Cluster availability management

• US 10,394,672 B2
• Filed: 03/25/2011
• Issued: 08/27/2019
• Est. Priority Date: 06/28/2005
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Armstrong, William Joseph, Hartung, Michael Howard, Hsu, Yu-Cheng, Wightwick, Glenn Rowan
• Primary Examiner(s): Truong, Loan L. T.
• Application Number:
  US13/072,307
• Publication Number:
  US 20110173493A1
• Time in Patent Office: 3,077 Days
• Field of Search: 714 39, 714 13, 714 61
• CPC Class Codes: G06F 11/2028 eliminating a faulty processor or activating a spare
• CPC Class Codes: G06F 11/2033 switching over of hardware resources
• CPC Class Codes: G06F 11/2046 where the redundant components share persistent storage G06F11/2043 takes precedence

Abstract

A first logical partition in a first processing complex of a server cluster is operated in an active mode and a second logical partition in the processing complex is operated in a standby mode. Upon detection of a failure in a second processing complex of the server cluster. the standby mode logical partition in the first processing complex is activated to an active mode. In one embodiment, partition resources are transferred from an active mode logical partition to the logical partition activated from standby mode. Other embodiments are described and claimed.

Claims

1. A method, comprising:

operating a first logical partition having transferable partition resources in a first physical processing complex of a server cluster in an active mode which includes operating an operating system and actively performing input/output operations between a host and a storage system, and a second logical partition having transferable partition resources in the same first physical processing complex and in a quiesced standby mode which includes operating an operating system but is otherwise substantially inactive as compared to said active mode wherein the transferable partition resources transferred to the second logical partition in the quiesced standby mode are reduced as compared to the transferrable partition resources transferred to the first logical partition in the active mode;

detecting a failure in a second physical processing complex different from the first physical processing complex of the server cluster;

in response to said failure detection, activating the standby logical partition in the first physical processing complex to operate in an active mode so that both the first and second logical partitions of the first physical processing complex operate in the active mode; and

subsequent to activating the second logical partition, transferring partition resources from the first logical partition to the second logical partition while the first logical partition remains in the active mode;

wherein said active mode operating includes providing access to a shared resource of data storage disk drives for a logical partition operating in an active mode and wherein said quiesced standby mode operating includes denying access to said shared resource of data storage disk drives for a logical partition operating in a quiesced standby mode.

2. The method of claim 1 further comprising:

repairing said second processing complex; and

in response to said repair, quiescing the second logical partition to operate in a quiesced standby mode.

3. The method of claim 1, further comprising:

reducing the partition resources of the first logical partition; and

subsequent to activating the second logical partition, increasing the partition resources of the second logical partition.

4. The method of claim 2, further comprising:

subsequent to the repair of the second processing complex, transferring partition resources from the second logical partition to the first logical partition.

5. The method of claim 2, further comprising:

reducing the partition resources of the second logical partition; and

subsequent to the repair of the second processing complex, increasing the partition resources of the first logical partition.

6. The method of claim 1 further comprising:

repairing said second processing complex;

subsequent to the repair of the second processing complex, transferring partition resources from the second logical partition to the first logical partition; and

quiescing the second logical partition to operate back in the quiesced standby mode.

7. The method of claim 1 wherein said partition resources include processing, memory and input/output adapter resources.

8. A system for use with a host and a storage system, comprising:

a server cluster having a first physical processing complex and a second physical processing complex, said first processing complex having a first logical partition having an operating system and transferable partition resources including shared resource data storage drives, and a second logical partition in the same first physical processing complex, having an operating system and transferable partition resources, said server cluster having logic adapted to;

operate said first logical partition in an active mode which includes operating an operating system and actively performing input/output operations between a host and a storage system, and said second logical partition in a quiesced standby mode which includes operating an operating system but is otherwise substantially inactive as compared to said active mode wherein the transferable partition resources transferred to the second logical partition in the quiesced standby mode are reduced as compared to the transferable partition resources transferred to the first logical partition in the active mode;

detect a failure in said second processing complex different from the first physical processing complex;

in response to said failure detection, activate said second logical partition from said quiesced standby mode to operate in an active mode so that both the first and second logical partitions of the first processing complex operate in the active mode; and

subsequent to activating the second logical partition, transfer partition resources from the first logical partition to the second logical partition while the first logical partition remains in the active mode;

wherein operating in the active mode includes providing access to shared resource data storage disk drives for a logical partition operating in an active mode and wherein operating in said quiesced standby mode includes denying access to said shared resource data storage disk drives for a logical partition operating in a quiesced standby mode.

9. The system of claim 8 wherein said server cluster logic is further adapted to, in response to repair of the second processing complex, quiesce the second logical partition from the active mode to operate in a quiesced standby mode.

10. The system of claim 8, wherein said first logical partition has partition resources, and said server cluster logic is further adapted to:

reduce the partition resources of the first logical partition; and

subsequent to activation of the second logical partition, increase the partition resources of the second logical partition.

11. The system of claim 9, wherein said second logical partition has partition resources and wherein said server cluster logic is further adapted to, subsequent to the repair of the second processing complex, transfer partition resources from the second logical partition to the first logical partition.

12. The system of claim 8, wherein said second logical partition has partition resources and wherein said server cluster logic is further adapted to:

reduce the partition resources of the second logical partition; and

subsequent to repair of the second processing complex, increase the partition resources of the first logical partition.

