Two-step recovery employing erasure coding in a geographically diverse data storage system

1. A system, comprising:

a processor; and

a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising:

in response to determining that a first segment has become less accessible from a previous state of accessibility of the first segment, determining an index of the first segment, wherein the first segment is comprised in a first chunk of a first zone of zones of a geographically diverse data storage system, wherein the zones of the geographically diverse data storage system employ hierarchical erasure coding, and wherein the hierarchical erasure coding comprises a first-level erasure coding scheme and at least a first second-level erasure coding scheme;

determining a second chunk of a second zone of the zones based on the hierarchical erasure coding, wherein the second chunk and the second zone are determined to be relevant to a recovery of the first segment according to a defined relevancy criterion;

determining a second segment of the second relevant chunk based on the index and the hierarchical erasure coding, wherein the second segment is determined to be relevant to the recovery of the first segment according to the defined relevancy criterion;

generating a first recovered segment based at least in part on the second segment and the hierarchical erasure coding, wherein the first recovered segment represents same information as was represented on the first segment prior to the first segment becoming less accessible; and

initiating recovery of a third segment of the first chunk based on other data segments of the first chunk and coding segments for the first chunk.

2. The system of claim 1 , wherein the operations further comprise replacing the first segment with the first recovered segment in the first chunk of the first zone of the geographically diverse data storage system.

3. The system of claim 2 , wherein the first segment is stored in part in a first physical memory cell of a first storage device of the first zone, wherein the replacing the first segment with the first recovered segment occurs at a second physical memory cell of a second storage device of the first zone, and wherein the first physical memory cell is a different physical memory cell than the second physical memory cell.

4. The system of claim 3 , wherein the first storage device is a different storage device than the second storage device.

5. The system of claim 4 , wherein the first-level erasure coding scheme is a zone-level erasure coding scheme that protects at a whole chunk level across the zones of the geographically diverse data storage system.

6. The system of claim 5 , wherein the zone-level erasure coding scheme is a ‘4+2’ erasure coding scheme.

7. The system of claim 4 , wherein the first second-level erasure coding scheme is a first chunk-level erasure coding scheme that protects at a chunk-segment level across the first chunk of the first zone of the geographically diverse data storage system.

8. The system of claim 7 , wherein a second second-level erasure coding scheme is a second chunk-level erasure coding scheme that protects at the chunk-segment level across a second chunk of the first zone of the geographically diverse data storage system.

9. The system of claim 8 , wherein the first chunk-level erasure coding scheme is a different chunk-level erasure coding scheme than the second chunk-level erasure coding scheme.

10. The system of claim 9 , wherein the first chunk-level erasure coding scheme is a ‘12+4’ chunk-level erasure coding scheme.

11. The system of claim 9 , wherein the first chunk-level erasure coding scheme is a ‘10+2’ chunk-level erasure coding scheme.

12. The system of claim 8 , wherein the first chunk-level erasure coding scheme is a same chunk-level erasure coding scheme as the second chunk-level erasure coding scheme.

13. The system of claim 12 , wherein the first chunk-level erasure coding scheme is selected from a group of chunk-level erasure coding schema comprising a ‘12+4’ chunk-level erasure coding scheme and a ‘10+2’ chunk-level erasure coding scheme.

14. A method, comprising:

determining, by a system comprising a processor and a memory, an index of a first segment, wherein the first segment is comprised in a first chunk of a first zone of zones of a geographically diverse data storage system, and wherein the zones of the geographically diverse data storage system stores data according to a hierarchical erasure coding scheme, wherein the hierarchical erasure coding scheme comprises a first-level erasure coding scheme and at least a first second-level erasure coding scheme;

determining, by the system, a second chunk of a second zone of the zones based on the hierarchical erasure coding scheme, wherein the second chunk is determined to be a relevant chunk based on the hierarchical erasure coding scheme, and wherein the second zone is determined to be a relevant zone based on the hierarchical erasure coding scheme;

determining, by the system, a second segment of the second chunk, wherein the second segment is determined to be a relevant segment based on the index and the hierarchical erasure coding scheme;

in response to receiving an indication that the first segment is inaccessible, replacing, by the system, the first segment with a first recovered segment that is determined based, at least in part, on the second segment and on the hierarchical erasure coding scheme, wherein the first recovered segment represents the same information as was represented on the first segment prior to the first segment becoming inaccessible; and

initiating, by the system, recovering intra-zone at the first zone a third segment of the first chunk based on available segments of the first chunk comprising the first recovered segment.

15. The method of claim 14 , wherein the hierarchical erasure coding comprises a zone-level erasure coding scheme and at least a first chunk-level erasure coding scheme.

16. The method of claim 15 , wherein the zone-level erasure coding scheme is a ‘4+2’ erasure coding scheme, and wherein the first chunk-level erasure coding scheme is selected from a group of chunk-level erasure coding schema comprising a ‘12+4’ chunk-level erasure coding scheme and a ‘10+2’ chunk-level erasure coding scheme.

17. A non-transitory machine-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:

in response to receiving an indication that a first segment is inaccessible, determining an index of the first segment, wherein the first segment is comprised in a first chunk of a first zone of zones of a geographically diverse data storage system, and wherein the zones of the geographically diverse data storage system stores data according to a hierarchical erasure coding scheme, wherein the hierarchical erasure coding comprises a first-level erasure coding scheme and at least a first second-level erasure coding scheme;

determining a second segment of a second chunk of a second zone of the zones based on the index and on the hierarchical erasure coding scheme, wherein the second segment, the second chunk, and the second zone are used in connection with a recovery of the first segment;

replacing, by the system, the first segment with a first recovered segment that is determined based, at least in part, on the second segment and on the hierarchical erasure coding scheme, wherein the first recovered segment represents the same information as was represented on the first segment prior to the first segment becoming inaccessible; and

causing, at the first zone, an intra-zone recovery of at least a third segment of the first chunk based on available segments of the first chunk comprising the first recovered segment.

18. The non-transitory machine-readable storage medium of claim 17 , wherein the hierarchical erasure coding comprises a zone-level erasure coding scheme and at least a first chunk-level erasure coding scheme.

19. The non-transitory machine-readable storage medium of claim 17 , wherein the first-level erasure coding scheme is a ‘4+2’ erasure coding scheme, and wherein the first second-level erasure coding scheme is selected from a group of second-level erasure coding schema comprising at least a ‘12+4’ chunk-level erasure coding scheme and a ‘10+2’ chunk-level erasure coding scheme.

20. The non-transitory machine-readable storage medium of claim 18 , wherein a second second-level erasure coding scheme is a second chunk-level erasure coding scheme that protects at the chunk-segment level across a second chunk of the first zone of the geographically diverse data storage system.