Method and apparatus for managing clustered computer systems

• US 6,393,485 B1
• Filed: 10/27/1998
• Issued: 05/21/2002
• Est. Priority Date: 10/27/1998
• Status: Expired due to Term

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Goal, Patrick M., Chao, Ching-Yun, McCarty, Richard James
• Primary Examiner(s): Harrell, Robert B.
• Application Number:
  US09/181,825
• Time in Patent Office: 1,302 Days
• Field of Search: 709/200, 709/202, 709/203, 709/105, 709/208, 709/209, 709/210, 709/217, 709/218, 709/219, 709/231, 714/4, 714/2, 714/22, 714/3, 714/6
• US Class Current: 709/231
• CPC Class Codes: G06F 11/1425 by reconfiguration of node membership
• CPC Class Codes: G06F 11/1482 by means of middleware or OS functionality
• CPC Class Codes: G06F 11/183 by voting, the voting not being performed by the redundant components
• CPC Class Codes: G06F 11/2023 Failover techniques
• CPC Class Codes: G06F 11/2046 where the redundant components share persistent storage G06F11/2043 takes precedence
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1029 using data related to the state of servers by a load balancer
• CPC Class Codes: H04L 67/1031 Controlling of the operation of servers by a load balancer, e.g. adding or removing servers that serve requests
• CPC Class Codes: H04L 67/1034 Reaction to server failures by a load balancer
• CPC Class Codes: H04L 69/329 in the application layer [OSI layer 7]
• CPC Class Codes: H04L 9/40 Network security protocols

Abstract

A clustered computer system provides both speed and reliability advantages. However, when communications between the clustered computers is compromised those same computers can become confused and corrupt database files. The present method and apparatus are used to improve the management of clustered computer systems. Specifically, the system expands the number of nodes available for failover conditions.

Claims

1. A data processing system comprising:

(a) means for establishing a multi-cluster comprising at least a first cluster, wherein the first cluster comprises at least a first node, and a second cluster, wherein the second cluster comprises at least a second node;

(b) means for managing the first cluster with a first cluster services program and managing the second cluster with a second cluster services program; and

(c) means for managing inter-node communication between the first node and the second node with a multi-cluster services program.

2. The data processing system of claim 1 wherein (c) comprises means for initiating the multi-cluster services program automatically when the first node is booted.

3. The data processing system of claim 2 further comprises means initiating the first cluster services program resident on the first node after initiating the multi-cluster services program.

4. The data processing system of claim 3 wherein the multi-cluster services program and the first cluster services program are binary compatible.

5. The data processing system of claim 1 further comprises:

(d) means for failing over between the first node and the second node within the multi-cluster.

6. The data processing system of claim 5 wherein (d) comprises means for updating a cluster wide data file.

7. The data processing system of claim 1 wherein the multi-cluster services program manages using a resource API within the first node and the second node.

8. The data processing system of claim 1 wherein (a) comprises means for establishing a multi-cluster of at least three nodes.

9. The data processing system of claim 1 wherein (c) comprises means for managing a cluster node membership database.

10. The data processing system of claim 1 wherein (c) comprises means for managing a heartbeat signal sent between the first node and the second node within the multi-cluster.

11. The data processing system of claim 1 further comprises means for presenting an image of a single cluster with a cluster manager.

12. A method of managing a clustered computer system, said method comprising the steps of:

(a) establishing a multi-cluster comprising at least a first cluster, wherein the first cluster comprises at least a first node, and a second cluster, wherein the second cluster comprises at least a second node;

(b) managing the first cluster with a first cluster services program and managing the second cluster with a second cluster services program; and

(c) managing inter-node communication between the first node and the second node with a multi-cluster services program.

13. The method of claim 12 wherein step (c) comprises initiating the multi-cluster services program automatically when the first node is booted.

14. The method of claim 13 further comprises initiating the first cluster services program resident on the first node after initiating the multi-cluster services program.

15. The method of claim 14 wherein the multi-cluster services program and the first cluster services program are binary compatible.

16. The method of claim 12 further comprises:

(d) failing over between the first node and the second node within the multi-cluster.

17. The method of claim 16 further comprises:

(d) failing back to said first node.

18. The method of claim 16 wherein step (d) comprises updating a cluster wide data file.

19. The method of claim 12 wherein the multi-cluster services program manages using a resource API within the first node and the second node.

20. The method of claim 12 wherein step (a) comprises establishing a multi-cluster of at least three nodes.

21. The method of claim 12 wherein step (c) comprises managing a cluster node membership database.

22. The method of claim 12 wherein step (c) comprises managing a heartbeat signal sent between the first node and the second node within the multi-cluster.

23. The method of claim 12 further comprises presenting an image of a single cluster with a cluster manager.

24. A computer program product for executing a method in a data processing system,

(a) first instructions for establishing a multi-cluster comprising at least a first cluster, wherein the first cluster comprises at least a first node, and a second cluster, wherein the second cluster comprises at least a second node;

(b) second instructions for managing the first cluster with a first cluster services program and managing the second cluster with a second cluster services program; and

(c) third instructions for managing inter-node communication between the first node and the second node with a multi-cluster services program.

25. The computer program product of claim 24 further comprises:

(d) fourth instructions for failing over between the first node and the second node within the multi-cluster.

26. The computer program product of claim 24 wherein said third instruction further comprises instructions for managing a cluster node membership database.

27. The computer program product of claim 24 wherein said third instructions further comprises instructions for managing a heartbeat signal sent between the first node and the second node within the multi-cluster.