Abstract: A system and method for reconfiguring a TCP window in a switch of a network system, where the size of the window is determined based on the operating speed of a work station to which data packets in the window are being sent and the size of the switch buffer. The algorithm includes establishing a connection between a server and the station, where the connection includes TCP data packets. The algorithm identifies a TCP window size requested by the station, and identifies the connection speed of the station in the switch. The algorithm then modifies the TCP window size of the connection if the identified TCP window size does not support the connection speed and the size of the buffer. The algorithm also changes the TCP check-sum based on the new TCP window size.

Abstract: Devices, systems, and methods are provided involving queue management. One embodiment includes a computing device having a priority aware queue. In this embodiment, the device includes a queue having a number of counters associated therewith to monitor a number of items each having a classification level associated therewith. The device also includes computer executable instructions to review each of the number of counters to determine whether to discard the item based upon whether at least one of the counters indicates that a higher classification item is being held in the queue.

Abstract: Network devices and methods are provided involving a support chip in association with network chips. One embodiment includes a network device having a processor, a high speed interconnect, and a number of network chips coupled to one another through the high speed interconnect. The number of network chips include a conduit port which can be selectively chosen to exchange packets, received to the number of network chips, with the processor. The support chip is coupled to the number of network chips in association with selecting a conduit port on one of the number of network chips to exchange packets with the processor.

Abstract: Network devices and methods are provided for device monitoring. One embodiment includes a network device having a processor, a high speed interconnect and a number of network chips. The number of network chips are coupled to one another through the high speed interconnect. The number of network chips have a conduit port which can be selectively chosen to exchange packets, received to any network chip, with the processor.

Abstract: Systems, methods, and devices are provided for moving packets on a network device. One method includes receiving packets to a number of network chips, the number of network chips having a conduit port which can be selectively chosen to exchange packets with a processor responsible for processing packets. The method includes adding data for additional functionality to certain packets. Adding data includes encapsulating the certain packets to maintain an appearance of a certain packet format.

Abstract: A method for generating a modified packet for output from a router. First, a received packet is stored in one memory location. Modified bytes corresponding to the received packet are computed and stored in a separate memory location. The modified packet is generated by multiplexing between select unmodified bytes of the received packet with the modified bytes.

Abstract: Network devices, systems, and methods are provided involving item routing management. One embodiment includes a computing device item routing management having a number of queues and a logic component. The number of queues can hold a number of items to be routed, via a routing path within the computing device, at least one of the items having time information associated therewith. The logic component can review at least one of the number of items held within the queue based upon the time information to determine whether to discard the item.

Abstract: A system and method for reconfiguring a TCP window in a switch of a network system, where the size of the window is determined based on the operating speed of a work station to which data packets in the window are being sent and the size of the switch buffer. The algorithm includes establishing a connection between a server and the station, where the connection includes TCP data packets. The algorithm identifies a TCP window size requested by the station, and identifies the connection speed of the station in the switch. The algorithm then modifies the TCP window size of the connection if the identified TCP window size does not support the connection speed and the size of the buffer. The algorithm also changes the TCP check-sum based on the new TCP window size.

Abstract: The present invention is a system and method for forwarding packets in order. A first packet may be received for forwarding. Subsequently, a second packet may be received for forwarding. A first memory request corresponding to the first packet is sent. A second memory request corresponding to the second packet may be sent prior to receiving a first memory reply corresponding to the first memory request. The first packet is forwarded prior to forwarding the second packet. In this novel manner, bandwidth in a network apparatus may be utilized with greater efficiency while maintaining packet ordering.

Abstract: A system for forwarding packets. The system has a first node for creating requests that contain a number of filters for specifying packet forwarding criteria. The first node also specifies values for the filters based on a packet to be forwarded. The system also has a second node coupled to the first node and to a number of ports. The second node has at least one table for specifying which of the ports are to receive the packet based on the filter values. The second node determines which of the ports are to receive the packet based on the table information and the filter values.

Abstract: A method and system thereof for forwarding data packets according to an order of forwarding while lessening delays. A resource request corresponding to a first data packet that is first according to the order is generated. A first resource request corresponding to a second data packet that follows the first data packet according to the order is generated. Generation of a subsequent resource request for the second data packet is delayed for a specified time period. A second resource request for the second data packet is generated before the specified time period is due to expire when the first data packet is forwarded. In this manner, a delay attributable to the specified time period is lessened.

Abstract: A method and system thereof for forwarding data packets according to an order of forwarding while lessening delays. A resource request corresponding to a first data packet that is first according to the order is generated. A first resource request corresponding to a second data packet that follows the first data packet according to the order is generated. Generation of a subsequent resource request for the second data packet is delayed for a specified time period. A second resource request for the second data packet is generated before the specified time period is due to expire when the first data packet is forwarded. In this manner, a delay attributable to the specified time period is lessened.

Abstract: A system for forwarding packets. The system has a first node for creating requests that contain a number of filters for specifying packet forwarding criteria. The first node also specifies values for the filters based on a packet to be forwarded. The system also has a second node coupled to the first node and to a number of ports. The second node has at least one table for specifying which of the ports are to receive the packet based on the filter values. The second node determines which of the ports are to receive the packet based on the table information and the filter values.

Abstract: The present invention is a system and method for forwarding packets in order. A first packet may be received for forwarding. Subsequently, a second packet may be received for forwarding. A first memory request corresponding to the first packet is sent. A second memory request corresponding to the second packet may be sent prior to receiving a first memory reply corresponding to the first memory request. The first packet is forwarded prior to forwarding the second packet. In this novel manner, bandwidth in a network apparatus may be utilized with greater efficiency while maintaining packet ordering.

Abstract: A method for generating a modified packet for output from a router. First, a received packet is stored in one memory location. Modified bytes corresponding to the received packet are computed and stored in a separate memory location. The modified packet is generated by multiplexing between select unmodified bytes of the received packet with the modified bytes.

Abstract: A system for coordinating the measurement activity of a plurality of emulators and their associated internal analyzers uses a bus with three signal lines. A READY signal is set false by any emulator that initiates a break (a transition from running user code to running a monitor). The READY signal is set false by the breaking emulator at the very beginning of its break, without waiting for the resumption of the monitor program. The false ready signal is detected immediately by the other emulators, which then break in sympathy. The READY signal is further used to restart all emulators in unison. The emulator that initiated the break remains running its monitor, while the others start their monitors, determine that they did not cause the break, and then in anticipation of a restart, essentially suspend their monitors and prepared to start running user code. As each emulator becomes ready it releases the READY signal. As the last emulator becomes ready, it too releases READY, which then does true.

Abstract: A system for coordinating the measurement activity of a plurality of emulators and their associated internal analyzers uses a bus with three signal lines. A READY signal is set false by any emulator that initiates a break (a transition from running user code to running a monitor). The READY signal is set false by the breaking emulator at the very beginning of its break, without waiting for the resumption of the monitor program. The false ready signal is detected immediately by the other emulators, which then break in sympathy. The READY signal is further used to restart all emulators in unsion. The emulator that initiated the break remains running its monitor, while the others start their monitors, determine that they did not cause the break, and then in anticipation of a restart, essentially suspend their monitors and prepare to start running user code. As each emulator becomes ready it releases the READY signal. As the last emulator becomes ready, it too releases READY, which then goes true.