George A. Grover

MENTOR: an algorithm for mesh network topological optimization and routing

The problem of obtaining a minimum cost topology for a mesh network given matrices specifying the cost of links between all pairs of nodes and the internode requirements is considered. A heuristic algorithm which works in terms of general network design principles and uses utilization as a figure of merit is presented. The procedure is applicable to a wide variety of networks, especially to the problem of obtaining starting topologies for other network design procedures. The algorithms computational complexity is shown to be of order N/sup 2/, a significant improvement over currently used algorithms and fast enough to be embedded in the inner loop of other more general design procedures, e.g., node selection procedures. Computational experience is presented which shows that the procedure is fast and simple and yields solutions of a quality competitive with other much slower procedures. >

Real-time packet switching: a performance analysis

The authors model the internal structure of a packet-switching node in a real-time system and characterize the tradeoff between throughput, delay, and packet loss as a function of the buffer size, switching speed, etc. They assume a simple shared-single-path switch fabric, though the analysis can be generalized to a wider class of switch fabrics. They show that with a small number of buffers the node will provide a guaranteed delay bound for high-priority traffic, a low average delay for low-priority traffic, no loss of packets at the input and low probability of packet loss at output. >

Implementing System/36 advanced peer-to-peer networking

System/36 Advanced Peer-to-Peer Networking (APPN) provides highly dynamic, fully distributed peer networking for low-end processors. It is built upon existing SNA Logical Unit 6.2 and Node type 2.1 support. APPN presents System/36 users with a simplified model of communications. The structure of the APPN subsystem is outlined, with particular emphasis on the integration of APPN functions with existing SNA support. The authors describe how particular aspects of the APPN design have been tuned to the System/36 operating environment.

BUFFER SIZE REQUIREMENTS UNDER LONGEST QUEUE FIRST

A model of a switching component in a packet switching network is considered. Packets from several incoming channels arrive and must be routed to the appropriate outgoing port according to a service policy. A task confronting the designer of such a system is the selection of policy and the determination of the corresponding input buffer requirements which will prevent packet loss. One natural choice is the Longest Queue First discipline, and tight bounds on the buffer size required at each channel under this policy are obtained. The bounds depend on the channel speeds and are logarithmic in the number of channels. As a consequence, Longest Queue First is shown to require less storage than Exhaustive Round Robin and First Come First Served in preventing packet overflow.

Windows in the sky: flow control in SNA networks with satellite links

Geosynchronous communications satellites provide a unique means of high-speed computer-to-computer transmission of large volumes of data over long distances. The physical distances involved in transmitting to and from the satellites cause relatively long propagation delays for messages. In order that the high bandwidth be used effectively, large quantities of data have to be transmitted before pausing for an acknowledgment. This condition creates a potential for some new and unique types of traffic jams. This paper discusses these situations in the context of Systems Network Architecture (SNA) networks. In particular, the issues related to SNAs flow control and traffic management facilities in the presence of satellite links are discussed, along with potential solutions to ensure efficient network operation.

A full-duplex DLC protocol on two links

The authors consider a special case of multilink protocol, namely, a system consisting of two half-duplex parallel links that carry data in opposite directions between two nodes. They construct a protocol that simulates a full-duplex reliable link between the two nodes. Synchronization is achieved without resorting to the use of serial numbers. A validation proof of the protocol is provided. The design of the protocol exhibits an instance of the value of correctness proofs in the design process, as several successive protocols, discussed in the paper, were only found to be incorrect through the effort to prove them otherwise. >

Standoff and standoff resolution in deadlock free networks with virtual circuits

One of the most common approaches to deadlock prevention is a mechanism known as buffer preallocation. The key concept is that buffers are allocated, most usually for a virtual circuit or class of virtual circuits, before any data is transmitted, and this allocation is done in such a way that no deadlocks are possible. This preallocation typically occurs through the transmission of reservation control messages prior to the transmission of normal data traffic. Control traffic deadlock prevention has yet to be studied. It is shown that deadlocks may occur in connection with this initializing control traffic, and that the resolution of such deadlocks must be handled with some care. If such resolution is not handled with sufficient care, a condition termed standoff may result, whereby contention for the allocation of one or more critical buffers results in resource being allocated to none of the contending parties. Protocols that prevent the phenomenon of standoff, thereby ensuring true deadlock-free operation are described. >