3com Corporation

Trw Limited

3com Corportion

Peter Si-Sheng Wang

Kenneth Araujo

Ismail Dalgic

Vipin Kumar Jain

Christopher Hume Lamb

Ben Yunbei Yu

William Paul Sherer

Paul William Sherer

Opher Yaron

Wen-Tsung Tang

Zvika Bronstein

Cheng T Chen

Cyndi Jung

Guy M Chemla

Michael C MacDonald

Robert J Abel

Anthony Ballardie

Charles Hardin

The scalability and throughput for high-capacity communication switches is improved by providing a distributed arbitration algorithm which addresses the arbitration inefficiency of prior art systems. Distributed arbitration logic units in each satellite unit in a communication switch execute a protocol for computing a connection map for the switch fabric during each arbitration cycle. The protocol includes a plurality of phases including broadcasting backpressure parameters among the arbitration logic units, generating bids for access to switch fabric resources in each of the arbitration logic units utilizing information shared with other arbitration logic units, broadcasting the results of the bidding process, and configuring the switch fabric using the results.

Distributed switch fabric arbitration

A method and system for efficiently handling forwarding of multicast packets by ignoring VLAN (virtual local area network) context during lookup. In one embodiment, the present invention receives, at an intermediate device, multicast registration information for a client. The present embodiment then creates a forwarding database of the multicast registration information. In the present embodiment, when handling a multicast packet at an intermediate device, the present invention accesses the multicast registration information stored in the forwarding database. More particularly, in this embodiment, the present invention accesses the multicast registration information stored in the forwarding database without utilizing VLAN context of the client. As a result, the present invention allows the intermediate device to forward a single multicast packet which will later be supplied to registered member ports. The member ports apply the appropriate VLAN context. In so doing, the present invention prevents unnecessary replication of multicast packets and avoids superfluous expensive lookups in multicast registration tables.

System and method for efficiently handling multicast packets by ignoring VLAN context

The invention provides an information appliance and a network appliance (or telephone) that function independently as well as with each other as companion appliances. The information appliance stores user information corresponding to a particular user. The telephone is linked to network. In some embodiments, the companion appliances are capable of simultaneously exchanging voice and data messages with devices connected to the network. The appliances are connected to each other physically through a communications port, and exchange data link layer formatted data corresponding to user personalized information, commands from the user, and responses including message status information corresponding to action of the network connected devices. The user information enables the telephone to perform network communications according to user specified settings, and enables the telephone to assume the user specific information appliance network identification. The information appliance is typically a portable computer and in some embodiments is a palm-sized computer. In some embodiments, the telephone is an Ethernet telephone. One aspect of the invention provides a method for transmitting data from a portable computer to a telephone. Other aspects of the invention include: a method for exchanging voice and data messages between a telephone and devices connected to a network, a portable computer adapted for connection to a telephone, a telephone adapted for connection to a portable computer, and a communications system including the telephone connected to the portable computer.

Method apparatus and communications system for companion information and network appliances

A method to dynamically allocate time slots in multiple channels of a bandwidth over which a device can communicate on the network. In one embodiment, the present invention recites a method comprising several steps. First, a request to log onto a network is received from a device. Then, a loading condition of the network is determined. Finally, specific transmitting channels on which the new device is allocated to transmit information is assigned.

Dynamic bandwidth allocation through multi-channel time slot assignment and migration for broadband access

One embodiment of the invention includes an apparatus for providing electric power to a telephone across a transmission line where the telephone is coupled to a network device. A power and data coupler (&ldquo;the coupler&rdquo;) is coupled to one end of the transmission line. The transmission line is also adapted for transmission of a data signal. The data signal includes telephone signal data for communications with the telephone. The coupler has a data input and a power input. Power from the power input is coupled to the data signal from the data input and the combined power supply current and data signal is coupled to one end of the transmission line. The opposite end of the transmission line is coupled to a power and data decoupler (&ldquo;the decoupler&rdquo;). The decoupler has a power output and a data output. Both the data output and power output of the decoupler are coupled to the network device. The combined power and data signal is decoupled by the decoupler, and the data signal is supplied to the data output and the power is supplied to the power output. The invention also includes a circuit. The telephone circuit receives the power from the power output and receives the telephone signal data. The circuit couples the power and the telephone signal data together to make a combined power and telephone signal, which can be used by the telephone.

Power transfer apparatus for use by network devices including telephone equipment

A method and system for efficiently handling multicast packets by aggregating VLAN (virtual local area network) context. In one embodiment, multicast registration information is received for a first client in one VLAN and then multicast registration information for the second client in a second VLAN. An aggregated list is created of the multicast registration information for the first client and the second client. In this embodiment, the aggregated list of the multicast registration information is forwarded for the first client and the second client to a second intermediate device. Then, when handling a multicast packet at the second intermediate device, the present invention accesses the aggregated list of the multicast registration information for the first client and the second client. As a result, the present invention allows the second intermediate device to perceive having only a single VLAN registered to receive the multicast packet.

