Multiple sourcing storage devices for ultra reliable mirrored storage subsystems

• US 7,376,862 B2
• Filed: 06/24/2004
• Issued: 05/20/2008
• Est. Priority Date: 06/24/2004
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Hajji, Amine M., Hyde, Joseph S. II
• Primary Examiner(s): Baderman; Scott
• Assistant Examiner(s): Contino; Paul F
• Application Number:
  US10/876,976
• Publication Number:
  US 20050289387A1
• Time in Patent Office: 1,426 Days
• Field of Search: 714/6, 714/42
• US Class Current: 714/6.1
• CPC Class Codes: G06F 11/1096 Parity calculation or recalculation after configuration or reconfiguration of the system
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 11/2289 by configuration test

Abstract

One aspect of the invention is a method for configuring an array of storage devices to reduce the probability of data loss due to clustered storage device failures in the array. An example of this method includes identifying all storage devices in a primary set of storage devices and a first mirror set of storage devices in the array of storage devices. This example also includes obtaining data regarding each identified storage device. This example further includes determining if any of the storage devices in the primary set of storage devices has a vital characteristic that is the same as a vital characteristic of any of the storage devices in the first mirror set of storage devices, and if so, indicating an array configuration error, and if not, continuing the configuration.

Claims

1. A storage medium tangibly embodying a program of machine-readable instructions executable by a digital processing apparatus to perform operations for configuring an array of storage devices to reduce the probability of data loss due to clustered storage device failures in the array, the operations comprising:

identifying all storage devices in a primary set of storage devices and a first mirror set of storage devices in the array of storage devices;

obtaining data regarding each identified storage device;

determining if any of the storage devices in the primary set of storage devices has a vital characteristic that is the same as a vital characteristic of any of the storage devices in the first mirror set of storage devices;

and if so, indicating an array configuration error;

and if not, continuing the configuration.

2. The storage medium of claim 1, wherein the operations further comprise halting the configuration of the array if an array configuration error is indicated.

3. The storage medium of claim 2, wherein the operations further comprise, after indicating an array configuration error:

receiving a command to continue the configuration; and

continuing the configuration.

4. The storage medium of claim 1, wherein the vital characteristic is a manufacturer identifier.

5. The storage medium of claim 1, wherein the vital characteristic is a product identifier.

6. The storage medium of claim 1, wherein the vital characteristic is power on hours, and wherein the operations further comprise:

determining if at least one of the storage devices in the primary set of storage devices has a manufacturer identifier that is the same as the manufacturer identifier of at least one of the storage devices in the first mirror set of storage devices;

and wherein the operation of determining if any of the storage devices in the primary set of storage devices has the vital characteristic that is the same as the vital characteristic of any of the storage devices in the first mirror set of storage devices, is conducted only for storage devices determined to have the same manufacturer identifier;

and wherein power on hours are the same if the power on hours do not have a difference of at least a specified number of hours.

7. The storage medium of claim 1, wherein the vital characteristic is power on hours, and wherein the operations further comprise:

determining if at least one of the storage devices in the primary set of storage devices has a storage device product identifier that is the same as the storage device product identifier of at least one of the storage devices in the first mirror set of storage devices;

and wherein the operation of determining if any of the storage devices in the primary set of storage devices has the vital characteristic that is the same as the vital characteristic of any of the storage devices in the first mirror set of storage devices, is conducted only for storage devices determined to have the same product identifier;

and wherein power on hours are the same if the power on hours do not have a difference of at least a specified number of hours.

8. The storage medium of claim 1, wherein the vital characteristic is power cycles, and wherein the operations further comprise:

determining if at least one of the storage devices in the primary set of storage devices has a manufacturer identifier that is the same as the manufacturer identifier of at least one of the storage devices in the first mirror set of storage devices;

and wherein the operation of determining if any of the storage devices in the primary set of storage devices has the vital characteristic that is the same as the vital characteristic of any of the storage devices in the first mirror set of storage devices, is conducted only for storage devices determined to have the same manufacturer identifier;

and wherein power cycles are the same if the power cycles do not have a difference of at least a specified number of power cycles.

9. The storage medium of claim 1, wherein the vital characteristic is power cycles, and wherein the operations further comprise:

determining if at least one of the storage devices in the primary set of storage devices has a storage device product identifier that is the same as the storage device product identifier of at least one of the storage devices in the first mirror set of storage devices;

and wherein the operation of determining if any of the storage devices in the primary set of storage devices has the vital characteristic that is the same as the vital characteristic of any of the storage devices in the first mirror set of storage devices, is conducted only for storage devices determined to have the same product identifier;

and wherein power cycles are the same if the power cycles do not have a difference of at least a specified number of power cycles.

