Model-Based Concurrency Analysis of Network Simulations

To achieve highest performance, parallel simulation of networks on modern hardware architectures depends on large numbers of independent computational tasks. However, the properties determining a network model's concurrency are still not well understood. In this paper, we propose an analytical model that enables concurrency estimations based on model knowledge and on statistics gathered from sequential simulation runs. In contrast to an automated concurrency analysis of event traces, the analytical approach enables insights into the relationship between the topology and communication patterns of the simulated network, and the resulting concurrency. We consider three fundamentally different network models as implemented in the network simulators PeerSim and ns-3: a large-scale application-layer peer-to-peer network, IP-based routing in a fixed topology, and a wireless ad-hoc network. For each model, we conduct an in-depth analysis, exposing the relationships between model characteristics and concurrency. Our analysis is validated by comparing estimated concurrency values to reference results of a trace-based analysis. The identification of key factors for concurrency forms a step towards a classification of network models according to their potential for parallelization.

[1]  David M. Nicol,et al.  Performance prediction of a parallel simulator , 1999, Proceedings Thirteenth Workshop on Parallel and Distributed Simulation. PADS 99. (Cat. No.PR00155).

[2]  Kalyan S. Perumalla.  Discrete-event Execution Alternatives on General Purpose Graphical Processing Units (GPGPUs) , 2006, 20th Workshop on Principles of Advanced and Distributed Simulation (PADS'06).

[3]  David M. Nicol,et al.  Lookahead revisited in wireless network simulations , 2002, Proceedings 16th Workshop on Parallel and Distributed Simulation.

[4]  George Riley,et al.  Distributed simulation with MPI in ns-3 , 2011, SimuTools.

[5]  Rajive L. Bagrodia,et al.  Path lookahead: a data flow view of PDES models , 1999, Proceedings Thirteenth Workshop on Parallel and Distributed Simulation. PADS 99. (Cat. No.PR00155).

[6]  Richard M. Fujimoto,et al.  On the parallel simulation of scale-free networks , 2013, SIGSIM-PADS.

[7]  Yue Li,et al.  A large-scale real-time network simulation study using PRIME , 2009, Proceedings of the 2009 Winter Simulation Conference (WSC).

[8]  Christoph Roth,et al.  Asynchronous parallel MPSoC simulation on the Single-Chip Cloud Computer , 2012, 2012 International Symposium on System on Chip (SoC).

[9]  Peter Martini,et al.  Good news for parallel wireless network simulations , 2009, MSWiM '09.

[10]  Hannes Hartenstein,et al.  Exploiting the parallelism of large-scale application-layer networks by adaptive GPU-based simulation , 2014, Proceedings of the Winter Simulation Conference 2014.

[11]  George F. Riley,et al.  Performance of conservative synchronization methods for complex interconnected campus networks in ns-3 , 2014, Proceedings of the Winter Simulation Conference 2014.

[12]  David Mazières,et al.  Kademlia: A Peer-to-Peer Information System Based on the XOR Metric , 2002, IPTPS.

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

[14]  D. Farnsworth.  A First Course in Order Statistics , 1993 .

[15]  Klaus Wehrle,et al.  Multi-level Parallelism for Time- and Cost-Efficient Parallel Discrete Event Simulation on GPUs , 2012, 2012 ACM/IEEE/SCS 26th Workshop on Principles of Advanced and Distributed Simulation.

[16]  Xvhv Vlpxodwlrq,et al.  A PRACTICAL EFFICIENCY CRITERION FOR THE NULL MESSAGE ALGORITHM , 2003 .

[17]  Hannes Hartenstein,et al.  Parallelism potentials in distributed simulations of Kademlia-based peer-to-peer networks , 2014, SimuTools.