Method for management tables recovery

• US 10,459,803 B2
• Filed: 08/24/2017
• Issued: 10/29/2019
• Est. Priority Date: 06/28/2017
• Status: Active Grant

• Current Assignee: JP Morgan Chase Bank, N.A. (JP Morgan Chase & Co)
• Original Assignee: Western Digital Technologies Incorporated (Western Digital Corporation)
• Inventors: Sela, Rotem, Shaharabany, Amir, Sapir, Miki, Klein, Eliad Adi
• Primary Examiner(s): Patel, Kamini B
• Application Number:
  US15/685,555
• Publication Number:
  US 20190004907A1
• Time in Patent Office: 796 Days
• Field of Search: 714 19
• CPC Class Codes: G06F 11/073 in a memory management context, e.g. virtual memory or cache management memory management G06F12/00; testing of static memory units G11C29/00
• CPC Class Codes: G06F 11/0793 Remedial or corrective actions recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40
• CPC Class Codes: G06F 11/1417 Boot up procedures
• CPC Class Codes: G06F 11/1451 by selection of backup contents
• CPC Class Codes: G06F 11/1469 Backup restoration techniques
• CPC Class Codes: G06F 2201/805 Real-time
• CPC Class Codes: G06F 2201/82 Solving problems relating to consistency ensuring consistency in mirrored systems G06F11/2064
• CPC Class Codes: G06F 9/4401 Bootstrapping security arrangements therefor G06F21/57
• CPC Class Codes: G06F 9/4406 Loading of operating system

Abstract

A controller receives an indication that a memory management table loaded to a random-access storage device is in a corrupted state. The controller retrieves one or more error recovery parameters of a memory unit stored in metadata of a physical block of a plurality of physical blocks of the non-volatile storage device. The controller examines the one or more error recovery parameters to determine whether the one or more error recovery parameters indicate the memory unit is fresh or stale. The controller updates the memory management table with logical-to-physical translation information of the metadata for the memory unit that is determined to be fresh. The controller writes the updated memory management table to the non-volatile storage device.

Claims

1. A method for self-recovery of memory management tables for solid state storage devices, comprising:

receiving, by a controller, an indication that a memory management table loaded to a random-access storage device and associated with a non-volatile storage device is in a corrupted state;

retrieving one or more error recovery parameters of a first memory unit stored in metadata of a physical block of a plurality of physical blocks of the non-volatile storage device;

examining the one or more error recovery parameters to determine whether the one or more error recovery parameters indicate the first memory unit is fresh or stale, wherein the first memory unit is determined to be fresh if a sequence number of the error recovery parameters corresponding to the first memory unit is greater than a sequence number corresponding to a second memory unit stored in the metadata with the same logical address as the first memory unit;

updating the memory management table with logical-to-physical translation information of the metadata for the first memory unit that is determined to be fresh; and

writing the updated memory management table to the non-volatile storage device.

2. The method of claim 1, wherein said writing is in response to the one or more error recovery parameters for all memory units for all blocks of the plurality of blocks have been examined.

3. The method of claim 1, wherein said writing is in response to no more space being available in volatile memory to store the entire memory management table.

4. The method of claim 1, further comprising, upon receiving a write request, updating the metadata and the memory management table with a logical address of the first memory unit.

5. The method of claim 1, wherein the one or more error recovery parameters are the logical address of the first memory unit and a sequence number of the first memory unit.

6. The method of claim 1, further comprising updating the metadata with a program erase count (PEC).

7. The method of claim 1, wherein the one or more error recovery parameters are loaded to volatile memory.

8. The method of claim 1, wherein the indication that the memory management table is in a corrupted state further comprises receiving a command for self-recovery of memory management tables.

9. The method of claim 8, wherein the command is received during system boot-up.

10. The method of claim 8, wherein the command is received after system boot-up.

11. The method of claim 1, wherein the indication that the memory management table is in a corrupted state further comprises determining that a threshold number of attempts to boot the memory controller has failed.

