Abstract
Reconfiguration of an interconnection network is fundamental for the provisioning of a reliable service. Current reconfiguration methods either include deadlock-avoidance mechanisms that impose performance penalties during the reconfiguration, or are tied to the Up*/Down* routing algorithm which achieves relatively low performance. In addition, some of the methods require complex network switches, and some are limited to distributed routing systems. This paper presents a new dynamic reconfiguration method, RecTOR, which ensures deadlock-freedom during the reconfiguration without causing performance degradation such as increased latency or decreased throughput. Moreover, it is based on a simple concept, is easy to implement, is applicable for both source and distributed routing systems, and assumes Transition-Oriented Routing which achieves excellent performance. Our simulation results confirm that RecTOR supports a better network service to the applications than Overlapping Reconfiguration does.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Duato, J., Yalamanchili, S., Ni, L.: Interconnection Networks: An Engineering Approach. Morgan Kaufmann Publishers, San Francisco (2003)
Duato, J., Lysne, O., Pang, R., Pinkston, T.M.: Part I: A theory for deadlock-free dynamic network reconfiguration. IEEE Trans. Parallel and Distributed Systems 16(5), 412–427 (2005)
Schroeder, M.D., et al.: Autonet: A high-speed, self-configuring local area network using point-to-point links. SRC Research Report 59, Digital Equipment Corporation (1990)
Rodeheffer, T.L., Schroeder, M.D.: Automatic reconfiguration in Autonet. In: 13th ACM Symp. Operating Systems Principles, pp. 183–197 (1991)
Boden, N.J., et al.: Myrinet: A gigabit-per-second local area network. IEEE Micro. 15(1), 29–36 (1995)
Teodosiu, D., et al.: Hardware fault containment in scalable shared-memory multiprocessors. SIGARCH Computer Architecture News 25(2), 73–84 (1997)
Lysne, O., Duato, J.: Fast dynamic reconfiguration in irregular networks. In: Int’l. Conf. Parallel Processing, pp. 449–458 (2000)
Casado, R., Bermúdez, A., Duato, J., Quiles, F.J., Sánchez, J.L.: A protocol for deadlock-free dynamic reconfiguration in high-speed local area networks. IEEE Trans. Parallel and Distributed Systems 12(2), 115–132 (2001)
Natchev, N., Avresky, D., Shurbanov, V.: Dynamic reconfiguration in high-speed computer clusters. In: 3rd Int’l. Conf. Cluster Computing, pp. 380–387 (2001)
Pinkston, T.M., Pang, R., Duato, J.: Deadlock-free dynamic reconfiguration schemes for increased network dependability. IEEE Trans. Parallel and Distributed Systems 14(8), 780–794 (2003)
Lysne, O., Pinkston, T.M., Duato, J.: Part II: A methodology for developing deadlock-free dynamic network reconfiguration processes. IEEE Trans. Parallel and Distributed Systems 16(5), 428–443 (2005)
Avresky, D., Natchev, N.: Dynamic reconfiguration in computer clusters with irregular topologies in the presence of multiple node and link failures. IEEE Trans. Computers 54(5), 603–615 (2005)
Acosta, J.R., Avresky, D.R.: Dynamic network reconfiguration in presence of multiple node and link failures using autonomous agents. In: 2005 Int’l. Conf. Collaborative Computing: Networking, Applications and Worksharing (2005)
Acosta, J.R., Avresky, D.R.: Intelligent dynamic network reconfiguration. In: Int’l. Parallel and Distributed Processing Symp. (2007)
Robles-Gómez, A., Bermúdez, A., Casado, R., Solheim, Å.G.: Deadlock-free dynamic network reconfiguration based on close Up*/Down* graphs. In: Luque, E., Margalef, T., Benítez, D. (eds.) Euro-Par 2008. LNCS, vol. 5168, pp. 940–949. Springer, Heidelberg (2008)
InfiniBand Trade Association: InfiniBand Architecture Specification v. 1.2.1 (2007), http://www.infinibandta.org/specs
Zafar, B., Pinkston, T.M., Bermúdez, A., Duato, J.: Deadlock-free dynamic reconfiguration over InfiniBand networks. Int’l. Jrnl. Parallel, Emergent and Distributed Systems 19(2), 127–143 (2004)
Bermúdez, A., Casado, R., Quiles, F.J., Duato, J.: Handling topology changes in InfiniBand. IEEE Trans. Parallel and Distributed Systems 18(2), 172–185 (2007)
Lysne, O., et al.: Simple deadlock-free dynamic network reconfiguration. In: 11th Int’l. Conf. High Performance Computing, pp. 504–515 (2004)
Lysne, O., et al.: An efficient and deadlock-free network reconfiguration protocol. IEEE Trans. Computers 57(6), 762–779 (2008)
Solheim, Å.G., et al.: Efficient and deadlock-free reconfiguration for source routed networks. In: 9th Worksh. Communication Architecture for Clusters (2009)
Sancho, J.C., Robles, A., Flich, J., López, P., Duato, J.: Effective methodology for deadlock-free minimal routing in InfiniBand networks. In: Int’l. Conf. Parallel Processing, pp. 409–418 (2002)
Dally, W.J., Seitz, C.L.: Deadlock-free message routing in multiprocessor interconnection networks. IEEE Trans. Computers 36(5), 547–553 (1987)
Francois, P., Bonaventure, O.: Avoiding transient loops during IGP convergence in IP networks. In: 24th IEEE INFOCOM, vol. 1, pp. 237–247 (2005)
Tyan, H.-Y.: Design, Realization and Evaluation of a Component-Based Compositional Software Architecture for Network Simulation. PhD thesis, Ohio State University (2002)
Top 500 project: Top 500 Supercomputer Sites (November 2008), http://top500.org
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Solheim, Å.G., Lysne, O., Skeie, T. (2009). RecTOR: A New and Efficient Method for Dynamic Network Reconfiguration. In: Sips, H., Epema, D., Lin, HX. (eds) Euro-Par 2009 Parallel Processing. Euro-Par 2009. Lecture Notes in Computer Science, vol 5704. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03869-3_97
Download citation
DOI: https://doi.org/10.1007/978-3-642-03869-3_97
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03868-6
Online ISBN: 978-3-642-03869-3
eBook Packages: Computer ScienceComputer Science (R0)