ACCELERATED DATA RECOVERY IN A STORAGE SYSTEM

• US 20160170846A1
• Filed: 12/12/2014
• Published: 06/16/2016
• Est. Priority Date: 12/12/2014
• Status: Active Grant

• Current Assignee: SK Hynix NAND Product Solutions Corporation (SK Hynix Inc.)
• Original Assignee: Intel Corporation
• Inventors: Hands, Jonmichael P.
• Granted Patent: US 9,575,853 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/1662 the resynchronized component or unit being a persistent storage device re-synchronization of failed mirror storage G06F11/2082; rebuild or reconstruction of parity RAID storage G06F11/1008
• CPC Class Codes: G06F 11/2082 Data synchronisation
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 13/42 Bus transfer protocol, e.g. handshake; Synchronisation
• CPC Class Codes: G06F 2201/805 Real-time
• CPC Class Codes: G06F 2201/82 Solving problems relating to consistency
• CPC Class Codes: G06F 2213/0036 Small computer system interface [SCSI]

Abstract

One embodiment provides a storage system. The storage system includes storage system control logic to identify at least one target storage device in response to detection of a failed storage device, request a state of a target device logical block address (LBA) from each of the at least one target storage device, and read data associated with a mapped device LBA from each target storage device and write the data to at least one replacement storage device. Another embodiment provides a storage device. The storage device includes device control logic to determine a state of a target device logical block address (LBA) in response to a request; a host interface to provide a reply to the request, the reply including a state indicator related to the state of the target device LBA; a map table including a plurality of device LBAs and respective state indicators; and non-volatile memory (NVM) including data related to at least one mapped LBA.

Claims

1. A storage system comprising:

storage system control logic to;

identify at least one target storage device in response to detection of a failed storage device,

request a state of a target device logical block address (LBA) from each of the at least one target storage device, and

read data associated with a mapped device LBA from each target storage device and write the data to at least one replacement storage device.

2. The storage system of claim 1, wherein the storage system control logic is further to request a trim command (TRIM) from a computing device to be provided to each target storage device.

3. The storage system of claim 1, wherein the storage system control logic is further to identify each target device LBA.

4. The storage system of claim 1, wherein the storage system control logic is further to request from each target storage device a respective state of each target device LBA of a range of target device LBAs.

5. The storage system of claim 1, wherein the storage system control logic is further to request a listing of mapped device LBAs from each target storage device.

6. The storage system of claim 1, wherein the state corresponds to mapped or unmapped.

7. A storage device comprising:

device control logic to determine a state of a target device logical block address (LBA) in response to a request;

a host interface to provide a reply to the request, the reply comprising a state indicator related to the state of the target device LBA;

a map table comprising a plurality of device LBAs and respective state indicators; and

non-volatile memory (NVM) comprising data related to at least one mapped LBA.

8. The storage device of claim 7, wherein the device control logic is to unmap a device LBA in response to a receiving trim command (TRIM).

9. The storage device of claim 7, wherein the device control logic is further to determine a respective state of each target device LBA of a range of target device LBAs in response to the request.

10. The storage device of claim 7, wherein the device control logic is further to determine a respective state of each device LBA of the plurality of device LBAs in response to the request.

11. The storage device of claim 10, wherein the reply comprises at least a portion of the plurality of device LBAs and a respective state of each device LBA in the portion is mapped.

12. The storage device of claim 7, wherein the state corresponds to mapped or unmapped.

13. A method comprising:

identifying, by storage system control logic, at least one target storage device in response to detection of a failed storage device;

requesting, by storage system control logic, a state of a target device logical block address (LBA) from each of the at least one target storage device;

reading, by storage system control logic, data associated with a mapped device LBA from each target storage device; and

writing, by storage system control logic, the data to at least one replacement storage device.

14. The method of claim 13, further comprising requesting, by storage system control logic, a trim command (TRIM) from a computing device to be provided to each target storage device.

15. The method of claim 13, further comprising identifying, by storage system control logic, each target device LBA.

16. The method of claim 13, further comprising requesting, by storage system control logic, from each target storage device a respective state of each target device LBA of a range of target device LBAs.

17. The method of claim 13, further comprising requesting, by storage system control logic, a listing of mapped device LBAs from each target storage device.

18. The method of claim 13, wherein the state corresponds to mapped or unmapped.

19. A method comprising:

determining, by device control logic, a state of a target device logical block address (LBA) in response to a request based, at least in part, on a map table comprising a plurality of device LBAs and respective state indicators, the map table related to a non-volatile memory (NVM) that comprises data related to at least one mapped LBA; and

providing, by a host interface, a reply to the request, the reply comprising a state indicator related to the state of the target device LBA.

20. The method of claim 19, further comprising unmapping, by the device control logic, a device LBA in response to a receiving trim command (TRIM).

21. The method of claim 19, further comprising determining, by the device control logic, a respective state of each target device LBA of a range of target device LBAs in response to the request.

22. The method of claim 19, further comprising determining, by the device control logic, a respective state of each device LBA of the plurality of device LBAs in response to the request.

23. The method of claim 22, wherein the reply comprises at least a portion of the plurality of device LBAs and a respective state of each device LBA in the portion is mapped.

24. The method of claim 19, wherein the state corresponds to mapped or unmapped.