Fault-protection mechanism for protecting multi-protocol-label switching (MPLS) capability within a distributed processor router operating in an MPLS network

• US 20030212927A1
• Filed: 05/08/2002
• Published: 11/13/2003
• Est. Priority Date: 05/08/2002
• Status: Active Grant

• Current Assignee: Parity Networks LLC
• Original Assignee: Sherwood Partners Incorporated
• Inventors: Akyol, Bora, Murugan, Sundara Vadive, Navar, Venu Gopal
• Granted Patent: US 6,915,445 B2
• Time in Patent Office: Days
• US Class Current: 714/47
• CPC Class Codes: H04B 1/74 for increasing reliability, e.g. using redundant or spare channels or apparatus replacing by standby devices for amplifiers H03F1/52, H03F1/542

Abstract

A method for providing fault-tolerance for Multi-Path Label Switching (MPLS) functionality in a multi-processor network routing node has the steps of (a) implementing an MPLS server application including state information, on a first and a second processor in the node; (b) designating the MPLS server on the first processor as a master server and the MPLS server on the second processor as a backup server, and providing MPLS functionality in the node with the master MPLS server; (c) directing all required MPLS events to both the master and the backup MPLS servers during operation; (d) monitoring operation of the master server; and (e) in the event of failure of the master server, designating the backup server as the master, allowing MPLS functions to continue on the routing node.

Claims

1. A method for providing fault-tolerance for Multi-Path Label Switching (MPLS) functionality in a multi-processor network routing node, comprising the steps of:

(a) implementing an MPLS server application including state information, on a first and a second processor in the node;

(b) designating the MPLS server on the first processor as a master server and the MPLS server on the second processor as a backup server, and providing MPLS functionality in the node with the master MPLS server;

(c) directing all required MPLS events to both the master and the backup MPLS servers during operation;

(d) monitoring operation of the master server; and

(e) in the event of failure of the master server, designating the backup server as the master, allowing MPLS functions to continue on the routing node.

2. The method of claim 1 wherein, in step (d), monitoring is accomplished by a software distribution module (SDM) executing on a third processor in the node.

3. The method of claim 1 further comprising client MPLS applications executing on one or more processors in the node dedicated to processing incoming data packets, further comprising a step for passing information from the master MPLS server to the one or more MPLS clients.

4. The method of claim 3 wherein the processors dedicated to processing incoming data packets comprise line cards (LC) with processors, the LCs each comprising one or more ports interfacing with the network for receiving and sending data packets, and control cards (CC) with processors, the CCs for providing control functions, and the MPLS servers are established on control cards, one of which becomes an MPLS master control card, and the other an MPLS backup control card.

5. The method of claim 2 wherein the processors upon which MPLS servers are established are control cards (CC) with processors, the CCs for providing control functions, and the SDM is established on a CC other than those upon which MPLS servers are established.

6. The method of claim 5 wherein a primary SDM is established on a first global master CC (GMCC) and a backup SDM is established on a global backup CC (GBCC), and wherein the global backup becomes the global master in the event of failure of the global master.

7. The method of claim 6 comprising a further step, once a GBCC becomes a GMCC, for establishing and enabling a new GBCC.

8. The method of claim 1 comprising a further step, once a backup MPLS server has become the master MPLS server, of designating and enabling a new backup MPLS server.

9. The method of claim 4 comprising a further step, once a backup MPLS CC has become the Master MPLS CC, of designating and enabling a new backup MPLS CC.

10. The method of claim 1 wherein the network is the Internet network.

11. The method of claim 1 wherein, in step (a), the MPLS server application is configured with a resource reservation protocol (RSVP) stack.

12. The method of claim 2 wherein the MPLS server applications are included with the SDM in a bootable software image.

13. The method of claim 6 wherein the GMCC determines server assignments at startup of the routing node.

14. The method of claim 13 wherein state information and data structures are copied from the MPLS master server to the MPLS backup server at startup of the routing node after server task assignment and initialization.

15. A control system for providing fault-tolerance for Multi-Path Label Switching (MPLS) functionality in a multi-processor network routing node, comprising:

a master MPLS server application including state information, implemented on a first processor in the node; and

a backup MPLS server application implemented on a second processor in the node;

characterized in that the master server provides MPLS functionality with all MPLS events directed to both the master and the backup server, and control is switched to the backup server as master in the event of failure of the master server.

