Method and apparatus for identifying data inconsistency in a dispersed storage network

• US 10,268,712 B2
• Filed: 08/05/2016
• Issued: 04/23/2019
• Est. Priority Date: 08/27/2009
• Status: Active Grant

• Current Assignee: Pure Storage, Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Mark, Zachary J.
• Primary Examiner(s): Hershley, Mark E
• Application Number:
  US15/230,113
• Publication Number:
  US 20160342631A1
• Time in Patent Office: 991 Days
• Field of Search: 707691
• CPC Class Codes: G06F 16/10 File systems; File servers
• CPC Class Codes: G06F 16/215 Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
• CPC Class Codes: G06F 16/2365 Ensuring data consistency and integrity

Abstract

A method includes sending a set of digest list requests to a set of storage units regarding integrity data for a set of encoded data slices. The method further includes receiving, in response to the integrity data requests, the corresponding integrity data from at least some storage units of the set of storage units regarding at least some of the encoded data slices of the set of encoded data slices to produce a set of integrity data. The method further includes determining whether an inconsistency exists in the set of integrity data. When the inconsistency exists, the method further includes identifying an inconsistent encoded data slice of the at least some of the encoded data slices is inconsistent with other encoded data slices of the at least some of the encoded data slices. The method further includes updating the inconsistent encoded data slice to resolve the inconsistency.

Claims

1. A method for execution by a computing device of a dispersed storage network (DSN), the method comprises:

sending a set of digest list requests to a set of storage units regarding integrity data for a set of encoded data slices, wherein a data segment of a data object is dispersed storage error encoded to produce the set of encoded data slices, wherein the set of encoded data slices has a corresponding set of slice names, wherein each storage unit of the set of storage units stores an encoded data slice of the set of encoded data slices and corresponding integrity data in accordance with one of the corresponding set of slice names, and wherein a digest list request of the set of digest list requests is requesting a storage unit of the set of storage units to respond with integrity data of an encoded data slice of the set of encoded data slices and to not send the encoded data slice;

receiving, in response to the integrity data requests, the corresponding integrity data from at least some storage units of the set of storage units regarding at least some of the encoded data slices of the set of encoded data slices to produce a set of integrity data;

determining whether an inconsistency exists in the set of integrity data by comparing the corresponding integrity data received from a first storage unit of the at least some storage units to the corresponding integrity data received from two or more other storage units of the at least some storage units;

when the corresponding integrity data for the first storage unit is substantially similar to the corresponding integrity data for the two or more other storage units, determining the inconsistency does not exist; and

when the corresponding integrity data for the first storage unit is not substantially similar to the corresponding integrity data for the two or more other storage units, determining the inconsistency exists;

when the inconsistency exists;

identifying an inconsistent encoded data slice of the at least some of the encoded data slices that is inconsistent with other encoded data slices of the at least some of the encoded data slices; and

updating the inconsistent encoded data slice to resolve the inconsistency.

2. The method of claim 1, wherein the identifying the inconsistent encoded data slice comprises:

sending a set of slice name requests to the set of storage units;

receiving slices names from the at least some of the storage units to produce a received set of slice names;

comparing revision levels of slice names of the received set of slice names; and

identifying the inconsistent encoded data slice based on the corresponding slice name of the inconsistent encoded data slice having a different revision level than a revision level of other slice names of the received set of slice names.

3. The method of claim 1, wherein the identifying the inconsistent encoded data slice comprises:

sending a set of slice name requests to the set of storage units;

receiving slices names from the at least some of the storage units to produce a received set of slice names; and

identifying the inconsistent encoded data slice based on not receiving the corresponding slice name in the received set of slice names.

4. The method of claim 1, wherein the identifying the inconsistent encoded data slice comprises:

sending a set of slice name requests to the set of storage units;

receiving slices names from the at least some of the storage units to produce a received set of slice names; and

identifying the inconsistent encoded data slice based on the corresponding slice name being corrupted.

5. The method of claim 1, wherein the identifying the inconsistent encoded data slice comprises:

sending a set of encoded data slice retrieval requests to the set of storage units;

receiving encoded data slices from the at least some of the storage units to produce a received set of encoded data slices; and

identifying the inconsistent encoded data slice based on not receiving the inconsistent encoded data slice in the received set of encoded data slices.