10. The storage medium of claim 1, wherein the vital characteristic is manufacturing date, and wherein the operations further comprise:

determining if at least one of the storage devices in the primary set of storage devices has a manufacturer identifier that is the same as the manufacturer identifier of at least one of the storage devices in the first mirror set of storage devices;

and wherein the operation of determining if any of the storage devices in the primary set of storage devices has the vital characteristic that is the same as the vital characteristic of any of the storage devices in the first mirror set of storage devices, is conducted only for storage devices determined to have the same manufacturer identifier;

and wherein two manufacturing dates are the same if the two manufacturing dates do not differ by more than a specified number of days.

11. The storage medium of claim 1, wherein the vital characteristic is manufacturing date, and wherein the operations further comprise:

determining if at least one of the storage devices in the primary set of storage devices has a storage device product identifier that is the same as the storage device product identifier of at least one of the storage devices in the first mirror set of storage devices;

and wherein the operation of determining if any of the storage devices in the primary set of storage devices has the vital characteristic that is the same as the vital characteristic of any of the storage devices in the first mirror set of storage devices, is conducted only for storage devices determined to have the same product identifier;

and wherein two manufacturing dates are the same if the two manufacturing dates do not differ by more than a specified number of days.

12. The storage medium of claim 1:

wherein the operation of determining if any of the storage devices in the primary set of storage devices has a vital characteristic that is the same as a vital characteristic of any of the storage devices in the first mirror set of storage devices, is repeated for a plurality of vital characteristics;

and wherein an array configuration error is indicated only if the plurality of vital characteristics of any of the storage devices in the primary set of storage devices are the same as the plurality of vital characteristics of any of the storage devices in the first mirror set of storage devices.

13. The storage medium of claim 1, wherein the data obtained regarding each of the storage devices identified in the array includes vital product data.

14. The storage medium of claim 1, wherein the data obtained regarding each of the storage devices identified in the array is obtained from the respective storage device.

15. The storage medium of claim 1, wherein the operations further comprise identifying all storage devices in a second mirror set of storage devices in the array of storage devices;

for each storage device identified in the second mirror set of storage devices, obtaining data regarding the storage device;

determining if any of the storage devices in the second mirror set of storage devices has a vital characteristic that is the same as a vital characteristic of any of the storage devices in a combined set of storage devices that includes the primary set of storage devices and the first mirror set of storage devices;

and if so, indicating an improper configuration error;

and if not, continuing the configuration process.

16. A storage medium tangibly embodying a program of machine-readable instructions executable by a digital processing apparatus to perform operations for replacing a failed storage device in an array of storage devices having a plurality of sets of storage devices, to reduce the probability of data loss due to clustered storage device failures in the array, the operations comprising:

identifying a set of storage devices of which the failed storage device is a member;

identifying all storage devices in each set of storage devices in the array other than the set of storage devices of which the failed storage device is a member;

obtaining data regarding each identified storage device;

identifying a vital characteristic of a potential replacement storage device;

determining if any identified storage device has a vital characteristic that is the same as the vital characteristic of the potential replacement storage device;

and if so, indicating a array configuration error;

and if not, configuring the array with the potential replacement storage device.

17. The storage medium of claim 16, wherein the vital characteristic is a manufacturer identifier.

18. The storage medium of claim 16, wherein the vital characteristic is a product identifier.

19. The storage medium of claim 16, wherein the vital characteristic is power on hours, and wherein the operations further comprise:

determining if at least one of the identified storage devices has a manufacturer identifier that is the same as a manufacturer identifier of the potential replacement storage device;

and wherein the operation of determining if any identified storage device has a vital characteristic that is the same as the vital characteristic of the potential replacement storage device, is conducted only for each storage device that has a manufacturer identifier that is the same as the manufacturer identifier of the potential replacement storage device;

and wherein power on hours are the same if the power on hours do not have a difference of at least a specified number of hours.

20. The storage medium of claim 16, wherein the vital characteristic is power cycles, and wherein the operations further comprise:

determining if at least one of the identified storage devices has a manufacturer identifier that is the same as a manufacturer identifier of the potential replacement storage device;

and wherein the operation of determining if any identified storage device has a vital characteristic that is the same as the vital characteristic of the potential replacement storage device, is conducted only for each storage device that has a manufacturer identifier that is the same as the manufacturer identifier of the potential replacement storage device;

and wherein power cycles are the same if the power cycles do not have a difference of at least a specified number of power cycles.

