End-system aware, rate-adaptive protocol for network transport in LambdaGrid environments

ABSTRACT

Next-generation e-Science applications will require the ability to transfer information at high data rates between distributed computing centers and data repositories. A LambdaGrid offers dedicated, optical, circuit-switched, point-to-point connections that can be reserved exclusively for such applications. These dedicated high-speed connections eliminate network congestion as seen in traditional Internet, but they effectively push the network congestion to the end systems, as processing speeds cannot keep up with networking speeds. Thus, developing an efficient transport protocol over such high-speed dedicated circuits is of critical importance.We propose the idea of a end-system aware, rate-adaptive protocol for network transport, based on end-system performance monitoring. Our proposed protocol significantly improves the performance of data transfer over LambdaGrids by intelligently adapting the sending rate based on end-system constraints. We demonstrate the effectiveness of our proposed protocol and illustrate the performance gains achieved via wide-area network emulation.

REFERENCES

• 1: Banerjee, A., Feng, W., Mukherjee, B., and Ghosal, D. 2006. RAPID: An end-system aware protocol for intelligent data transfer over lambda-grids. Proceedings of 20th International Parallel and Distributed Processing Symposium (IPDPS 2006), Rhode Island, Greece.
• 2: Borman, D., Braden, R., and Jacobson, V. 1992. TCP extensions for high performance. RFC1323, Internet Engineering Task Force (IETF).
• 3: Brakmo, L., and Peterson, L. 2003. TCP Vegas: End to end congestion avoidance on a global internet. IEEE Journal of Selected Areas in Communications 13, 8, 1465--1480.
• 4: Pallab Datta , Sushant Sharma , Wu-Chun Feng, A Feedback Mechanism for Network Scheduling in LambdaGrids, Proceedings of the Sixth IEEE International Symposium on Cluster Computing and the Grid (CCGRID'06), p.584-591, May 16-19, 2006 [doi>10.1109/CCGRID.2006.5]
• 5: Dickens, P. 2003. FOBS: A lightweight communication protocol for grid computing. 9th International Euro-Par Conference, Austria, 938--946.
• 6: W. Feng , P. Tinnakornsrisuphap, The failure of TCP in high-performance computational grids, Proceedings of the 2000 ACM/IEEE conference on Supercomputing (CDROM), p.37-es, November 04-10, 2000, Dallas, Texas, United States
• 7: Wu-Chun Feng , Mark K. Gardner , Jeffrey R. Hay, The MAGNeT Toolkit: Design, Implementation and Evaluation, The Journal of Supercomputing, v.23 n.1, p.67-79, August 2002 [doi>10.1023/A:1015737203428]
• 8: S. Floyd, HighSpeed TCP for Large Congestion Windows, RFC Editor, 2003
• 9: Gardner, M., Feng, W., and Hay, J. 2002. Monitoring protocol traffic with a MAGNeT. Proceedings of the 3rd Passive and Active Measurement Workshop (PAM2002), Fort Collins, Colorado.
• 10: Mark K. Gardnery , Wu-chun Fengyz , Michael Broxtonyx , Adam Engelharty , Gus Hurwitzy, MAGNET: A Tool for Debugging, Analyzing and Adapting Computing Systems, Proceedings of the 3st International Symposium on Cluster Computing and the Grid, p.310, May 12-15, 2003
• 11: Gu, Y., and Grossman, R. 2003. End-to-end congestion control for high performance data transfer. IEEE/ACM Transactions on Networking.
• 12: Yunhong Gu , Xinwei Hong , Robert L. Grossman, Experiences in Design and Implementation of a High Performance Transport Protocol, Proceedings of the 2004 ACM/IEEE conference on Supercomputing, p.22, November 06-12, 2004 [doi>10.1109/SC.2004.24]
• 13: Gu, Y., Hong, X., Mazzucco, M., and Grossman, R. 2003. SABUL: A high performance data transfer protocol. IEEE Communication Letters.
