System and method of direct write and mapping of data in a non-volatile memory having multiple sub-drives
A system and method is disclosed for managing data in a non-volatile memory. The system may include a non-volatile memory having multiple non-volatile memory sub-drives. A controller of the memory system is configured to route incoming host data to a desired sub-drive, keep data within the same sub-drive as its source during a garbage collection operation, and re-map data between sub-drives, separate from any garbage collection operation, when a sub-drive overflows its designated amount logical address space. The method may include initial data sorting of host writes into sub-drives based on any number of hot/cold sorting functions. In one implementation, the initial host write data sorting may be based on a host list of recently written blocks for each sub-drive and a second write to a logical address encompassed by the list may trigger routing the host write to a hotter sub-drive than the current sub-drive.
1. A method for managing data, the method comprising:
receiving a data write;
directing the data write to one of a plurality of sub-drives in a storage device;
determining whether a valid data characteristic of the one of the plurality of sub-drives meets a logical address space criteria; and
when the valid data characteristic of the one of the plurality of sub-drives meets the logical address space criteria, re-mapping a superblock from the one of the plurality of sub-drives to another of the plurality of sub-drives, without rewriting any data from the superblock to another physical location, based on a current data temperature of the superblock.
2. The method of claim 1 , wherein re-mapping the superblock comprises selecting a coldest superblock of a sub-drive containing a valid data characteristic that meets the logical address space criteria, and re-mapping the coldest superblock to a next colder sub-drive of the plurality of sub-drives in the storage device.
3. The method of claim 1 , wherein re-mapping the superblock from the one of the plurality of sub-drives to another of the plurality of sub-drives comprises:
remapping the superblock to a next colder sub-drive of the plurality of sub-drives, wherein the next colder sub-drive comprises a sub-drive associated with data having a data temperature less than a data temperature of data associated with the one of the plurality of sub-drives.
4. The method of claim 3 , further comprising selecting a coldest superblock of the one of the plurality of sub-drives and logically remapping the coldest superblock to the next colder sub-drive.
5. The method of claim 1 , wherein re-mapping the superblock from the one of the plurality of sub-drives to another of the plurality of sub-drives comprises:
remapping the superblock to a next hotter sub-drive, the next hotter sub-drive comprising a sub-drive associated with data having a data temperature greater than a data temperature of data associated with the one of the plurality of sub-drives.
6. The method of claim 5 , further comprising selecting a hottest superblock of the one of the plurality of sub-drives and logically remapping the hottest superblock to the next hotter sub-drive.
7. The method of claim 1 , wherein directing the data write to one of the plurality of sub-drives based on a first sorting technique comprises:
writing data associated with logical block addresses to a next hotter sub-drive relative to last sub-drive that previous data associated with the logical block addresses was written to.
8. A storage system, comprising:
means for receiving a data write;
means for directing the data write to one of a plurality of sub-drives in a storage device;
means for determining whether a valid data characteristic of the one of the plurality of sub-drives meets a logical address space criteria; and
when the valid data characteristic of the one of the plurality of sub-drives meets the logical address space criteria, means for re-mapping a superblock from the one of the plurality of sub-drives to another of the plurality of sub-drives, without rewriting any data from the superblock to another physical location, based on a current data temperature of the superblock.
9. The storage system of claim 8 , wherein means for re-mapping the superblock comprises means for selecting a coldest superblock of a sub-drive containing a valid data characteristic that meets the logical address space criteria, and means for re-mapping the coldest superblock to a next colder sub-drive of the storage device.
10. The storage system of claim 8 , wherein a detected garbage collection trigger comprises a number of shared free blocks for the plurality of sub-drives falling below a predetermined threshold.
11. The storage system of claim 10 , comprising:
means for moving valid data during a garbage collection operation from a source superblock by first selecting a sub-drive from which to select the source superblock based on an analysis of write amplification for an entirety of the storage device for a current workload.
12. The storage system of claim 11 , wherein selecting the sub-drive from which to select the source superblock comprises selecting the sub-drive based on a calculated target overprovisioning of each of the plurality of sub-drives.
13. The storage system of claim 11 , comprising means for selecting as the source superblock for the selected sub-drive based on a valid data characteristic in the source superblock.
14. The storage system of claim 8 , further comprising
means for selecting, as a particular sub-drive for initiating a garbage collection operation, a sub-drive having a greatest amount of overprovisioning over a target overprovisioning level, wherein the target overprovisioning level differs for each of the plurality of sub-drives and is based on a respective portion of a total logical address space of the storage device currently associated with each of the plurality of sub-drives and a total host write workload attributed to each of the plurality of sub-drives.
15. A storage system, comprising:
a storage device having a plurality of sub-drives;
one or more controllers configured to cause:
receiving a data write;
directing the data write to one of the plurality of sub-drives in the storage device;
determining whether a valid data characteristic of the one of the plurality of sub-drives meets a logical address space criteria; and
when the valid data characteristic of the one of the plurality of sub-drives meets the logical address space criteria, re-mapping a superblock from the one of the plurality of sub-drives to another of the plurality of sub-drives, without rewriting any data from the superblock to another physical location, based on a current data temperature of the superblock.
16. The storage system of claim 15 , wherein re-mapping the superblock comprises selecting a coldest superblock of a sub-drive containing a valid data characteristic that meets the logical address space criteria, and re-mapping the coldest superblock to a next colder sub-drive of the storage device.
17. The storage system of claim 15 , wherein a detected garbage collection trigger comprises a number of shared free blocks for the plurality of sub-drives falling below a predetermined threshold.
18. The storage system of claim 17 , wherein the one or more controllers are configured to cause:
moving valid data during a garbage collection operation from a source superblock by
first selecting a sub-drive from which to select the source superblock based on an analysis of write amplification for an entirety of the storage device for a current workload.
19. The storage system of claim 18 , wherein selecting the sub-drive from which to select the source superblock comprises selecting the sub-drive based on a calculated target overprovisioning of each of the plurality of sub-drives.
20. The storage system of claim 15 , wherein the one or more controllers are configured to cause:
selecting, as a particular sub-drive for initiating a garbage collection operation, a sub-drive having a greatest amount of overprovisioning over a target overprovisioning level, wherein the target overprovisioning level differs for each of the plurality of sub-drives and is based on a respective portion of a total logical address space of the storage device currently associated with each of the plurality of sub-drives and a total host write workload attributed to each of the plurality of sub-drives.