Memory system failure detection and self recovery of memory dice
Exemplary methods, apparatuses, and systems including memory self-recovery management to correct failures due to soft-error rate events. The self-recovery manager detects a failure of a memory device. The self-recovery manager retrieves a set of register values from the memory device. The self-recovery manager stores the set of register values from the memory device. The self-recovery manager issues a reset command to the memory device, the reset command including generating a re-initialized set of register values. The self-recovery manager compares the set of register values with the re-initialized set of register values. The self-recovery manager triggering a self-recovery attempt using the comparison of the set of register values with the re-initialized set of register values.
1. A method of error recovery, the method comprising:
detecting a failure of a memory device;
retrieving a set of register values from the memory device;
storing the set of register values from the memory device;
issuing a reset command to the memory device, wherein the reset command includes generating a re-initialized set of register values;
comparing the set of register values with the re-initialized set of register values; and
triggering a self-recovery attempt using the comparison of the set of register values with the re-initialized set of register values.
2. The method of claim 1 , wherein detecting the failure comprises detecting an indication of a retirement of one or more dice of the memory device.
3. The method of claim 1 , wherein the reset command includes a power cycling, and wherein the re-initialized set of register values correspond to a default value stored in a non-volatile storage location.
4. The method of claim 1 further comprising:
identifying, based on the comparison of the set of register values with the re-initialized set of register values, that the set of register values represents an unexpected state;
recovering, in response to identifying the unexpected state, from the unexpected state using the re-initialized set of register values; and
determining, in response to recovering from the unexpected state, a status of the memory device.
5. The method of claim 1 , wherein detecting the failure of the memory device comprises identifying a number of grown bad blocks over a time interval satisfies a threshold rate of grown bad blocks.
6. The method of claim 1 , wherein detecting the failure of the memory device comprises:
computing a rate of failures of the memory device;
comparing the rate of failures with an expected failure rate of the memory device, wherein the expected failure rate is a statistical estimate of manufacturing deviation; and
determining a failure state when the rate of failures is greater than the expected failure rate.
7. The method of claim 1 , wherein triggering a self-recovery attempt using the comparison of the set of register values with the re-initialized set of register values comprises:
computing a difference of the set of register values and the re-initialized set of register values;
determining that the difference satisfies a threshold; and
in response to determining that the difference satisfies a threshold, triggering a self-recovery attempt.
8. The method of claim 7 , further comprising:
determining that the difference does not satisfy a threshold; and
in response to determining that the difference does not satisfy a threshold, resuming normal error handling.
9. A non-transitory computer-readable storage medium comprising instructions that, when executed by a processing device, cause the processing device to:
detect a failure of a memory device;
retrieve a set of trim values from the memory device;
store the set of trim values in a non-volatile memory location;
issue a reset command to the memory device, wherein the reset command includes generating a re-initialized set of trim values;
compare the set of trim values with the re-initialized set of trim values; and
trigger a self-recovery attempt using the comparison of the set of trim values with the re-initialized set of trim values.
10. The non-transitory computer-readable storage medium of claim 9 , wherein the instructions that cause the processing device to detect the failure comprise instructions that, when executed by a processing device, cause the processing device to detect an indication of a retirement of one or more dice of the memory device.
11. The non-transitory computer-readable storage medium of claim 9 , wherein the reset command includes a power cycling, and wherein the re-initialized set of trim values are a set of default values stored in a non-volatile storage location.
12. The non-transitory computer-readable storage medium of claim 9 , the instructions further causing the processing device to:
identify, using the comparison of the set of trim values with the re-initialized set of trim values, that the set of trim values represents an unexpected state;
recover from the unexpected state using the re-initialized set of trim values; and
determine, in response to recovering from the unexpected state, a status of the memory device.
13. The non-transitory computer-readable storage medium of claim 9 , wherein the instructions that cause the processing device to detect the failure of the memory device comprise instructions that, when executed by a processing device, cause the processing device to identify a number of grown bad blocks over a time interval satisfies a threshold rate of grown bad blocks.
14. The non-transitory computer-readable storage medium of claim 9 , wherein the instructions that cause the processing device to detect the failure of the memory device comprise instructions that, when executed by a processing device, cause the processing device to:
compute a rate of failures of the memory device;
compare the rate of failures with an expected failure rate of the memory device, wherein the expected failure rate is a statistical estimate of manufacturing deviation; and
determine a failure state when the rate of failures is greater than the expected failure rate.
15. The non-transitory computer-readable storage medium of claim 9 , wherein the instructions that cause the processing device to trigger a self-recovery attempt using the comparison of the set of trim values with the re-initialized set of trim values comprise instructions that, when executed by a processing device, cause the processing device to:
compute a difference of the set of trim values and the re-initialized set of trim values;
determine that the difference satisfies a threshold; and
in response to determining that the difference satisfies a threshold, trigger a self-recovery attempt.
16. A system comprising:
a plurality of memory devices; and
a processing device, operatively coupled with the plurality of memory devices, to:
detect a failure of a memory device;
retrieve a set of trim values from the memory device;
store the set of trim values from the memory device;
issue a reset command to the memory device, wherein the reset command includes generating a re-initialized set of trim values;
compare the set of trim values with the re-initialized set of trim values; and
trigger a self-recovery attempt using the comparison of the set of trim values with the re-initialized set of trim values, wherein triggering the self-recovery attempt comprises:
computing a difference of the set of register values and the re-initialized set of register values;
determining that the difference satisfies a threshold; and
in response to determining that the difference satisfies a threshold, triggering a self-recovery attempt.
17. The system of claim 16 , the processing device, operatively coupled with the plurality of memory devices, further to detect an indication of a retirement of one or more dice of the memory device.
18. The system of claim 16 , wherein the reset command includes a power cycling, and wherein the re-initialized set of trim values correspond to a set of default values.
19. The system of claim 16 , the processing device, operatively coupled with the plurality of memory devices, further to:
identify, based on the comparison of the set of trim values with the re-initialized set of trim values, that the set of trim values represents an unexpected state;
recover from the unexpected state using the re-initialized set of trim values; and
determine, in response to recovering from the unexpected state, a status of the memory device.
20. The system of claim 16 , the processing device, operatively coupled with the plurality of memory devices, further to:
compute a rate of failures of the memory device;
compare the rate of failures with an expected failure rate of the memory device, wherein the expected failure rate is a statistical estimate of manufacturing deviation; and
determine a failure state when the rate of failures is greater than the expected failure rate.