Abstract: Systems and methods for scheduling data packets in a network processor are disclosed. Embodiments provide a network processor that comprises a best-effort scheduler with a minimal calendar structure for addressing schedule control blocks. In one embodiment, a four-entry calendar structure provides for rate-limited weighted best effort scheduling. Each of a plurality of different flows has associated schedule control blocks. Schedule control blocks are stored as linked lists in a last-in-first-out buffer. Each calendar entry is associated with a different linked list by storing in the calendar entry the address of the first-out schedule control block in the linked list. Each schedule control block has a counter and is assigned a rate limit according to the bandwidth priority of the flow to which the corresponding packet belongs.

Abstract: A configurable lookup table system including a first controller coupled to a first lookup table and a second controller coupled to a second lookup table is disclosed. The first controller configures the first lookup table for a first type lookup, which can be a Layer 2 or Media Access Control (MAC) type. The second controller configures the second lookup table based on a mode determination. If in a first mode, the second lookup table can be configured for a second type lookup, which can be a Layer 3 or Internet Protocol (IP) type. If in a second mode, the second lookup table can be configured for the first type lookup. This approach provides an efficient scheme for controlling and using multiple internal lookup tables for a variety of product configurations.

Abstract: The present invention is based on a dual dynamic Network Address Translation (NAT): one Network Address Translation (NAT) is executed close to the client stations of customers (to NAT), and one Network Address Translation (NAT) is executed close to the application server (to un-NAT). The networks between the client stations and the application server, only see registerd addresses (public IP addresses), while the application only sees the real private IP address. The present invention is based on a method for “NATting” and “un-NATting” the IP addresses without having to pre configure the “NATting” devices (the devices executing the operations of translating the network addresses).

Abstract: A GEM OAM frame transmission method used in a Gigabit-capable passive optical network is provided. The method defines an OAM frame structure in a GEM mode of the Gigabit-capable passive optical network and enables an OAM to be achieved even when the GEM mode is operated. The method comprises the steps of: constructing a GEM OAM frame including a GEM header field and a GEM payload field, the GEM header field containing OAM representation information indicating that the GEM OAM frame contains the OAM information, the GEM payload field containing the OAM information; and transmitting the constructed GEM OAM frame in order to enable the ONU/ONT to perform an operation according to the OAM information.

Abstract: A protocol processing engine system, which is arranged between a host side and a media access control (MAC) layer to thus speed up data transmission. The system includes a host interface, a network media access control (MAC) interface, a receiving subsystem and a transmitting subsystem. The system uses the host interface to interface with the host side and the network MAC interface to interface with the network MAC layer. The receiving subsystem classifies a connection received from the network MAC layer into a priority connection, fast connection or slow connection based on a pre-stored information, and activates its respective hardware circuit based on the connection classified in order to speed up data transmission of the connection. The transmitting subsystem transmits a connection received from the host interface to the network MAC interface.

Abstract: An apparatus and method for performing packet header lookup based on sequential lookup is provided. A header analyzer separates a header from a packet received via a network and outputs a lookup sequence. A unit lookup unit looks up matching the header combination rules with each field to be analyzed and input from the header analyzer based on the lookup sequence input from the header analyzer and outputs a match signal and a match address. A rule combination memory stores identification information for the header combination rules. A sequence combination memory stores lookup sequence information and sequence combination information. A rule combination unit generates match results based on the match signal input from the unit lookup unit and data read from the rule combination memory and the sequence combination memory.

Abstract: Systems and methods that provide receive queue provisioning are provided. In one embodiment, a communications system may include, for example, a first queue pair (QP), a second QP, a general pool and a resource manager. The first QP may be associated with a first connection and with at least one of a first limit value and an out-of-order threshold. The first QP may include, for example, a first send queue (SQ). The second QP may be associated with a second connection and with a second limit value. The second QP may include, for example, a second SQ. The general pool may include, for example, a shared receive queue (SRQ) that is shared by the first QP and the second QP. The resource manager may provide, for example, provisioning for the SRQ and may manage the first limit value and the second limit value.

Abstract: Methods and systems for distributing packets across all available output paths within a network is provided. A distribution key is extracted from each packet and is hashed to generate a hash value. An output path for each packet is selected by using all N bits of the hash value to address a distribution table having at least 2N indications of the output paths available for that packet. Thus, the stream of packets is distributed, or split up, across the available output paths, thereby balancing the load. In some embodiments, the order of the output paths is randomized within each distribution table. Other embodiments include a forwarding table used to determine the available output paths for a particular packet. In yet other embodiments, the distribution key includes the packet's source and destination; thus preventing packets within the same stream having varying latencies due to traveling along varying paths.

Abstract: Disclosed is a method, a device, such as a mobile station, and an information bearing medium that tangibly embodies a program of machine-readable instructions that are executable by a digital processing apparatus to perform operations to receive data packets. In this case the operations include verifying the correctness of a received data packet; storing a data packet found to have an incorrect TCP layer header checksum and signaling the source of the received data packets and, in response to receiving another instance of a previously received incorrect data packet, verifying the correctness of the received another instance of the data packet and, if correct, using information obtained from verifying the correctness of a header of the received another instance of the data packet to re-verify the correctness of the at least one stored data packet that was previously found to be incorrect.

Abstract: Methods and apparatus for transmitting a signal having a first frame duration being correlated to a second frame duration are described herein.

Abstract: Local rerouting around a failed component link of a link bundle is provided by immediately substituting one or more other component links of the same link bundle. The substitution of component links is performed at the point of failure without signaling to other nodes. This minimizes signaling traffic particularly when large numbers of LSPs are impacted by a single component link failure. Also, since LSP repair can be accomplished very quickly, traffic disruption is minimized.

Abstract: A video teleconferencing method for providing reservationless conferencing. The method involves creating a conference profile identifying selected connection parameters; allocating a dial-in number; notifying participants of the dial-in number; detecting a call from a requesting participant; determining if sufficient resources for the participant are available; and connecting the requesting participant into the reservationless conference. Additionally, the video teleconferencing method allows the conference time to be automatically extended. This is done using timers and reallocating available resources when the original end of conference time arrives. The method also enables the conference to automatically terminate after all conference participants leave the conference.