Abstract: A grid router includes a plurality of external interface units to receive packets of services from one point and to provide packets of services to another point and a second plurality of mailbox units to store and forward the packets associated with mailboxes, one per service. Each mailbox unit is connected to each external interface unit. The units are implemented on PCs (personal computers) having memory controllers and move the packets through the router close to or at the I/O (input/output) rate of the memory controllers.

Abstract: Method for operating an electronic network having a hardware layer and requiring network functions, involves virtualizing networking functions to virtual machines; using an addressing overlay above the hardware layer providing identities to the virtual machines and other network entities, the virtual machines being likely to move around different hardware components over the network, and the identities moving with the virtual machines; directing data flows around the network via the virtual machines using software defined flow mapping, the flows being directed among the virtual machines using the moving identities. The identities are mapped to the hardware locations of the virtual machines and the mapping is updated upon moving of the machine.

Abstract: A grid router for routing data over a grid sessionwise, involves multiple devices forwarding data according to sessions over an unreliable network between the devices. The devices include a first group of mailbox units to handle the sessions and a second group of egress units to forward session data to devices external to the network. The mailbox units and egress units are connected in a CLOS network such that each mailbox unit is accessible by each egress unit. The router further includes a distributed entity, which assigning specific sessions to specific mailbox units and to specific egress units and further defomes quality of service (QoS) levels for each session in the presence of congestion in either the network or the devices.

Abstract: A grid router including devices forwarding session data over an unreliable network between the devices, and distributed means providing quality of service levels defined per session given network or device congestion, the devices including session-handling units and egress units forwaring session data to devices external to the network, the router transporting the data across a link with acknowledgement, identifying link congestion and modifying the transporting as a function of the congestion, the router also connecting a multicast session, token bucket shaper with token bucket shapers of external devices, joining session token bucket shapers used for unicast and multicast sessions to the multicast session, token bucket shaper and deducting tokens consumed by the multicast session from a token budget of the session token bucket shaper, the router attributing priorities to a single traffic session as the session moves through the router while keeping packet order within the session.

Abstract: TCP Proxy apparatus for a wireless network section to a TCP-enabled network includes a latency aware unit for monitoring round trip time over the wireless access network section to determine latency within the access section; and a filter for filtering out momentary changes in the latency. Momentary fluctuations in the wireless connection causes instantaneous packet loss, which merely requires minimal packet retransmission, temporarily affecting latency. The filter ensures that such fluctuations do not activate the TCP congestion avoidance mechanisms and unnecessarily slow down the overall transmission rate.

Abstract: A grid router for routing packets and a network containing the same. The router comprises ingress units (IE), mailbox units (MU), and egress units (EU) connected in a structure of succeeding layers, said layered structure being segregated such that units in a given layer are connected only to a subset of units in a succeeding layer, wherein said grid router comprises a hashing unit for using a hashing function to direct incoming packets through said layers, and wherein said hashing function is configured to reinforce said segregation by directing packets arriving at a given unit in one layer only to units of a corresponding subset in said succeeding layer.

Abstract: System for bandwidth assignment to manage congestion over a network bottleneck, comprises a regulation point being set up downstream of the bottleneck in the network to manage congestion in data packets arriving from various sources via the bottleneck. For each of the sources, a priority level assigner assigns priority levels to respective data packets. A token bucket assigns tokens at a limiting rate to the prioritized data packets, the tokens allowing passage of packets to which they are assigned. The token bucket is a multi-priority token bucket, meaning it has at least two thresholds corresponding to the priority levels assigned to the packets. The token bucket only assigns a token to an arriving packet having a respective priority level if there are sufficient tokens currently in the bucket to reach the threshold corresponding to the packet's priority level.

Abstract: A grid router for routing packets and a network containing the same. The router comprises ingress units (IE), mailbox units (MU), and egress units (EU) connected in a structure of succeeding layers, said layered structure being segregated such that units in a given layer are connected only to a subset of units in a succeeding layer, wherein said grid router comprises a hashing unit for using a hashing function to direct incoming packets through said layers, and wherein said hashing function is configured to reinforce said segregation by directing packets arriving at a given unit in one layer only to units of a corresponding subset in said succeeding layer.

Abstract: System for bandwidth assignment to manage congestion over a network bottleneck, comprises a regulation point being set up downstream of the bottleneck in the network to manage congestion in data packets arriving from various sources via the bottleneck. For each of the sources, a priority level assigner assigns priority levels to respective data packets. A token bucket assigns tokens at a limiting rate to the prioritized data packets, the tokens allowing passage of packets to which they are assigned. The token bucket is a multi-priority token bucket, meaning it has at least two thresholds corresponding to the priority levels assigned to the packets. The token bucket only assigns a token to an arriving packet having a respective priority level if there are sufficient tokens currently in the bucket to reach the threshold corresponding to the packet's priority level.