Adaptive Load Sharing for Network Processors

A novel scheme for processing packets in a router is presented that provides load sharing among multiple network processors distributed within the router. It is complemented by a feedback control mechanism designed to prevent processor overload. Incoming traffic is scheduled to multiple processors based on a deterministic mapping. The mapping formula is derived from the robust hash routing (also known as the highest random weight - HRW) scheme, introduced in K. W. Ross, IEEE Network, 11(6), 1997, and D. G. Thaler et al., IEEE Trans. Networking, 6(1), 1998. No state information on individual flow mapping has to be stored, but for each packet, a mapping function is computed over an identifier vector, a predefined set of fields in the packet. An adaptive extension to the HRW scheme is provided to cope with biased traffic patterns. We prove that our adaptation possesses the minimal disruption property with respect to the mapping and exploit that property to minimize the probability of flow reordering. Simulation results indicate that the scheme achieves significant improvements in processor utilization. A higher number of router interfaces can thus be supported with the same amount of processing power.

[1]  Germán S. Goldszmidt,et al.  Scaling Internet services by dynamic allocation of connections , 1999, Integrated Network Management VI. Distributed Management for the Networked Millennium. Proceedings of the Sixth IFIP/IEEE International Symposium on Integrated Network Management. (Cat. No.99EX302).

[2]  H. Ali,et al.  Task Scheduling in Multiprocessing Systems , 1995, Computer.

[3]  Thomas Kunz,et al.  The Influence of Different Workload Descriptions on a Heuristic Load Balancing Scheme , 1991, IEEE Trans. Software Eng..

[4]  H. V. Jagadish,et al.  Towards a Gigabit IP Router , 1992, J. High Speed Networks.

[5]  Victor C. M. Leung,et al.  A framework for optimizing the cost and performance of next-generation IP routers , 1999, IEEE J. Sel. Areas Commun..

[6]  David Thaler,et al.  Using name-based mappings to increase hit rates , 1998, TNET.

[7]  Mark A. McComb.  A Practical Guide to Heavy Tails , 2000, Technometrics.

[8]  Keith W. Ross,et al.  Hash routing for collections of shared Web caches , 1997, IEEE Netw..

[9]  Martina Zitterbart,et al.  Analysis of TCP/IP for high performance parallel implementations , 1992, [1992] Proceedings 17th Conference on Local Computer Networks.

[10]  Thomas L. Casavant,et al.  A Taxonomy of Scheduling in General-Purpose Distributed Computing Systems , 1988, IEEE Trans. Software Eng..

[11]  Donald E. Knuth,et al.  The art of computer programming, volume 3: (2nd ed.) sorting and searching , 1998 .

[12]  Martina Zitterbart,et al.  Multiprocessing in High Performance IP Routers , 1992, Protocols for High-Speed Networks.

[13]  M. Crovella,et al.  Heavy-tailed probability distributions in the World Wide Web , 1998 .

[14]  Yin Zhang,et al.  On the characteristics and origins of internet flow rates , 2002, SIGCOMM '02.

[15]  Svante Carlsson,et al.  Small forwarding tables for fast routing lookups , 1997, SIGCOMM '97.

[16]  Ray Jain,et al.  The art of computer systems performance analysis - techniques for experimental design, measurement, simulation, and modeling , 1991, Wiley professional computing.

[17]  Marshall T. Rose,et al.  Management Information Base for network management of TCP/IP-based internets , 1990, RFC.

[18]  Craig Partridge,et al.  Packet reordering is not pathological network behavior , 1999, TNET.

[19]  Al Morton,et al.  Packet Reordering Metric for IPPM , 2003 .

[20]  Ellen W. Zegura,et al.  Performance of hashing-based schemes for Internet load balancing , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

[21]  George Kingsley Zipf,et al.  Human behavior and the principle of least effort , 1949 .

[22]  Gunnar Karlsson,et al.  Fast address look-up for internet routers , 1998, Broadband Communications.

[23]  Fred Baker,et al.  Requirements for IP Version 4 Routers , 1995, RFC.

[24]  Anees Shaikh,et al.  Load-sensitive routing of long-lived IP flows , 1999, SIGCOMM '99.

[25]  Donald Ervin Knuth,et al.  The Art of Computer Programming , 1968 .

[26]  R. Wilder,et al.  Wide-area Internet traffic patterns and characteristics , 1997, IEEE Netw..

[27]  Edward D. Lazowska,et al.  Adaptive load sharing in homogeneous distributed systems , 1986, IEEE Transactions on Software Engineering.

[28]  C. Semeria,et al.  Internet Backbone Routers and Evolving Internet Design , 1998 .

[29]  Hung-Hsiang Jonathan Chao,et al.  Next generation routers , 2002, Proc. IEEE.

[30]  T. V. Lakshman,et al.  Beyond best effort: router architectures for the differentiated services of tomorrow's Internet , 1998, IEEE Commun. Mag..

[31]  Artur Binczewski,et al.  Shall we worry about Packet Reordering? , 2005, TNC.

[32]  Ali R. Hurson,et al.  Scheduling and Load Balancing in Parallel and Distributed Systems , 1995 .

[33]  Tilman Wolf,et al.  Design issues for high-performance active routers , 2001, IEEE J. Sel. Areas Commun..

[34]  Donald E. Knuth,et al.  Sorting and Searching , 1973 .

[35]  Oscar H. Ibarra,et al.  Adaptive load sharing for clustered digital library servers , 1998, Proceedings. The Seventh International Symposium on High Performance Distributed Computing (Cat. No.98TB100244).

[36]  G. Barish,et al.  World Wide Web caching: trends and techniques , 2000, IEEE Commun. Mag..

[37]  Donald E. Knuth,et al.  The art of computer programming: sorting and searching (volume 3) , 1973 .

[38]  Craig Partridge,et al.  A Fifty Gigabit Per Second IP Router , 2001 .

[39]  David Waitzman,et al.  A 50-Gb/s IP router , 1998, TNET.

[40]  Pawel Gburzynski,et al.  Load balancing for parallel forwarding , 2005, IEEE/ACM Transactions on Networking.

[41]  Bernard Metzler,et al.  Scalable and Adaptive Load Balancing on IBM PowerNP , 2002 .