12. A method for self-recovery of memory management tables for solid state storage devices, comprising:

receiving, by a controller, an indication that a memory management table loaded to a random-access storage device and associated with a non-volatile storage device is in a corrupted state;

retrieving one or more error recovery parameters of a memory unit stored in metadata of a physical block of a plurality of physical blocks of the non-volatile storage device wherein the memory unit is a first memory unit;

when the first memory unit and a second memory unit both have the same logical address and;

when a sequence number of the error recovery parameters corresponding to the first memory unit is greater than a sequence number corresponding to the second memory unit in the metadata, determining that the memory unit is fresh; and

when the sequence number of the error recovery parameters corresponding to the first memory unit is less than the sequence number corresponding to the second memory unit in the metadata, determining that the memory unit is stale;

examining the one or more error recovery parameters to determine whether the one or more error recovery parameters indicate the memory unit is fresh or stale;

updating the memory management table with logical-to-physical translation information of the metadata for the memory unit that is determined to be fresh; and

writing the updated memory management table to the non-volatile storage device.

13. The method of claim 12, wherein when the one or more error recovery parameters are determined to be stale, discarding the one or more error recovery parameters.

14. The method of claim 12, wherein when the one or more error recovery parameters are determined to be fresh, updating the metadata with one or more of the error recovery parameters.

15. The method of claim 14, further comprising signaling to a host device that a recovery procedure is completed successfully.

16. A storage device comprising:

a non-volatile storage device;

a random-access storage device; and

a controller coupled to the non-volatile storage device and the random-access storage device, the controller configured to;

receive an indication that a memory management table loaded to a random-access storage device and associated with a non-volatile storage device is in a corrupted state;

retrieve one or more error recovery parameters of a first memory unit stored in metadata of a physical block of a plurality of physical blocks of the non-volatile storage device;

examine the one or more error recovery parameters to determine whether the one or more error recovery parameters indicate the first memory unit is fresh or stale, wherein the first memory unit is determined to be fresh if a sequence number of the error recovery parameters corresponding to the first memory unit is greater than a sequence number corresponding to a second memory unit stored in the metadata with the same logical address as the first memory unit;

update the memory management table with logical-to-physical translation information of the metadata for the first memory unit that is determined to be fresh; and

write the updated memory management table to the non-volatile storage device.

17. The storage device of claim 16, wherein the non-volatile storage device is selected from the group consisting of a NAND flash memory device, a phase-change memory device (PCM), a magnetoresistive random access memory device (MRAM), and a resistive random access memory device (ReRAM).

18. A storage device comprising:

a non-volatile storage device;

a random-access storage device; and

a controller coupled to the non-volatile storage device and the random-access storage device, the controller configured to;

receive an indication that a memory management table loaded to a random-access storage device and associated with a non-volatile storage device is in a corrupted state;

retrieve one or more error recovery parameters of a memory unit stored in metadata of a physical block of a plurality of physical blocks of the non-volatile storage device;

examine the one or more error recovery parameters to determine whether the one or more error recovery parameters indicate the memory unit is fresh or stale wherein the memory unit is a first memory unit;

when the first memory unit and a second memory unit both have the same logical address and;

when a sequence number of the error recovery parameters corresponding to the first memory unit is greater than a sequence number corresponding to a second memory unit in the metadata, determine that the memory unit is fresh; and

when the sequence number of the error recovery parameters corresponding to the first memory unit is less than the sequence number corresponding to the second memory unit in the metadata;

determine that the memory unit is stale;

update the memory management table with logical-to-physical translation information of the metadata for the memory unit that is determined to be fresh; and

write the updated memory management table to the non-volatile storage device.

19. A storage device comprising:

means for receiving an indication that a memory management table loaded to a random-access storage device and associated with a non-volatile storage device is in a corrupted state;

means for retrieving one or more error recovery parameters of a first memory unit stored in metadata of a physical block of a plurality of physical blocks of the non-volatile storage device;

means for examining the one or more error recovery parameters to determine whether the one or more error recovery parameters indicate the first memory unit is fresh or stale;

means for determining the first memory unit is fresh if a sequence number of the error recovery parameters corresponding to the first memory unit is greater than a sequence number corresponding to a second memory unit stored in the metadata with the same logical address as the first memory unit;

means for updating the memory management table with logical-to-physical translation information of the metadata for the first memory unit that is determined to be fresh; and

means for writing the updated memory management table to the non-volatile storage device.

20. The storage device of claim 19, further comprising means for determining that the first memory unit is stale.

21. The storage device of claim 19, further comprising means for discarding the one or more error recovery parameters.

22. The storage device of claim 19, further comprising means for updating the metadata with one or more of the error recovery parameters.