Abstract: A network device receives a label-switched-path (LSP) labeled data packet, maps the LSP labeled data packet to an input queue, maps a data packet in the input queue to an output queue based on a received LSP label value and a received exp label value, and transmits the LSP labeled data packet from the output queue.

Abstract: A device generates a service protection factor (SPFi) for links (N) on a link aggregation group (LAG), determines a traffic allocation bandwidth on the LAG for a service class based on the service protection factor (SPFi) and a congestion guard factor (CGFi), and restricts the traffic allocation bandwidth on the LAG. The service protection factor (SPFi) may guarantee a service availability target in the presence of link failure, and the congestion guard factor (CGFi) may protect against link overload that may arise from imperfectness in traffic load balancing across links in the LAG.

Abstract: The present invention provides improved work schedulers for computer systems and communication processors. A preferred embodiment of the present invention includes systems with buffer memory for storing one or more communication packets or work requests arranged on a plurality of scheduling queues and information for controlling the scheduling of the queues, with output processors for outputting packets from the buffer memory; and with control processors for performing the scheduling methods of this invention. The scheduling methods repetitively initialize each queue's service credits, repetitively process each queue in a round-robin order by granting each queue with remaining service credits no more than one quantum of service and updating that queue's service credits to reflect the service actually used and the service available for use but not actually used.

Abstract: A communication system comprising a plurality of sources, a plurality of destinations, and a plurality of switches forming an asynchronous transfer mode (ATM) network connecting the sources to the destinations. Each switch in the plurality of switches includes a plurality of line cards. The ATM network comprises a plurality of connections where, for each respective connection, one of the plurality of sources is linked to one of the plurality of destinations through the network by linking one or more switches, in the plurality of switches, that is associated with the respective connection. The ATM network further comprises operation administration and maintenance (OAM) cell processing circuitry for detecting a failure in a connection in the network. The failure is localized to the exact line card in a switch associated with the connection that is causing the connection to fail.

Abstract: The present invention provides hierarchical structures of queues and schedulers for switches and routers with, preferably fully-connected, mesh fabrics, for efficiently and properly handling the quality or service requirements of multiple network services, such as ATM and IP, in switch or router. The switches of this invention provide, for example, fair allocation of bandwidths to different network services, to different QoS classes within network services, and to different resources within the switch by use of, preferably, weighted, fair scheduling methods. The switches and routers of this invention are particularly directed to multi-protocol, high-throughput communication application, but may have wide applicability in systems generally where data packets are switched or routed.