Michael Fry
ABSTRACT
There is increasing market pressure to provide support for the open interconnection of systems via general purpose protocol suites such as OSI and TCP/IP. The complexity of these protocols means that the achievement of acceptable performance is not easy. Indeed, some would claim it is impossible, and advocate lean, closed protocols. A further aspect of communications architectures in the world outside the research laboratory is that they must be well structured and modular, in order to meet the needs of orderly systems development and the provision of configurable products. This paper examines the trade-offs between these three aspects of protocol stack development: conformance to standards, reasonable performance and modularity. It finds that while a considerable amount of work has been carried out in recent times, it is apparent that we do not know yet how to achieve all three.
- ANDERSON, D.P. 1988. A software architecture for network communication. Proceedings of the 8th International Conference on Distributed Computer Systems (May), IEEE, New York, pp. 376-383.Google Scholar
Cross Ref
- BOLOT, J-C., AND UDAYA SHANKAR, A. 1990. Dynamical belu~vior of rate-based flow control mechanisms. Comput. Commun. Rev. 20,2 (Apr.), pp. 35-49. Google ScholarDigital Library
- BORMAN, D. A. 1989. Implementing TCP/IP on a Cray computer. Comput. Commun. Rev. 19,2 (Apr.), pp. 11-15. Google ScholarDigital Library
- BRADY, P.T. 1988. Effects on respcmse time performance using an edge-w-edge protocol in an X~.5 packet network. IEEE Network 2,4 (Jul.) pp. 45-54.Google ScholarDigital Library
- CABRERA, L-F., HUNTER, E., KARELS, MJ., MOSHER, D.A. 1988. Usex-lxocess communication performance in networks of computers. IEEE Trans. Softw. Eng. SE.14, 1 (Jan.), pp. 38-53. Google ScholarDigital Library
- CHERITON, D. R., AND ZWAENEIK)EL, W. 1983. The distributed V keaxtel and its perfo~ for diskless workstations. In Proceedings of the 9th ACM Symposium on Operating Systems Principles (Bretton Woods, NH, Oct. 10-13). ACM, New York, pp. 129- 140. Google ScholarDigital Library
- CHONG, H.Y. 1986. Software development and implementation of NBS Class-4 Transpcm ProlocoL Comput. Networks and ISDN Syst. 11 (5), pp. 353- 365. Google ScholarDigital Library
- CLARK, D.D. 1985. The structuring of systems using ~s. In Proceedings of the lOth ACM Synq~sium on Operating Systems Principles (Ow~ Island, Wash. Dec. 1-4). ACM, New York, pp. 171-180. Google ScholarDigital Library
- CLARK, D. D., JACOBSEN, V., ROMKEY, jo, SALWEN, H. 1989. An analysis of TCP processing overhead. IEEE Commun. 27,6 (June), pp 23-29.Google ScholarDigital Library
- CLARK, D. D., LAMBERT, M. L., AND ZHANG, L. 1987. NETBLT: a high throughlmt ~ protocol. In Proceedings of the SIGCOMM "87 Workshop on Frontiers in Computer Conununications Technology (Stowe, Vt., Aug. 11-13). ACM, New York, pp. 353- 359. Google ScholarDigital Library
- CLARK, D. D. 1988. The design philosophy of the DARPA Inlernet protocols. Proceedings of the SIGCOMM "88 Symposium on Conmmnications Architectures and Protocols (Stanford, Cal., Aug. 16- 19). ACM, New York, pp. 243-250. Google ScholarDigital Library
- DEAI'ON, G. 1990. Considerations for advanced networking in the 1990's. In Proceedings of the 10th International Conference on Computer Communication, S. Ramani, H. Shrikumar and S. V. Raghavan, Eds. Narosa Publishing House, New Delhi, pp. 13-20.Google Scholar
- FELDMEIER, D., AND BIERSACK, E. 1990. Comparison of error control protcr~ls for high bandwidth-delay prodtw.t networks. In Proceedings of the Second IFIP WG6.1/WG6.4 International Workshop on Protocols for High-Speed Networks (Palo Alto, Cal., Nov. 27-29).Google Scholar
