Selective relocation of data of a subset of a data block based on distribution of reliability statistics
A data integrity check is performed on a data block of the memory component to obtain a reliability statistic for each of a set of sampled memory cells in the data block. A distribution statistic is determined based on the reliability statistic for each of the set of sampled memory cells. A subset of the data block is identified to be relocated to another data block of the memory component based on the distribution statistic. Data of the subset of the data block is relocated to the other data block.
1. A system comprising:
a memory component; and
a processing device, operatively coupled with the memory component, to:
obtain a reliability statistic for each of a set of sampled memory cells in a data block of the memory component;
determine a distribution statistic based on the reliability statistic for each of the set of sampled memory cells;
determine, based on the distribution statistic, that read disturb stress is concentrated on a subset of the data block; and
relocate data of the subset of the data block to another data block of the memory component.
2. The system of claim 1 , wherein the processing device is further to:
determine that a number of read operations performed on the data block satisfies a read threshold criterion, wherein the processing device is to obtain the reliability statistic for each of the set of sampled memory cells in response to determining that the number of read operations satisfies the read threshold criterion.
3. The system of claim 1 , wherein to obtain a reliability statistic for each of the set of sampled memory cells, the processing device is to:
perform an error correction operation on second data stored at the subset of the data block.
4. The system of claim 1 , wherein the reliability statistic for each of the set of sampled memory cells in the data block correspond to a residual bit error rate (RBER).
5. The system of claim 1 , wherein the set of sampled memory cells in the data block comprises at least one of one or more memory cells, a word line, or a group of word lines of the data block.
6. The system of claim 1 , wherein, to determine that read disturb stress is concentrated on a subset of the data block, the processing device is to:
determine that the distribution statistic for the data of the subset of the data block satisfies a distribution statistic threshold criterion.
7. The system of claim 1 , wherein the memory component comprises NAND flash memory cells.
8. The system of claim 1 , wherein the distribution statistic corresponds to a uniformity of read disturb stress in the data block.
9. A method comprising:
determining that a number of read operations performed on a data block of a memory component satisfies a read threshold criterion;
in response to determining the number of read operations performed on the data block of the memory component satisfies the read threshold criterion, obtaining reliability statistics for a set of sampled memory cells in the data block;
generating a distribution statistic based on the reliability statistics for the set of sampled memory cells;
in response to determining that the distribution statistic satisfies a distribution statistic threshold criterion, determining, based on the distribution statistic, that read disturb is concentrated on a subset of the data block; and
storing data stored at the subset of the data block at another data block of the memory component.
10. The method of claim 9 , wherein the distribution statistic corresponds to a uniformity of read disturb stress in the data block.
11. The method of claim 9 , wherein the set of sampled memory cells in the data block comprises at least one of one or more memory cells, a word line, or a group of word lines of the data block.
12. The method of claim 9 , wherein the reliability statistic for each of the set of sampled memory cells in the data block correspond to a residual bit error rate (RBER).
13. The method of claim 12 , wherein storing the data stored at the subset of the data block at the other data block further comprises:
identifying second data stored at a second subset of the data block; and
determining to not store the second data at the other data block.
14. The method of claim 9 , further comprising:
upon storing the data at the other data block, erasing the data stored at the subset of the data block.
15. A non-transitory computer-readable storage medium comprising instructions that, when executed by a processing device, cause the processing device to:
obtain a reliability statistic for each of a set of sampled memory cells in a data block of a memory component;
determine a distribution statistic based on the reliability statistic for each of the set of sampled memory cells;
determine, based on the distribution statistic, that read disturb stress is concentrated on a subset of the data block; and
relocate data of the subset of the data block to another data block of the memory component.
16. The non-transitory computer-readable storage medium of claim 15 , wherein the processing device is further to:
determine that a number of read operations performed on the data block satisfies a read threshold criterion, wherein the processing device is to obtain the reliability statistic for each of the set of sampled memory cells in response to determining that the number of read operations satisfies the read threshold criterion.
17. The non-transitory computer-readable storage medium of claim 15 , wherein to obtain a reliability statistic for each of the set of sampled memory cells, the processing device is to:
perform an error correction operation on second data stored at the subset of the data block.
18. The non-transitory computer-readable storage medium of claim 15 , wherein the reliability statistic for each of the set of sampled memory cells in the data block correspond to a residual bit error rate (RBER).
19. The non-transitory computer-readable storage medium of claim 15 , wherein the set of sampled memory cells in the data block comprises at least one of one or more memory cells, a word line, or a group of word lines of the data block.
20. The non-transitory computer-readable storage medium of claim 15 , wherein the distribution statistic based on the reliability statistic for each of the set of sampled memory cells comprises at least one of: maximum-minimum delta, maximum-average delta, standard deviation or skewness.