Abstract.
This paper proposes an interconnection network system for clusters based on parallel links over commodity Ethernet to provide both wide bandwidth and high fault tolerancy. In the proposed scheme, RI2N, multiple links are employed to enhance the total bandwidth in normal mode, or provide redundant connections in failure mode with automatic software control. In a current prototype implementation at the user-level in library, normal mode functionality provides a maximum bandwidth of 40 MByte/sec over four links of Fast Ethernet, and 191 MByte/sec over two links of Gigabit Ethernet.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Myricom, INC., http://www.myri.com/myrinet/
InfiniBand Trade Association, http://www.infinibandta.org/
Dolphin Interconnect Solutions Inc., http://www.dolphinics.com/
Quadrix Solutions, Inc., http://quadrix.com/
IEEE802.3ad, http://grouper.ieee.org/groups/802/3/ad/
Tezuka, H., Hori, A., Ishikawa, Y., Sato, M.: PM: An Operating System Coordinated High Performance Communication Library. In: Hertzberger, B., Sloot, P.M.A. (eds.) HPCN-Europe 1997. LNCS, vol. 1225, pp. 708–717. Springer, Heidelberg (1997)
Chen, P.M., Lee, E.K., Gibson, G.A., Katz, R.H., Patterson, D.A.: RAID: High-Performance, Reliable Secondary Storage. ACM Computing Surveys 26(2), 145–185 (1994)
Bosilca, G., Bouteiller, A., Cappello, F., Djailali, S., Fedak, G., Germain, C., Herault, T., Lemarinier, P., Lodygensky, O., Magniette, F., Neri, V., Selikhov, A.: MPICH-V: Toward a Scalable Fault Tolerant MPI for Volatile Nodes. In: ACM/IEEE International Conference on Supercomputing SC 2002 (2002)
Elnozahy, E., Johnson, D., Wang, Y.: A survey of rollback-recovery protocols in message-passing systems. Technical Report CMU-CS-96-181, Carnegie Mellon University (October 1996)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Miura, S., Boku, T., Sato, M., Takahashi, D. (2003). RI2N – Interconnection Network System for Clusters with Wide-Bandwidth and Fault-Tolerancy Based on Multiple Links. In: Veidenbaum, A., Joe, K., Amano, H., Aiso, H. (eds) High Performance Computing. ISHPC 2003. Lecture Notes in Computer Science, vol 2858. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39707-6_28
Download citation
DOI: https://doi.org/10.1007/978-3-540-39707-6_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20359-9
Online ISBN: 978-3-540-39707-6
eBook Packages: Springer Book Archive