21. The storage medium of claim 16, wherein the vital characteristic is manufacturing date, and wherein the operations further comprise:

determining if at least one of the identified storage devices has a manufacturer identifier that is the same as a manufacturer identifier of the potential replacement storage device;

and wherein the operation of determining if any identified storage device has a vital characteristic that is the same as the vital characteristic of the potential replacement storage device, is conducted only for each storage device that has a manufacturer identifier that is the same as the manufacturer identifier of the potential replacement storage device;

and wherein two manufacturing dates are the same if the two manufacturing dates do not differ by more than a specified number of days.

22. A computing system, comprising:

a memory; and

a processing device coupled to the memory, wherein the processing device is programmed to perform operations for configuring an array of storage devices to reduce the probability of data loss due to clustered storage device failures in the array, the operations comprising;

identifying all storage devices in a primary set of storage devices and a first mirror set of storage devices in the array of storage devices;

obtaining data regarding each identified storage device;

determining if any of the storage devices in the primary set of storage devices has a vital characteristic that is the same as a vital characteristic of any of the storage devices in the first mirror set of storage devices;

and if so, indicating an array configuration error;

and if not, continuing the configuration.

23. A computing system, comprising:

a memory; and

a processing device coupled to the memory, wherein the processing device is programmed to perform operations for replacing a failed storage device in an array of storage devices having a plurality of sets of storage devices, to reduce the probability of data loss due to clustered storage device failures in the array, the operations comprising;

identifying a set of storage devices of which the failed storage device is a member;

identifying all storage devices in each set of storage devices in the array other than the set of storage devices of which the failed storage device is a member;

obtaining data regarding each identified storage device;

identifying a vital characteristic of a potential replacement storage device;

determining if any identified storage device has a vital characteristic that is the same as the vital characteristic of the potential replacement storage device;

and if so, indicating a array configuration error;

and if not, configuring the array with the potential replacement storage device.

24. A computing system for configuring an array of storage devices to reduce the probability of data loss due to clustered storage device failures in the array, the computing system comprising:

means for identifying all storage devices in a primary set of storage devices and a first mirror set of storage devices in the array of storage devices;

means for obtaining data regarding each identified storage device;

means for determining if any of the storage devices in the primary set of storage devices has a vital characteristic that is the same as a vital characteristic of any of the storage devices in the first mirror set of storage devices;

and if so, means for indicating an array configuration error;

and if not, means for continuing the configuration.

25. A computing system for replacing a failed storage device in an array of storage devices having a plurality of sets of storage devices, to reduce the probability of data loss due to clustered storage device failures in the array, the computing system comprising:

means for identifying a set of storage devices of which the failed storage device is a member;

means for identifying all storage devices in each set of storage devices in the array other than the set of storage devices of which the failed storage device is a member;

means for obtaining data regarding each identified storage device;

means for identifying a vital characteristic of a potential replacement storage device;

means for determining if any identified storage device has a vital characteristic that is the same as the vital characteristic of the potential replacement storage device;

and if so, means for indicating a array configuration error;

and if not, means for configuring the array with the potential replacement storage device.

26. method for configuring an array of storage devices to reduce the probability of data loss due to clustered storage device failures in the array, the method comprising the following operations:

identifying all storage devices in a primary set of storage devices and a first mirror set of storage devices in the array of storage devices;

obtaining data regarding each identified storage device;

determining if any of the storage devices in the primary set of storage devices has a vital characteristic that is the same as a vital characteristic of any of the storage devices in the first mirror set of storage devices;

and if so, indicating an array configuration error;

and if not, continuing the configuration.

27. A method for replacing a failed storage device in an array of storage devices having a plurality of sets of storage devices, to reduce the probability of data loss due to clustered storage device failures in the array, the method comprising the following operations:

identifying a set of storage devices of which the failed storage device is a member;

identifying all storage devices in each set of storage devices in the array other than the set of storage devices of which the failed storage device is a member;

obtaining data regarding each identified storage device;

identifying a vital characteristic of a potential replacement storage device;

determining if any identified storage device has a vital characteristic that is the same as the vital characteristic of the potential replacement storage device;

and if so, indicating a array configuration error;

and if not, configuring the array with the potential replacement storage device.