Method and system for migrating data between flash memory devices

• US 9,519,577 B2
• Filed: 08/27/2014
• Issued: 12/13/2016
• Est. Priority Date: 09/03/2013
• Status: Active Grant

• Current Assignee: SanDisk Technologies LLC (Western Digital Corporation)
• Original Assignee: SanDisk Technologies LLC (Western Digital Corporation)
• Inventors: Kruger, Warren Fritz
• Primary Examiner(s): Gu, Shawn X
• Application Number:
  US14/470,580
• Publication Number:
  US 20150067244A1
• Time in Patent Office: 839 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/004 Error avoidance G06F11/07 and subgroups take precedence
• CPC Class Codes: G06F 11/1451 by selection of backup contents
• CPC Class Codes: G06F 11/1456 Hardware arrangements for backup
• CPC Class Codes: G06F 11/1458 Management of the backup or restore process
• CPC Class Codes: G06F 11/1612 where the redundant component is persistent storage
• CPC Class Codes: G06F 12/0246 in block erasable memory, e.g. flash memory
• CPC Class Codes: G06F 2201/81 Threshold
• CPC Class Codes: G06F 2212/1032 Reliability improvement, data loss prevention, degraded operation etc
• CPC Class Codes: G06F 2212/1044 Space efficiency improvement
• CPC Class Codes: G06F 2212/7204 Capacity control, e.g. partitioning, end-of-life degradation
• CPC Class Codes: G06F 2212/7208 Multiple device management, e.g. distributing data over multiple flash devices
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

The embodiments described herein include systems, methods and/or devices that may enhance the endurance of a storage system including a storage medium. The method includes: dividing a plurality of flash memory devices into logical chunks each logical chunk including one or more flash memory blocks; and detecting a trigger condition with respect to a respective flash memory device of the plurality of flash memory devices. In response to detecting the trigger condition, the method includes: selecting one of the logical chunks of the respective flash memory device for migration in accordance with predefined selection criteria; and storing a replicated logical chunk, comprising a copy of the selected logical chunk, at a second flash memory device. The method includes: remapping an address of the selected logical chunk to a physical location of the replicated logical chunk; and decreasing a number of logical chunks associated with the respective flash memory device.

Claims

1. A method of managing a storage system that comprises a storage controller and a plurality of flash memory devices, each with a plurality of flash memory blocks, the method comprising:

at the storage controller;

dividing each of the plurality of flash memory devices into a plurality of logical chunks, wherein each logical chunk includes one or more flash memory blocks;

detecting failure of a number of flash memory blocks for a respective flash memory device of the plurality of flash memory devices, wherein each flash memory block is the minimum size erasable unit of a respective flash memory device in the plurality of flash memory devices;

in accordance with a determination that the number of failed flash memory blocks satisfies a predefined threshold for the respective flash memory device, performing a migration process that includes;

selecting one of the plurality of logical chunks of the respective flash memory device for migration in accordance with predefined selection criteria;

storing a replicated logical chunk, comprising a copy of the selected logical chunk, at a second flash memory device different from the respective flash memory device;

remapping an address of the selected logical chunk to a physical location of the replicated logical chunk; and

decreasing a number of logical chunks associated with the respective flash memory device, resulting in a reduced, non-zero number of logical chunks associated with the respective flash memory device;

wherein, upon completion of the migration process, logical chunks of the plurality of logical chunks, other than the selected one, continue to be stored by the respective flash memory device.

2. The method of claim 1, further comprising, reducing an advertised size of the respective memory device to a non-zero value, in accordance with the determination that the number of failed flash memory blocks satisfy the predefined threshold for the respective flash memory device.

3. The method of claim 1, wherein the storage controller detects failure of the number of flash memory blocks for the respective flash memory device after directing a memory access request to the respective flash memory device.

4. The method of claim 1, further comprising

in accordance with the determination that the number of failed flash memory blocks satisfies the predefined threshold for the respective flash memory device, querying the respective flash memory device to determine whether the size of the respective flash memory device is smaller than a previous size of the respective flash memory device;

and

wherein the selecting and storing are performed in accordance with a determination that the query indicates that the size of the respective flash memory device is smaller than the previous size of the respective flash memory device.

5. The method of claim 1, wherein each logical chunk includes a predefined number of flash memory blocks, wherein the predefined number is an integer greater than one, and a predefined trigger condition indicates that a counter of failed flash memory blocks for the respective flash memory device satisfies a threshold comprising the predefined number of flash memory blocks included in each logical chunk or an integer multiple of the predefined number of flash memory blocks included in each logical chunk.

6. The method of claim 1, wherein the logical chunks are allocated for storing data and are organized into a plurality of redundancy sets, each redundancy set comprising one or more logical chunks and storing redundant data sufficient to enable recovery of data stored in at least one of the one or more logical chunks.

7. The method of claim 6, wherein the replicated logical chunk is included in a respective redundancy set of the plurality of redundancy sets that formerly included the selected logical chunk.

8. The method of claim 6, wherein a respective redundancy set of the plurality of redundancy sets is a contiguous stripe across the plurality of flash memory devices, and wherein the replicated logical chunk is stored in a same contiguous stripe as the selected logical chunk at the second flash memory device different from the respective flash memory device.

9. The method of claim 6, wherein the replicated logical chunk is stored in accordance with a preferred storage utilization scheme, the method including, associating the replicated logical chunk with a respective redundancy set of the plurality of redundancy sets in an indirection table.

