Abstract: Methods and devices are provided for memory management. One embodiment includes creating a memory control block including a number of sub-blocks, where the number of sub-blocks are capable of storing at least one data structure in a memory device. The method also includes scanning the control block for a free-able data structure having a defined data structure property, marking the free-able data structure as free-able in a bit map, and de-allocating the free-able data structure.

Abstract: One embodiment disclosed relates to a method of connection-rate filtering. A rate of traffic through a port of a network device is measured. The measured traffic rate is compared with a pre-set threshold rate. Packets are sampled from the port over a period of time if the pre-set threshold rate is exceeded by the measured traffic rate, and the sampled packets are analyzed. Other embodiments are also disclosed.

Abstract: Methods, computer readable media, and device embodiments are provided for port configuration. One method embodiment includes defining a number of ports for which a number of port configuration properties are to be configured, grouping the number of ports into one or more port configuration groups, and defining the number of port configuration properties to be configured within a particular port configuration group.

Abstract: In a packet-based switch, a method for managing data flow between the switch and other switches that are interconnected in a mesh network. The method includes receiving at the switch a topology inform packet sent from a first switch of the other switches. The topology inform packet includes at least an identifier of the first switch. The method also includes updating a link state database associated with the first switch. The link state database is configured for storing topology data pertaining to the mesh network. The method further includes forwarding the topology inform packet to at least another switch of the other switches to enable at least another switch to update a link state database associated with at least another switch.

Abstract: A method for managing multiple active paths among a plurality of network switches to identify and select an alternate path in response to failure of a path from a switch to a device. Load balancing protocols of the present invention enable the simultaneous use of multiple paths between network devices through a mesh of compliant network switches. When a port of a network switch fails (or the link connected to a port fails), a switch in accordance with the present invention selects an alternate port which may be used for forwarding packets to devices normally reached through the failed port. Networks switches operable in accordance with the structures and protocols of the present invention exchange messages to identify potential alternate paths. A potential alternate path is used to send a query message to a neighboring network switch to determine if a path to the identified devices is available through the neighboring network switch.

Abstract: One embodiment relates to a method of transporting data packets between a plurality of transport units in a building. Transmit flows are created and associated with source-destination address pairs of new data streams received from outside a network of the transport units. A separate sequence space is provided for each transmit flow. The transmission of the data packets belonging to a same transmit flow is advantageously spread among multiple link-layer links. Other embodiments, aspects and features are also disclosed.

Abstract: Methods and devices are provided for memory management. One embodiment includes creating a memory control block including a number of sub-blocks, where the number of sub-blocks are capable of storing at least one data structure in a memory device. The method also includes scanning the control block for a free-able data structure having a defined data structure property, marking the free-able data structure as free-able in a bit map, and de-allocating the free-able data structure.

Abstract: Methods, computer readable media, and device embodiments are provided for port configuration. One method embodiment includes defining a number of ports for which a number of port configuration properties are to be configured, grouping the number of ports into one or more port configuration groups, and defining the number of port configuration properties to be configured within a particular port configuration group.

Abstract: A switch to switch protocol for network load balancing which negotiates among switches operable in accordance with the invention to assign a unique loop bit offset identifier value to each switch. Various other load balancing protocols associated with the switches then utilize the loop bit offset value as an identifier field when determining loops in the network of switches and costs associated with non-looped paths in the switches. A loop bit offset identifier requires less switch processing overhead than techniques which utilize an entire address value (i.e., MAC address value) for such protocols. Further, the loop bit offset identifier assigned by the present invention reduces the size of load balancing related packets. Specifically, cost computation related packets are reduced in size to the minimum 64 byte packet size through use of the loop bit offset identifier value of the present invention.

Abstract: A method for disseminating MAC addresses for discovered network devices through a plurality of network switches which cooperate to enable maintaining multiple active paths between such devices. Where a plurality of network switches cooperate through load balancing protocols to enable simultaneous use of multiple paths between, protocols of the present invention permit newly discovered MAC addresses attached to ports of an edge switch to be disseminated through the network switches. When an edge switch detects a device having a previously unknown MAC address, a MAC address information packet is generated and disseminated from the edge switch the other switched of the same load balance domain. The packet is preferably, in effect, broadcast using the pruned broadcast tree constructed and maintained by other protocols related to the present invention. Each intermediate switch on the broadcast tree eventually receives the MAC address information packet from a neighboring switch in the load balance domain.

Abstract: A method for generating and maintaining a pruned broadcast tree for a network of switches operating multiple simultaneously active paths between devices with a load balancing family of protocols. The pruned broadcast tree is preferably generated as a by product of cost propagation aspects of the load balancing protocols exchanged among cooperating network switches. The load balance protocols operable within the network switches in association with the present invention permit multiple simultaneously active paths to be utilized among the network devices. The pruned broadcast tree is therefore used to reduce the latency of broadcast messages propagated within the network switches to reach all devices in the network. The broadcast tree defines a minimized set of devices to which a broadcast message need be forward to assure transmission to all network devices. The pruned broadcast tree, once established, is updated only in response to failure of a link and recovery of a failed link.