16. The control system of claim 15 further comprising a software distribution module (SDM) executing on a third processor in the node, wherein the SDM monitors master MPLS function, and implements switchover as necessary.

17. The control system of claim 15 further comprising client MPLS applications executing on one or more processors in the node dedicated to processing incoming data packets, wherein information is passed from the master MPLS server to the one or more MPLS clients.

18. The control system of claim 17 wherein the processors dedicated to processing incoming data packets comprise line cards (LC) with processors, the LCs each comprising one or more ports interfacing with the network for receiving and sending data packets, and control cards (CC) with processors, the CCs for providing control functions, and the MPLS servers are established on control cards.

19. The control system of claim 16 wherein the processors upon which MPLS servers are established are control cards (CC) with processors, the CCs for providing control functions, and the SDM is established on a CC other than those upon which MPLS servers are established.

20. The control system of claim 19 wherein a primary SDM is established on a first global master CC (GMCC) and a backup SDM is established on a global backup CC (GBCC), and wherein the global backup becomes the global master in the event of failure of the global master.

21. The control system of claim 20 wherein, once a GBCC becomes a GMCC, a new GBCC is established and enabled.

22. The control system of claim 15 wherein, once the backup MPLS server has become the master MPLS server, a new backup MPLS server is designated and enabled.

23. The control system of claim 18 wherein, once a backup MPLS CC has become the Master MPLS CC, a new backup MPLS CC is designated and enabled.

24. The control system of claim 15 wherein the network is the Internet network.

25. The control system of claim 15 wherein the MPLS server application is configured with a resource reservation protocol (RSVP) stack.

26. The control system of claim 16 wherein the MPLS server applications are included with the SDM in a bootable software image.

27. The control system of claim 20 wherein the GMCC determines server assignments at startup of the routing node.

28. The control system of claim 27 wherein state information and data structures are copied from the MPLS master server to the MPLS backup server at startup of the routing node after server task assignment and initialization.

29. A network routing node comprising:

a plurality of processors; and

a control system for providing fault-tolerance for Multi-Path Label Switching (MPLS) functionality, the control system having a master MPLS server application including state information, implemented on a first of the plurality of processors, and a backup MPLS server application implemented on a second of the plurality of processors in the node;

characterized in that the master server provides MPLS functionality with all MPLS events directed to both the master and the backup server, and control is switched to the backup server as master in the event of failure of the master server.

30. The network routing node of claim 29 further comprising a software distribution module (SDM) executing on a third of the plurality of processors in the node, wherein the SDM monitors master MPLS function, and implements switchover as necessary.

31. The network routing node of claim 29 further comprising client MPLS applications executing on one or more of the plurality of processors in the node, the clients dedicated to processing incoming data packets, wherein information is passed from the master MPLS server to the one or more MPLS clients.

32. The network routing node of claim 31 wherein the clients dedicated to processing incoming data packets comprise line cards (LC) with processors, the LCs each comprising one or more ports interfacing with the network for receiving and sending data packets, and control cards (CC) with processors, the CCs for providing control functions, and the MPLS servers are established on control cards.

33. The network routing node of claim 30 wherein the processors upon which MPLS servers are established are control cards (CC) with processors, the CCs for providing control functions, and the SDM is established on a CC other than those upon which MPLS servers are established.

34. The network routing node of claim 33 wherein a primary SDM is established on a first global master CC (GMCC) and a backup SDM is established on a global backup CC (GBCC), and wherein the global backup becomes the global master in the event of failure of the global master.

35. The network routing node of claim 34 wherein, once a GBCC becomes a GMCC, a new GBCC is established and enabled.

36. The network routing node of claim 29 wherein, once the backup MPLS server has become the master MPLS server, a new backup MPLS server is designated and enabled.

37. The network routing node of claim 32 wherein, once a backup MPLS CC has become the Master MPLS CC, a new backup MPLS CC is designated and enabled.

38. The network routing node of claim 29 wherein the network is the Internet network.

39. The network routing node of claim 29 wherein the MPLS server application is configured with a resource reservation protocol (RSVP) stack.

40. The network routing node of claim 30 wherein the MPLS server applications are included with the SDM in a bootable software image.

41. The network routing node of claim 34 wherein the GMCC determines server assignments at startup of the routing node.

42. The network routing node of claim 41 wherein state information and data structures are copied from the MPLS master server to the MPLS backup server at startup of the routing node after server task assignment and initialization.