Selective ECC refresh for on die buffered non-volatile memory

• US 9,489,263 B2
• Filed: 01/09/2015
• Issued: 11/08/2016
• Est. Priority Date: 01/09/2014
• Status: Active Grant

• Current Assignee: SanDisk Technologies LLC (Western Digital Corporation)
• Original Assignee: SanDisk Technologies LLC (Western Digital Corporation)
• Inventors: Hyun, Jea, Wood, Robert
• Primary Examiner(s): Chase, Shelly A
• Application Number:
  US14/593,965
• Publication Number:
  US 20150193302A1
• Time in Patent Office: 669 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/1072 in multilevel memories
• CPC Class Codes: G06F 11/108 Parity data distribution in semiconductor storages, e.g. in SSD
• CPC Class Codes: G11C 16/349 Arrangements for evaluating degradation, retention or wearout, e.g. by counting erase cycles
• CPC Class Codes: G11C 2211/5641 Multilevel memory having cells with different number of storage levels
• CPC Class Codes: G11C 29/021 in voltage or current generators
• CPC Class Codes: G11C 29/028 with adaption or trimming of parameters
• CPC Class Codes: G11C 29/52 Protection of memory contents; Detection of errors in memory contents

Abstract

Apparatuses, systems, methods, and computer program products are disclosed for on die buffered non-volatile memory management. A method includes storing data in a first set of non-volatile memory cells. A method includes determining whether to perform an error-correcting code (ECC) refresh for data to be copied from a first set of non-volatile memory cells to a second set of non-volatile memory cells based on one or more attributes associated with the data. A method includes storing data in a second set of non-volatile storage cells representing data using more storage cells per cell than a first set of non-volatile storage cells.

Claims

1. A method comprising:

determining whether to perform an error correcting code (ECC) refresh for data to be copied from a first set of non-volatile memory cells to a second set of non-volatile memory cells based on one or more attributes associated with the data, the second set of non-volatile memory cells configured to store more bits per cell than the first set of non-volatile memory cells;

adjusting one or more read voltage thresholds for the first set of non-volatile memory cells in response to determining to perform the ECC refresh; and

reading the data from the first set of non-volatile memory cells using the adjusted one or more read voltage thresholds for copying the data to the second set of non-volatile memory cells.

2. The method of claim 1, further comprising storing the data in the second set of non-volatile memory cells by writing the data stored in the first set of non-volatile memory cells to the second set of non-volatile memory cells internally within a non-volatile memory element comprising the first and second sets of non-volatile memory cells in response to determining not to perform the ECC refresh.

3. The method of claim 1, wherein the one or more read voltage thresholds for the first set of non-volatile memory cells is adjusted proactively based on one or more storage media characteristics for the first set of non-volatile memory cells.

4. The method of claim 3, wherein the one or more storage media characteristics comprise one or more of a program/erase cycle count, a read count, a retention time, a temperature, and an error rate for the first set of non-volatile memory cells.

5. The method of claim 1, further comprising aborting copying of the data to the second set of non-volatile memory cells in response to a power level failing to satisfy a threshold, and erasing the second set of non-volatile memory cells and accessing the data from the first set of non-volatile memory cells after recovery from the power level failing.

6. The method of claim 1, further comprising marking the second set of non-volatile memory cells as filled in response to storing the data in the second set of non-volatile memory cells and erasing one or more sets of non-volatile memory cells not marked as filled after recovery from a power level failing to satisfy a threshold.

7. The method of claim 1, wherein the one or more attributes associated with the data comprise one or more of a write frequency for the data, a read frequency for the data, a quality-of-service level for the data, an age for the data, an error rate for the data, a capacity threshold being satisfied for the first set of non-volatile memory cells, and a program/erase cycle count for the first set of non-volatile memory cells.