- FRY, M.R. 1990. The efficiency of OSI protocol stacks: A computer systems persIx~tive. In Proceedings of the lOth International Conference on Computer Communication, S. Rammfi, H. Shrikumar and S. V. Raghavan, Eds. Narosa Publishing House, New Delhi, pp. 553-557.Google Scholar
- HOWF.~, N. R., AND WEAVER, A. C. 1989. Measurements of Ada overhead in OSI-style communications systems. IEEE Trans. Softw. Eng. 15, 12 (Dec.), pp. 1507-1517. Google ScholarDigital Library
- HUTCtHNSON, N.C., AND PETERSON, L.L. 1988. Design of the x-kerneL In Proceedings of the SIGCOMM "88 Synwosium on Communications Architectures and Protocols (Stanford, Cal., Aug. 16- 19). ACM, New York, pp. 65-75. Google ScholarDigital Library
- HUTCHINSON, N. C., PETERSON, L.L., ABBOTT, M.B., AND O~MJ.EY, S. 1989. RPC in the xkernel: Evaluating new design techniques. In Proceedings of the 12th ACM Syml~sium on Operating Systems Principles (Austin, "rex. Nov. 8-11). ACM, New York, pp. 91-101. Google ScholarDigital Library
- JACOBSEN, V. 1988. Congeatkm avoidarr, e and controL Proceedings of the SIGCOMM "88 SynguTsium on Convnun~ ations Architectures and Protocols (Stanford, Cal., Aug. 16-19). ACM, New York, pp. 314-329. Google ScholarDigital Library
- KANAKIA, H., AND CHERITON, D. 1988. The VMP Network Adapter ~ (NAB): High-performance network communication for multiproc~ssors. In Proceedings of the SIGCOMM "88 Symposium on Communications Architectures and Protocols (Stanford, Cal., Aug. 16-19). ACM, New York, pp. 175-187. Google ScholarDigital Library
- KLINE, C. 1987. Supercomputers on the lnternet: a case study. In Proceedings of the SIGCOMM '87 Workshop on Frontiers in Computer Conmmnications Technology (Stowe, Vt., Aug. 11-13). ACM, New York, pp. 27-33. Google ScholarDigital Library
- LANTZ, K.A., NOWICKI, W.I., AND THEIMER, M. M. 1985. An empirical study of distributed application performance. IEEE Trans. Softw. Eng. SE-I 1, 10 (Oct.), pp. 1162-i 173. Google ScholarDigital Library
- L1NINGTON, P.F. 1989. Why OSI? Comput. Networks and ISDN Syst. 17 (Sept.), pp. 287-290. Google ScholarDigital Library
- LISKOV, B., CURTIS, D., JOHNSON, P., SCHEIF~ER, R. 1987. Implementation of Argus. In Proceedings of the 11 th ACM Symposium on Operating Systems Principles (Litchfield Park, At. Dec. 3-6). ACM, New York, pp. 111-122. Google ScholarDigital Library
- MEISTER, B. 1987. A performance study of the ISO Transport Protocol. Proceech'ngs of the 7th international Conference on Distributed Computer Systems (May), IEEE, New York, pp. 398-405.Google Scholar
- MURRAY WOODSIE, C., AND RAMIRO MONTEALEGRE, J. 1989. TI~ effect of buffering strategies on protocol execution performance. IEEE Trans. Commun. 37,6 (June), pp. 545-554.Google Scholar
- NOWICKI, B. 1989. Transport issues in the Network File System. Comput. Commun. Rev. 19,2 (Apr.), pp. 16-20. Google ScholarDigital Library
- O'MALLEY, S. 1990. (In discussion at Second IFIP International Workshop on Protocols for High-S~ Networks).Google Scholar
- O'MALLEY, S. AND PETERSON, L. 1990. A highly-layered architecture for high-~ networks. In Proceedings of the Second IFIP WG6.11WG6.4 International Workshop on Protocols for High-Speed Networks (Palo Alto, Cal., Nov. 27-29).Google Scholar
- PARTRIDGE, C. 1990. How slow is one gigabit persecond? Comput. Commun. Rev. 20,1 (Jan.),pp. 44-53. Google ScholarDigital Library
- PARULKAR, G.M., AND TURNER, J.S. 1990. Towards a framework for high ~ communication in a heterogenous networking environment. IEEE Network 4,2 (Mar.) pp. 19-27.Google ScholarDigital Library
- POPEK, G. J., AND WALKER, B. 1985. The LOCUS Distributed System Architecture. MIT Press. Google ScholarDigital Library
- RAMAKRISHNAN, K.K., AND J IN, R. 1990. A binary feedback scheme for congestion avoidance in computer networks. ACM Trans. Comput. Syst. 8,2 (May), pp. 158-181. Google ScholarDigital Library
