Selective relocation of data of a subset of a data block based on distribution of reliability statistics

Patent metadata

Field	Value
Publication number	US-11740805-B2
Application number	US-202217837578-A
Country	US
Kind code	B2
Filing date	Jun 10, 2022
Priority date	Dec 4, 2018
Publication date	Aug 29, 2023
Grant date	Aug 29, 2023

Abstract

A distribution statistic is generated for a data block of a memory component based on a reliability statistic for memory cells sampled in the data block. The distribution statistic is indicative of at least one of a uniformity or a non-uniformity of read disturb stress on the sampled memory cells. At least a subset of the data block is relocated to another data block of the memory component in view of the distribution statistic.

First claim

What is claimed is:

1. A method comprising:
generating a distribution statistic for a data block of a memory component based on a reliability statistic for memory cells sampled in the data block, wherein the distribution statistic is indicative of at least one of a uniformity or a non-uniformity of read disturb stress on the sampled memory cells; and
relocating at least a subset of the data block to another data block of the memory component in view of the distribution statistic.

2. The method of claim 1 , wherein relocating the subset of the data block to the other data block of the memory component in view of the distribution statistic comprises:
determining, based on the distribution statistic, whether the read disturb stress is uniformly or non-uniformly distributed across the data block, wherein the subset of the data block is relocated to the other data block of the memory component in response to determining that the read disturb stress is non-uniformly distributed across the data block.

3. The method of claim 2 , further comprising:
responsive to determining, based on the distribution statistic, that the read disturb stress is uniformly distributed across the data block, relocating one or more additional subsets of the data block with the subset to the other data block.

4. The method of claim 1 , further comprising:
identifying, in view of the distribution statistic, one or more portions of the data block that satisfy a reliability statistic criterion, wherein the subset of the data block comprises the identified one or more portions of the data block.

5. The method of claim 4 , wherein identifying the one or more portions of the data block that satisfy the reliability statistic criterion comprises:
determining that a respective reliability statistic for each memory cell of the one or more portions of the data block exceeds a threshold reliability statistic.

6. The method of claim 4 , wherein identifying the one or more portions of the data block that satisfy the reliability statistic criterion comprises:
responsive to determining that a respective reliability statistic for each sampled memory cell of the data block falls below a threshold reliability statistic, determining that the one or more portions of the data block are associated with a particular range of reliability statistics that is adjacent to the threshold reliability statistic.

7. The method of claim 4 , wherein the one or more portions of the data block are associated with a first range of reliability statistics and one or more additional portions of the data block are associated with a second range of reliability statistics, and wherein identifying the one or more portions of the data block that satisfy the reliability statistic criterion comprises:
determining that a number of memory cells included in the one or more portions of the data block is smaller than a number of memory cells included in the one or more additional portions of the data block.

8. The method of claim 1 , wherein the reliability statistic for each of the sampled memory cells corresponds to a residual bit error rate.

9. The method of claim 1 , wherein the sampled memory cells comprise at least one of one or more memory cells, a wordline, or a group of wordlines of the data block.

10. The method of claim 1 , wherein the distribution statistic corresponds to a statistical metric for reliability statistics for each of the sampled memory cells, the statistical metric comprising at least one of a maximum-minimum delta metric, a maximum-average delta metric, a max-average metric, a max-min average metric, a standard deviation metric, a skewness metric, or a z-score metric.

11. A system comprising:
a memory component comprising a plurality of data blocks each comprising memory cells configured to store data; and
a processing device operatively coupled to the memory component, the processing device to perform operations comprising:
generating a distribution statistic for a data block of a memory component based on a reliability statistic for a portion of the memory cells sampled in the data block, wherein the distribution statistic is indicative of at least one of a uniformity or a non-uniformity of read disturb stress on the sampled portion of the memory cells; and
relocating at least a subset of the data block to another data block of the memory component in view of the distribution statistic.

12. The system of claim 11 , wherein relocating the subset of the data block to the other data block of the memory component in view of the distribution statistic comprises:
determining, based on the distribution statistic, whether the read disturb stress is uniformly or non-uniformly distributed across the data block, wherein the subset of the data block is relocated to the other data block of the memory component in response to determining that the read disturb stress is non-uniformly distributed across the data block.

13. The system of claim 12 , wherein the operations further comprise:
responsive to determining, based on the distribution statistic, that the read disturb stress is uniformly distributed across the data block, relocating one or more additional subsets of the data block with the subset to the other data block.

14. The system of claim 11 , wherein the operations further comprise:
identifying, in view of the distribution statistic, one or more portions of the data block that satisfy a reliability statistic criterion, wherein the subset of the data block comprises the identified one or more portions of the data block.

15. The system of claim 14 , wherein identifying the one or more portions of the data block that satisfy the reliability statistic criterion comprises:
determining that a respective reliability statistic for each memory cell of the one or more portions of the data block exceeds a threshold reliability statistic.

16. The system of claim 14 , wherein identifying the one or more portions of the data block that satisfy the reliability statistic criterion comprises:
responsive to determining that a respective reliability statistic for each sampled memory cell of the data block falls below a threshold reliability statistic, determining that the one or more portions of the data block are associated with a particular range of reliability statistics that is adjacent to the threshold reliability statistic.

17. A non-transitory computer-readable storage medium comprising instructions that, when executed by a processing device, cause the processing device to perform operations comprising:
generating a distribution statistic for a data block of a memory component based on a reliability statistic for memory cells sampled in the data block, wherein the distribution statistic is indicative of at least one of a uniformity or a non-uniformity of read disturb stress on the sampled memory cells; and
relocating at least a subset of the data block to another data block of the memory component in view of the distribution statistic.

18. The non-transitory computer-readable storage medium of claim 17 , wherein relocating the subset of the data block to the other data block of the memory component in view of the distribution statistic comprises:
determining, based on the distribution statistic, whether the read disturb stress is uniformly or non-uniformly distributed across the data block, wherein the subset of the data block is relocated to the other data block of the memory component in response to determining that the read disturb stress is non-uniformly distributed across the data block.

Assignees

• Micron Technology Inc

Inventors

• Malshe Ashutosh
• Muchherla Kishore Kumar
• Rayaprolu Vamsi Vamsi
• Singidi Harish R

Classifications

• G06F3/0619 Primary

  in relation to data integrity, e.g. data losses, bit errors · CPC title

• G06F3/0655

  Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices · CPC title

• G06F3/0679

  Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP] · CPC title

• G06F16/2365

  Ensuring data consistency and integrity · CPC title

• G06F3/0614 Primary

  Improving the reliability of storage systems · CPC title