Method and system for resource monitoring of disparate resources in a server cluster

• US 6,178,529 B1
• Filed: 11/03/1997
• Issued: 01/23/2001
• Est. Priority Date: 11/03/1997
• Status: Expired due to Term

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Short, Robert T., Massa, Michael T., Vert, John D., Gamache, Rod
• Primary Examiner(s): Beausoliel, Jr., Robert W.
• Assistant Examiner(s): REVAK, CHRISTOPHER A
• Application Number:
  US08/963,049
• Time in Patent Office: 1,177 Days
• Field of Search: 714/47, 714/39, 714/51, 714/48, 714/49, 714/25, 714/15, 709/100, 709/104, 709/223, 709/226, 709/304, 709/229, 709/224, 709/331, 709/332, 717/11, 717/10, 707/203, 707/202
• US Class Current: 714/51
• CPC Class Codes: G06F 11/2025 using centralised failover control functionality
• CPC Class Codes: G06F 11/2038 with a single idle spare processing component
• CPC Class Codes: G06F 11/2041 with more than one idle spare processing component
• CPC Class Codes: G06F 11/2046 where the redundant components share persistent storage G06F11/2043 takes precedence

Abstract

A method and system in a server cluster for monitoring and controlling a resource object, such as a physical device or application. A cluster service connects to a resource monitoring component to control and monitor the health of one or more resource objects. The resource component includes a plurality of methods, common to all such resource components, for calling by the resource monitor to control and monitor operation of the resource object therethrough. The common methods enable the cluster server to treat all resources similarly without regard to the type of resource.

Claims

1. In a server cluster having resource objects of different types, a system for monitoring and controlling a resource object, comprising, a cluster service, a resource component connected to the resource object for management thereof, the resource component including a plurality of methods common to resource components for calling by the cluster service to control operation of the resource object and monitor for states of the resource object therethrough, the resource object monitored for states common to the other resource objects of the server cluster independent of the type of each other resource object.

2. The system of claim 1 wherein the resource component comprises a dynamic link library.

3. The system of claim 1 wherein the resource component is connected to the cluster service through a resource monitor.

4. The system of claim 1 wherein one of the plurality of common methods causes the resource component to make the resource object available to a node of the cluster.

5. The system of claim 1 wherein the resource object comprises a physical device.

6. The system of claim 1 wherein the resource object comprises an application.

7. The system of claim 1 wherein the resource object comprises data.

8. The system of claim 1 wherein the resource object comprises a logical construct.

9. The system of claim 1 wherein the plurality of common methods includes an open command to create an instance of the resource component and a close command to close the instance of the resource.

10. The system of claim 1 wherein one of the plurality of common methods causes the resource component to make the resource object unavailable to a node of the cluster.

11. The system of claim 1 wherein one of the plurality of common methods causes the resource component to forcefully terminate the operation of the resource object.

12. The system of claim 1 wherein one of the plurality of common methods is periodically issued by the resource monitor to cause the resource component to check on the status of the resource object.

13. The system of claim 1 wherein the resource component includes means for asynchronously reporting an error in the resource object.

14. The system of claim 1 wherein the common set of methods comprise open, close, online, offline and terminate methods.

15. The system of claim 1 wherein the common set of states comprise at least one of an offline, offline pending, online, online pending and failed state.

16. The system of claim 1 wherein the common set of states comprise online and failed states, and wherein the cluster service changes the state of the resource object from a failed state to an online state.

17. The system of claim 16 wherein the cluster service changes the state of the resource object to the online state by moving the resource object to another server of the cluster.

18. In a server cluster, a process for monitoring a resource object, comprising, providing a cluster service, running a resource component for management of the resource object, the resource component including a plurality of methods common to resource components, and calling at least one of the methods of the resource component to monitor for states of the resource object therethrough, the resource object monitored for states included in a set of states, the set of states defined relative to a version and being independent of the type of the resource objects.

19. The process of claim 18 wherein running a resource component includes loading a dynamic link library.

20. The process of claim 18 further comprising calling at least one of the methods in the resource component to make the resource object available to a node of the cluster.

21. The process of claim 20 wherein the resource object is an application, and further comprising running the application on a node of the cluster in response to the method call.

