Systems and methods for identifying storage resources that are not in use
An apparatus, system, and method are disclosed for managing a non-volatile storage medium. A storage controller receives a message that identifies data that no longer needs to be retained on the non-volatile storage medium. The data may be identified using a logical identifier. The message may comprise a hint, directive, or other indication that the data has been erased and/or deleted. In response to the message, the storage controller records an indication that the contents of a physical storage location and/or physical address associated with the logical identifier do not need to be preserved on the non-volatile storage medium.
1. A method for managing data in a NAND flash storage system, the method comprising:
receiving an empty-block directive from a host at a storage controller in the NAND flash storage system, the empty-block directive including a logical identifier associated with a physical storage location comprising data that does not need to be preserved;
returning by the storage controller an indication that the logical identifier is empty, in response to a read command from the host requesting to read the data identified by the logical identifier included in the empty-block directive, wherein the data in the physical storage location remains on the NAND flash storage system;
maintaining by the storage controller an index of mappings between the logical identifier and the physical storage location; and
updating the index of mappings by the storage controller, in response to the empty-block directive, to indicate that the data in the physical storage location does not need to be preserved.
2. The method of claim 1 , wherein the indication is at least one zero.
3. The method of claim 1 , further comprising:
determining that the empty-block directive further includes an indication that the data identified by the logical identifier should be overwritten; and
overwriting the data identified by the logical identifier.
4. The method of claim 1 , wherein the empty-block directive is part of a block storage protocol.
5. The method of claim 1 , wherein the empty-block directive is received through an application programming interface.
6. The method of claim 1 , wherein the empty-block directive is received from a file system.
7. A method for managing data in a system having a host processor and a block-based NAND flash storage system, the NAND flash storage system having physical NAND flash storage locations controlled by a NAND controller, the method comprising:
receiving, via the host processor, an indication of deletion of a file at the host processor;
creating, via the host processor, an empty-block identifier in response to the indication of deletion;
receiving, via the NAND controller, the empty-block identifier;
maintaining, via the NAND controller, an index of mappings between logical identifiers and physical NAND flash storage locations; and
updating the index of mappings, in response to the receiving the empty-block identifier, to indicate that data associated with the file on one or more of the physical NAND flash storage locations identified by the empty-block identifier does not need to be preserved.
8. The method of claim 7 , further comprising:
receiving, via the NAND controller, a read command including a logical identifier that was associated with the empty-block; and
returning, via the NAND controller, a data string indicating that the logical identifier is empty in response to the receiving the read command.
9. The method of claim 8 , wherein the data string comprises at least one zero.
10. The method of claim 7 , wherein the empty-block identifier indicates that the data associated with the file on the one or more physical NAND flash storage locations identified by the empty-block identifier should be overwritten.
11. The method of claim 7 , further comprising transmitting a message indicating that the data associated with the file on one or more physical NAND flash storage locations identified by the empty-block identifier has been overwritten.
12. The method of claim 7 , further comprising overwriting the data associated with the file on the one or more physical NAND flash storage locations identified by the empty-block identifier with a series of characters such that the overwritten data is non-recoverable.
13. The method of claim 7 , further comprising performing garbage collection, via the NAND controller, in the NAND flash storage system.
14. The method of claim 13 , wherein performing garbage collection comprises:
copying a block containing data that should be preserved from an erase block comprising blocks containing data that does not need to be preserved; and
erasing the erase block.
15. The method of claim 14 , further comprising writing the copied data, via the NAND controller, to the erased erase block.
16. The method of claim 7 , wherein the NAND flash storage system is an append-only storage system.
17. The method of claim 14 , wherein each of the one or more physical NAND flash storage locations are smaller than the erase block.
18. The method of claim 1 , further comprising transmitting a message indicating that the data in the physical storage location has been deleted in response to a delete command.
19. The method of claim 1 , further comprising overwriting the data in the physical storage location with a series of characters such that the overwritten data is non-recoverable.
20. The method of claim 1 , further comprising removing a mapping between the logical identifier and the physical storage location from the index of mappings; and erasing the data stored in the physical storage location.