British Telecommunications Public Limited Company

British Telecommunications Corporation

Cable Television Laboratories, Inc.

Robert J Briscoe

Arnaud Jacquet

Andrea Soppera

Philip L Eardley

Michael Rizzo

Tobias Moncaster

Luis Alberto Campos

Gregory Charles White

Karthik Sundaresan

Trevor Burbridge

Alan P Smith

Steve Glennon

Alessandro Salvatori

Gabriele Corliano

Ian R Fairman

Stephen Clifford Appleby

Carla Di Cairano-Gilfedder

Steven Rudkin

Paul Andrew Evans

Peter Hovell

Hui Min J Tay

Sebastien Cazalet

Anargyros Garyfalos

Mirja Kuehlewind

C Di Cairano-Gilfedder

Andrew M Claridge

Philip Eardley

A scheduling device for managing a packet queue of a communication gateway includes a receiving portion configured to receive data packets according to at least one communication protocol, a processor, and classification module configured to separate the received data packets into a first traffic queue and a second traffic queue separate from the first traffic queue. The first traffic queue includes a low latency service flow classified to have strict priority. The second traffic queue includes a primary service flow classified as having a classic priority. The classification module separates the received data packets so that those with a first indicator are sent to the first traffic queue and those without the first indicator are sent to the second traffic queue.

Systems and methods for queue protection

The invention relates to a method of controlling packets in a data packet network, the method comprising the steps of: a source node sending a first set of packets to a receiver node over the data packet network via an intermediate node, wherein the first set of packets are marked as being of a class of service preventing them from being forwarded to the receiver node if a packet queue exists at an intermediate node; the source node receiving an acknowledgement of a received packet of the first set of packets from the receiver node; and the source node sending a second set of packets to the receiver node over the data packet network.

Data packet network

The invention includes a network node, and a method of controlling the network node in a data packet network, wherein the method comprising the steps of: receiving a first data packet from a first external network node; analysing the first data packet to determine if it is of a class of service deemed to be queuable or unqueuable; and, if it is queuable, sending the first data packet to a second external node via an intermediate node, wherein the first data packet is reclassified to be of the unqueuable class of service such that the intermediate node should not forward the first data packet to the second external network node if a packet queue exists at the intermediate node.

A method of attributing contributions to congestion of a shared resource to respective user registers, the resource being operable to serve requests for service, each of a plurality of the requests having a user indication associated therewith indicating with which of a plurality of user registers the request is associated.

Attribution of congestion contributions

A method and apparatus for changing a packet tag status value from a first value to a different value upon said packet arriving at a buffer if there already is a packet in the buffer queue having the same first status value. A sequence of tag status values () in packets received at an end node is used to determine the queue length of the buffer in the packet network. An end node can thereafter adapt its sending rate to the rate of the buffer.

Re-marking of packets for queue control

Disclosed is a method and apparatus for a packet data flow to use markings on packets () that indicate the longest instantaneous queue length on a path in order to rapidly increase the flow rate up to an available capacity of a network node without overshoot, in order to avoid the TCP Slow start process.

Fast friendly start for a data flow

Congestion in respect to a network element operable to forward data items in a telecommunications networks, and in respect to a processing element operable to process requests for service is signaled. In either, the element is operable to perform its processing function at up to a processing rate which is subject to variation, and has a queue for items awaiting processing having a counter associated therewith which maintains a count from which a queue metric is derivable. A method comprises: updating the count at a rate dependent on the processing rate; further updating the count in response to receipt of items awaiting processing; and signalling a measure of congestion in respect of the element in dependence on the queue metric; then altering the rate at which the count is being updated and adjusting the counter whereby to cause a change in the queue metric if the processing rate has changed.

Signalling congestion

Methods and apparatus are disclosed for signalling congestion being caused by data items such as packets, received at a network element such as a router, in a communications network such as the Internet, or being caused by items otherwise requiring service or capacity from a shared resource. Preferred embodiments of the method involve identifying whether or not received data items received at a network element are capable of carrying congestion indications such as ECN marks, and for those that are capable, assigning congestion indications to the data items in dependence on a queue length characterization based on a substantially current, instantaneous measurement of the length of the queue, whereas for those that are not capable, a sanction such as dropping may be applied in dependence on a different queue length characterization based on a weighted moving average of current, recent, and less recent measurements of the length of the queue.

