Abstract: A call admission control technique allowing flexible and reliable call admissions at an ATM switch in the case of an ATM network including both QoS-specified and QoS-unspecified virtual connections is disclosed. In the case where a QoS (Quality of Service) specified connection request occurs, an estimated bandwidth is calculated which is to be assigned to an existing QoS-unspecified traffic on the link associated with the QoS-specified connection request. A call control processor of the ATM switch determines whether the QoS-specified connection request is accepted, depending on whether a requested bandwidth is smaller than an available bandwidth that is obtained by subtracting an assigned bandwidth and the estimated bandwidth from a full bandwidth of the link.

Abstract: A device and method are disclosed for correctly restoring a read clock when there are a plurality of STM data stream transmission sources. In a CES device of an ATM communication system, ATM cells from respective connections, which are to be delivered to the same outgoing line, are accumulated in a reassembly buffer memory and a PLO control unit aggregates the amount of ATM cells accumulated in the reassembly buffer memory for each connection. Subsequently, the PLO control unit calculates the frequency of a read clock based on the amount of accumulated ATM cells for each connection. A PLO restores the read clock which is applied to read data from the reassembly buffer memory for delivery to an STM network.

Abstract: A circuit simulation apparatus is disclosed by which, even if an STS-N frame of an abnormal length is detected by a reassembly buffer, the frame length can be compensated for while preventing an overflow of the reassembly buffer. When an STS-(N×M) frame formed by multiplexing M STS-N frames formed from different channels is cellularized into ATM cells or M different STS-N frames assembled from ATM cells are multiplexed into an STS-(N×M) frame, an ATM cell sync signal and ATM cell data from a buffer section are outputted as a frame pulse signal and frame data from a reassembly section to a circuit termination section, and frame length compensation of the frame pulse signal and the frame data is performed by the reassembly section.

Abstract: A system and method that optimizes transmission control protocol (TCP) flow control without intruding upon TCP's core algorithms. A control module relatively near a sender's local area network (LAN) automatically identifies a packet flow that has become window-limited. After the packet flow has been identified as window-limited, the control module relatively near the sender's LAN and another control module relatively near a receiver's LAN optimize the packet flow by increasing the window size indicated in the receiver's acknowledgment packet. Both control modules operate synchronously to transparently manage the packet flow between the sender and the receiver.

Abstract: A system to convert first data signals into second data signals is provided. The first system may receive one of the first data signals associated with a data frame, determine first synchronization information corresponding to one of the second data signals associated with the data frame, and output the first synchronization information. The second system may receive the first synchronization information from the first system, determine second synchronization information corresponding to another one of the second data signals associated with a subsequent data frame based on the first synchronization information, and allocate a position in the subsequent data frame based on the second synchronization information.

Abstract: A network device is provided. The network device includes a controller configured to identify a head portion of a data packet received by the network device, and inhibit a transmission of the head portions of two received data packets from consecutive slots in a transmission cycle.

Abstract: A system permits queues to use more than an allocated amount of bandwidth. The system allocates an amount of bandwidth to each of the queues and determines whether any of the queues is using less than the allocated amount of bandwidth. If so, the system reallocates the allocated bandwidth from one of the queues to at least one other one of the queues based on the amount of bandwidth used by each of the queues.

Abstract: A reorder engine classifies information relating to incoming data items as belonging to either a first, second, or third region. The information relating to the data items may arrive at the reorder engine out of order. The data items each include a sequence number through which the reorder engine may reconstruct the correct order of the data items. Based on the classification, the reorder engine may either process the data items normally or drop certain ones of the data items. The majority of incoming data items will fall in the first region and are processed normally. Data items arriving in the second region indicate that a previous data item is late or delayed. If this previous data item is delayed but does eventually arrive, it will arrive in the third region and is simply ignored.

Abstract: An interconnect network for operation within communication node, wherein the interconnect network may have features including the ability to transfer a variety of communication protocols, scalable bandwidth and reduced down-time. According to one embodiment of the invention, the communication node includes a plurality of I/O channels for coupling information into and out of the node, and the interconnect network includes at least one local interconnect module having local transfer elements for transferring information between the plurality of I/O channels; and scaling elements for expanding the interconnect network to include additional local interconnect modules, such that information can be transferred between the local interconnect modules included in the interconnect network.

Abstract: A Cable Modem Termination System (CMTS) is partitioned into Line Cards, I/O Cards, and a midplane to provide enhanced Reliability, Availability, and Serviceability. Each I/O Card provides a cabling interface for coupling an assigned Line Card to other portions of a Hybrid-Fiber-Coax Network. A plurality of RF signals is coupled via connectors between each Line Card and a corresponding I/O Card, via the midplane. This permits a Line Card to be removed for servicing without requiring recabling of the corresponding I/O Card. Preferably, a rectangular-multi-pin collinear connector-cascade (Line Card jack, midplane double-plug, and I/O Card jack) is used to couple the plurality of RF signals. The connector-cascade is configured with protective RF ground pins adjacent and surrounding each of a plurality of RF signal pins.

