RUNTIME BALANCING EFFECT IN DISTRIBUTED SIMULATION MODEL
Read the full article ';
For citation: Shinkaruk D.N. Runtime balancing effect in distributed simulation model. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2015,vol. 15, no. 1, pp. 101–106
The paper deals with study of the load distribution effect between computing nodes for simulation run-time of a distributed computer network model. Two main types of balancing are considered: computational load balancing and reduction of transmitted amounts of data. Simulation was performed on one computer, and distribution was carried out between the cores of one processor. Simulation experiments showed that the lack of balance in the amounts of data, transferred between parts of a distributed model, leads to decrease of the simulation speed by several times due to overhead charges for data transmission between logical processes because of MPI usage. Model run-time changing at uneven distribution of computational load depends to a large extent on the load, which is created by the applications running on the simulated network nodes. It is shown that a balanced model is performed much faster than unbalanced version even when using applications that do not require significant computing resources. Simulation time reduction can be achieved by model separation in such manner as to reduce amounts of data transferred between its parts and reduce variability of loads generated by applications in different logical processes.
1. Mikov A.I., Zamyatina E.B. Tekhnologiya imitatsionnogo modelirovaniya bol'shikh sistem [Simulation technology of large systems]. Trudy Vserossiiskoi Nauchnoi Konferentsii "Nauchnyi Servis v Seti Internet" [Proc. All-Russian Conference Scientific Service in the Internet"]. Moscow, MGU Publ., 2008, pp. 199–204.
2. Aliev T.I. Osnovy Modelirovaniya Diskretnykh Sistem [Basics of Discrete Systems' Modeling]. St. Petersburg, SPbSU ITMO, 2009, 363 p.
3. Fujimoto R.M. Parallel and Distributed Simulation Systems. Wiley, 2000, 320 p.
4. Perumalla K., Park A., Wu H., Ammar M.H., Riley G.F. Large-scale network simulation: how big? How fast? IEEE 20th Int. Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, 2003, pp. 116–123.
5. Manjikian N., Loucks W.M. High performance parallel logic simulations on a network of workstations. ACM SIGSIM Simulation Digest, 1993, vol. 23, no. 1, pp. 76–84.
6. Misra J. Distributed discrete-event simulation. ACM Computing Surveys, 1989, vol. 18, no. 1, pp. 39–65.
7. Chandy K.M., Misra J. Distributed simulation: a case study in design and verification of distributed programs. IEEE Transactions on Software Engineering, 1979, vol. SE-5, no. 5, pp. 440–452.
8. Wentong C., Turner S.J., Hanfeng Z. A load management system for running HLA-based distributed simulations over the grid. Distributed Simulation and Real-Time Applications, 2002, pp. 7–14.
9. Deelman E., Szymanski B.K. Dynamic load balancing in parallel discrete event simulation for spatially explicit problems. Proc. Workshop on Parallel and Distributed Simulation, PADS'98. Banff, Canada, 1998, pp. 46–53.
10. Schlagenhaft R., Ruhwandl M., Bauer H., Sporrer C. Dynamic load balancing of a multi-cluster simulator on a network of workstations. Proc. 9th Workshop on Parallel and Distributed Simulation, PADS'95. Lake Placid, USA, 1995, vol. 25, no. 1, pp. 175–180.
11. Renard K., Peri C., Clarke J. A performance and scalability evaluation of the NS-3 distributed scheduler. 2012. Available at: http://eudl.eu/pdf/10.4108/icst.simutools.2012.247679 (accessed 18.11.2014).
12. Nandy B., Loucks W.M. An algorithm for partitioning and mapping conservative parallel simulation onto multicomputers. Proc. 6th Workshop on Parallel and Distributed Simulation, 1992, pp. 139–146.
13. Nandy B., Loucks W.M. On a parallel partitioning technique for use with conservative parallel simulation. Proc. 7th Workshop on Parallel and Distributed Simulation. San Diego, USA, 1993, vol. 23, no. 1, pp. 43–51.
14. Ferscha A. Parallel and Distributed Simulation of Discrete Event Systems. In: Handbook of Parallel and Distributed Computing. McGraw-Hill, 1995, 49 p.
15. Henderson T.R., Floyd S., Riley G.F. NS-3 Project Goals. Available at: http://www2.nsnam.org/docs/meetings/wns2/wns2-ns3.pdf (accessed 15.11.2014)
16. Aliev T.I., Sosnin V.V., Shinkaruk D.N., Tikhonov M.Yu., Burmakin N.G. SAPR marshrutiziruemoi komp'yuternoi seti na osnove komponentov s otkrytymi iskhodnymi kodami [Creating A CAD Simulator of a routed computer network using open source components]. Izv. vuzov. Priborostroenie, 2012, vol. 55, no. 10, pp. 47–53.
17. Sosnin V.V., Shinkaruk D.N. Osobennosti proektirovaniya imitatsionnoi modeli marshrutiziruemoi komp'yuternoi seti [Designing features of routed network simulation model]. Sbornik Trudov Molodykh Uchenykh i Sotrudnikov Kafedry VT. Vypusk 3 [Proc. of Young Scientists and Staff of the Department VT. Issue 3]. St. Petersburg, NIU ITMO, 2012, pp. 57–63.
18. Pelkey J., Riley G. Distributed simulation with MPI in NS-3. 2011. Available at: http://users.ece.gatech.edu/~riley/ece6110/handouts/DistNS3.pdf (accessed 15.11.2014).
19. Liu X., Chien A.A. Traffic-based load balance for scalable network emulation. Proc. 2003 ACM/IEEE Conference on Supercomputing, 2003, pp. 40. doi: 10.1145/1048935.1050190
20. Zhou S. Trace-driven simulation study of dynamic load balancing
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License