• 14: Eric He , Jason Leigh , Oliver Yu , Thomas A. DeFanti, Reliable Blast UDP: Predictable High Performance Bulk Data Transfer, Proceedings of the IEEE International Conference on Cluster Computing, p.317, September 23-26, 2002
• 15: HTTP://JOSH.TRANCESOFTWARE.COM/LINUX/LINUX_CPU_SCEDULER.PDF. 2005. The Linux 2.6 Scheduler, December.
• 16: HTTP://WWW.BITCONJURER.ORG/BITTORRENT. 2005. BitTorrent, November.
• 17: HTTP://WWW.CANARIE.CA/CANET4/. 2005. CANARIE CA*network 4, December.
• 18: HTTP://WWW.KAZAA.COM. 2005. Kazaa, December.
• 19: HTTP://WWW.CHELSIO.COM/PRODUCTS/T210.HTM. 2006. Chelsio T210 10 Gigabit Ethernet Adapter, April.
• 20: HTTP://WWW.CSM.ORNL.GOV/ULTRANET. 2006. DoE UltraScience Net, May.
• 21: HTTP://WWW.ICAIR.ORG/OMNINET/. 2006. OMNInet, January.
• 22: HTTP://WWW.INDIANA.EDU/~ANML/ANMLRESEARCH.HTML. 2006. Tsunami, March.
• 23: HTTP://WWW.JA.NET/DEVELOPMENT/UKLIGHT/. 2006. UKlight, February.
• 24: HTTP://WWW.NLR.NET. 2006. National Lambda Rail, July.
• 25: HTTP://WWW.SURFNET.NL/EN/. 2006. SURFnet, June.
• 26: V. Jacobson, Congestion avoidance and control, ACM SIGCOMM Computer Communication Review, v.18 n.4, p.314-329, August 1988
• 27: Jin, C., Wei, D., Low, S., Buhrmaster, G., Bunn, J., Choe, D., Cottrell, R., Doyle, J., Feng, W., Martin, O., Newman, H., Paganini, F., Ravot, S., and Singh, S. 2005. FAST TCP: From background theory to experiments. IEEE Network 19, 1, 4--11.
• 28: Kelly, T. 2003. Scalable TCP: Improving performance in highspeed wide area networks. 1st International Workshop on Protocols for Fast Long-Distance Networks (PFLDNet) 33, 2, 83--91.
• 29: M. Mathis , J. Mahdavi , S. Floyd , A. Romanow, TCP Selective Acknowledgement Options, RFC Editor, 1996
• 30: Rao, N., Wu, Q., Carter, S., and Wang, W. 2004. Experimental results on data transfers over dedicated channels. Proceedings of the 1st International Workshop on Provisioning and Transport for Hybrid Networks (PATHNETS), in conjunction with the 1st International Conference on Broadband Networks.
• 31: Larry L. Smarr , Andrew A. Chien , Tom DeFanti , Jason Leigh , Philip M. Papadopoulos, The OptIPuter, Communications of the ACM, v.46 n.11, November 2003 [doi>10.1145/948383.948410]
• 32: Jean Walrand , Pravin Varaiya, High-performance communication networks (2nd ed.), Morgan Kaufmann Publishers Inc., San Francisco, CA, 1999
• 33: R. X. Wu , A. A. Chien, GTP: group transport protocol for lambda-Grids, Proceedings of the 2004 IEEE International Symposium on Cluster Computing and the Grid, p.228-238, April 19-22, 2004
• 34: Xiong, C., Leigh, J., He, E., Vishwanath, V., Murata, T., Renambot, L., and Defanti, T. 2005. Lambdastream-a data transport protocol for streaming network intensive applications over photonic networks. Proceedings of 3rd International Workshop on Protocols for Fast Long-Distance Networks (PFLDNet), Lyon, France.
• 35: Zheng, X., Mudambi, A., and Veeraraghavan, M. 2004. FRTP: Fixed rate transport protocol - a modified version of sabul for end-to-end circuits. Proceedings of the 1st International Workshop on Provisioning and Transport for Hybrid Networks (PATHNETS), in conjunction with the 1st International Conference on Broadband Networks.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.4 Systems and Software
          Subjects: Information networks

Additional Classification:
  C. Computer Systems Organization
  C.2 COMPUTER-COMMUNICATION NETWORKS
      C.2.3 Network Operations
          Subjects: Network management
      C.2.4 Distributed Systems

  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.4 Systems and Software
          Subjects: Distributed systems

General Terms:
Design, Management