators are available and enable high-accuracy simulation but they lead to prohibitively long simulation times. Therefore, many simulation frameworks have been developed that simulate networks at higher levels, thus enabling fast simulation but losing accuracy. One such framework, SimGrid, uses a flow-level approach that approximates the behavior of TCP networks, including TCP's bandwidth sharing properties. A preliminary study of the accuracy loss by comparing it to popular packet-level simulators has been proposed in [11] and in which regimes in which SimGrid's accuracy is comparable to that of these packet-level simulators are identified. In this article we come back on this study, reproduce these experiments and provide a deeper analysis that enables us to greatly improve SimGrid's range of validity