FASTER RECONSTRUCTION OF SEGMENTS USING A DEDICATED SPARE MEMORY UNIT

• US 20160239397A1
• Filed: 02/12/2015
• Published: 08/18/2016
• Est. Priority Date: 02/12/2015
• Status: Active Grant

• Current Assignee: NetApp, Inc.
• Original Assignee: NetApp, Inc.
• Inventors: Thomas, Arvind, Bysani, Premnath
• Granted Patent: US 9,632,891 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 11/1088 Reconstruction on already foreseen single or plurality of spare disks
• CPC Class Codes: G06F 11/1666 where the redundant component is memory or memory area
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 2201/805 Real-time
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

Techniques for faster reconstruction of segments using a dedicated spare memory unit are described. Zone segments in memory units are associated with a dedicated spare memory unit. The zone segments are reconstructed in the dedicated spare memory unit in response to a failed memory unit except for an identified failed zone segment of the failed memory unit. The identified failed zone segment of the failed memory unit is retained in the dedicated spare unit. Other embodiments are described and claimed.

Claims

1. A computer-implemented method, comprising:

segmenting a memory unit into a plurality of zone segments;

associating the plurality of zone segments with a dedicated spare memory unit assigned to a memory unit group; and

reconstructing, in the dedicated spare memory unit, each one of the plurality of zone segments in response to a failed memory unit except for an identified failed zone segment of the failed memory unit.

2. The method of claim 1, comprising assigning the memory unit to the memory unit group.

3. The method of claim 1, comprising promoting the dedicated spare memory unit to the failed memory unit in response to a detection or prediction of a memory unit failure.

4. The method of claim 1, comprising:

detecting or predicting a memory unit failure;

retaining the identified failed zone segment in the dedicated spare memory unit in response to the detection or the prediction of the memory unit failure; and

copying each remaining one of the plurality of zone segments in the predicted failed disk into the dedicated spare memory unit.

5. The method of claim 1, comprising assigning the dedicated spare memory unit to the memory unit group from a pool of spare memory units.

6. The method of claim 1, comprising copying the plurality of zone segments into the dedicated spare memory unit when the dedicated spare memory unit is first assigned to the memory unit group.

7. The method of claim 1, comprising performing a mirror copy into the dedicated spare memory unit for a write operation into one of the plurality of zone segments.

8. The method of claim 1, comprising:

determining a total number of the plurality of zone segments is equal to a total number of memory units in the memory unit group, the total number of memory units in the memory unit group to include any parity memory units assigned to the memory unit group; and

determining a size of each of the plurality of zone segments as a size of a memory unit divided by the total number of memory units in the memory unit group.

9. A system, comprising:

a plurality of memory units;

a memory unit group including the plurality of memory units; and

at least one processor device, in communication with the memory unit group, operable in the computing storage environment, wherein the at least one processor device;

splits each one of the plurality of memory unit into a plurality of zone segments;

associates the plurality of zone segments with a dedicated spare memory unit; and

reconstructs, in the dedicated spare memory unit, each one of the plurality of zone segments in response to a failed memory unit except for an identified failed zone segment of the failed memory unit.

10. The system of claim 9, wherein the processor device promotes the dedicated spare memory unit to the failed memory unit in response to a detection or prediction of a memory unit failure.

11. The system of claim 9, wherein the processor device:

detects or predicts a memory unit failure;

retains the identified failed zone segment in the dedicated spare memory unit in response to the detection or the prediction of the memory unit failure; and

copy each remaining one of the plurality of zone segments in the predicted failed disk into the dedicated spare memory unit.

12. The system of claim 9, comprising a pool of spare memory units controlled by the processor device and in communication with the memory unit group, wherein the processor device:

assigns the dedicated spare memory unit to the memory unit group from the pool of spare memory units; and

copies the plurality of zone segments into the dedicated spare memory unit when the dedicated spare memory unit is first assigned to the memory unit group.

13. The system of claim 9, wherein the processor device performs a mirror copy into the dedicated spare memory unit.

14. The system of claim 9, wherein the processor device:

determines a total number of the plurality of zone segments is equal to a total number of memory units in the memory unit group, the total number of memory units in the memory unit group to include any parity memory units assigned to the memory unit group.

15. At least one non-transitory computer-readable storage medium comprising instructions that, when executed, cause a system to:

associate a plurality of zone segments in a plurality of memory units with a dedicated spare memory unit; and

reconstruct, in the dedicated spare memory unit, each one of the plurality of zone segments in response to a failed memory unit except for an identified failed zone segment of the failed memory unit, wherein the identified failed zone segment of the failed memory unit is retained in the dedicated spare unit.

16. The computer-readable storage medium of claim 15, comprising further instructions that, when executed, cause a system to split the dedicated spare memory unit into the plurality of zone segments.

17. The computer-readable storage medium of claim 15, comprising further instructions that, when executed, cause a system to:

replace the failed memory unit with the dedicated spare memory unit,

detects or predicts a memory unit failure;

retains the identified failed zone segment in the dedicated spare memory unit in response to the detection or the prediction of the memory unit failure; and

copy each remaining one of the plurality of zone segments in the predicted failed disk into the dedicated spare memory unit

18. The computer-readable storage medium of claim 15, comprising further instructions that, when executed, cause a system to copy the plurality of zone segments into the dedicated spare memory unit.

19. The computer-readable storage medium of claim 15, comprising further instructions that, when executed, cause a system to perform a mirror copy into the dedicated spare memory unit.

20. The computer-readable storage medium of claim 15, comprising further instructions that, when executed, cause a system to:

determine a total number of the plurality of zone segments; and

determine a size of each of the plurality of zone segments.