22. The process of claim 18 further comprising calling at least one of the methods in the resource component to make the resource object unavailable to a node of the cluster.

23. The process of claim 18 further comprising calling at least one of the methods in the resource component to create an instance of the resource component.

24. The process of claim 18 further comprising calling at least one of the methods in the resource component to forcefully terminate the operation of the resource object.

25. The process of claim 18 wherein calling at least one of the methods of the resource component to monitor the state of the resource object includes periodically calling the resource component to check on the status of the resource object.

26. The process of claim 18 wherein calling at least one of the methods of the resource component to monitor the state of the resource object includes reporting an error in the resource object by an asynchronous callback from the resource component.

27. The process of claim 18 wherein the common set of methods comprise open, close, online, offline and terminate methods.

28. The process of claim 18 wherein the common set of states comprise at least one of an offline, offline pending, online, online pending and failed state.

29. The process of claim 18 wherein the common set of states comprise online and failed states, and further comprising changing the state of the resource object from a failed state to an online state.

30. The process of claim 29 wherein changing the state of the resource object to the online state includes moving the resource object to another server of the cluster.

31. The process of claim 18 further comprising controlling the resource object based on the state thereof.

32. In a server cluster having resource objects of different types, a process comprising, providing a resource component for each resource object, each resource component including a plurality of methods common to resource components, running the resource component, and monitoring the state of a resource object through at least one of the methods, the resource object monitored for states in a set of states common to other resource objects of the server cluster independent of the types of the other resource objects.

33. The process of claim 32 wherein monitoring the state of the resource object includes periodically calling the resource component to check on the status of the resource object.

34. The process of claim 32 wherein monitoring the state of the resource object includes reporting an error in the resource object by an asynchronous callback from the resource component.

35. The process of claim 32 wherein monitoring the state of the resource object includes determining whether a function completes before a predetermined time duration.

36. The process of claim 35 further comprising, starting a thread when the function fails to complete before the predetermined time duration.

37. The process of claim 36 wherein the thread completes a request with an error pending message.

38. The process of claim 32 wherein the common set of methods comprise open, close, online, offline and terminate methods.

39. The process of claim 32 wherein the common set of states comprise at least one of an offline, offline pending, online, online pending and failed state.

40. The process of claim 32 wherein the common set of states comprise online and failed states, and further comprising changing the state of the resource object from a failed state to an online state.

41. The process of claim 40 wherein changing the state of the resource object to the online state includes moving the resource object to another server of the cluster.

42. The process of claim 32 further comprising controlling the resource object based on the state thereof.

43. A computer-readable medium including computer-executable instructions, comprising:

providing a resource object in a server cluster;

running a resource component in the server cluster, the resource component including a plurality of methods common to resource components; and

monitoring for at least one state of the resource object by calling at least one of the methods of the resource component, the at least one state being included in a set of states that is defined relative to a version and is common to resource objects of the server cluster independent of their type.

44. The computer-readable medium including computer-executable instructions of claim 43, wherein running a resource component includes loading a dynamic link library.

45. The computer-readable medium including computer-executable instructions of claim 43, wherein monitoring the state of the resource object includes periodically calling the resource component.

46. The computer-readable medium of claim 43 including further computer-executable instructions for, reporting an error in the resource object by an asynchronous callback from the resource component.

47. The computer-readable medium including computer-executable instructions of claim 43, wherein monitoring the state of the resource object includes determining whether a function completes before a time duration.

48. The computer-readable medium of claim 47 including further computer-executable instructions for, starting a thread when the function fails to complete before the time duration.

49. The computer-readable medium including computer-executable instructions of claim 48, wherein the thread completes a request with an error pending message.

50. The computer-readable medium of claim 43 including further computer-executable instructions for, calling at least one of the methods in the resource component to make the resource object available to a node of the cluster.

51. The computer-readable medium of claim 43 including further computer-executable instructions for, calling at least one of the methods in the resource component to make the resource object unavailable to a node of the cluster.

52. The computer-readable medium of claim 43 including further computer-executable instructions for, calling at least one of the methods in the resource component to forcefully terminate the operation of the resource object.

53. The computer-readable medium of claim 43 including further computer-executable instructions comprising controlling the resource object based on the state thereof.