Granted Patent B2

US 12,585,541 · App. 18/967,825 · Granted Mar 24, 2026

Inventors: Thomas D. Cocagne (Elk Grove Village, IL); Jason K. Resch (Warwick, RI); Ilya Volvovski (Chicago, IL)

Assignee: Pure Storage, Inc.

G06F11/1092G06F3/0619G06F3/0659G06F3/0689

Abstract

Claims (36)

1 . A method for execution by a storage network that includes a processor, the method comprising:

encoding at least one data object in the storage network as encoded data slices that include one or more locally decodable code segments;

detecting at least one storage error associated with storage of at least one of the encoded data slices in the storage network; and

recovering the at least one of the encoded data slices utilizing the one or more locally decodable code segments.

2 . The method of claim 1 , further comprising:

rebuilding the at least one of the encoded data slices associated with the storage error utilizing the at least one data object recovered based on the one or more locally decodable code segments.

3 . The method of claim 2 , wherein the rebuilding includes re-encoding the at least one data object via dispersed error encoding.

4 . The method of claim 2 , further comprising:

issuing a rebuilding request to a rebuilding module.

5 . The method of claim 4 , wherein issuing the rebuilding request includes:

identifying a storage unit of the storage network associated with the storage error.

6 . The method of claim 5 , wherein issuing the rebuilding request further includes:

sending the rebuilding request to the rebuilding module that is associated with the storage unit.

7 . The method of claim 1 , wherein the encoded data slices are stored in a set of storage units of the storage network.

8 . The method of claim 1 , wherein a read threshold number of the encoded data slices are required to decode the at least one data object.

9 . The method of claim 1 , wherein the at least one storage error is determined to exist in response to detecting that less than a write threshold number of encoded data slices are available.

10 . The method of claim 1 , wherein the at least one storage error is determined to exist in response to detecting a device failure or in response to detecting that a storage network storage utilization level is greater than a maximum storage utilization threshold level.

11 . A processing system of a storage network comprises:

at least one processor;

a memory that stores operational instructions, that when executed by the at least one processor cause the processing system to perform operations that include:

encoding at least one data object in the storage network as encoded data slices that include one or more locally decodable code segments;

detecting at least one storage error associated with storage of at least one of the encoded data slices in the storage network; and

recovering the at least one of the encoded data slices utilizing the one or more locally decodable code segments.

12 . The processing system of claim 11 , wherein the operations further include:

rebuilding the at least one of the encoded data slices associated with the storage error utilizing the at least one data object recovered based on the one or more locally decodable code segments.

13 . The processing system of claim 12 , wherein the rebuilding includes re-encoding the at least one data object via dispersed error encoding.

14 . The processing system of claim 12 , wherein the operations further include:

issuing a rebuilding request to a rebuilding module.

15 . The processing system of claim 14 , wherein issuing the rebuilding request includes:

identifying a storage unit of the storage network associated with the storage error.

16 . The processing system of claim 15 , wherein issuing the rebuilding request further includes:

sending the rebuilding request to the rebuilding module that is associated with the storage unit.

17 . The processing system of claim 11 , wherein the encoded data slices are stored in a set of storage units of the storage network.

18 . The processing system of claim 11 , wherein a read threshold number of the encoded data slices are required to decode the at least one data object.

19 . The processing system of claim 11 , wherein the at least one storage error is determined to exist in response to detecting that less than a write threshold number of encoded data slices are available.

20 . The processing system of claim 11 , wherein the at least one storage error is determined to exist in response to detecting a device failure or in response to detecting that a storage network storage utilization level is greater than a maximum storage utilization threshold level.

Assignments (1)

Continuity (7)

References Cited (170)