Method and system for stateful switch-over in a high-availability point to point system

• US 7,363,534 B1
• Filed: 09/30/2002
• Issued: 04/22/2008
• Est. Priority Date: 09/30/2002
• Status: Expired due to Fees

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Krishnamurthy, Ramesh, Haag, Jeffrey D.
• Primary Examiner(s): Lohn; Joshua A.
• Application Number:
  US10/260,771
• Time in Patent Office: 2,031 Days
• Field of Search: 714/4, 714/10, 714/13
• US Class Current: 714/13
• CPC Class Codes: G06F 11/2028 eliminating a faulty processor or activating a spare
• CPC Class Codes: G06F 11/203 using migration
• CPC Class Codes: H04L 69/16 Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
• CPC Class Codes: H04L 69/168 specially adapted for link layer protocols, e.g. asynchronous transfer mode [ATM], synchronous optical network [SONET] or point-to-point protocol [PPP]

Abstract

A method and system for stateful switch-over in a high-availability point to point system is disclosed. The disclosed method includes in one embodiment detecting a change in state of a point to point link between a first peer data processing system and a second peer data processing system; storing state data for the point to point link with an active processor within the first peer data processing system in response to detecting the change in state; and transferring a copy of the state data to a standby processor within the first peer data processing system. The disclosed method includes in another embodiment, transferring data between the first peer data processing system and the second peer data processing system utilizing the active processor; detecting a switch-over condition; and transferring data between the first peer data processing system and the second peer data processing system utilizing the standby processor in response to detecting the switch-over condition.

Claims

1. A method comprising:

detecting a change in state of a point to point link between a first peer data processing system and a second peer data processing system, wherein said detecting comprises detecting an authentication of said point to point link;

in response to said detecting, storing state data for said point to point link with an active processor within said first peer data processing system, wherein

said storing comprises storing an authenticated peer data processing system name;

in response to said storing, transferring a copy of said state data to a standby processor within said first peer data processing system;

detecting a switch-over condition, wherein

said detecting a switch-over condition comprises detecting a hardware failure of said active processor;

transferring data between said first peer data processing system and said second peer data processing system utilizing said active processor; and

transferring said data between said first peer data processing system and said second peer data processing system utilizing said standby processor in response to said detecting said switch-over condition.

2. The method of claim 1, wherein,

said detecting comprises,

detecting a network control protocol open event.

3. The method of claim 1, wherein,

said detecting comprises,

detecting a link control protocol close event.

4. The method of claim 1, wherein,

said detecting comprises,

detecting a network control protocol close event.

5. The method of claim 1, wherein,

said storing comprises,

storing a configuration acknowledgment packet transferred between said first peer data processing system and said second peer data processing system.

6. The method of claim 1, wherein,

said storing comprises,

storing a negotiated network-layer protocol address.

7. The method of claim 1, wherein,

said transferring comprises,

transferring a state data message including at least one attribute/value pair from said active processor to said standby processor.

8. The method of claim 1, wherein,

said detecting a switch-over condition comprises,

detecting a software failure of said active processor.

9. The method of claim 1, wherein,

said detecting a switch-over condition comprises,

detecting an administrator-initiated switch-over command.

10. A method comprising:

maintaining state data for a point to point link between a first peer data processing system and a second peer data processing system with both an active processor and a standby processor within said first peer data processing system, wherein

said maintaining comprises

storing said state data with said active processor in response to detecting said change in state, and

performing transferring said copy of said state data to said standby processor in response to storing said state data with said active processor, and

said storing comprises storing an authenticated peer data processing system name;

transferring data between said first peer data processing system and said second peer data processing system utilizing said active processor;

detecting a switch-over condition, wherein

said detecting comprises detecting a hardware failure of said active processor;

detecting a change in state of said point to point link, wherein said detecting a change in state of said point to point link comprises detecting an authentication of said point to point link; and

in response to said detecting said switch-over condition, transferring data between said first peer data processing system and said second peer data processing system utilizing said standby processor, wherein said maintaining state data comprises copying said state data in response to detecting said switch-over condition.

11. The method of claim 10, wherein,

said detecting a change in state of said point to point link comprises,

detecting a network control protocol open event.

12. The method of claim 10, wherein,

said detecting a change in state of said point to point link comprises,

detecting a link control protocol close event.

13. The method of claim 10, wherein,

said detecting a change in state of said point to point link comprises,

detecting a network control protocol close event.

