Fault resilient storage device

1. A method for operating a storage device comprising storage media, the method comprising:

determining, by the storage device, that the storage device is in a first fault state from which recovery is possible by power cycling the storage device or by formatting the storage media;

determining, by the storage device, that the storage device is in a second fault state from which partial recovery is possible by operating the storage device with reduced performance, with reduced capacity, or in a read-only mode; and

operating the storage device with reduced performance, with reduced capacity, or in the read-only mode.

2. The method of claim 1 , further comprising:

determining, by the storage device, that the storage device is in a third fault state different from the first fault state and the second fault state; and

operating the storage device in a mode in which read and write operations are not performed, and in which the storage device returns errors in response to received read or write commands, wherein:

the storage device comprises a controller comprising a first core and a second core, and

the third fault state comprises a sub-state in which the first core determines that the second core has failed.

3. The method of claim 1 , further comprising:

receiving a query, from a host, regarding a status of the storage device, and

responding to the query with a status corresponding to a status in a status hierarchy.

4. The method of claim 3 , wherein the status hierarchy comprises a first level, comprising:

a fully resilient status, corresponding to the first fault state; and

a partially resilient status, corresponding to the second fault state.

5. The method of claim 4 , wherein the partially resilient status comprises a first sub-status indicating a loss of capability, the first sub-status comprising:

a first sub-sub-status, indicating operation in a sustainable read-only mode; and

a second sub-sub-status, indicating operation in an unsustainable read-only mode.

6. The method of claim 3 wherein the receiving of the query comprises receiving the query through a nonvolatile memory express (NVMe) interface, and the responding to the query comprises responding through the nonvolatile memory express (NVMe) interface.

7. The method of claim 1 , wherein:

the first fault state comprises a first sub-state in which a program execution error of a controller of the storage device has caused incorrect data to be written to the storage media;

the determining that the storage device is in the first fault state comprises determining that a pointer is out of range; and

the first fault state comprises a second sub-state in which a program execution error of a controller of the storage device has occurred since the most recent write to storage media by the controller.

8. The method of claim 7 , further comprising reformatting a portion of the storage media, wherein the reformatting comprises reformatting the entire storage media.

9. The method of claim 1 , comprising operating the storage device with reduced performance.

10. The method of claim 9 , wherein the operating with reduced performance comprises:

receiving, from a host connected to the storage device, a write command comprising data;

writing the data to the storage media; and

sending a command completion to the host,

wherein the writing of the data to the storage media and the sending of the command completion to the host is performed as part of a synchronous write.

11. The method of claim 9 , wherein the operating with reduced performance comprises:

performing a first write to the storage media;

waiting, during an interval corresponding to the reduced performance; and

performing a second write to the storage media.

12. The method of claim 1 , comprising operating the storage device with reduced capacity.

13. A storage device comprising:

a processing circuit; and

storage media,

the processing circuit being configured to:

determine that the storage device is in a first fault state from which recovery is possible by power cycling the storage device or by formatting the storage media;

determine that the storage device is in a second fault state from which partial recovery is possible by operating the storage device with reduced performance, with reduced capacity, or in a read-only mode; and

operate the storage device with reduced performance, with reduced capacity, or in the read-only mode.

14. The storage device of claim 13 , wherein the processing circuit is further configured to:

receive a query, from a host, regarding a status of the device, and

respond to the query with a status corresponding to a status in a status hierarchy,

wherein the status hierarchy comprises a first level, comprising:

a fully resilient status, corresponding to the first fault state; and

a partially resilient status, corresponding to the second fault state.

15. The storage device of claim 14 wherein the receiving of the query comprises receiving the query through a nonvolatile memory express (NVMe) interface, and the responding to the query comprises responding through the nonvolatile memory express (NVMe) interface.

16. The storage device of claim 13 , wherein the processing circuit is configured to operate the storage device with reduced performance,

wherein the operating with reduced performance comprises:

performing a first write to the storage media;

waiting, during an interval corresponding to the reduced performance; and

performing a second write to the storage media.

17. A system, comprising a storage device comprising:

means for processing; and

storage media,

the means for processing being configured to:

determine that the storage device is in a first fault state from which recovery is possible by power cycling the storage device or by formatting the storage media;

determine that the storage device is in a second fault state from which partial recovery is possible by operating the storage device with reduced performance, with reduced capacity, or in a read-only mode; and

operate the storage device with reduced performance, with reduced capacity, or in the read-only mode.

18. The system of claim 17 , wherein the means for processing is further configured to:

receive a query, from a host, regarding a status of the device, and

respond to the query with a status corresponding to a status in a status hierarchy,

wherein the status hierarchy comprises a first level, comprising:

a fully resilient status, corresponding to the first fault state; and

a partially resilient status, corresponding to the second fault state.

19. The system of claim 18 wherein the receiving of the query comprises receiving the query through a nonvolatile memory express (NVMe) interface, and the responding to the query comprises responding through the nonvolatile memory express (NVMe) interface.

20. The system of claim 17 , wherein the means for processing is configured to operate the storage device with reduced performance,

wherein the operating with reduced performance comprises:

receiving, from a host connected to the storage device, a write command comprising data;

writing the data to the storage media; and

sending a command completion to the host,

wherein the writing of the data to the storage media and the sending of the command completion to the host is performed as part of a synchronous write.