Write stream separation into multiple partitions
A method of operating a storage controller is provided. The method includes receiving data transferred by a host for storage in a target partition of a storage media, and detecting properties of the data. The method also includes establishing one or more inferred partitions on the storage media based at least on the properties of the data, and based at least on the properties of the data, sorting subsets of the data for storage within the target partition and the one or more inferred partitions.
1. A method of operating a storage controller, the method comprising:
receiving data transferred by a host for storage in a target partition of a storage media;
detecting properties of the data;
establishing one or more inferred partitions on the storage media based at least on the properties of the data; and
based at least on the properties of the data, sorting subsets of the data for storage within the target partition and the one or more inferred partitions.
2. The method of claim 1 , wherein the properties of the data include a frequency of updates to the data on the storage media, and recently updated data is stored in a first inferred partition, and infrequently updated data is stored in a second inferred partition.
3. The method of claim 2 , wherein the first inferred partition is higher performance than the second inferred partition.
4. The method of claim 3 , wherein the second inferred partition is garbage collected more frequently than the first inferred partition.
5. The method of claim 1 , wherein the properties of the data include a write command size, and data having small write commands is stored in a small block partition, and data having large write commands is stored in a large block partition.
6. The method of claim 5 , wherein the small block partition contains data blocks having a smaller size than data blocks within the large block partition.
7. The method of claim 1 , wherein the properties of the data include a write command location, and filesystem data and metadata is written in fixed locations, and user data is written to non-fixed locations.
8. The method of claim 1 , wherein the one or more inferred partitions include at least two partitions comprising different physical media.
9. The method of claim 1 , wherein the one or more inferred partitions include at least two partitions having different qualities of service.
10. The method of claim 1 , wherein the one or more inferred partitions include at least two partitions having different levels of power loss recovery.
11. A storage controller for a storage system, comprising:
a host interface, configured to receive data for storage within the storage system, and to transmit data from the storage system to a host system;
a storage interface, configured to transmit data to the storage system, and to receive data from the storage system; and
processing circuitry coupled with the host interface and the storage interface, configured to:
receive data transferred by a host for storage in a target partition of a storage media within the storage system;
detect properties of the data;
establish one or more inferred partitions on the storage media based at least on the properties of the data; and
based at least on the properties of the data, sort subsets of the data for storage within the target partition and the one or more inferred partitions.
12. The storage controller of claim 11 , wherein the properties of the data include a frequency of updates to the data on the storage media, and recently updated data is stored in a first inferred partition, and infrequently updated data is stored in a second inferred partition.
13. The storage controller of claim 12 , wherein the first inferred partition is higher performance than the second inferred partition.
14. The storage controller of claim 13 , wherein the second inferred partition is garbage collected more frequently than the first inferred partition.
15. The storage controller of claim 11 , wherein the properties of the data include a write command size, and data having small write commands is stored in a small block partition, and data having large write commands is stored in a large block partition.
16. The storage controller of claim 15 , wherein the small block partition contains data blocks having a smaller size than data blocks within the large block partition.
17. The storage controller of claim 11 , wherein the properties of the data include a write command location, and filesystem data and metadata is written in fixed locations, and user data is written to non-fixed locations.
18. The storage controller of claim 11 , wherein the one or more inferred partitions include at least two partitions comprising different physical media.
19. The storage controller of claim 11 , wherein the one or more inferred partitions include at least two partitions having different qualities of service.
20. The storage controller of claim 11 , wherein the one or more inferred partitions include at least two partitions having different levels of power loss recovery.