6. The method of claim 1, wherein the identifying the inconsistent encoded data slice comprises:

sending a set of encoded data slice retrieval requests to the set of storage units;

receiving encoded data slices from the at least some of the storage units to produce a received set of encoded data slices; and

identifying the inconsistent encoded data slice based on the inconsistent encoded data slice being corrupted.

7. The method of claim 1, wherein the updating the inconsistent encoded data slice comprises:

rebuilding the inconsistent encoded data slice to produce a rebuilt encoded data slice.

8. The method of claim 1, wherein the set of digest list requests comprises:

a range of sets of slice names to inquire about a plurality of sets of encoded data slices.

9. A computing device of a dispersed storage network (DSN) comprises:

an interface;

memory; and

a processing module operably coupled to the interface and to the memory, wherein the processing module is operable to;

send, via the interface, a set of digest list requests to a set of storage units regarding integrity data for a set of encoded data slices, wherein a data segment of a data object is dispersed storage error encoded to produce the set of encoded data slices, wherein the set of encoded data slices has a corresponding set of slice names, wherein each storage unit of the set of storage units stores an encoded data slice of the set of encoded data slices and corresponding integrity data in accordance with one of the corresponding set of slice names, and wherein a digest list request of the set of digest list requests is requesting a storage unit of the set of storage units to respond with integrity data of an encoded data slice of the set of encoded data slices and to not send the encoded data slice;

receive, via the interface and in response to the integrity data requests, the corresponding integrity data from at least some storage units of the set of storage units regarding at least some of the encoded data slices of the set of encoded data slices to produce a set of integrity data;

determine whether an inconsistency exists in the set of integrity data by comparing the corresponding integrity data received from a first storage unit of the at least some storage units to the corresponding integrity data received from two or more other storage units of the at least some storage units;

when the corresponding integrity data for the first storage unit is substantially similar to the corresponding integrity data for the two or more other storage units, determine the inconsistency does not exist; and

when the corresponding integrity data for the first storage unit is not substantially similar to the corresponding integrity data for the two or more other storage units, determine the inconsistency exists;

when the inconsistency exists;

identify an inconsistent encoded data slice of the at least some of the encoded data slices that is inconsistent with other encoded data slices of the at least some of the encoded data slices; and

update the inconsistent encoded data slice to resolve the inconsistency.

10. The computing device of claim 9, wherein the processing module is further operable to identify the inconsistent encoded data slice by:

sending, via the interface, a set of slice name requests to the set of storage units;

receiving, via the interface, slices names from the at least some of the storage units to produce a received set of slice names;

comparing revision levels of slice names of the received set of slice names; and

identifying the inconsistent encoded data slice based on the corresponding slice name of the inconsistent encoded data slice having a different revision level than a revision level of other slice names of the received set of slice names.

11. The computing device of claim 9, wherein the processing module is further operable to identify the inconsistent encoded data slice by:

sending, via the interface, a set of slice name requests to the set of storage units;

receiving, via the interface, slices names from the at least some of the storage units to produce a received set of slice names; and

identifying the inconsistent encoded data slice based on not receiving the corresponding slice name in the received set of slice names.

12. The computing device of claim 9, wherein the processing module is further operable to identify the inconsistent encoded data slice by:

sending, via the interface, a set of slice name requests to the set of storage units;

receiving, via the interface, slices names from the at least some of the storage units to produce a received set of slice names; and

identifying the inconsistent encoded data slice based on the corresponding slice name being corrupted.

13. The computing device of claim 9, wherein the processing module is further operable to identify the inconsistent encoded data slice by:

sending, via the interface, a set of encoded data slice retrieval requests to the set of storage units;

receiving, via the interface, encoded data slices from the at least some of the storage units to produce a received set of encoded data slices; and

identifying the inconsistent encoded data slice based on not receiving the inconsistent encoded data slice in the received set of encoded data slices.

14. The computing device of claim 9, wherein the processing module is further operable to identify the inconsistent encoded data slice by:

sending, via the interface, a set of encoded data slice retrieval requests to the set of storage units;

receiving, via the interface, encoded data slices from the at least some of the storage units to produce a received set of encoded data slices; and

identifying the inconsistent encoded data slice based on the inconsistent encoded data slice being corrupted.

15. The computing device of claim 9, wherein the processing module is further operable to update the inconsistent encoded data slice by:

rebuilding the inconsistent encoded data slice to produce a rebuilt encoded data slice.

16. The computing device of claim 9, wherein the set of digest list requests comprises:

a range of sets of slice names to inquire about a plurality of sets of encoded data slices.