10. The method of claim 1, wherein the predefined selection criteria include a least utilized logical chunk or least populated logical chunk of the respective flash memory device.

11. The method of claim 1, wherein the predefined selection criteria include a logical chunk associated with a memory access request.

12. The method of claim 1, wherein a size of a plurality of logical chunks is predetermined by software.

13. The method of claim 1, wherein a size of a plurality of logical chunks is determined based on a protocol used by the storage system.

14. The method of claim 1, further comprising:

in accordance with the determination that the number of failed flash memory blocks satisfies the predefined threshold for the respective flash memory device, re-encoding data in at least one logical chunk of the respective flash memory device with a higher level of error correction protection than a prior encoding of the data in the at least one logical chunk of the respective flash memory device.

15. A storage controller, comprising:

one or more processors;

a host interface configured to couple the storage controller to a host;

a storage medium interface configured to couple the storage controller to a storage medium including a plurality of flash memory devices, each with a plurality of flash memory blocks; and

a storage controller memory storing instructions, which, when executed by the one or more processors, causes the storage controller to perform operations comprising;

dividing each of the plurality of flash memory devices into a plurality of logical chunks, wherein each logical chunk includes one or more flash memory blocks;

detecting failure of a number of flash memory blocks for a respective flash memory device of the plurality of flash memory devices, wherein each flash memory block is the minimum size erasable unit of a respective flash memory device in the plurality of flash memory devices;

in accordance with a determination that the number of failed flash memory blocks satisfies a predefined threshold for the respective flash memory device, performing a migration process that includes;

selecting one of the plurality of logical chunks of the respective flash memory device for migration in accordance with predefined selection criteria; and

storing a replicated logical chunk, comprising a copy of the selected logical chunk, at a second flash memory device different from the respective flash memory device;

remapping an address of the selected logical chunk to a physical location of the replicated logical chunk; and

decreasing a number of logical chunks associated with the respective flash memory device, resulting in a reduced, non-zero number of logical chunks associated with the respective flash memory device;

wherein, upon completion of the migration process, logical chunks of the plurality of logical chunks, other than the selected one, continue to be stored by the respective flash memory device.

16. The storage controller of claim 15, wherein the logical chunks are allocated for storing data and are organized into a plurality of redundancy sets, each redundancy set comprising one or more logical chunks and storing redundant data sufficient to enable recovery of data stored in at least one of the one or more logical chunks.

17. The storage controller of claim 16, wherein the replicated logical chunk is included in a respective redundancy set of the plurality of redundancy sets that formerly included the selected logical chunk.

18. The storage controller of claim 16, wherein a respective redundancy set of the plurality of redundancy sets is a contiguous stripe across the plurality of flash memory devices, and wherein the replicated logical chunk is stored in a same contiguous stripe as the selected logical chunk at the second flash memory device different from the respective flash memory device.

19. The storage controller of claim 16, wherein the replicated logical chunk is stored in accordance with a preferred storage utilization scheme, and the storage controller associates the replicated logical chunk with a respective redundancy set of the plurality of redundancy sets in an indirection table.

20. A non-transitory computer readable storage medium, storing one or more programs for execution by one or more processors of a storage controller coupled to a storage medium including a plurality of flash memory devices, wherein each flash memory device includes a plurality of flash memory blocks, the one or more programs including instructions that when executed by the one or more processors cause the storage controller to:

divide each of the plurality of flash memory devices into a plurality of logical chunks, wherein each logical chunk includes one or more flash memory blocks;

detect failure of a number of flash memory blocks for a respective flash memory device of the plurality of flash memory devices, wherein each flash memory block is the minimum size erasable unit of a respective flash memory device in the plurality of flash memory devices;

in accordance with a determination that the number of failed flash memory blocks satisfies a predefined threshold for the respective flash memory device, performing a migration process that includes;

selecting one of the plurality of logical chunks of the respective flash memory device for migration in accordance with predefined selection criteria;

storing a replicated logical chunk, comprising a copy of the selected logical chunk, at a second flash memory device different from the respective flash memory device;

remapping an address of the selected logical chunk to a physical location of the replicated logical chunk; and

decreasing a number of logical chunks associated with the respective flash memory device, resulting a reduced, non-zero number of logical chunks associated with the respective flash memory device;

wherein, upon completion of the migration process, logical chunks of the plurality of logical chunks, other than the selected one, continue to be stored by the respective flash memory device.

21. The non-transitory computer readable storage medium of claim 20, wherein the logical chunks are allocated for storing data and are organized into a plurality of redundancy sets, each redundancy set comprising one or more logical chunks and storing redundant data sufficient to enable recovery of data stored in at least one of the one or more logical chunks.

22. The non-transitory computer readable storage medium of claim 21, wherein the replicated logical chunk is included in a respective redundancy set of the plurality of redundancy sets that formerly included the selected logical chunk.

23. The non-transitory computer readable storage medium of claim 21, wherein a respective redundancy set of the plurality of redundancy sets is a contiguous stripe across the plurality of flash memory devices, and wherein the replicated logical chunk is stored in a same contiguous stripe as the selected logical chunk at the second flash memory device different from the respective flash memory device.

24. The non-transitory computer readable storage medium of claim 21, wherein the replicated logical chunk is stored in accordance with a preferred storage utilization scheme, and the one or more programs include instructions that when executed by the one or more processors cause the storage controller to associate the replicated logical chunk with a respective redundancy set of the plurality of redundancy sets in an indirection table.