Performance and deadlock mitigation during a memory die fail storm
A method is described that includes processing, by a memory subsystem, a read memory command that is addressed to a first die of a memory device. The memory subsystem determines whether processing the read memory command failed to correctly read user data from the first die and, in response to determining that processing the read memory command failed to correctly read user data from the first die, determines whether the first die has failed. In response to determining that the first die has failed, the memory subsystem performs an abbreviated error recovery procedure to successfully perform the read memory command instead of a full error recovery procedure.
1. A method comprising:
processing, by a memory subsystem, a first operation corresponding to a first read memory command that is addressed to a first die of a memory device;
determining, by the memory subsystem, that processing the first operation corresponding to the first read memory command failed to correctly read first user data from the first die;
determining, by the memory subsystem in response to determining that processing the first operation corresponding to the first read memory command failed to correctly read the first user data from the first die, whether the first die has failed; and
performing, by the memory subsystem in response to determining that the first die has failed, an abbreviated error recovery procedure to successfully perform the first operation corresponding to the first read memory command instead of a full error recovery procedure, wherein the abbreviated error recovery procedure skips one or more operations of the full error recovery procedure.
2. The method of claim 1 , further comprising:
processing, by the memory subsystem, a second operation corresponding to a second read memory command that is addressed to a second die of the memory device;
determining, by the memory subsystem, that processing the second operation corresponding to the second read memory command failed to correctly read second user data from the second die;
determining, by the memory subsystem in response to determining that processing the second operation corresponding to the second read memory command failed to correctly read the second user data from the second die, whether the second die has failed; and
performing, by the memory subsystem in response to determining that the second die has not failed, the full error recovery procedure to successfully perform the second operation corresponding to the second read memory command.
3. The method of claim 1 , wherein the full error recovery procedure includes a set of read retries on a corresponding die using a set of read voltages and a redundant array of independent negative AND (NAND) (RAIN) recovery procedure when the set of retries on the corresponding die fails, and
wherein the abbreviated recovery procedure consists of the RAIN recovery procedure.
4. The method of claim 3 , wherein the RAIN recovery procedure includes:
reading first data from a second die of the memory device;
reading second data from a third die of the memory device; and
performing an exclusive-or operation with the first data and the second data to generate the first user data.
5. The method of claim 1 , further comprising:
determining, in response to determining that the first die has failed, a historical rate of success of a redundant array of independent negative AND (NAND) (RAIN) recovery procedure in relation to the first die,
wherein the abbreviated error recovery procedure is performed further in response to determining that the historical rate of success of the RAIN recovery procedure in relation to the first die fails to meet a recovery threshold.
6. The method of claim 5 , further comprising:
generating, by the memory subsystem in response to determining that the historical rate of success of the RAIN recovery procedure in relation to the first die failing to meet a recovery threshold, an error message, which indicates that the first operation corresponding to the first read memory command could not be fulfilled.
7. The method of claim 1 , further comprising:
tracking, by the memory subsystem, memory command errors per die in the memory device, including the first die,
wherein the tracking includes recording a read memory command error in response to failing to correctly read the first user data from the first die.
8. A non-transitory computer-readable storage medium comprising instructions that, when executed by a processing device, cause the processing device to:
process a first operation corresponding to a first read memory command that is addressed to a first die of a memory device of a memory subsystem;
determine that processing the first operation corresponding to the first read memory command failed to correctly read first user data from the first die;
determine, in response to determining that processing the first operation corresponding to the first read memory command failed to correctly read the first user data from the first die, whether the first die has failed; and
perform, in response to determining that the first die has failed, an abbreviated error recovery procedure to successfully perform the first operation corresponding to the first read memory command instead of a full error recovery procedure wherein the abbreviated error recovery procedure skips one or more operations of the full error recovery procedure.
