Luminous Networks, Inc.

Adtran Gmbh

Cisco Technology, Inc.

Prasad Prabhakar Jogalekar

Vinay K Bannai

Jason C Fan

Charles Barry

Robert F Kalman

Rajneesh Kumar

Arnold M Bilstad

In one embodiment, a network device receives a request from a client in association with a connection, where the request indicates an amount of one or more resources that is requested to support the connection. The network device determines whether the amount of the resources is available. The network device may then allocate a level of the resources to the connection according to whether the amount of the resources is available.

Policy-based resource management

The disclosed network includes two rings, wherein a first ring transmits data in a clockwise direction, and the other ring transmits data in a counterclockwise direction. The traffic is removed from the ring by the destination node. During normal operations (i.e., all spans operational), data between nodes can flow on either ring. Thus, both rings are fully utilized during normal operations. The nodes periodically test the bit error rate of the links (or the error rate is constantly calculated) to detect a fault in one of the links. The detection of such a fault sends a broadcast signal to all nodes to reconfigure a routing table within the node so as to identify the optimum routing of source traffic to the destination node after the fault.

Utilizing bandwidth in ring network using path cost and protection techniques

Switch for dynamically rerouting traffic due to detection of faulty link

An automatic network topology identification technique is described herein. Each node in the network periodically or constantly transmits its unique address to its neighboring node. Once a node receives a different message from its neighbor, the node identifies a topology change in the network. In one embodiment, a current topology is associated with a session number. When a change in the topology is detected, the detecting node increments the session number and broadcasts the change in topology. The other nodes, detecting the changed session number, now know that there has been a change in the network. In response, the nodes in the network modify routing tables and other information stored at the node related to the topology. In one embodiment, the technique is used to reassign shortened addresses to each device on the network to support a dual-addressing mode of the network. The dual addressing mode substitutes reduced-length addresses (referred to as short addresses) for standard addresses (referred to as long addresses) for traffic whose source or destination is internal to a given virtual network topology. The required length of short addresses used for a given virtual topology is dependent on the number of devices reachable within the topology.

Automatic network topology identification by nodes in the network

Routing switch detecting change in session identifier before reconfiguring routing table

A system and method are disclosed for policy based accounting and billing for network services. In one embodiment, a packet forwarding device receives a packet to be forwarded over the network, accesses a policy table to identify a billing party associated with the packet, obtains billing information, and stores a record of the forwarded packet and the associated billing party.

Policy based accounting and billing for network services

The disclosed network includes two rings, wherein a first ring transmits data in a clockwise direction, and the other ring transmits data in a counterclockwise direction. The traffic is removed from the ring by the destination node. During normal operations (i.e., all spans operational), data between nodes flows on the ring that would provide the minimum number of hops to the destination node. Thus, both rings are fully utilized during normal operations. The nodes periodically test the bit error rate of the links (or the error rate is constantly calculated) to detect a fault in one of the links. The detection of such a fault sends a broadcast signal to all nodes to reconfigure a routing table within the node so as to identify the optimum routing of source traffic to the destination node after the fault. Since the available links will now see more data traffic due to the failed link, traffic designated as 'unprotected' traffic is given lower priority and may be dropped or delayed in favor of the 'protected' traffic. Specific techniques are described for identifying a failed link, communicating the failed link to the other nodes, differentiating between protected and unprotected classes of traffic, and updating the routing tables.

Dynamically allocated ring protection and restoration technique

A dual addressing mode is described in which reduced-length addresses (referred to as short addresses) are substituted for standard addresses (referred to as long addresses) for traffic whose source or destination is internal to a given virtual network topology. The required length of short addresses used for a given virtual topology is dependent on the number of devices reachable within the topology. For a virtual topology with less than 256 addressable devices, for example, 8-bit short addresses can be used. When a node within the virtual network sees a packet with a short destination address in the header, the node understands the address to be within the virtual network and routes the packet accordingly. If a source address is a short address, the virtual network can identify the source within the virtual network. For packets originating in the virtual network whose destination is also in the virtual network, both the source and destination addresses can be short addresses. Thus, devices within a virtual network topology are addressable in a dual manner on the data link layer and/or network layer by traffic flowing internal to, or private to, the virtual network. Also described is a technique for automatically assigning source addresses to devices within the virtual network.

Dual-mode virtual network addressing

The disclosed network includes two rings, wherein a first ring transmits data in a clockwise direction, and the other ring transmits data in a counterclockwise direction. The traffic is removed from the ring by the destination node. During normal operations (i.e., all spans operational), data between nodes flows on the ring that would provide the minimum number of hops to the destination node. Thus, both rings are fully utilized during normal operations. The nodes periodically test the bit error rate of the links (or the error rate is constantly calculated) to detect a fault in one of the links. The detection of such a fault sends a broadcast signal to all nodes to reconfigure a routing table within the node so as to identify the optimum routing of source traffic to the destination node after the fault. Since the available links will now see more data traffic due to the failed link, traffic designated as &ldquo;unprotected&rdquo; traffic is given lower priority and may be dropped or delayed in favor of the &ldquo;protected&rdquo; traffic. Specific techniques are described for identifying a failed link, communicating the failed link to the other nodes, differentiating between protected and unprotected classes of traffic, and updating the routing tables.

Growing community of inventors

Sunnyvale, CA, United States of America

Prasad Prabhakar Jogalekar