- RENESSE, R. VAN, STAVEREN, H. VAN, AND TANENBAUM, A.S. 1988. Performance of the world's fastest distributed operating system. Oper. Syst. Rev. 22,4 (Oct.), pp. 25-34. Google ScholarDigital Library
- SAL~, J.H., REED, D. P., AND CLARK, D.D. 1984. End-to-end arguments in system design. ACM Trans. Comput. Syst. 2,4 (Nov.), pp. 277-288. Google ScholarDigital Library
- SAL'IT_,ER, J.H., CLARK, D.D., ROMKEY, J.L., AND GRAMLICH, W.C. 1985. The desktop computer as a network participant. IEEE J. Select. Areas Comm. SAC-7, 3 (May), pp. 468-478.Google Scholar
- SCHROEDER, M., AND BURROWS, M. 1989. Performance of Firefly RPC. In Proceedings of the 12th ACM Symposium on Operating Systems Principles (Austin, Tex. Nov. 8-11). ACM, New York, pp. 83-90. Google ScholarDigital Library
- SKIA)WER, D. 1989. Improving the efficiency of the OSI checksum calculation. Comput. Commun. Rev. 19,5 (OcL), pp. 32-43. Google ScholarDigital Library
- STELLA ATKINS, M. 1988. Experiments in SR with different upcall program structures. A CM Trans. Comput. Syst. 6,4 (Nov.), pp. 365-392. Google ScholarDigital Library
- STERBENZ, j. P. G., AND PARULKAR, G. M. 1990. AXON: Application-orienteA lightweight transport txol~ol design. In Proceedings of the l Oth International Conference on Computer Communication, S. Ramani, H. Shrikumar and S. V. Raghavan, Eds. Narosa Publishing House, New Delhi, pp. 379-387.Google Scholar
- STRAYER, W.T., AND WEAVER, A.C. 1988. Performance measurement of data transfer services in MAP. IEEE Network 2,3 (May) pp. 75-81.Google ScholarDigital Library
- SVOBODOVA, L. 1989A. Implementing OSI systems. IEEE J. Select. Areas Comm. SAC-7, 7 (Sept), pp. 1115-1130.Google Scholar
- SVOBODOVA, L. 1989B. Measured performance of transport services in LAN's. Comput. Networks and ISDN Syst. 18 (Nov.), pp. 31-45.Google ScholarCross Ref
- VARGHESE, G., AND LAUCK, T. 1987. Hashed and hierarchical timing wheels: Data structures for the efficient implementation of a timer facility. In Proceedings of the 11th ACM Symposium on Operating Systems Principles (Litchfield Park, Ar. Dec. 3-6). ACM, New York, pp. 25-34. Google ScholarDigital Library
- WATSON, R.W., AND MAMRAK, S.A. 1987. Cmining efficiency in wanspoN services by ~Ixopria~ design and implementation choice~. ACM Trans. Comput. Syst. 5,2 (May), pp. 97-120. Google ScholarDigital Library
- YOUNG, M., TEVANIAN, A., RASII{D, R., CK)LUB, D., EPPINGER, J., CI~W, J., BOLOSKY, W., BLACK, D., AND BARON, R. 1987. The duality of memory and communicalion in the implementation of a multiprocessor operating system. In Proceedings of the l lth ACM Symposium on Operating Systems Principles (Austin, 'rex. Nov. 8-11). ACM, New York, pp. 63-76. Google ScholarDigital Library
- ZII-II~RBART, M., AND GERTEIS, W. 1990. OSI protocols for high-speed networks? In Proceedings of the lOlh International Conference on Computer Communication, S. Ramani, H. Shrikumar and S. V. Raghavan, Eds. Narosa Publishing House, New Delhi, pp. 309-314.Google Scholar
Index Terms
- Practical trade-offs for open interconnection
Recommendations
Performance Evaluation and Design Trade-Offs for Network-on-Chip Interconnect Architectures
Multiprocessor system-on-chip (MP-SoC) platforms are emerging as an important trend for SoC design. Power and wire design constraints are forcing the adoption of new design methodologies for system-on-chip (SoC), namely, those that incorporate ...
Evaluation and design trade-offs between circuit-switched and packet-switched NOCs for application-specific SOCs
DAC '06: Proceedings of the 43rd annual Design Automation ConferenceNOC architectures have to deliver good latency-throughput performance in the face of very tight power and area budgets. However, the latency and the power consumption for transferring information down the transmitter stack, through the channel, and up ...
Comments