Abstract: A method and apparatus for replicating packet data within a network element are described herein. In one embodiment, a method includes storing packet data within a storage element, maintaining a transmit count value of the storage element, determining a release count value of the storage element, comparing the transmit count value and the release count value, and de-allocating the storage element in response to comparing the transmit count value and the release count value.

Abstract: A method and apparatus for providing scalability and fault tolerance to a distributed network. According to one embodiment of the invention, a network management system comprises a set of one or more element management servers. One of the plurality of element management servers is designated as a master server. The master server determines which of the plurality of element management servers are to manage each of a set of one or more network elements. In one embodiment, peered and federated services are used within the network management system to provide scalability and fault tolerance.

Abstract: A method and apparatus for a fault tolerant network element is described. In one embodiment of the invention, a computer implemented method comprises storing an operation and executing the operation idempotently with a network resource process.

Abstract: A ring network element and the ring network architectures it enables. According to one embodiment of the invention, a single network element includes a full TDM cross-connect and a multiple ring unit. The full TDM cross-connect is coupled to every line card slot in the single network element with the same amount of bandwidth connection. In addition, the full TDM cross-connect is programmable on an STS-1 basis. The multiple ring unit allows for the simultaneous support of multiple TDM rings.

Abstract: A method and apparatus for hierarchical circuits with different switching decisions is described. In one embodiment, a computer implemented method provides for receiving a first and second packet on a virtual connection that traverses said network element, the first packet and the second packet being of a first traffic type that corresponds to the virtual connection, the first packet's payload being a third packet of a second traffic type and the second packet's payload being a fourth packet of a third traffic type, processing the first and the second packet with a first traffic type function, separating the third packet and the fourth packet into different traffic flows based on their traffic types, applying a first set of one or more features to the third packet, and applying a second set of one or more features to the fourth packet.

Abstract: A method and apparatus for a label forwarding information base is described. A machine-readable medium provides instructions, which when executed by a set of one or more processors, cause said set of processors to perform operations that comprise selecting forwarding information for a label of a packet with a set of most significant bits (MSBs) of the label and a set of least significant bits (LSBs) of the label, but not all of the label's bits unless the set of MSBs and the set of LSBs match a second label's MSBs and LSBs, and forwarding the packet with the forwarding information.

Abstract: A method and apparatus for the transmission of data through multiple clock domains using synchronous and asynchronous FIFOs are described. In an embodiment, a method includes receiving data at a first data transfer rate. Additionally, the method includes storing the data at the first data transfer rate in a synchronous storage device having a first storage area. The data at the first data transfer rate stored in the synchronous storage device is processed. The processing includes removing the data from the synchronous storage device. The processing also includes storing the data at the first data transfer rate in an asynchronous storage device having a second storage area. Additionally, the processing includes transmitting the data out from the asynchronous storage device at a second data transfer rate, wherein the storage area of the synchronous storage device is larger than the second storage area of the asynchronous storage device.

Abstract: A method and apparatus for graceful restart is described. A method in a network device provides for refreshing a set of one or more labels after a label propagation module has restarted, the set of one or more labels having been allocated for the label propagation module prior to the label propagation module dying, and communicating the refreshed set of labels to a set of one or more peer label switching network devices.

Abstract: In one embodiment, a network element is to be coupled to a first and second span of a number of spans that interconnect a set of network elements to form a ring network. In addition, each of the spans has two sub-spans on which traffic travels in opposite directions on a number of channels that circumvent the ring. Additionally, the channels on each sub-span include working channels and protecting channels. Furthermore, the network element includes a traffic handler to reprogram, responsive to protection switches and un-switches, the connection configuration on the protecting channels of the sub-spans of the first and second spans that provide traffic to the network element.

Abstract: Use of transaction agents to perform distributed transactions. According to one embodiment of the invention a coordinator transaction agent that includes an itinerary and a state machine is instantiated. The itinerary indicates a plurality of network elements and the plurality of network elements is in communication with the coordinator transaction agent. The coordinator transaction agent causes itself to be replicated onto the plurality of network elements according to the itinerary. Each of the replicated transaction agents causing an indication of their replication to be communicated back to the coordinator transaction agent. The coordinator transaction agent coordinating operations of the state machine in each of the replicated transaction agents to implement a distributed state machine.