14. The method of claim 10, wherein,

said storing comprises,

storing a configuration acknowledgment packet transferred between said first peer data processing system and said second peer data processing system.

15. The method of claim 10, wherein,

said storing comprises,

storing a negotiated network-layer protocol address.

16. The method of claim 10, wherein,

said transferring a copy of said state data to said standby processor comprises,

transferring a state data message including at least one attribute/value pair from said active processor to said standby processor.

17. The method of claim 10, wherein,

said maintaining comprises,

storing said state data for said point to point link with both said active processor and said standby processor;

and

dynamically updating said state data with both said active processor and said standby processor.

18. The method of claim 17, wherein,

said storing comprises,

storing a configuration acknowledgment packet transferred between said first peer data processing system and said second peer data processing system.

19. The method of claim 17, wherein,

said storing comprises,

storing an authenticated peer data processing system name.

20. The method of claim 17, wherein,

said storing comprises,

storing a negotiated network-layer protocol address.

21. The method of claim 10, wherein,

said detecting comprises,

detecting a software failure of said active processor.

22. The method of claim 10, wherein,

said detecting comprises,

detecting an administrator-initiated switch-over command.

23. A method comprising:

configuring a point to point link between a first peer data processing system and a second peer data processing system, said first peer data processing system including an active processor and a standby processor;

detecting a change in state of said point to point link, wherein

said detecting a change in state of said point to point link comprises

detecting an authentication of said point to point link, and

detecting a switch-over condition, and

said switch-over condition comprises detecting a hardware failure of said active processor;

storing state data for said point to point link with both said active processor and said standby processor, wherein

said storing state data comprises

transferring a copy of said state data to said standby processor in response to storing said state data at said active processor, and

storing an authenticated peer data processing system name;

dynamically updating said state data with both said active processor and said standby processor; and

transferring data between said first peer data processing system and said second peer data processing system utilizing said standby processor in response to detecting a switch-over condition.

24. The method of claim 23, wherein,

said configuring comprises,

transferring a configuration request packet and a configuration acknowledgment packet between said first peer data processing system and said second peer data processing system.

25. The method of claim 24, wherein,

said storing comprises,

storing a configuration acknowledgment packet transferred between said first peer data processing system and said second peer data processing system.

26. The method of claim 24, wherein,

said storing comprises,

storing a negotiated network-layer protocol address.

27. A computer-readable storage medium having a plurality of instructions executable by a computer embodied therein, wherein said plurality of instructions when executed cause said computer to perform a method comprising:

detecting a change in state of a point to point link between a first peer data processing system and a second peer data processing system, wherein said detecting a change in state of said point to point link comprises, detecting an authentication of said point to point link;

in response to said detecting, storing state data for said point to point link with an active processor within said first peer data processing system, wherein

said storing comprises storing state data for said point to point link selected from a group consisting of;

a configuration acknowledgment packet transferred between said first peer data Processing system and said second peer data processing system, an authenticated peer data processing system name, and a negotiated network-layer protocol address;

in response to said storing, transferring a copy of said state data to a standby processor within said first peer data processing system;

transferring data between said first peer data processing system and said second peer data processing system utilizing said active processor;

detecting said switch-over condition, wherein

said detecting a switch-over condition comprises detecting a switch-over condition selected from a group consisting of;

a hardware failure of said active processor, a software failure of said active processor, and an administrator-initiated switch-over command; and

transferring said data between said first peer data Processing system and said second peer data processing system utilizing said standby processor in response to said detecting said switch-over condition.

28. The computer-readable storage medium of claim 27, wherein,

said detecting comprises,

detecting a change in state of said point to point link selected from a group consisting of:

a network control protocol open event, a link control protocol close event, and a network control protocol close event.

29. The computer-readable storage medium of claim 27, wherein,

said transferring comprises,

transferring a state data message including at least one attribute/value pair from said active processor to said standby processor.

30. A computer-readable storage medium having a plurality of instructions executable by a computer embodied therein, wherein said plurality of instructions when executed cause said computer to perform a method comprising:

maintaining state data for a point to point link between a first peer data processing system and a second peer data processing system with both an active processor and a standby processor within said first peer data processing system, wherein

said maintaining comprises

storing said state data with said active processor in response to detecting said change in states, and

performing transferring said copy of said state data to said standby processor in response to storing said state data with said active processor, and

said storing comprises storing an authenticated peer data processing system name;

transferring data between said first peer data processing system and said second peer data processing system utilizing said active processor;

detecting a switch-over condition, wherein

said detecting a switch-over condition is selected from a group consisting of;

a hardware failure of said active processor, a software failure of said active processor, and an administrator-initiated switch-over command;

detecting a change in state of said point to point link, wherein said detecting a change in state of said point to point link comprises detecting an authentication of said point to point link; and

in response to said detecting said switch-over condition, transferring data between said first peer data processing system and said second peer data processing system utilizing said standby processor, wherein said maintaining state data comprises copying said state data in response to detecting said switch-over condition.