Methods and apparatus are disclosed for obtaining and processing information from a predetermined portion of a header of a data item such as an IP packet transmitted via a communication network such as a packet network, the portion carrying a codepoint selected from a first set of codepoints each of which has a pre-defined meaning according to a first pre-defined communication protocol. The method comprises: receiving the data item; inspecting the header whereby to determine the codepoint carried by the predetermined portion thereof; identifying whether the codepoint is a member of a second set of codepoints, the second set comprising fewer possible codepoints than the first set; and in the event that the codepoint is identified as being a member of the second set, and in dependence on such an identification being made, interpreting that codepoint according to a different pre-defined communication protocol as having a different pre-defined meaning and routing the data item via the communication network via the second pre-defined communication protocol.

Obtaining information from data items

Downstream path congestion is measured in respect of a node via which a plurality of data units are traversing an end-to-end path from a sender to a receiver. Each data unit has a first indication settable in dependence on information from the receiver to each of at least two states whereby to indicate different levels of congestion experienced on the end-to-end path by data units previously received by the receiver, and a second indication settable to an initial state and to at least one updated state indicative of congestion experienced by data units on their path from the sender to said node. A plurality of data units are received at the node, and the downstream path congestion measure is determined in dependence on an inflation factor itself dependent on the proportion of a set of the data units whose second indication on receipt at the node is in the initial state.

Determining path congestion measures

Apparatus and methods for policing flows of data units () along a path in a data network in dependence on congestion indications associated with said data units indicating whether or not said data units have experienced, or are expected to experience, congestion on the path, said apparatus and methods allowing for a high but not unlimited short-term burst rate (w) of data units having congestion indications associated therewith, the short-term burst rate being high when compared with a long-term average rate (w) at which data units having congestion indications associated therewith may be forwarded without the data units being subjected to a policing action such as dropping, delaying or marking for possible sanction.

Policing in data networks

Methods and apparatus for providing path characterization information relating to a network characteristic such as network congestion to nodes in a data network using data units being forwarded from a source to a destination via a plurality of nodes in the network, the method comprising: receiving, at a first proxy node, data units from a source, each data unit comprising a destination indication indicative of an intended destination; identifying, in respect of an intended destination indicated, a second proxy node in the network to which data units may be forwarded before being forwarded to the intended destination; and forwarding a first and at least one subsequent data unit from the first to the second proxy node via 'one or more intermediate nodes; the method further comprising assigning conditions to path characterization metrics in respect of data units traversing a path across the network from the first to the second proxy node, the initial condition being dependent on information received by the first from the second proxy node.

Path characterisation in networks

Methods and an associated traffic management module and system are disclosed for monitoring, at a traffic management module () within a data network, path characterisation information indicative of at least one measure of a dynamic network characteristic at a remote node () outside said data network. The method involves a traffic management module () receiving at least one data unit from a remote node () outside said data network, and in the event that said at least one data unit is encapsulated in an outer header and that an inner header of said data unit includes path characterisation information, performing the following in respect of said data unit: (a) monitoring said path characterisation information in said inner header; and (b) forwarding said data unit according to a first treatment category. In the event that these conditions are not met, the data unit is instead subjected to an alternative treatment.

Monitoring path characterisation information

Methods and apparatus are disclosed for obtaining information from one or more headers of a data item transmitted via a communication network, a predetermined portion of at least one header carrying a symbol or combination of symbols having a first pre-defined meaning according to a first pre-defined communication protocol. The method comprises inspecting at least one header of a received data item whereby to identify the symbol or combination of symbols carried by the predetermined portion thereof; identifying whether at least one other portion of a header of the data item is carrying the same symbol or combination of symbols; and in the event that it is identified that at least one other portion of a header of the data item is carrying the same symbol or combination of symbols, 'interpreting and/or processing at least one of the one or more headers according to a second pre-defined communication protocol, the second communication protocol differing from the first communication protocol.

Growing community of inventors

Woodbridge, United Kingdom

Robert J Briscoe