13. The system of claim 8 wherein said first logical partition has partition resources, and said server cluster logic is further adapted to:

subsequent to repair of the second processing complex, transfer partition resources from the second logical partition to the first logical partition; and

quiesce the second logical partition from the active mode to operate back in the quiesced standby mode.

14. The system of claim 8 wherein said partition resources include processing, memory and input/output adapter resources.

15. An article of manufacture, comprising:

a computer readable storage medium having computer readable program code enabled to be executed by a system to perform operations, wherein the system has a server cluster having a first physical processing complex and a second physical processing complex, said first processing complex having a first logical partition having transferable partition resources including shared resource data storage drives and a second logical partition having transferable partition resources, and wherein the system executed operations comprise;

operating said first logical partition in an active mode which includes operating an operating system and actively performing input/output operations between a host and a storage system and said second logical partition in a quiesced standby mode which includes operating an operating system but is otherwise substantially inactive as compared to said active mode wherein the transferable partition resources transferred to the second logical partition in the quiesced standby mode are reduced as compared to the transferable partition resources transferred to the first logical partition in the active mode;

detecting a failure in said second processing complex different from the first physical processing complex;

in response to said failure detection, activating said second logical partition from said quiesced standby mode to operate in an active mode so that both the first and second logical partitions of the first processing complex operate in the active mode; and

subsequent to activating the second logical partition, transferring partition resources from the first logical partition to the second logical partition while the first logical partition remains in the active mode;

wherein said active mode operating includes providing access to a shared resource of data storage disk drives for a logical partition operating in an active mode and wherein said quiesced standby mode operating includes denying access to said shared resource of data storage disk drives for a logical partition operating in a quiesced standby mode.

16. The article of claim 15 and wherein said system executed operations further comprise:

repairing said second processing complex; and

in response to repair of the second processing complex, quiescing the second logical partition from the active mode to operate in a quiesced standby mode.

17. The article of claim 15, wherein said first logical partition has partition resources, and wherein said system executed operations further comprise:

reducing the partition resources of the first logical partition; and

subsequent to activation of the second logical partition, increasing the partition resources of the second logical partition.

18. The article of claim 16, wherein said second logical partition has partition resources and wherein said system executed operations further comprise, subsequent to the repair of the second processing complex, transferring partition resources from the second logical partition to the first logical partition.

19. The article of claim 16, wherein said second logical partition has partition resources and wherein said system executed operations further comprise:

reducing the partition resources of the second logical partition; and

subsequent to the repair of the second processing complex, increasing the partition resources of the first logical partition.

20. The article of claim 15 wherein said first logical partition has partition resources, and wherein said system executed operations further comprise:

subsequent to repair of the second processing complex, transferring partition resources from the second logical partition to the first logical partition; and

quiescing the second logical partition from the active mode to operate back in the quiesced standby mode.

21. The article of claim 15 wherein said partition resources include processing, memory and input/output adapter resources.

22. A method for deploying computing instructions, comprising:

integrating computer-readable code into a system, wherein the system has a server cluster having a first physical processing complex and a second physical processing complex, said first processing complex having a first logical partition and a second logical partition, and wherein the code in combination with the system is enabled to cause the system to perform;

operating said first logical partition having transferable partition resources in an active mode which includes operating an operating system and actively performing input/output operations between a host and a storage system and said second logical partition having transferable partition resources in a quiesced standby mode which includes operating an operating system but is otherwise substantially inactive as compared to said active mode wherein the transferable partition resources transferred to the second logical partition in the quiesced standby mode are reduced as compared to the transferrable partition resources transferred to the first logical partition in the active mode;

detecting a failure in said second processing complex different from the first physical processing complex;

in response to said failure detection, activating said second logical partition from said quiesced standby mode to operate in an active mode so that both the first and second logical partitions of the first processing complex operate in the active mode; and

subsequent to activating the second logical partition, transferring partition resources from the first logical partition to the second logical partition while the first logical partition remains in the active mode;

wherein said active mode operating includes providing access to a shared resource of data storage disk drives for a logical partition operating in an active mode and wherein said quiesced standby mode operating includes denying access to said shared resource of data storage disk drives for a logical partition operating in a quiesced standby mode.

23. The method of claim 22 and wherein the code in combination with the system is further enabled to cause the system to perform:

repairing said second processing complex; and

in response to repair of the second processing complex, quiescing the second logical partition from the active mode to operate in a quiesced standby mode.

24. The method of claim 22, wherein said first logical partition has partition resources, and wherein the code in combination with the system is further enabled to cause the system to perform:

reducing the partition resources of the first logical partition; and

subsequent to activation of the second logical partition, increasing the partition resources of the second logical partition.

25. The method of claim 23, wherein said second logical partition has partition resources and wherein the code in combination with the system is further enabled to cause the system to perform, subsequent to the repair of the second processing complex, transferring partition resources from the second logical partition to the first logical partition.

26. The method of claim 23, wherein said second logical partition has partition resources and wherein the code in combination with the system is further enabled to cause the system to perform:

reducing the partition resources of the second logical partition; and

subsequent to the repair of the second processing complex, increasing the partition resources of the first logical partition.

27. The method of claim 22 wherein said first logical partition has partition resources, and wherein the code in combination with the system is further enabled to cause the system to perform:

subsequent to repair of the second processing complex, transferring partition resources from the second logical partition to the first logical partition; and

quiescing the second logical partition from the active mode to operate back in the quiesced standby mode.

28. The method of claim 22 wherein said partition resources include processing, memory and input/output adapter resources.