31. The computer-readable storage medium of claim 30, wherein,

said detecting a change in state of said point to point link comprises,

detecting a change in state of said point to point link selected from a group consisting of:

a network control protocol open event, a link control protocol close event, and a network control protocol close event.

32. The computer-readable storage medium of claim 30, wherein,

said transferring a copy of said state data to said standby processor comprises,

transferring a state data message including at least one attribute/value pair from said active processor to said standby processor.

33. The computer-readable storage medium of claim 30, wherein,

said maintaining comprises,

storing said state data for said point to point link with both said active processor and said standby processor;

and

dynamically updating said state data with both said active processor and said standby processor.

34. The computer-readable storage medium of claim 33, wherein,

said storing comprises,

storing state data for said point to point link selected from a group consisting of:

a configuration acknowledgment packet transferred between said first peer data processing system and said second peer data processing system, an authenticated peer data processing system name, and a negotiated network-layer protocol address.

35. A computer-readable storage medium having a plurality of instructions executable by a computer embodied therein, wherein said plurality of instructions when executed cause said computer to perform a method comprising:

configuring a point to point link between a first peer data processing system and a second peer data processing system, said first peer data processing system including an active processor and a standby processor;

detecting a change in state of said point to point link, wherein

said detecting a change in state of said point to point link comprises

detecting an authentication of said point to point link, and

detecting a switch-over condition, and

said switch-over condition comprises detecting a hardware failure of said active processor;

storing state data for said point to point link with both said active processor and said standby processor, wherein

said storing state data comprises

transferring a copy of said state data to said standby processor in response to storing said state data at said active processor, and

storing state data for said point to point link selected from a group consisting of;

a configuration acknowledgment packet transferred between said first peer data processing system and said second peer data processing system, an authenticated peer data processing system name, and a negotiated network-layer protocol address;

dynamically updating said state data with both said active processor and said standby processor; and

transferring data between said first peer data processing system and said second peer data processing system utilizing said standby processor in response to detecting a switch-over condition.

36. The computer-readable storage medium of claim 35, wherein,

said configuring comprises,

transferring a configuration request packet and a configuration acknowledgment packet between said first peer data processing system and said second peer data processing system.

37. An apparatus comprising:

means for detecting a change in state of a point to point link between a first peer data processing system and a second peer data processing system, wherein said detecting a change in state of said point to point link comprises, detecting an authentication of said point to point link;

means for storing state data for said point to point link with an active processor within said first peer data processing system in response to a detection of a change in state of said point to point link, wherein

said means for storing comprises means for storing state data for said point to point link selected from a group consisting of;

a configuration acknowledgment packet transferred between said first peer data processing system and said second peer data processing system, an authenticated peer data processing system name, and a negotiated network-layer protocol address;

means for transferring, in response to said state data being stored with said active processor, a copy of said state data to a standby processor within said first peer data processing system;

means for detecting a switch-over condition, wherein

said means for detecting a switch-over condition comprises means for detecting a hardware failure of said active processor; and

means for transferring data between said first peer data processing system and said second peer data processing system utilizing said standby processor in response to said means for detecting said switch-over condition and coupled thereto.

38. The apparatus of claim 37, further comprising,

means for transferring data between said first peer data processing system and said second peer data processing system utilizing said active processor;

means for transferring said data between said first peer data processing system and said second peer data processing system utilizing said standby processor in response to said detection of a switch-over condition.

39. The apparatus of claim 38, wherein,

said means for detecting a switch-over condition comprises,

means for detecting a switch-over condition selected from a group consisting of:

a hardware failure of said active processor, a software failure of said active processor, and an administrator-initiated switch-over command.

40. The apparatus of claim 37, wherein,

said means for detecting comprises,

means for detecting a change in state of said point to point link selected from a group consisting of:

a network control protocol open event, a link control protocol close event, and a network control protocol close event.

41. The apparatus of claim 37, wherein,

said means for transferring comprises,

means for transferring a state data message including at least one attribute/value pair from said active processor to said standby processor.