Abstract: A method and apparatus for combining data packets having different protocol encapsulations within a circuit is described. In one embodiment, a method includes receiving a number of Internet Protocol (IP) packets over Ethernet on a real circuit. Each IP packet over Ethernet has an Ethernet header and an IP address. The method also includes removing the Ethernet header from the number of IP packets. Moreover, a number IP packets within a Point-to-Point Protocol (PPP) over Ethernet are received on at least one virtual circuit. Each of the number of IP packets within the PPP over Ethernet includes a PPP header, a PPP over Ethernet (PPPoE) header, an Ethernet header and an IP address. Additionally, the at least one virtual circuit runs within the real circuit. The method also includes removing the PPP header and the PPPoE header from the number of IP packets within the PPP over Ethernet and removing the Ethernet header from the number of IP packets within the PPP over Ethernet.

Abstract: A method and apparatus for non-stop forwarding of label switched traffic is described. A method comprises each of a plurality of clients separately allocating labels from different exclusive logical partitions of a label space, each of said plurality of clients identifying the labels they have allocated to a label manager, responsive to a first of said plurality of clients restarting, said label manager transmitting to said first client a first indication reflecting labels that said first client had allocated from its exclusive partition prior to said restarting, said first client allocating new labels from said exclusive partition respective of said first indication.

Abstract: A method and apparatus for exception handling in a multi-processor environment are described. In an embodiment, a method for handling a number of exceptions within a processor in a multi-processing system includes receiving an exception within the processor, wherein each processor in the multi-processor system shares a same memory. The method also includes executing a number of instructions at an address within a common interrupt handling vector address space of the same memory. The number of instructions cause the processor to determine an identification of the processor based on a query that is internal to the processor. Additionally, the method includes modifying execution flow of the exception to execute an interrupt handler located within one of a number of different interrupt handling vector address spaces.

Abstract: In an embodiment, an apparatus includes a storage unit to store data from a data signal. The apparatus also includes control circuitry coupled to the storage unit. The control circuitry is to cause the storage of the data from the data signal into the storage unit at a nominal rate upon determining that the data signal includes a number of errors.

Abstract: A machine readable medium for tunneling Ethernet is described. A machine readable medium comprises receiving an Ethernet frame and transmitting the Ethernet frame over a non-homogenous tunnel, the tunnel distinguishing subscriber traffic.

Abstract: A method and apparatus for disabling a data interface between network element data processing units is described. In one embodiment, the method includes transmitting data frames over a data connection through an interface of a first network element data processing unit to a second network element data processing unit, disabling the interface, receiving an interface disable signal, completing transmission of data frames currently being transmitted, upon receiving an interface disable signal, disabling the interface, the disabling not causing data loss, receiving acknowledgements over the data connection, and enabling the data connection after receiving a number of acknowledgements.

Abstract: A method and apparatus for managing an information routing information base is described. A method comprises managing a routing information base (RIB), the RIB including a first set of elements that indicate a set of destinations, a second set of elements that indicate a set of next hops, a third set of elements that indicate a set of interfaces, receiving a message that indicates a modification to a plurality of routes corresponding to a plurality of the first set of elements, and modifying a first relationship between one of the second set of elements and a first one of the third set of elements and a second relationship between the one of the second set of elements and a second one of the third set of elements in accordance with the message, the one of the second set of elements referenced by the plurality of the first set of elements.

Abstract: A method and apparatus for selectively packet mirroring is described. A method in a network element comprises selectively mirroring packets, the packets being associated with a first virtual path, the first virtual path indicating a first physical path and a first virtual path identifier and the selectively mirrored packets forwarded in accordance with a second virtual path, said second virtual path indicating a second physical path and a second virtual path identifier.

Abstract: A number of classes are received. Each class has a number of classification rules. A result is output indicating a first class of the number of classes conflicts with a second class of the number of classes upon determining that at least one of classification rules of the first class overlaps with one of the classification rules of the second class.

Abstract: A method and apparatus for sharing memory space of multiple memory units by multiple processing units are described. In an embodiment, a method includes storing a set of data across more than one of at least two memory units upon determining that the number of sets of data is static. The method also includes storing the set of data within a single memory unit of the at least two memory units upon determining that the set of data is dynamic.