Workload Generation and Instrumentation for Reproducible Networking Experiments

We propose the design of a benchmarking and instrumentation component for the GENI experimental networking testbed. Our design uses a workload generation system to create reproducible network conditions and an instrumentation component to collect measurement data. We discuss the research challenges related to this design.

[1]  Anja Feldmann,et al.  Internet clean-slate design: what and why? , 2007, CCRV.

[2]  Ning Yang,et al.  An Architecture for Distributed Real-Time Passive Network Measurement , 2006, 14th IEEE International Symposium on Modeling, Analysis, and Simulation.

[3]  Fred Kuhns,et al.  The open network laboratory: a resource for networking research and education , 2005, CCRV.

[4]  David E. Culler,et al.  Operating Systems Support for Planetary-Scale Network Services , 2004, NSDI.

[5]  Charles E. Barb,et al.  An integrated experimental environment for distributed systems and networks , 2002, USENIX Symposium on Operating Systems Design and Implementation.

[6]  Matthew R. Guthaus,et al.  MiBench: A free, commercially representative embedded benchmark suite , 2001, Proceedings of the Fourth Annual IEEE International Workshop on Workload Characterization. WWC-4 (Cat. No.01EX538).

[7]  David J. Lilja,et al.  Measuring computer performance : A practitioner's guide , 2000 .

[8]  Reinhold Weicker,et al.  Dhrystone: a synthetic systems programming benchmark , 1984, CACM.

[9]  Raj Jain,et al.  The art of computer systems performance analysis - techniques for experimental design, measurement, simulation, and modeling , 1991, Wiley professional computing.

[10]  Brian A. Wichmann,et al.  A Synthetic Benchmark , 1976, Comput. J..