42. An apparatus comprising:

means for maintaining state data for a point to point link between a first peer data processing system and a second peer data processing system with both an active processor and a standby processor within said first peer data processing system, wherein

said means for maintaining comprises

means for storing said state data with said active processor in response to a detection of a chance in state of said point to point link, and

means for performing transferring said copy of said state data to said standby processor in response to said state data being stored with said active processor, and

said means for storing comprises means for storing state data for said point to point link selected from a croup consisting of;

a configuration acknowledgment packet transferred between said first peer data processing system and said second peer data processing system, an authenticated peer data processing system name, and a negotiated network-layer protocol address;

means for transferring data between said first peer data processing system and said second peer data processing system utilizing said active processor;

means for detecting a switch-over condition, wherein

said means for detecting comprises means for detecting a switch-over condition selected from a group consisting of;

a hardware failure of said active processor, a software failure of said active processor, and an administrator-initiated switch-over command;

means for detecting a change in state of said point to point link, wherein said detecting a change in state of said point to point link comprises, detecting an authentication of said point to point link; and

means for transferring data, in response to a detection of a switch-over condition, between said first peer data processing system and said second peer data processing system utilizing said standby processor, wherein said means for maintaining state data comprises means for copying said state data in response to detecting said switch-over condition.

43. The apparatus of claim 42, wherein,

said means for detecting a change in state of said point to point link comprises,

means for detecting a change in state of said point to point link selected from a group consisting of:

a network control protocol open event, a link control protocol close event, and a network control protocol close event.

44. The apparatus of claim 42, wherein,

said means for transferring a copy of said state data to said standby processor comprises,

means for transferring a state data message including at least one attribute/value pair from said active processor to said standby processor.

45. The apparatus of claim 42, wherein,

said means for maintaining comprises,

means for storing said state data for said point to point link with both said active processor and said standby processor;

and

means for dynamically updating said state data with both said active processor and said standby processor.

46. The apparatus of claim 45, wherein,

said means for storing comprises,

means for storing state data for said point to point link selected from a group consisting of:

a configuration acknowledgment packet transferred between said first peer data processing system and said second peer data processing system, an authenticated peer data processing system name, and a negotiated network-layer protocol address.

47. An apparatus comprising:

means for configuring a point to point link between a first peer data processing system and a second peer data processing system, said first peer data processing system including an active processor and a standby processor;

means for detecting a change in state of said point to point link, wherein

said means for detecting a change in state of said point to point link comprises

detecting an authentication of said point to point link, and

detecting a switch-over condition, and

said switch-over condition comprises detecting a hardware failure of said active processor;

means for storing state data for said point to point link with both said active processor and said standby processor, wherein

said means for storing state data comprises

means for transferring a copy of said state data to said standby processor in response to storing said state data at said active processor, and

means for storing state data for said point to point link selected from a group consisting of;

a configuration acknowledgment packet transferred between said first peer data processing system and said second peer data processing system, an authenticated peer data processing system name, and a negotiated network-layer protocol address;

means for dynamically updating said state data with both said active processor and said standby processor; and

means for transferring data between said first peer data processing system and said second peer data processing system utilizing said standby processor responsive to a detection of a switch-over condition.

48. The apparatus of claim 47, wherein,

said means for configuring comprises,

means for transferring a configuration request packet and a configuration acknowledgment packet between said first peer data processing system and said second peer data processing system.

49. A data processing system comprising:

a line card to provide a point to point link between said data processing system and a peer data processing system, the line card detecting a change in state of said point to point link, wherein said detecting a change in state of said point to point link comprises detecting an authentication of said point to point link;

an active processor coupled to said line card to configure said point to point link, to store state data for said point to point link locally, to transfer data utilizing said point to point link, and to transmit a copy of said state data to a standby processor, wherein

said detecting comprises detecting a hardware failure of said active processor, and

said active processor is configured to maintain state data for said point to point link; and

a standby processor coupled to said active processor to receive said state data, to store said state data locally, to detect a switch-over condition in said active processor, and to transfer data utilizing said point to point link in response to a detection of a switch-over condition in said active processor by copying said state data in response to said detection of said switch-over condition, wherein

both said active processor and said standby processor are within said data processing system,

said detecting comprises detecting a hardware failure of said active processor,

said maintaining comprises

storing said state data with said active processor in response to detecting said change in state, and

performing transferring said copy of said state data to said standby processor in response to storing said state data with said active processor, and

said storing comprises storing an authenticated peer data processing system name.