Abstract: A laptop computer is coupled to a first port of a network hub for the purpose of assigning a logical address to it. The network manager depresses a front panel button on the hub to activate a logical address learn mode. The network manager types a “ping” command into the laptop, specifying as the logical destination address the address to be adopted by the hub. The laptop, unable to find a matching physical address for the logical address, issues an address-resolution packet (ARP). The hub responds by adopting the destination address as its logical address and exiting learn mode; the hub replies with its physical address. The laptop, now informed of the hub's physical address, issues the ping request. The hub responds normally to this request, providing confirmation at the laptop that the logical address has been properly assigned.

Abstract: A method for disseminating MAC addresses for discovered network devices through a plurality of network switches which cooperate to enable maintaining multiple active paths between such devices. Where a plurality of network switches cooperate through load balancing protocols to enable simultaneous use of multiple paths between, protocols of the present invention permit newly discovered MAC addresses attached to ports of an edge switch to be disseminated through the network switches. When an edge switch detects a device having a previously unknown MAC address, a MAC address information packet is generated and disseminated from the edge switch the other switched of the same load balance domain. The packet is preferably, in effect, broadcast using the pruned broadcast tree constructed and maintained by other protocols related to the present invention. Each intermediate switch on the broadcast tree eventually receives the MAC address information packet from a neighboring switch in the load balance domain.

Abstract: A switch to switch protocol for network load balancing which negotiates among switches operable in accordance with the invention to assign a unique loop bit offset identifier value to each switch. Various other load balancing protocols associated with the switches then utilize the loop bit offset value as an identifier field when determining loops in the network of switches and costs associated with non-looped paths in the switches. A loop bit offset identifier requires less switch processing overhead than techniques which utilize an entire address value (i.e., MAC address value) for such protocols. Further, the loop bit offset identifier assigned by the present invention reduces the size of load balancing related packets. Specifically, cost computation related packets are reduced in size to the minimum 64 byte packet size through use of the loop bit offset identifier value of the present invention.

Abstract: A switch to switch protocol for network load balancing which permits parallel redundant paths in a network to be utilized while reducing broadcast or problems inherent in prior switch configuration protocols. In particular, the present invention includes in the protocol a hello packet protocol which serves to exchange load balancing information among switches within a common load balance domain. Further, the hello packet protocol of the present invention enables detection and correction of improperly configured loops outside a load balance domain.

Abstract: A method for computing cost information associated with a port of a switch in a network of switches. Cost information is computed as a port load factor: a ratio of port latency over available throughput. Port latency is determined as the depth of a queue associated with the port divided by the speed of the port. Available throughput is determined as the speed of the slowest port on a given path associated with the port in question. Preferably, the queue depth is measured in bits and the port speed and available throughput are measured in bits per second. Further, in the preferred embodiment, port latency is computed as a weighted average as ((15×previous latency)+current latency)/16. A higher value for the port load factor indicates a port which is more heavily loaded. The load factor is therefore useful in load balancing among the ports of switches and paths associated therewith.

Abstract: A method for disseminating MAC addresses for discovered network devices through a plurality of network switches which cooperate to enable maintaining multiple active paths between such devices. Where a plurality of network switches cooperate through load balancing protocols to enable simultaneous use of multiple paths between, protocols of the present invention permit newly discovered MAC addresses attached to ports of an edge switch to be disseminated through the network switches. When an edge switch detects a device having a previously unknown MAC address, a MAC address information packet is generated and disseminated from the edge switch the other switched of the same load balance domain. The packet is preferably, in effect, broadcast using the pruned broadcast tree constructed and maintained by other protocols related to the present invention.

Abstract: A method for managing multiple active paths among a plurality of network switches to identify and select an alternate path in response to failure of a path from a switch to a device. Load balancing protocols of the present invention enable the simultaneous use of multiple paths between network devices through a mesh of compliant network switches. When a port of a network switch fails (or the link connected to a port fails), a switch in accordance with the present invention selects an alternate port which may be used for forwarding packets to devices normally reached through the failed port. Networks switches operable in accordance with the structures and protocols of the present invention exchange messages to identify potential alternate paths. A potential alternate path is used to send a query message to a neighboring network switch to determine if a path to the identified devices is available through the neighboring network switch.

Abstract: A switch to switch protocol for network load balancing which exchanges cost information among all switches in a load balance domain. As compared to prior techniques, the protocol of the present invention updates all switches in the load balance domain periodically. All switches in the load balance domain are thereby assured of having consistent cost information regarding all switches in the load balance domain. Further, the protocol of the present invention reduces the volume of cost messaging traffic as exemplified by techniques which generate updates to the information any time a cost parameter of a switch changed. The preferred embodiment of he protocol of the present invention exchanges messages describing the switch latency for each switch in the load balance domain. A bit mask field in the transmitted cost packets indicates which switches have already received the cost information.

Abstract: A switch to switch protocol for network load balancing which negotiates among switches operable in accordance with the invention to assign a unique loop bit offset identifier value to each switch. Various other load balancing protocols associated with the switches then utilize the loop bit offset value as an identifier field when determining loops in the network of switches and costs associated with non-looped paths in the switches. A loop bit offset identifier requires less switch processing overhead than techniques which utilize an entire address value (i.e., MAC address value) for such protocols. Further, the loop bit offset identifier assigned by the present invention reduces the size of load balancing related packets. Specifically, cost computation related packets are reduced in size to the minimum 64 byte packet size through use of the loop bit offset identifier value of the present invention.