9. The non-transitory computer-readable storage medium of claim 8 , wherein the processing device is further to:
process a second operation corresponding to a second read memory command that is addressed to a second die of the memory device;
determine that processing the second operation corresponding to the second read memory command failed to correctly read second user data from the second die;
determine, in response to determining that processing the second operation corresponding to the second read memory command failed to correctly read the second user data from the second die, whether the second die has failed; and
perform, in response to determining that the second die has not failed, the full error recovery procedure to successfully perform the second operation corresponding to the second read memory command.
10. The non-transitory computer-readable storage medium of claim 8 , wherein the full error recovery procedure includes a set of read retries on a corresponding die using a set of read voltages and a redundant array of independent negative AND (NAND) (RAIN) recovery procedure when the set of retries on the corresponding die fails, and
wherein the abbreviated recovery procedure consists of the RAIN recovery procedure.
11. The non-transitory computer-readable storage medium of claim 10 , wherein the RAIN recovery procedure includes:
reading first data from a second die of the memory device;
reading second data from a third die of the memory device; and
performing an exclusive-or operation with the first data and the second data to generate the first user data.
12. The non-transitory computer-readable storage medium of claim 8 , wherein the processing device is further to:
determine, in response to determining that the first die has failed, a historical rate of success of a redundant array of independent negative AND (NAND) (RAIN) recovery procedure in relation to the first die,
wherein the abbreviated error recovery procedure is performed further in response to determining that the historical rate of success of the RAIN recovery procedure in relation to the first die fails to meet a recovery threshold.
13. The non-transitory computer-readable storage medium of claim 12 , wherein the processing device is further to:
generate, in response to determining that the historical rate of success of the RAIN recovery procedure in relation to the first die failing to meet a recovery threshold, an error message, which indicates that the first operation corresponding to the first read memory command could not be fulfilled.
14. The non-transitory computer-readable storage medium of claim 8 , wherein the processing device is further to:
track memory command errors per die in the memory device, including the first die,
wherein the tracking includes recording a read memory command error in response to failing to correctly read the first user data from the first die.
15. A system comprising:
a memory device; and
a processing device, operatively coupled with the memory device, to:
process a first read operation corresponding to a first memory command that is addressed to a first die of the memory device;
determine, in response to determining that processing the first operation corresponding to the first read memory command failed to correctly read first user data from the first die, whether the first die has failed; and
perform, in response to determining that the first die has failed, an abbreviated error recovery procedure to successfully perform the first operation corresponding to the first read memory command instead of a full error recovery procedure, wherein the abbreviated error recovery procedure skips one or more operations of the full error recovery procedure.
16. The system of claim 15 , wherein the processing device is further to:
process a second operation corresponding to a second read memory command that is addressed to a second die of the memory device;
determine that processing the second operation corresponding to the second read memory command failed to correctly read second user data from the second die;
determine, in response to determining that processing the second operation corresponding to the second read memory command failed to correctly read the second user data from the second die, whether the second die has failed; and
perform, in response to determining that the second die has not failed, the full error recovery procedure to successfully perform the second operation corresponding to the second read memory command.
17. The system of claim 15 , wherein the full error recovery procedure includes a set of read retries on a corresponding die using a set of read voltages and a redundant array of independent negative AND (NAND) (RAIN) recovery procedure when the set of retries on the corresponding die fails, and
wherein the abbreviated recovery procedure consists of the RAIN recovery procedure.
18. The system of claim 17 , wherein the RAIN recovery procedure includes:
reading first data from a second die of the memory device;
reading second data from a third die of the memory device; and
performing an exclusive-or operation with the first data and the second data to generate the first user data.
19. The system of claim 15 , wherein the processing device is further to:
determine, in response to determining that the first die has failed, a historical rate of success of a redundant array of independent negative AND (NAND) (RAIN) recovery procedure in relation to the first die,
wherein the abbreviated error recovery procedure is performed further in response to determining that the historical rate of success of the RAIN recovery procedure in relation to the first die fails to meet a recovery threshold.
20. The system of claim 19 , wherein the processing device is further to:
generate, in response to determining that the historical rate of success of the RAIN recovery procedure in relation to the first die failing to meet a recovery threshold, an error message, which indicates that the first operation corresponding to the first read memory command could not be fulfilled.