8. An apparatus comprising:

a buffer module configured to store data in a first set of non-volatile storage cells;

a refresh module configured to determine whether to perform an error-correcting code (ECC) refresh for the data for storing the data in a second set of non-volatile storage cells based on one or more data factors; and

a copyback module configured to store the data in the second set of non-volatile storage cells, the second set of non-volatile storage cells representing data using more storage states per cell than the first set of non-volatile storage cells.

9. The apparatus of claim 8, wherein the refresh module is configured to perform an ECC refresh for the data by decoding one or more ECC code words of the data using an error-correcting code decoder and by re-encoding the data using an error-correcting code encoder for storing the re-encoded data in the second set of non-volatile storage cells.

10. The apparatus of claim 9, wherein the refresh module is further configured to re-packetize the re-encoded data.

11. The apparatus of claim 8, further comprising a read voltage module configured to determine one or more read voltage thresholds for the first set of non-volatile storage cells proactively based on one or more storage media characteristics for the first set of non-volatile storage cells, the copyback module configured to use the one or more read voltage thresholds to read the data from the first set of non-volatile storage cells for storing in the second set of non-volatile storage cells.

12. The apparatus of claim 8, further comprising a logical-to-physical mapping module configured to maintain a first logical-to-physical mapping for a location of the data in the first set of non-volatile storage cells and to maintain a second logical-to-physical mapping for a location of the data in the second set of non-volatile storage cells.

13. The apparatus of claim 8, further comprising a storage capacity recovery module configured to recover storage capacity of the first set of non-volatile storage cells in response to one or more of the copyback module verifying data integrity of the data in the second set of non-volatile storage cells, an access rate for the data failing to satisfy an access threshold, a quality-of-service level for the data failing to satisfy a threshold, and a storage capacity threshold being satisfied.

14. The apparatus of claim 8, wherein the copyback module is configured to verify integrity of the data in the second set of non-volatile storage cells in response to a trigger, the trigger comprising at least one of a read request for the data, a background scan of the second set of non-volatile storage cells, a storage capacity threshold being satisfied, and a storage capacity recovery event for the first set of non-volatile storage cells.

15. The apparatus of claim 8, further comprising a power-cut module configured to abort the copyback module storing the data in the second set of non-volatile storage cells in response to a power level failing to satisfy a threshold and to erase the second set of non-volatile storage cells in response to recovery from the power level failing such that the data is accessed from the first set of non-volatile storage cells after recovery from the power level failing.

16. The apparatus of claim 8, further comprising a power-cut module configured to mark the second set of non-volatile storage cells as filled in response to the copyback module storing the data to the second set of non-volatile storage cells and to erase one or more sets of non-volatile storage cells not marked as filled after recovery from a power level failing to satisfy a threshold.

17. The apparatus of claim 8, further comprising a data factor module configured to maintain metadata indicating the one or more data factors over time based on at least one of a storage request for the data and a background scan of the data, the data factor module configured to determine the one or more data factors by reading at least a subset of the data from the first set of non-volatile storage cells and factoring in results of the reading of the at least a subset to determine the one or more data factors.

18. The apparatus of claim 8, wherein the copyback module is configured to store the data in the second set of non-volatile storage cells by writing the data from the first set of non-volatile storage cells to the second set of non-volatile storage cells internally within a non-volatile memory element comprising the first and second sets of cells in response to the refresh module determining not to perform the ECC refresh.

19. A system comprising:

a non-volatile memory element comprising a set of single level cell (SLC) non-volatile memory cells and a set of triple level cell (TLC) non-volatile memory cells; and

a controller that buffers data in the set of SLC non-volatile memory cells and copies the data to the set of TLC non-volatile memory cells, the controller selectively determining whether to perform an error-correcting code (ECC) refresh for storing the data in the TLC non-volatile memory cells based on one or more data factors.

20. The system of claim 19, wherein the controller performs the ECC refresh by performing an error-correcting code (ECC) decode for the data from the set of SLC non-volatile memory cells and an ECC re-encode for the data for copying to the set of TLC non-volatile memory cells.