Analysis of design alternatives for a packet switched I/O system

This paper describes an application of analytical modeling to the design and evaluation of a general purpose, packet-switched image processing system that will soon enter an implementation phase. A bottom-up modeling approach is used to evaluate such design issues as optimal packet size, optimal channel access method(s), and required number of processors and disks. Based on the characteristics of various hardware components and the predicted workload, specific design recommendations are made.

[1]  Lawrence G. Roberts,et al.  Dynamic allocation of satellite capacity through packet reservation , 1973, AFIPS National Computer Conference.

[2]  K. Mani Chandy,et al.  Parametric Analysis of Queuing Networks , 1975, IBM J. Res. Dev..

[3]  J.C. Browne,et al.  Hierarchical techniques for the development of realistic models of complex computer systems , 1975, Proceedings of the IEEE.

[4]  Leonard Kleinrock,et al.  Packet Switching in a Multiaccess Broadcast Channel: Performance Evaluation , 1975, IEEE Trans. Commun..

[5]  Norman Abramson,et al.  The Throughput of Packet Broadcasting Channels , 1977, IEEE Trans. Commun..

[6]  Izhak Rubin,et al.  Message Delays in FDMA and TDMA Communication Channels , 1979, IEEE Trans. Commun..

[7]  S. Lam,et al.  Satellite Packet Communication - Multiple Access Protocols and Performance , 1979, IEEE Transactions on Communications.

[8]  F.A. Tobagi,et al.  Modeling and measurement techniques in packet communication networks , 1978, Proceedings of the IEEE.

[9]  Lawrence G. Roberts,et al.  Extensions of packet communication technology to a hand held personal terminal , 1972, AFIPS '72 (Spring).

[10]  Satish Kumar Tripathi,et al.  On approximate solution techniques for queueing network models of computer systems , 1979 .

[11]  Edward D. Lazowska,et al.  The behavior of Ethernet-like computer communications networks , 1979, SOSP '79.

[12]  Edward D. Lazowska,et al.  Near-complete decomposability of queueing networks with clusters of strongly interacting servers , 1980, Performance.