ERROR HANDLING
Respective error handling (EH) flags can be set based at least in part on media management data of a memory device. Whether any of the EH flags are set can be determined. In response to determining that at least one of the EH flags is set, a subset of a plurality of operations of an EH flow associated with the set EH flags can be performed.
1 . A method, comprising:
determining a status of error handling (EH) flags, which are set based on media management data associated with multiple error mechanisms of a memory device; and
responsive to determining that at least one of the EH flags is set, performing a subset of a plurality of operations of a default EH flow based on which EH flags are set;
wherein the respective EH flags include: an EH flag having its status determined based on a read disturb scan; and an EH flag having its status determined based on a media scan separate from the read disturb scan that involves tracking a quantity of reads for a memory cell.
2 . The method of claim 1 , further comprising, responsive to determining that none of the EH flags are set, performing the plurality of operations of the default EH flow.
3 . The method of claim 1 , including an EH flag having its status determined based on the media scan separate from the read disturb scan, and wherein the media scan separate from the read disturb scan involves cross-temperature data.
4 . The method of claim 3 , wherein the respective EH flags include an EH flag having its status determined based on whether a block of memory cells has experienced a program status failure.
5 . The method of claim 1 , further comprising performing the media scan separate from the read disturb scan periodically.
6 . The method of claim 1 , further comprising obtaining at least a portion of the media management data via a workload dependent scan of the memory device.
7 . The method of claim 1 , wherein at least a portion of the media management data is based on a program operation status of the memory device.
8 . The method of claim 1 , wherein at least a portion of the media management data is based on a difference of a first temperature of a memory cell of the memory device when data is written to the memory cell and a second temperature of the memory cell when the data read from the memory device.
9 . The method of claim 1 , further comprising:
responsive to determining that performing the subset of the plurality of operations of the default EH flow did not resolve an error of the memory device, performing all the plurality of operations of the default EH flow.
10 . An apparatus, comprising:
a memory device; and
a processor coupled to the memory device and configured to:
retrieve memory management data corresponding to the memory device; perform a subset of operations of a default error handling (EH) flow based on the retrieved memory management data,
wherein the subset of operations of the default EH flow performed by the processor is based on EH flags, wherein the EH flags include:
an EH flag having its status determined based on a program operation status failure; and
an EH flag having its status determined based on a media scan separate from a read disturb scan that involves tracking a quantity of reads for a block of memory cells of the memory device.
11 . The apparatus of claim 10 , wherein the EH flags include an EH flag having its status determined based on the media scan separate from the read disturb scan, and wherein the media scan separate from the read disturb scan involves cross-temperature data.
12 . The apparatus of claim 10 , further comprising a local memory coupled to the processor, and
wherein the processor is further configured to retrieve the memory management data from the local memory in response to initiation of the default EH flow.
13 . The apparatus of claim 11 , wherein the processor is further configured to, responsive to powering down of a memory sub-system including the memory device, communicate the memory management data from local memory to the memory device.
14 . The apparatus of claim 13 , wherein the processor is further configured to, responsive to powering up of the memory sub-system, communicate the memory management data from the memory device to the local memory.
15 . The apparatus of claim 10 , wherein memory management data retrieved includes a raw bit error rate (RBER).
16 . The apparatus of claim 10 , wherein the processor is further configured to perform only the respective operations of the default EH flow associated with the EH flags which are set.
17 . The apparatus of claim 10 , wherein:
the default EH flow includes a redundant array of independent NAND (RAIN) recovery operation, and
the processor is further configured to perform the RAIN recovery operation only in response to an associated EH flag being set or all the operations of the default EH flow are performed.
18 . A non-transitory computer-readable medium storing instructions executable by a processing device to:
store memory management data generated by a plurality of memory management operations of a memory device,
set, based at least in part on the memory management data corresponding to at least two different error mechanisms, a plurality of error handling (EH) flags; and
perform, based on the plurality of EH flags, the different operations of an EH flow; wherein the respective EH flags include:
a first EH flag having its status determined based on a read disturb scan that involves tracking a quantity of reads for a block of memory cells; and
a second EH flag having its status determined based on a media scan separate from the read disturb scan.
19 . The computer-readable medium of claim 18 , further storing instructions executable to:
subsequent to performance of the respective operations of the EH flow, determine that a number of errors associated with the at least two different error mechanisms are not resolved; and
responsive to determining that the number of errors associated with the at least two different error mechanisms are not resolved, perform all operations of the EH flow.
20 . The computer-readable medium of claim 18 , wherein:
the plurality of memory management operations include a program operation status of the memory device, and
the medium further stores instructions executable to, responsive to the program operation status indicating a failure:
set a particular one of the number of flags associated with a program failure operation of the EH flow; and
fold the block of data.