Distributed and disjoint forwarding and routing system and method

• US 20050050136A1
• Filed: 08/28/2003
• Published: 03/03/2005
• Est. Priority Date: 08/28/2003
• Status: Active Grant

• Current Assignee: WSOU Investments, LLC (WSOU Holdings, LLC)
• Original Assignee: Alcatel-Lucent SA (Nokia Corporation)
• Inventors: Golla, Prasad N.
• Granted Patent: US 7,606,140 B2
• Time in Patent Office: Days
• US Class Current: 709/200
• CPC Class Codes: H04L 45/02 Topology update or discovery
• CPC Class Codes: H04L 45/22 Alternate routing
• CPC Class Codes: H04L 45/24 Multipath
• CPC Class Codes: H04L 45/28 using route fault recovery
• CPC Class Codes: H04L 45/54 Organization of routing tables
• CPC Class Codes: H04L 45/60 Router architectures
• CPC Class Codes: H04L 45/64 using an overlay routing layer

Abstract

A distributed and disjoint forwarding and routing system and method operable with a routing element having a scalable cluster-based architecture, wherein the control plane and data plane are loosely-coupled for effectuating non-disruptive switchover in the event of a failure. The routing element includes a partitionable data plane having one or more forwarding tables and a partitionable control plane having one or more routing tables operating under control of at least one routing protocol process. One or more update buffers are provided with respect to the forwarding and routing tables. A partitionable update agent module is disposed between the data and control planes for mediating the updating and coordination of the forward tables based on the routing tables.

Claims

1. A router, comprising:

a partitionable data plane including a plurality of forwarding tables, each forwarding table including forwarding information for effectuating a data forwarding process through said router;

a partitionable control plane including a plurality of routing tables operating under control of at least one routing protocol process, said routing tables including information for effectuating routing decisions with respect to said data forwarding process;

a control plane update agent module for maintaining a redundant set of routing table information in at least one control plane update buffer, wherein said control plane update agent module is operable to synchronize said routing tables; and

a data plane update agent module operably coupled to said control plane update agent module for coordinating said forwarding information with said routing table information in association with a set of data plane update buffers.

2. The router as set forth in claim 1, wherein said data forwarding process continues to proceed in an event of failure based on information stored in at least one of said data plane update buffers and said control plane update buffer.

3. The router as set forth in claim 2, wherein said event of failure comprises a failure associated with said partitionable data plane.

4. The router as set forth in claim 2, wherein said event of failure comprises a failure associated with said partitionable control plane.

5. The router as set forth in claim 2, wherein said partitionable data plane comprises a plurality of data plane nodes, each having at least one forwarding table and at least one data plane update buffer.

6. The router as set forth in claim 5, wherein said plurality of data plane nodes are organized into a scalable cluster.

7. The router as set forth in claim 5, wherein said data plane update agent module comprises a plurality of data plane update agents, each being associated with a data plane node.

8. The router as set forth in claim 5, wherein said plurality of data plane nodes are organized into a distributed network having a topology selected from the group consisting of ring topologies, star topologies, Clos topologies, toroid topologies, hypercube topologies and polyhedron topologies.

9. The router as set forth in claim 2, wherein said partitionable control plane comprises a plurality of control plane nodes, each having at least one routing table and at least one control plane update buffer.

10. The router as set forth in claim 9, wherein said plurality of control plane nodes are organized into a scalable cluster.

11. The router as set forth in claim 9, wherein said control plane update agent module comprises a plurality of control plane update agents, each being associated with a control plane node.

12. The router as set forth in claim 9, wherein said plurality of control plane nodes are organized into a distributed network having a topology selected from the group consisting of ring topologies, star topologies, Clos topologies, toroid topologies, hypercube topologies and polyhedron topologies.

