Abstract: A data processing system performs any-to-any transmission of data blocks. The system receives the data blocks on incoming data streams, and load balances the data blocks across a number of processing paths. The processing paths process the data blocks causing one or more of the data blocks to become out of order relative to an order in which the data blocks were received. The system hashes the data blocks to determine a manner in which to transmit the data blocks, reorders the data blocks to restore the order in which the data blocks were received, and transmits the reordered data blocks on outgoing data streams.

Abstract: A network device includes interface logic and processing logic. The interface logic receives data. The processing logic generates a checksum of the data and fragments the data into one or more cells. The processing logic further determines whether one of the one or more cells includes at least one of cell overhead bytes and cell pad bytes, and selectively inserts the checksum into the at least one of cell overhead bytes and pad bytes based on the determination.

Abstract: A system selectively drops data from queues. The system includes a drop table that stores drop probabilities. The system selects one of the queues to examine and generates an index into the drop table to identify one of the drop probabilities for the examined queue. The system then determines whether to drop data from the examined queue based on the identified drop probability.

Abstract: Techniques for delivering and receiving multicast content across a unicast network are described. A system that supports delivery and reception of multicast content across a unicast network includes a first device and a second device. The first device may be a destination device or a multicast-enabled router. The second device is multicast-enabled, and may be a multicast-enabled router. The first device determines whether a route between a destination device and a source of multicast packets is multicast-enabled, sends a unicast request message that includes as a destination address an address associated with the source and is marked for interception by a second device based on the determination, and receives the multicast packets as unicast packets from the second device. The second device intercepts the unicast request message and delivers the multicast packets to the requesting device as unicast packets in response to the unicast request message.

Abstract: Techniques are described for distribution of label switched packets, such as multiprotocol label switched (MPLS) packets, across multiple physical data paths. The techniques may, for example, be used to load balance the label switched packets across an aggregated link having two or more logically associated physical interconnects. A network device, for example, includes an interface card to receive packets associated with a common label switched path (LSP), and a control unit to distribute the packets across multiple paths. The network device may include label data that maps ranges of labels, such as MPLS labels, to types of payloads carried by the label switched packets. In accordance with the label data, the control unit extracts flow information from the label switched packets and distributes the label switched packets across the paths based on the flow information.

Abstract: A software module operating within a network device, such as an operating system, manages state information within hierarchically ordered and temporally-linked data structure. The software module sends state change messages to other software modules within the network device, referred to as consumers, in an order that corresponds to the hierarchical order and the temporal linking. The data structure may comprise a plurality of objects to store state information. The operating system may receive event messages that indicate a change to the state information. The objects may be hierarchically linked in accordance with a hierarchy representing relationships of event messages. The objects may be temporally linked in accordance with the order in which the operating system receives event messages. The operating system may traverse the data structure according to the temporal and hierarchical links to select state change messages to send to a consumer.

Abstract: A device includes an input processing unit and an output processing unit. The input processing unit dispatches first data to one of a group of processing engines, records an identity of the one processing engine in a location in a first memory, reserves one or more corresponding locations in a second memory, causes the first data to be processed by the one processing engine, and stores the processed first data in one of the locations in the second memory. The output processing unit receives second data, assigns an entry address corresponding to a location in an output memory to the second data, transfers the second data and the entry address to one of a group of second processing engines, causes the second data to be processed by the second processing engine, and stores the processed second data to the location in the output memory.

Abstract: In an ATM exchange, a cell transmission control section transmits an ATM cell to a transmission path of an ATM network. A traffic monitor monitors traffic of the cell transmissions. A statistical process section performs a temporal statistical process on the result of the traffic monitoring using a clock and a memory. A CAC produces an instruction for traffic control over a transmission terminal based on the result of the statistical process. A UPC controls traffic of a transmission path from the transmission terminal in accordance with the instruction.

Abstract: Techniques are described to replicate multicast packets in accordance with a hierarchical data structure. For example, upon receiving a multicast packet, a packet-forwarding engine may communicate the packet to packet-forwarding engines corresponding to starting nodes of the hierarchical data structure. The packet-forwarding engines corresponding to starting nodes of the hierarchical data structure may replicate the multicast packet for local interface cards, and forward the replicated packets to the network. Furthermore, the packet-forwarding engines may replicate the packet for packet-forwarding engines corresponding to downstream nodes. In this manner, the packet replication process is distributed throughout the router decreasing the complexity of necessary replication hardware. Furthermore, the packet replication process is highly scalable resulting in a latency of one fabric hop when the number of packet-forwarding engines doubles.

Abstract: A data compression system and method for that is capable of detecting and eliminating repeated phrases of variable length within a window of virtually unlimited size.

Abstract: A networking device, method, and web server software architecture are provided. The device may include a web server application program configured to run on an operating system of the device, and an event-based signaling mechanism configured to signal the web server application program when data has arrived on a socket of the operating system, by triggering an operating system-level signaling event. The web server application program is configured to read data off of the socket in response to detecting the event, without polling the socket first to determine that data is ready to be read from the socket.

