Autonomic power loss recovery for a multi-cluster storage sub-system

• US 20040255181A1
• Filed: 05/28/2003
• Published: 12/16/2004
• Est. Priority Date: 05/28/2003
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Hsu, Yu-Cheng, Legvold, Vernon J.
• Granted Patent: US 7,085,886 B2
• Time in Patent Office: Days
• US Class Current: 714/2
• CPC Class Codes: G06F 11/1441 Resetting or repowering
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing
• CPC Class Codes: Y10S 707/99948 Application of database or data structure, e.g. distributed, multimedia, or image

Abstract

An improved storage controller and method for storing and recovering data are disclosed. The storage controller includes a first cluster for directing data from a host computer to a storage device and a second cluster for directing data from a host computer to a storage device. A first cache memory is connected to the first cluster and a second cache memory is connected to the second cluster. A first preserved area of memory is connected to the first cluster and a second preserved area of memory is connected to the second cluster. Data is directed to the first cache and backed up to the second preserved area in a normal operating mode. Similarly, data is directed to the second cache and backed up to the first preserved area in the normal operating mode. In the event of a power failure or comparable event, data from the first and second preserved areas are transferred to, and stored on, a first storage device. Additionally, data from the first and second preserved areas are transferred to, and stored on, a second storage device. Thus, upon resumption of normal operation, if one of the clusters subsequently fails to resume normal operations, data from the failed cluster is available through the operating cluster.

Claims

1. A method for storing data in a data processing system having at least one host computer and at least one storage device, the method comprising:

directing that first modified data in a first cluster be stored in a preserved area of memory of the second cluster in a normal operating mode;

directing that second modified data in a second cluster be stored in a preserved portion of memory of the first cluster in the normal operating mode;

directing that the first modified data be stored in a first storage device in a power failure mode;

directing that the second modified data be stored in a second storage device in the power failure mode;

directing that the first modified data be transferred from the preserved area of the second cluster to the second storage device in the power failure mode; and

directing that the second modified data be transferred from the preserved area of the first cluster to the first storage device in the power failure mode;

whereby, if one of the first or second cluster fails to recover after a power failure, the modified data from the failed cluster is available through the other cluster.

2. The method of claim 1, wherein:

directing that the first modified data be transferred from the preserved area of the second cluster to the second storage device in the power failure mode comprises;

directing that the first modified data be transferred from the preserved area of the first cluster to the preserved area of the second cluster; and

directing that the first modified data be transferred from the preserved area of the second cluster to the second storage device; and

directing that the second modified data be transferred from the preserved area of the first cluster to the first storage device in the power failure mode comprises;

directing that the second modified data be transferred from the preserved area of the second cluster to the first preserved area of the first cluster; and

directing that the second modified data be transferred from the preserved area of the first cluster to the first storage device.

3. The method of claim 1, further comprising:

adjusting the capacity of the preserved area of the first cluster to accommodate the first and second modified data; and

adjusting the capacity of the preserved area of the second cluster to accommodate the first and second modified data.

4. The method of claim 1, further comprising:

providing the preserved area of the first cluster with temporary non-volatility means whereby data stored in the preserved area of the first cluster is preserved until such data is transferred to the first storage device; and

providing the preserved area of the second cluster with temporary non-volatility means whereby data stored in the preserved area of the second cluster is preserved until such data is transferred to the second storage device.

5. The method of claim 1, further comprising:

following the end of the power failure mode, attempting to restore the first and second clusters to the normal operating mode; and

if only one of the first or second clusters is restored, operating the data processing system in a modified operation mode whereby the restored cluster performs the function of the failed cluster.

6. A storage controller, comprising:

a first cluster for directing the transfer of data between a host computer and a storage device, the first cluster comprising;

a first cache memory;

a first preserved area of memory;

a first disk device;

a second cluster for directing the transfer of data between a host computer and a storage device, the second cluster comprising;

a second cache memory;

a second preserved area of memory;

a second disk device;

means for directing that first modified data be stored in the preserved area of the second cluster in a normal operating mode;

means for directing that second modified data be stored in the preserved area of the first cluster in the normal operating mode;

means for directing that the first modified data be stored in the first disk device in a power failure mode;

means for directing that the second modified data be stored in the second disk device in the power failure mode;

means for directing that the first modified data be transferred from the preserved area of the second cluster to the second disk device in the power failure mode; and

means for directing that the second modified data be transferred from the preserved area of the first cluster to the first disk device in the power failure mode;

whereby, if one of the first or second cluster fails to recover after a power failure, the modified data from the failed cluster is available through the other cluster.

7. The storage controller of claim 6, wherein:

the first preserved area comprises temporary non-volatility means whereby data stored in the first preserved area is preserved until such data is transferred to the first disk device; and

the second preserved area comprises temporary non-volatility means whereby data stored in the second preserved area is preserved until such data is transferred to the second disk device.

