Granted Patent B1

US 12,216,931 · App. 18/412,919 · Granted Feb 4, 2025

Inventors: Alan Chen (Simi Valley, CA); Craig Robertson (Simi Valley, CA); Robert Lercari (Thousand Oaks, CA); Andrey V. Kuzmin (Moscow, RU)

Assignee: Radian Memory Systems, LLC

G06F3/0655G06F3/061G06F3/0679

Abstract

Claims (67)

1. A storage device comprising:

an interface operable to communicate with a host;

flash memory having one or more namespaces and subdivisions, each of the subdivisions comprising one or more erase units;

logic operable to cause the storage device to:

receive via the interface, from a storage manager of the host, a query command and a write command, each of the query command and the write command being compatible with a non-volatile memory express (NVMe) command format;

transmit to the storage manager, via the interface, responsive to the query command, information representing the one or more namespaces and information representing the subdivisions;

receive via the interface, in association with the write command, write data, a designation of a given one of the one or more namespaces, a designation of a selected one of the subdivisions which is associated with the given one of the namespaces, and a logical block address (LBA);

store the write data in the one or more erase units of the flash memory which are associated with the selected one of the subdivisions,

track data validity information for the one or more erase units of flash memory which are associated with the selected one of the subdivisions; and

dependent on the data validity information, perform garbage collection in a manner dedicated to the selected one of the subdivisions;

wherein, as part of garbage collection, the logic is to cause the storage device to copy the write data to a destination erase unit of the flash memory, the destination erase unit being selected dependent on the selected one of the subdivisions; and

wherein said logic comprises at least one of (1) instructional logic stored on a physical storage medium that, when executed, is to control the operation of hardware circuitry of the storage device, or (2) hardware circuitry.

2. The storage device of claim 1 , wherein the logic is operable to cause the storage device to, in response to the query command:

identify the selected one of the subdivisions; and

transmit, to the host, information representing the selected one of the subdivisions.

3. The storage device of claim 2 , wherein the logic is operable to cause the storage device to, in response to the query command, explicitly identify the designation of the selected one of the subdivisions to the host.

4. The storage device of claim 1 , wherein the logic is operable to cause the storage device to, dependent on the data validity information: identify an erase unit of the flash memory which is fully released, and responsively control physical erasure of the identified erase unit.

5. The storage device of claim 1 , wherein the logic is operable to cause the storage device to receive, in association with the write command, a host-provided address, and to:

derive, from the host-provided address, a first address portion;

identify the given one of the one or more namespaces from the first address portion;

perform one or more operations to subdivide the host-provided address into a second address portion and a third address portion;

identify the selected one of the subdivisions from the second address portion; and

identify the LBA from the third address portion.

6. The storage device of claim 1 , wherein:

the interface is also to receive a read command from the storage manager, the read command being directed to the LBA; and

the logic is operable to cause the storage device to:

store into a look-up table a physical address which indicates a physical location at which the write data was stored;

in response to receipt of the read command, (1) use the LBA as an index into the look-up table to identify the physical address, (2) use the physical address to retrieve the write data, and (3) transmit the write data to the storage manager.

7. The storage device of claim 1 , wherein the logic is operable to cause the storage device to:

store a time associated with the selected one of the subdivisions; and

receive a request from the host for status information associated with the selected one of the subdivisions and responsively (1) identify the status information from the time and (2) transmit the status information to the host.

8. The storage device of claim 7 , wherein the time is associated with storage, by the storage device, of the write data into the flash memory.

9. The storage device of claim 1 , wherein the logic is operable to cause the storage device to store, for the selected one of the subdivisions, metadata representing an extent to which additional write data can be programmed into the one or more erase units which are associated with the selected one of the subdivisions without first erasing the one or more erase units which are associated with the selected one of the subdivisions.

10. The storage device of claim 9 , wherein the logic is operable to cause the storage device to transmit the metadata to the storage manager.

11. The storage device of claim 9 , wherein:

the query command is a first query command;

the interface is also to receive a second query command from the storage manager, via the interface;

responsive to the second query command, the logic is operable to cause the storage device to transmit, to the storage manager, via the interface, information dependent on the metadata.

12. The storage device of claim 1 , wherein the logic is operable to cause the storage device to, in response to the query command:

identify a size corresponding to the selected one of the subdivisions; and

transmit to a host information representing the size corresponding to the selected one of the subdivisions.

13. The storage device of claim 12 , wherein the size exactly corresponds to a non-power of two number of storage locations in the flash memory.

14. The storage device of claim 12 , wherein the size corresponds to a maximum writeable capacity for the selected one of the subdivisions.

15. The storage device of claim 1 , wherein the flash memory comprises planes, and wherein at least one of the subdivisions comprises erase units on different ones of the planes.

16. The storage device of claim 15 , wherein the erase units on different ones of the planes are also on at least two different dies.

17. The storage device of claim 15 , wherein the erase units on different ones of the planes are also all within a common die.

18. The storage device of claim 1 , wherein the logic is operable to cause the storage device to:

track metadata for each corresponding one of the subdivisions, wherein the metadata for each corresponding one of the subdivisions represents an extent to which the corresponding one of the subdivisions can continue to receive writeable data without first erasing the corresponding one of the subdivisions;

receive a maintenance command from a host, wherein the maintenance command specifies the selected one of the subdivisions; and

perform maintenance, responsive to the maintenance command, which changes the extent the corresponding one of the groups can continue to receive writeable data without first erasing the selected one of the subdivisions, and responsively update the metadata corresponding to the selected one of the subdivisions.

19. The storage device of claim 1 , wherein the logic is operable to cause the storage device to, responsive to receipt of a command from the host, dynamically control physical erasure of the one or more erase units associated with the specific one of the subdivisions.

20. An apparatus comprising:

a host having a storage manager; and

a solid state drive (SSD), the SSD comprising:

an interface operable to communicate with the host;

flash memory having one or more namespaces and subdivisions, each of the subdivisions comprising one or more erase units; and

logic operable to cause the storage device to:

receive via the interface, from the storage manager of the host, a query command and a write command, each of the query command and the write command being compatible with a non-volatile memory express (NVMe) command format;

transmit to the storage manager, via the interface, responsive to the query command, information representing the one or more namespaces and information representing the subdivisions;

receive via the interface, in association with the write command, write data, and host-provided address information;

derive, from the host-provided address information, a first address portion, and identify a given one of the one or more namespaces from the first address portion;

perform one or more operations to subdivide the host-provided address information into a second address portion and a third address portion, and to identify a selected one of the subdivisions from the second address portion and a logical block address (LBA) from the third address portion; and

store the write data in the one or more erase units of the flash memory which are associated with the selected one of the subdivisions,

track data validity information for the one or more erase units of flash memory which are associated with the selected one of the subdivisions; and

dependent on the data validity information, perform garbage collection in a manner dedicated to the selected one of the subdivisions;

wherein, as part of garbage collection, the logic is to cause the storage device to copy the write data to a destination erase unit of the flash memory, the destination erase unit being selected dependent on the selected one of the subdivisions; and

wherein said logic comprises at least one of (1) instructional logic stored on a physical storage medium that, when executed, is to control the operation of hardware circuitry of the storage device, or (2) hardware circuitry.

Assignments (2)

Continuity (9)

References Cited (217)