13. A fault-tolerant routing element having a distributed scalable architecture, comprising:

means for detecting a fault in an active node disposed in said routing element, said active node for executing a router process;

means for effectuating a continuous switchover from said active node to a redundant node responsive to detecting said fault, said redundant node for continuation of said router process; and

means for updating routing table information and forwarding table information associated with said routing element responsive to said continuous switchover operation.

14. The fault-tolerant routing element as set forth in claim 13, wherein said active node comprises a control plane node.

15. The fault-tolerant routing element as set forth in claim 13, wherein said active node comprises a data plane node.

16. The fault-tolerant routing element as set forth in claim 13, wherein said active node forms a portion of a topological cluster comprising a plurality of nodes.

17. A fault-tolerant routing method operable with a network element having a distributed scalable architecture, comprising:

detecting a fault in an active node disposed in said network element, said active node for executing a router process;

effectuating a continuous switchover from said active node to a redundant node responsive to detecting said fault, said redundant node for continuation of said router process; and

updating routing table information and forwarding table information associated and continuing to execute said router process based upon said updating step.

18. The fault-tolerant routing method as set forth in claim 17, further comprising the operation of determining if said fault comprises a fatal fault involving said network element'"'"'s control plane.

19. The fault-tolerant routing method as set forth in claim 17, further comprising the operation of determining if said fault comprises a fatal fault involving said network element'"'"'s data plane.

20. The fault-tolerant routing method as set forth in claim 17, wherein said updating of said routing table information and said forwarding table information is configurable based upon detecting said fault.

21. A router, comprising:

a plurality of control plane nodes for effectuating routing process functionality based on control updates from peer elements in a communications network, each control plane node including a routing information database, a control plane update buffer and a control plane update agent; and

a plurality of data plane nodes for forwarding data based on said routing process functionality, each data plane node including a forwarding information database, a data plane update buffer and a data plane update agent,

wherein said data plane update agents and control plane update agents operate to update said forward information databases and said routing information databases in an asynchronous manner.

22. The router as set forth in claim 21, wherein said plurality of control plane nodes and said plurality of data plane nodes are organized in a logically disjoint, distributed architecture.

23. The router as set forth in claim 22, wherein said distributed architecture comprises a scalable cluster having a topology selected from the group consisting of ring topologies, star topologies, Clos topologies, toroid topologies, hypercube topologies and polyhedron topologies.

24. The router as set forth in claim 22, wherein said data plane update buffers and said control plane update buffers are operable to be updated by said data plane update agents and said control plane update agents in an asynchronous manner.

25. The router as set forth in claim 22, wherein said data plane nodes are operable to continue to forward data upon detecting a fault condition in at least one of said control plane nodes.

26. A distributed network, comprising:

a first network element operable to route data; and

a second network element coupled to said first network element,

wherein at least one of said first network element and said second network element is comprised of a router with decoupled control and data planes.

27. The distributed network as set forth in claim 26, wherein said router comprises:

a plurality of control plane nodes for effectuating routing process functionality based on control updates from peer elements in said distributed network, each control plane node including a routing information database, a control plane update buffer and a control plane update agent; and

a plurality of data plane nodes for forwarding data based on said routing process functionality, each data plane node including a forwarding information database, a data plane update buffer and a data plane update agent,

wherein said data plane update agents and control plane update agents operate to update said forward information databases and said routing information databases in an asynchronous manner.

28. The distributed network as set forth in claim 27, wherein said plurality of control plane nodes and said plurality of data plane nodes are organized in a logically disjoint, distributed architecture.

29. The distributed network as set forth in claim 27, wherein said distributed architecture comprises a scalable cluster having a topology selected from the group consisting of ring topologies, star topologies, Clos topologies, toroid topologies, hypercube topologies and polyhedron topologies.

30. The distributed network as set forth in claim 27, wherein said data plane update buffers and said control plane update buffers are operable to be updated by said data plane update agents and said control plane update agents in an asynchronous manner.

31. The distributed network as set forth in claim 27, wherein said data plane nodes are operable to continue to forward data upon detecting a fault condition in at least one of said control plane nodes.