A virtual time system for virtualization-based network emulations and simulations

Simulation and emulation are commonly used to study the behaviour of communication networks, owing to the cost and complexity of exploring new ideas on actual networks. Emulations executing real code have high functional fidelity, but may not have high temporal fidelity because virtual machines usually use their host's clock. To enhance temporal fidelity, we designed a virtual time system for virtualization-based network emulations and simulations, such that virtual machines perceive time as if they were running concurrently in physical world. Our time virtualization is not exact: there exist temporal errors primarily due to scheduler timeslice, which is tunable in our system. We then study the tradeoff between temporal fidelity and execution speed under different lengths of timeslices, both experimentally and analytically. We demonstrate that our virtual time system is flexible such that it can achieve different level of temporal accuracy at the cost of different execution speed.

[1]  T.R. Henderson,et al.  CORE: A real-time network emulator , 2008, MILCOM 2008 - 2008 IEEE Military Communications Conference.

[2]  Kurt Rothermel,et al.  Time Jails: A Hybrid Approach to Scalable Network Emulation , 2008, 2008 22nd Workshop on Principles of Advanced and Distributed Simulation.

[3]  David M. Nicol,et al.  S3F: The Scalable Simulation Framework revisited , 2011, Proceedings of the 2011 Winter Simulation Conference (WSC).

[4]  Dejan Kostic,et al.  Scalability and accuracy in a large-scale network emulator , 2002, CCRV.

[5]  David M. Nicol,et al.  A Virtual Time System for OpenVZ-Based Network Emulations , 2011, 2011 IEEE Workshop on Principles of Advanced and Distributed Simulation.

[6]  David M. Nicol,et al.  Validation of Radio Channel Models Using an Anechoic Chamber , 2010, 2010 IEEE Workshop on Principles of Advanced and Distributed Simulation.

[7]  Andrew Tanenbaum MODERN OPERATING SYSTEMS, THIRD EDITION , 2009 .

[8]  Kang G. Shin,et al.  Performance Evaluation of Virtualization Technologies for Server Consolidation , 2007 .

[9]  Hyuk Lim,et al.  J-Sim: a simulation and emulation environment for wireless sensor networks , 2006, IEEE Wireless Communications.

[10]  David M. Nicol,et al.  A distributed memory LAPSE: parallel simulation of message-passing programs , 1994, PADS '94.

[11]  David M. Nicol Tradeoffs between model abstraction, execution speed, and behavioral accuracy , 2006 .

[12]  Yue Li,et al.  SVEET! a scalable virtualized evaluation environment for TCP , 2009, 2009 5th International Conference on Testbeds and Research Infrastructures for the Development of Networks & Communities and Workshops.

[13]  Yuhao Zheng Repeatability of Illinois Wireless Wind Tunnel * Technical Report ( May 23 , 2008 ) , 2008 .

[14]  David E. Culler,et al.  PlanetLab: an overlay testbed for broad-coverage services , 2003, CCRV.

[15]  Mike Hibler,et al.  An integrated experimental environment for distributed systems and networks , 2002, OPSR.

[16]  Dipankar Raychaudhuri,et al.  Evaluation Of OpenVZ Based Wireless Testbed Virtualization , 2008 .

[17]  John Lee,et al.  An integrated testbed for Virtual Ad Hoc Networks , 2009, 2009 5th International Conference on Testbeds and Research Infrastructures for the Development of Networks & Communities and Workshops.

[18]  Brian Walters,et al.  VMware Virtual Platform , 1999 .

[19]  Christian Benvenuti Understanding Linux Network Internals , 2005 .

[20]  Fabrice Bellard,et al.  QEMU, a Fast and Portable Dynamic Translator , 2005, USENIX ATC, FREENIX Track.

[21]  R. M. Fujimoto,et al.  Parallel discrete event simulation , 1989, WSC '89.

[22]  David M. Nicol,et al.  The cost of conservative synchronization in parallel discrete event simulations , 1993, JACM.

[23]  Ronald G. Minnich,et al.  Approaches for Scalable Modeling and Emulation of Cyber Systems: LDRD Final Report , 2009 .

[24]  Nitin H. Vaidya,et al.  Illinois wireless wind tunnel: a testbed for experimental evaluation of wireless networks , 2005, E-WIND '05.

[25]  Amin Vahdat,et al.  DieCast: Testing Distributed Systems with an Accurate Scale Model , 2008, TOCS.