System and method for efficiently handling multicast packets by aggregating VLAN context

Method of troubleshooting a path that includes a source node, a set of destination nodes, and a set of at least an intermediate node in a computer network. The source node sends a packet to an intermediate node in the set of at least an intermediate node. At least a layer- intermediate node in the set of at least an intermediate node inserts data into the packet, and the layer- intermediate node sends the packet to another node in the path. A packet for troubleshooting a path in a computer network is disclosed. The path includes a source node, a destination node, and a set of at least one intermediate node. The packet comprises an address that corresponds to the destination node and data inserted by layer- intermediate nodes through which the packet has traversed. A method of troubleshooting a path that includes a set of layer- devices and a set of layer- devices is disclosed. A node in a computer network is disclosed. The node is in a path that includes a source node and a destination node. The node includes layer- logic that receives a packet, and, if the packet includes an indicator that a trace is to be performed, inserts data into the packet and sends the packet to another node in the path.

Layer-2 trace method and node

A method to switch a dual-mode serializer-deserializer for data networks. In one embodiment, the present invention recites a method for configuring the communication mode of a device having a Media Access Control-Physical Layer (MAC-PHY) interface for communicating with another device. One step receives a control signal at a device having a MAC-PHY Interface. The control signal indicating whether the device will communicate data over its data path in an aggregate mode or in a non-aggregate mode. In another step, the device is configured to communicate in the mode selected by said control signal. In another step, data is communicated over the data path of the device in a synchronous manner when the device is in an aggregate mode, and is communicated over the data path of the device in an asynchronous manner when the device is in a non-aggregate mode.

Dual mode serializer-deserializer for data networks

A method to dynamically attach, manage, and access a LAN-attached SCSI and netSCSI device to a network. In one embodiment, the present invention recites a method for dynamically attaching, managing, and accessing a netSCSI device coupled to a network. In one step, a broadcast message from the netSCSI device, providing a network address of the netSCSI device, is received at a computer coupled to the network. In another step, the network address of the netSCSI device is mapped to a logical SCSI ID in the computer. With another step, the computer claims ownership of the netSCSI device by transmitting a message of ownership to it and including its own, network address. Finally, communication to the netSCSI device is performed by accessing the address map.

Method to dynamically attach, manage, and access a LAN-attached SCSI and netSCSI devices

A communications network operating in a data cable system that transmits a data over cable media access control (MAC) frame with an Ethernet/ISO8802-3 type packet protocol data unit payload. Time frames for transmission of data over the network are allocated to cable modems and time frames originally allocated to a cable modem for transmission of lower priority data can be utilized to transfer high priority data while aborting the transmission of lower priority data. A high level data link control (HDLC) section is coupled immediately before a cyclical redundancy check (CRC) to indicate that all data packet protocol data units (PDU) that are encapsulated by HDLC flags is high priority data that is not to be discarded and other data is to be abandoned.

Method and system to communicate prioritized traffic via fixed length data communication frames

A communications network system that transmits and receives communication frames that include a transmission status section that indicates a communication frame transmission is aborted. In one embodiment, a transmission status section includes a cyclical redundancy check value that is non-matching with the information in the communication frame. For example, a non-matching cyclical redundancy check value is created by generating a one's compliment of a CRC calculated based upon the information within a communication frame. The communication network includes a wireless network, a wired network (e.g., an Ethernet network) and a data cable system that transmits a data over cable media access control (MAC) frame with an Ethernet/&lsqb;ISO8802-3&rsqb; type packet protocol data unit payload.

Method and system to abort data communication traffic in a communication network

A method and system for intelligently selecting the multicast filtering mode of a port in a switch. In one embodiment the present invention determines whether a client is coupled to a port of a switch. In such an embodiment, provided that a client is coupled to the port, the present invention monitors the client to determine if the client is 802.1p compliant. Next, in this embodiment, provided that the client is 802.1p compliant, the present invention automatically selects a Filter Unregistered Groups mode for the port to which the client is coupled. Conversely, if the client is not 802.1p compliant, the present invention selects a Forward All Groups mode for the port to which the client is coupled. In so doing, the present invention intelligently selects the optimal multicast filter mode for a switch and its connected clients. Additionally, the present invention eliminates the need for expensive, time-consuming, and error-prone network administrator intervention.

Intelligent selection of multicast filtering modes for switch ports

A network intermediate device interacts with a remote network element and performs the control plane interactions for a communication protocol used on a network segment between the network intermediate device and the destination, and interacts with customer premises equipment CPE to offload data plane transactions according to the protocol normally performed by the network intermediate device to the CPE, without the CPE needing to be aware of the complexities of the protocol involved. By distributing certain recurring packet data processing functions, like appending headers and removing headers, to the endpoints, the packet processing at the network intermediate devices is streamlined and processing bottlenecks are alleviated.

Growing community of inventors

Cupertino, CA, United States of America

Peter Si-Sheng Wang