8. The storage controller of claim 6, further comprising:

means for adjusting the capacity of the preserved area of the first cluster to accommodate the first and second modified data; and

means for adjusting the capacity of the preserved area of the second cluster to accommodate the first and second modified data.

9. The storage controller of claim 6, further comprising:

following the end of the power failure mode, means for attempting to restore the first and second clusters to the normal operating mode; and

if only one of the first or second clusters is restored, means for operating the data processing system in a modified operation mode whereby the restored cluster performs the function of the failed cluster.

10. A data processing system, comprising:

at least one host computer;

at least one storage device;

a storage controller, comprising;

a first cluster for directing the transfer of data between a host computer and a storage device, the first cluster comprising;

a first cache memory;

a first preserved area of memory;

a first disk device;

a second cluster for directing the transfer of data between a host computer and a storage device, the second cluster comprising;

a second cache memory;

a second preserved area of memory;

a second disk device;

means for directing that first modified data be stored in the second preserved area in a normal operating mode;

means for directing that second modified data be stored in the first preserved area in the normal operating mode;

means for directing that the first modified data be stored in the first disk device in a power failure mode;

means for directing that the second modified data be stored in the second disk device in the power failure mode;

means for directing that the first modified data be transferred from the preserved area of the second cluster to the second disk device in the power failure mode; and

means for directing that the second modified data be transferred from the preserved area of the first cluster to the first disk device in the power failure mode;

whereby, if one of the first or second cluster fails to recover after a power failure, the modified data from the failed cluster is available through the other cluster.

11. The data processing system of claim 10, wherein:

the first preserved area comprises temporary non-volatility means whereby data stored in the first preserved area is preserved until such data is transferred to the first disk device; and

the second preserved area comprises temporary non-volatility means whereby data stored in the second preserved area is preserved until such data is transferred to the second disk device.

12. The data processing system of claim 10, further comprising:

means for adjusting the capacity of the preserved area of the first cluster to accommodate the first and second modified data; and

means for adjusting the capacity of the preserved area of the second cluster to accommodate the first and second modified data.

13. The data processing system of claim 10, further comprising:

following the end of the power failure mode, means for attempting to restore the first and second clusters to the normal operating mode; and

if only one of the first or second clusters is restored, means for operating the data processing system in a modified operation mode whereby the restored cluster performs the function of the failed cluster.

14. An article of manufacture for use in programming a storage controller to direct the transfer of data between host systems and storage devices, the article of manufacture comprising a storage medium having logic embedded therein to cause components of the storage controller to perform the steps of:

directing that first modified data in a first cluster be stored in a preserved area of memory of the second cluster in a normal operating mode;

directing that second modified data in a second cluster be stored in a preserved portion of memory of the first cluster in the normal operating mode;

directing that the first modified data be stored in a first storage device in a power failure mode;

directing that the second modified data be stored in a second storage device in the power failure mode;

directing that the first modified data be transferred from the preserved area of the second cluster to the second storage device in the power failure mode; and

directing that the second modified data be transferred from the preserved area of the first cluster to the first storage device in the power failure mode;

whereby, if one of the first or second cluster fails to recover after a power failure, the modified data from the failed cluster is available through the other cluster.

15. The article of manufacture of claim 14, wherein the logic further causes components of the storage controller to perform the steps of:

directing that the first modified data be transferred from the preserved area of the second cluster to the second storage device in the power failure mode comprises;

directing that the first modified data be transferred from the preserved area of the first cluster to the preserved area of the second cluster; and

directing that the first modified data be transferred from the preserved area of the second cluster to the second storage device; and

directing that the second modified data be transferred from the preserved area first cluster to the first storage device in the power failure mode comprises;

directing that the second modified data be transferred from the preserved area of the second cluster to the preserved area of the first cluster; and

directing that the second modified data be transferred from the preserved area of the first cluster to the first storage device.

16. The article of manufacture of claim 14, wherein the logic further causes components of the storage controller to perform the steps of:

adjusting the capacity of the preserved area of the first cluster to accommodate the first and second modified data; and

adjusting the capacity of the preserved area of the second cluster to accommodate the first and second modified data.

17. The article of manufacture of claim 14, wherein the logic further causes components of the storage controller to perform the steps of:

providing the preserved area of the first cluster with temporary non-volatility means whereby data stored in the preserved area first cluster is preserved until such data is transferred to the first storage device; and

providing the preserved area of the second cluster with temporary non-volatility means whereby data stored in the preserved area of the second cluster is preserved until such data is transferred to the second storage device.

18. The article of manufacture of claim 14, wherein the logic further causes components of the storage controller to perform the steps of:

following the end of the power failure mode, attempting to restore the first and second clusters to the normal operating mode;

if only one of the first or second clusters is restored, operating the data processing system in a modified operation mode whereby the restored cluster performs the function of the failed cluster.