Multi-channel sharing in a high-capacity network

• US 7,000,026 B2
• Filed: 12/22/2000
• Issued: 02/14/2006
• Est. Priority Date: 12/22/2000
• Status: Expired due to Term

• Current Assignee: Ciena Corporation
• Original Assignee: Nortel Networks Limited (Nortel Networks Corporation)
• Inventors: Beshai, Maged E., Vickers, Richard, Munter, Ernst A.
• Primary Examiner(s): Vaughn, Jr., William C.
• Assistant Examiner(s): DENNISON, JERRY B
• Application Number:
  US09/742,229
• Publication Number:
  US 20020083195A1
• Time in Patent Office: 1,880 Days
• Field of Search: 709/231, 709/238, 709/227, 709/232, 709/226, 370/395.43, 370/43, 370/542, 395/391, 395/466, 395/473, 395/465, 395/4, 725/105, 718/105
• US Class Current: 709/238
• CPC Class Codes: H04L 12/5692 Selection among different networks
• CPC Class Codes: H04L 47/125 by balancing the load, e.g. traffic engineering

Abstract

Methods and apparatus for transferring data segments of a data stream across multi-channel links in a high-capacity network, so that the segments are equitably smeared across the channels of each multi-channel link, are described. The high-capacity network comprises a multiplicity of distributed high-capacity edge nodes interconnected by multi-channel links to a plurality of core nodes. Each edge node comprises a source node and a sink node which may share memory and control. A path from a source node of a first edge node to a sink node of a second edge node traverses two links, a first link from the source node to a selected core node and a second link from the selected core node to the destination sink node. Tandem switching through an intermediate edge node is not required, even for data streams of very low bit rate.

Two types of core nodes are described. A core node of a first type is constructed as a high-capacity single-plane switch. A core node of a second type is constructed as a very-high capacity multiple-plane switch. Accordingly, traffic-load balancing across each multi-channel link in the network is realized by a data smearing process that is tailored to the core node type. A first-order data smearing method that balances the traffic loads among the channels of a first multi-channel link in a two-link path is used in conjunction with said first-type core nodes. A second-order data smearing method that balances the traffic load of each data stream across the channels of both links in a two-link path is used in conjunction with said second-type core nodes.

Both first-order and second-order smearing methods are exercised at each source node, and the core nodes, regardless of their type, perform rudimentary tasks and are deliberately kept devoid of quality-control capability.

Claims

1. A source node having a plurality of multi-channel links connecting to core nodes in a network, each of said multi-channel links comprising a respective plurality of channels, said source node operable to:

determine, for each multi-channel link in said plurality of multi-channel links;

a first merit index based on a known propagation delay along said each multi-channel link, said first merit index having a first upper bound corresponding to a lowest propagation delay;

a second merit index determined based on a current vacancy of said each multi-channel link, said second merit index having a second upper bound corresponding to full vacancy in said multi-channel link; and

a composite merit index determined as a sum of said first merit index and said second merit index;

retain, in a control table, an identifier of a last-used channel in each of said multi-channel links for each data stream from among a plurality of data steams originating from said source node;

receive a data unit belonging to a particular data stream from among said data streams;

select a particular multi-channel link from among said plurality of multi-channel links according to a desired distribution of data streams over the plurality of multi-channel links and according to said composite merit index of said each multi-channel link;

ascertain, using said control table, a particular last-used channel by said particular data stream in said particular multi-channel link; and

transmit said data unit over a particular channel in said particular multi-channel link, said particular channel bearing a logical relationship to said particular last-used channel.

2. The source node of claim 1 wherein said logical relationship is an adjacency relationship determined according to a round-robin selection process of channels of said particular multi-channel link.