Abstract: A networking system, device, and method are provided. The networking device typically includes a user-defined ruleset including HTTP request rules and HTTP response rules. The networking device may further include a request processor configured to receive an incoming HTTP request from the client, apply HTTP request rules to the incoming HTTP request, to thereby produce a modified HTTP request, and send the modified HTTP request to the server. The networking device may further include a response processor configured to receive an HTTP response to the modified HTTP request from the server, apply the HTTP response rules to the HTTP response, to thereby produce a modified HTTP response, and send the modified HTTP response to the client.

Abstract: Techniques are described for monitoring performance of a network. Particularly, network devices within the network exchange routing communications in accordance with one or more routing protocols, such as the Border Gateway Protocol (BGP), to automatically establish a community for monitoring performance throughout the network. Upon establishing the community, the network devices of the community exchange performance probes to collect comprehensive performance information for the network. This performance information may be aggregated via one or more computing devices. Using the aggregated performance information, numerous network performance characteristics may be computed, including delay, jitter, throughput, availability and packet loss.

Abstract: A network device utilizes fair bandwidth allocation techniques based on configurable service classes. The network device comprises a scheduler that receives a packet associated with a service flow for delivery to a destination. The scheduler identifies a service credit associated with the service flow that represents a bandwidth allocation available for consumption by an associated service flow. Based on the identified service credit, the downstream scheduler assigns the packet to one of a plurality of hold queues. The number of hold queues may remain static during the allocation of bandwidth, which reduces the complexity of the scheduler and permits fair bandwidth allocation to occur. Such a queuing architecture also allows the downstream scheduler to achieve rate limiting and minimum bandwidth guarantee without using separate algorithms and/or architectures.

Abstract: Techniques are described for providing QoS guarantees when coupling layer two (L2) networks via an intermediate Multi-protocol Label Switching (MPLS) network. A network device, such as a router, receives a request to transport data from an L2 connection. The request specifies one of more characteristics of the L2 connection, such as bandwidth, color, end-to-end delay, jitter, a security requirement, or a classification of traffic for the L2 connection. The network device selects a label switched path (LSP) through the MPLS network based on the characteristics of the L2 connection, and forwards the data from the L2 connection via the selected LSP. In this manner, an LSP and, in particular, one or more forwarding next hops for the LSP, is selected that provides a “virtual” L2 connection, or pseudo-wire, that more closely emulates a direct L2 connection between the L2 networks.

Abstract: A multi-chassis router allows an administrator to deliver commands from a single interface. Additionally, the multi-chassis router presents a software image consistent with that of a standalone router and uses commands and configurations consistent with those used by a standalone router. The multi-chassis router automatically distributes, processes and responds to administrator commands a single unit, minimizing time required to administer the multi-chassis router. In effect, an administrator does not need to account for the multiple chassis configuration, and an administrator familiar with the control and commands for a standalone router can use that knowledge to effectively control the operation of the multi-chassis router.

Abstract: Techniques are described for dynamically building an Ethernet virtual local area network (VLAN) interface in a network device. The techniques allow dynamic building of a second VLAN interface over a first VLAN interface statically built over an Ethernet port configured to support dynamic VLANs in a network device. A network device may receive a plurality of Ethernet packets from subscriber devices and dynamically build a second VLAN interface over the first VLAN interface for each of the subscribers. Once the second VLAN interface is built, the network device dynamically builds interface columns over the second VLAN interface for each protocol associated with the Ethernet packets. The network device may then authenticate a user associated with the plurality of Ethernet packets. Once the user has logged out of the network device, the network device may tear down the interface columns while persistently maintaining the corresponding second VLAN interface.

Abstract: A provider device determines that a failure has occurred in a link or path and notifies a customer device of the failure. The notifying causes the customer device to become aware of the failure in less than one second.

Abstract: A cable modem termination system that connects to cable modems includes a scheduler and a system manager. The scheduler schedules transmission opportunities for the cable modems and operates in multiple fragmentation modes. The scheduling of transmission opportunities by the scheduler differs among the fragmentation modes. The system manager compares one or more processing parameters associated with the cable modem termination system to one or more thresholds and causes the scheduler to transition among the fragmentation modes based on a result of the comparison.

Abstract: A device described herein may include an input port operable to receive data packets; a switching board operable to classify the data packets, determine whether the data packets should be accepted by the device, and determine whether received data packets are first data packets in a session; a management board operable to receive the data packets from the switching board that were determined by the switching board to be the first data packets in a session; and one or more processing boards operable to receive data packets from the switching board that were determined by the switching board to not be the first data packets in a session and to process the received data packets.

Abstract: A scheduling system includes a read sequence management table that includes a group of elements and an allocation processor that converts the group of elements in the read sequence management table to a group of corresponding slots in a time slot. The scheduling system further includes a schedule management table that stores information identifying elements within the read sequence management table for new lines based on peak rate values of the new lines. The schedule management table may identify a different element within the read sequence management table for new lines based on the peak rate values of the new lines and based on an arrangement of the new lines in designated positions of the schedule management table.