Abstract: A routing system decouples the routing functionality from the packet forwarding functionality. The decoupling of functionality is accomplished by coupling a set of routing engines to a set of packet-forwarding engines via a switch. The decoupling of functionality allows the routing system to easily be reconfigured and scaled. The decoupling of functionality also reduces the susceptibility of concurrently executing software processes from the malfunction of a single software process.

Abstract: Techniques are described that allow a network device, such as a router, to dynamically build VLAN interfaces based on subscriber information strings included within packets. In particular, the network device comprises an interface controller and a forwarding controller, where the forwarding controller receives the packet over an Ethernet port and forwards the received packet to the interface controller. The packet includes both Ethernet tagging information and a subscriber information string. The interface controller comprises an Ethernet module that dynamically builds a primary virtual local area network (VLAN) sub-interface (PVS) based on the Ethernet tagging information. The Ethernet module also dynamically builds a subscriber VLAN sub-interface (SVS) based on the subscriber information string. The SVS allows the network device to distinguish between subscribers residing on the same VLAN, and, therefore, to provide subscriber specific services.

Abstract: Techniques are described for testing connectivity to unnumbered interfaces of a target device. For example, a software utility and protocol are described that allows an administrator to specify a logical offset that may be internally resolved by the target device to one of a plurality of unnumbered interfaces during the test. Similarly, the administrator may specify an offset that may be internally resolved by the source device to one of a plurality of unnumbered interfaces from which the connectivity test is to originate. The source device may send enhanced request packets and receive enhanced reply packets specifying the source unnumbered interface and the destination unnumbered interface between which connectivity is to be tested. In this manner, an administrator may test for connectivity of particular interfaces even where internet protocol (IP) addresses or other identifiers for the interfaces are not externally known.

Abstract: Techniques are described for providing hybrid forwarding within an Ethernet-based service domain established over one or more intermediate networks, such as a service provider (SP) network. For example, the Ethernet-based service domain may comprise a virtual private local area network service (VPLS) domain. A hybrid VPLS domain may transport layer two (L2) communications, such as Ethernet packets, between remote customer networks via the SP network. The techniques described herein enable a network device, e.g., a router, within a SP network to forward packets from a source device of a hybrid VPLS domain toward one or more subscriber devices of the hybrid VPLS domain (i.e., in a downstream direction) using P2MP forwarding semantics. The same network device forwards packets from one of the subscriber devices toward the source device (i.e., in an upstream direction) using P2P forwarding semantics.

Abstract: A network router integrates routing functionality with accounting functionality for generation of flow statistics, and provides packet intercept functionality to provide a comprehensive traffic analysis environment. The router includes a set of interface cards to receive packets from a network, and a control unit to generate a first and second duplicate stream of the packets. The control unit provides the packets of the first stream to accounting modules for calculation of flow statistics, and applies an intercept filter to intercept at least a subset of the packets of the second stream for selected packet flows.

Abstract: Techniques allow network devices to set up multiple multicast distribution structures for a given multicast group and source. According to the techniques, a multicast protocol is extended to include an instance number in the control messages, where the instance number corresponds to one of a plurality of instances for the multicast group and source. The network device sends a join request for each of the N instances for the multicast group to a plurality of upstream routers. Each of the join requests specifies a different instance of the multicast group to be joined. The source device for the multicast group selects one of the N instances, for example using a unicast Equal Cost Multipath (ECMP) hashing algorithm, and sends multicast content for the multicast group to via the multicast distribution structure corresponding to the selected one of the N instances.

Abstract: Network devices in a multicast network exchange multicast optimization data to improve efficiency of multicasting in the network. A protocol, e.g., a routing protocol or a multicast protocol, may be extended to allow the network devices to exchange the multicast optimization data. Alternatively, a separate protocol may be established for exchanging MOD. A network device may receive a message from an upstream device located between the device and a source for a multicast group, wherein the message includes multicast optimization data that specifies at least one criterion for selecting an upstream device. The device may use the data to intelligently select an optimal upstream device for receiving multicast using any of a variety of criteria to rank the upstream routers, such as minimization of multicast traffic duplication, load balancing current bandwidth levels, and avoiding paths experiencing communication delays.

Abstract: In a PPP terminating equipment 100 connected with a switch fabric and terminating PPP link, the PPP terminating equipment 100 has an LCP echo requirement detecting section 20 detecting whether or not a received packet is the LCP echo requirement packet, and an LCP echo response producing section 40 producing a response packet to the LCP echo requirement by rewriting the LCP header of the received LCP echo requirement packet. The PPP terminating equipment 100 thereby produces and returns the response packet to the LCP echo requirement.

Abstract: A network router includes a set of interface cards to receive packets from a network, and a set of accounting modules to calculate flow statistics for the packets. The router further includes a control unit to adaptively update routing information in response to the calculated flow statistics, and to route the packets in accordance with the routing information. The control unit identifies potentially malicious packet flows for the received packets based on the flow statistics, and applies an intercept filter to intercept the packets of the identified packet flows. The control unit analyzes the intercepted packets in real-time to determine the presence of a network event, and updates the routing information based on the determination, e.g., by terminating routing for packets associated with malicious packet flows. In this manner, the router may adaptively respond to network events, such as network security violations.