Data storage device and method for time-pooled hot data relocation
Post-write data management operations, such as refresh read, data scrub, and data relocation, are typically performed after a certain period of time has elapsed. However, performing such operations based on probability of access can provide advantages. So, in one example, a post-write data management operation is performed more frequently on relatively-warmer data than on relatively-colder data.
1. A data storage device comprising:
a memory; and
a processor coupled with the memory and configured to perform as part of a garbage collection operation:
determine whether data stored in a source block in the memory has been read by a host more than a threshold number of times;
in response to determining that the data has been read by the host more than the threshold number of times, move the data to a first destination block;
in response to determining that the data has not been read by the host more than the threshold number of times, determine whether the data is from a host write;
in response to determining that the data is from the host write, move the data to a second destination block, wherein the second destination block is less likely to be accessed within a time period than the first destination block;
in response to determining that the data is not from a host write, determine whether the data is from a warm block;
in response to determining that the data is from a warm block, move the data to a third destination block, wherein the third destination block is less likely to be accessed within the time period than the second destination block; and
in response to determining that the data is not from a warm block, move the data to a fourth destination block, wherein the fourth destination block is less likely to be accessed within the time period than the third destination block.
2. The data storage device of claim 1 , wherein the processor is further configured to perform a post-write data management operation on the data in response to a determination that that data is at risk of being lost.
3. The data storage device of claim 2 , wherein the post-write data management operation comprises a refresh read operation.
4. The data storage device of claim 2 , wherein the post-write data management operation comprises a read scrub operation.
5. The data storage device of claim 2 , wherein the post-write data management operation comprises a data relocation operation.
6. The data storage device of claim 2 , wherein the determination that the data is at risk of being lost is made when the data has been stored longer than a threshold amount of time in the memory.
7. The data storage device of claim 2 , wherein the determination that the data is at risk of being lost is done when the data storage device boots up.
8. The data storage device of claim 2 , wherein the data at risk of being lost is stored in a block and the post-write data management operation is only performed on a part of the block that stores the data at risk of being lost.
9. The data storage device of claim 1 , wherein the memory comprises a three-dimensional memory array.
10. A data storage device comprising:
a memory; and
means for performing as part of a garbage collection operation:
determining whether data stored in a source block in the memory has been read by a host more than a threshold number of times;
in response to determining that the data has been read by the host more than the threshold number of times, moving the data to a first destination block;
in response to determining that the data has not been read by the host more than the threshold number of times, determining whether the data is from a host write;
in response to determining that the data is from the host write, moving the data to a second destination block, wherein the second destination block is less likely to be accessed within a time period than the first destination block;
in response to determining that the data is not from a host write, determining whether the data is from a warm block;
in response to determining that the data is from a warm block, moving the data to a third destination block, wherein the third destination block is less likely to be accessed within the time period than the second destination block; and
in response to determining that the data is not from a warm block, moving the data to a fourth destination block, wherein the fourth destination block is less likely to be accessed within the time period than the third destination block.
11. In a data storage device comprising a memory, a method comprising:
performing as part of a garbage collection operation:
determining whether data stored in a source block in the memory has been read by a host more than a threshold number of times;
in response to determining that the data has been read by the host more than the threshold number of times, moving the data to a first destination block;
in response to determining that the data has not been read by the host more than the threshold number of times, determining whether the data is from a host write;
in response to determining that the data is from the host write, moving the data to a second destination block, wherein the second destination block is less likely to be accessed within a time period than the first destination block;
in response to determining that the data is not from a host write, determining whether the data is from a warm block;
in response to determining that the data is from a warm block, moving the data to a third destination block, wherein the third destination block is less likely to be accessed within the time period than the second destination block; and
in response to determining that the data is not from a warm block, moving the data to a fourth destination block, wherein the fourth destination block is less likely to be accessed within the time period than the third destination block.
12. The method of claim 11 , further comprising performing a post-write data management operation on the data in response to a determination that that data is at risk of being lost.
13. The method of claim 12 , wherein the post-write data management operation comprises a refresh read operation.
14. The method of claim 12 , wherein the post-write data management operation comprises a read scrub operation.
15. The method of claim 12 , wherein the post-write data management operation comprises a data relocation operation.
16. The method of claim 12 , wherein the determination that the data is at risk of being lost is made when the data has been stored longer than a threshold amount of time in the memory.
17. The method of claim 12 , wherein the determination that the data is at risk of being lost is done when the data storage device boots up.
18. The method of claim 12 , wherein the data at risk of being lost is stored in a block and the post-write data management operation is only performed on a part of the block that stores the data at risk of being lost.
19. The method of claim 11 , wherein the memory comprises a three-dimensional memory array.