Regaining redundancy in distributed raid arrays using unallocated capacity

• US 9,952,929 B2
• Filed: 04/21/2016
• Issued: 04/24/2018
• Est. Priority Date: 04/21/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Agombar, John P., Boden, Ian, Hutchison, Gordon D., Sanders, Lee J.
• Primary Examiner(s): Wilson, Yolanda L
• Application Number:
  US15/134,490
• Publication Number:
  US 20170308436A1
• Time in Patent Office: 733 Days
• CPC Class Codes: G06F 11/1088 Reconstruction on already foreseen single or plurality of spare disks
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• CPC Class Codes: G06F 11/1666 where the redundant component is memory or memory area
• CPC Class Codes: G06F 2201/845 Systems in which the redundancy can be transformed in increased performance

Abstract

A method and system are provided for spare capacity usage for critical redundancy in storage arrays. The method may include monitoring a Redundant Array of Independent Disks (RAID) array to determine whether one or more redundancy units are at a critical level. A redundancy unit may be in a critical level when an additional drive failure will result in loss of data from the redundancy unit. The method may further include identifying available regions in the RAID array which are not allocated to user data in response to determining that a particular redundancy unit is critical. The method may further include determining an available region for the particular redundancy unit, where the available region is in a drive of the RAID array that does not contain data of the particular redundancy unit. The method may further include storing a critical stripe in the available region.

Claims

1. A computer-implemented method for regaining redundancy in storage arrays, the method comprising:

monitoring a Redundant Array of Independent Disks (RAID) array to determine whether one or more redundancy units are at a critical level, wherein a redundancy unit is at a critical level when an additional drive failure will result in loss of data from the redundancy unit, and wherein each redundancy unit has multiple data stripes and one or more parity stripes;

identifying, in response to determining that a particular redundancy unit is critical, available regions in the RAID array which are not allocated to user data;

determining, for the particular redundancy unit, an available region which is in a drive of the RAID array which does not contain any existing data of the particular redundancy unit; and

storing a critical stripe in the available region, wherein the critical stripe contains sufficient information to rebuild the particular redundancy unit in case of further drive failure,

wherein determining, for the particular redundancy unit, the available region which is in the drive of the RAID array which does not contain any existing data of the particular redundancy unit comprises;

determining a drive in the RAID array that has a lowest number of critical stripes; and

determining an available region in the drive having the lowest number of critical stripes.

2. The method as claimed in claim 1, the method further comprising providing a mapping from the existing stripes of the particular redundancy unit to the critical stripe.

3. The method as claimed in claim 2, wherein the mapping is stored in non-volatile data remote to the RAID array.

4. The method as claimed in claim 2, wherein the mapping is stored in metadata stored on the RAID array.

5. The method as claimed in claim 4, wherein the metadata is stored in a data field of stripes of a redundancy unit.

6. The method as claimed in claim 1, wherein the particular redundancy unit became critical due to a drive failure, and wherein the critical stripe contains rebuilt data of a stripe lost by the drive failure.

7. The method as claimed in claim 6, the method further comprising:

replacing the failed drive with a new drive;

rebuilding, in response to the replacing the failed drive, the data of the particular redundancy unit from the critical stripe in the new drive.

8. The method as claimed in claim 1, the method further comprising:

determining, in response to storing the critical stripe, that the particular redundancy unit is no longer at a critical level;

determining that a second drive in the RAID array has failed, the second drive having at least one stripe of the particular redundancy unit;

determining that the failure of the second drive has made the particular redundancy unit critical again;

storing a second critical stripe of the particular redundancy unit on a third drive in the RAID array, wherein the third drive does not contain any existing data of the particular redundancy unit prior to the storing the second critical stripe.

9. The method as claimed in claim 1, the method further comprising:

determining that at least one redundancy unit is no longer critical; and

releasing regions where critical stripes of the at least one redundancy units that are no longer critical are stored in order for the regions to become available for user data or spare space.

10. The method as claimed in claim 1, wherein the method is provided as a service in a cloud environment.

11. A system for regaining redundancy in storage arrays, including an array controller having a processor and a memory configured to provide computer program instructions to the processor to execute the function of components of the array controller, including:

a critical level monitoring component for monitoring a Redundant Array of Independent Disks (RAID) array to determine if a failure of a drive in the array causes one or more redundancy units to enter a critical level, wherein a critical level is when a further failure will result in loss of data from the redundancy unit, and wherein a redundancy unit has multiple data stripes and one or more parity stripes;

a space determining component for identifying available regions in the RAID array which are not allocated to user data;

a region selection component for determining for each critical redundancy unit, an available region which is in a drive of the RAID array which does not contain any existing data of the redundancy unit, wherein the region selection component is further configured to determine an available region which is in a drive having a lowest number of critical stripes; and

a critical stripe component for storing a critical stripe in the available region, wherein the critical stripe contains sufficient information to rebuild the redundancy unit in case of further drive failure.

12. The system as claimed in claim 11, the system further comprising a mapping component for providing a mapping from the existing stripes of the redundancy unit to the critical stripe.

13. The system as claimed in claim 12, wherein the mapping is stored in non-volatile data remote to the RAID array.

14. The system as claimed in claim 12, wherein the mapping is stored in metadata stored on the RAID array.

15. The system as claimed in claim 14, wherein the metadata is stored in a data field of stripes of a redundancy unit.

16. The system as claimed in claim 11, the system further comprising a redundancy unit rebuild component for rebuilding the data of the critical redundancy unit when a failed drive is replaced.

17. The system as claimed in claim 11, the system further comprising a critical stripe releasing component for releasing regions where critical stripes of the redundancy units that are no longer critical are stored in order for the regions to become available for user data or spare space again.

18. A computer program product for regaining redundancy in storage arrays, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:

monitoring a Redundant Array of Independent Disks (RAID) array to determine whether one or more redundancy units are at a critical level, wherein a redundancy unit is at a critical level when an additional drive failure will result in loss of data from the redundancy unit, and wherein each redundancy unit has multiple data stripes and one or more parity stripes;

identifying, in response to determining that a particular redundancy unit is critical, available regions in the RAID array which are not allocated to user data;

determining, for the particular redundancy unit, an available region which is in a drive of the RAID array which does not contain any existing data of the particular redundancy unit; and

storing a critical stripe in the available region, wherein the critical stripe contains sufficient information to rebuild the particular redundancy unit in case of further drive failure,

wherein determining, for the particular redundancy unit, the available region which is in the drive of the RAID array which does not contain any existing data of the particular redundancy unit comprises;

determining a drive in the RAID array that has a lowest number of critical stripes; and

determining an available region in the drive having the lowest number of critical stripes.