Abstract: A network statistics processing device comprises a port processing unit for determining an update from a forward statistic metric carried by an input PDU, an arbitration unit for placing the updates into a scheduled stream of updates, and a memory unit for storing statistic totals relating to the network operating parameters. The port processing unit also processes the statistic results retrieved from the memory into reverse statistic metrics that are inserted into an output PDU. A statistics monitoring and processing unit enables performance of high level statistical processing on selected updates and on the results. A method of generating and maintaining statistic totals on a plurality of network operating parameters is also described.

Abstract: A network statistics processing device comprises a port processing unit for determining an update from a forward statistic metric carried by an input PDU, an arbitration unit for placing the updates into a scheduled stream of updates, and a memory unit for storing statistic totals relating to the network operating parameters. The port processing unit also processes the statistic results retrieved from the memory into reverse statistic metrics that are inserted into an output PDU. A statistics monitoring and processing unit enables performance of high level statistical processing on selected updates and on the results. A method of generating and maintaining statistic totals on a plurality of network operating parameters is also described.

Abstract: A method of providing flow control feedback about a contention point such as a queuing point to a source of a multicast ATM virtual connection. The method includes (1) identifying a slowest output stream of the multicast connection at the contention point; (2) executing an explicit rate (ER) calculation only with respect to accounting characteristics of the slowest output stream at the contention point; and (3) signaling a result of the slowest stream ER calculation back to the source, preferably by updating resource management (RM) cells flowing towards the source.

Abstract: The method and system for buffering packets such as ATM cells at a queueing point of a device which employs a connection-orientated communications protocol includes the steps of logically partitioning a memory into plural reserved buffer spaces allocated to traffic classes and a shared buffer space available to any connection; determining whether to store or discard a given packet based on predetermined discard criteria; and filling the reserved buffer space to a predetermined state of congestion before storing the given packet in the shared buffer space. Reserved buffer space congestion states are defined with respect to individual connections, groups of connections, and the total capacity of the reserved buffer space itself. Packets are discarded when any, or alternatively a specific combination, of corresponding congestion states occur, and the shared space is congested as well.