Abstract
To analyse large-scale systems with high fidelity, it is necessary for a network testbed to offer both realistic emulation (to represent software execution) and effective simulation (to model background computation and communication). We present a network testbed that integrates a lightweight emulation system (modified earlier to operate in virtual time) with a parallel discrete event network simulator. Our contributions lie in the design of a global synchronization algorithm to manage virtual time as it transitions from emulation to simulation, and back. In particular, we optimize our previous algorithm to reduce overhead of synchronizations across simulation and emulation. We also address the unavoidable uncertainties introduced by the emulation by obtaining analytical bounds for the error, and produce empirical data showing that the error is as small as the minimum system execution unit. In addition, we observe excellent system scalability with large-scale network experiments, and demonstrate the performance improvement of the optimized global synchronization algorithm.
Acknowledgements
This material is based on work supported in part by the Department of Energy under Award Number DE-OE0000097, by the Boeing Corporation, and by the International Cooperative R&D Project of the Korea Institute of Energy Technology Evaluation and Planning (KETEP) grant funded by the Korean Ministry of Knowledge Economy (20111030100020).