Accounting for data whose rebuilding is deferred

• US 10,324,657 B2
• Filed: 11/16/2016
• Issued: 06/18/2019
• Est. Priority Date: 05/29/2015
• Status: Expired due to Fees

• Current Assignee: Pure Storage, Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Leggette, Wesley B., Resch, Jason K.
• Primary Examiner(s): Dang, Thanh-Ha
• Application Number:
  US15/353,486
• Publication Number:
  US 20170060481A1
• Time in Patent Office: 944 Days
• Field of Search: 707827
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 3/0622 in relation to access
• CPC Class Codes: G06F 3/0644 Management of space entities, e.g. partitions, extents, pools
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: H03M 13/1515 Reed-Solomon codes

Abstract

Systems and methods for accounting for data whose rebuilding is deferred in a dispersed storage network. The methods include determining a number of compromised slices associated with a dispersed storage unit. The number of existing slices associated with the dispersed storage unit is also determined. A comparison of the number of compromised slices plus the number of existing slices associated with the dispersed storage unit, to a storage capacity, is performed in order to produce a capacity determination. Write requests directed towards the dispersed storage unit may be failed based on the capacity determination. For example, the DS unit may fail write requests, when a write request would cause the dispersed storage unit to exceed the storage capacity of the dispersed storage unit when taking into consideration existing slices as well as compromised slices that need to be rebuilt.

Claims

1. A method of managing data storage in a dispersed storage network, the dispersed storage network including a plurality of dispersed storage units, the method comprising:

determining a number of compromised encoded data slices associated with a first dispersed storage unit of the plurality of dispersed storage units;

determining a number of existing stored encoded data slices associated with the first dispersed storage unit of the plurality of dispersed storage units;

comparing the number of compromised encoded data slices associated with the first dispersed storage unit of the plurality of dispersed storage units plus the number of existing stored encoded data slices associated with the first dispersed storage unit of the plurality of dispersed storage units to a storage capacity of the first dispersed storage unit of the plurality of dispersed storage units to produce a capacity determination, wherein the number of compromised encoded data slices reflects a number of corresponding deferred rebuilds; and

failing write requests to the first dispersed storage unit of the plurality of dispersed storage units based on the capacity determination, and

wherein a combination of the number of existing stored encoded data slices and the number of corresponding deferred rebuilds exceeds the capacity determination and the fail write requests prevents writing of additional encoded data slices beyond the capacity determination.

2. The method of claim 1, wherein compromised encoded data slices include one or more of bad slices and missing slices.

3. The method of claim 1, further comprising sending a report for receipt by a dispersed storage processing unit the report including the number of compromised encoded data slices associated with the first dispersed storage unit of the plurality of dispersed storage units.

4. The method of claim 3, wherein the report is used for quota enforcement.

5. The method of claim 3, wherein the report is used for storage location selection.

6. The method of claim 3, wherein the report is used for allotment enforcement.

7. The method of claim 3, wherein the report is used for capacity planning.

8. A dispersed storage unit for managing data storage in a dispersed storage network, the dispersed storage network including a plurality of dispersed storage units, the dispersed storage unit comprising:

a memory; and

a computer processor;

where the memory includes instructions for causing the computer processor to;

determine a number of compromised encoded data slices associated with a first dispersed storage unit of the plurality of dispersed storage units;

determine a number of existing stored encoded data slices associated with the first dispersed storage unit of the plurality of dispersed storage units;

compare the number of compromised encoded data slices associated with the first dispersed storage unit of the plurality of dispersed storage units plus the number of existing stored encoded data slices associated with the first dispersed storage unit of the plurality of dispersed storage units to a storage capacity of the first dispersed storage unit of the plurality of dispersed storage units to produce a capacity

determination, wherein the number of compromised encoded data slices reflects a number of corresponding deferred rebuilds; and

fail write requests to the first dispersed storage unit of the plurality of dispersed storage units based on the capacity determination, and

wherein a combination of the number of existing stored encoded data slices and the number of corresponding deferred rebuilds exceeds the capacity determination and the fail write requests prevents writing of additional encoded data slices beyond the capacity determination.

9. The dispersed storage unit of claim 8, wherein compromised encoded data slices include one or more of bad slices and missing slices.

10. The dispersed storage unit of claim 8, wherein the memory includes instructions for further causing the computer processor to send a report for receipt by a dispersed storage processing unit the report including the number of compromised encoded data slices associated with the dispersed storage unit.

11. The dispersed storage unit of claim 10, wherein the report is used for quota enforcement.

12. The dispersed storage unit of claim 10, wherein the report is used for storage location selection.

13. The dispersed storage unit of claim 10, wherein the report is used for allotment enforcement.

14. The dispersed storage unit of claim 10, wherein the report is used for capacity planning.

15. A dispersed storage network comprising:

a dispersed storage processing unit;

a plurality of dispersed storage units;

a first dispersed storage unit of the plurality of dispersed storage units including;

a first memory; and

a first computer processor;

where the first memory includes instructions for causing the first computer processor to;

determine a number of compromised encoded data slices associated with the first dispersed storage unit of the plurality of dispersed storage units;

determine a number of existing stored encoded data slices associated with the first dispersed storage unit of the plurality of dispersed storage units;

compare the number of compromised encoded data slices associated with the first dispersed storage unit of the plurality of dispersed storage units plus the number of existing stored encoded data slices associated with the first dispersed storage unit of the plurality of dispersed storage units to a storage capacity of the first dispersed storage unit of the plurality of dispersed storage units to produce a capacity determination, wherein the number of compromised encoded data slices reflects a number of corresponding deferred rebuilds; and

fail write requests to the first dispersed storage unit of the plurality of dispersed storage units based on the capacity determination, and

wherein a combination of the number of existing stored encoded data slices and the number of corresponding deferred rebuilds exceeds the capacity determination and the fail write requests prevents writing of additional encoded data slices beyond the capacity determination.

16. The dispersed storage network of claim 15, wherein compromised encoded data slices include one or more of bad slices and missing slices.

17. The dispersed storage network of claim 15, wherein the first memory includes instructions for further causing the first computer processor to send a report for receipt by the dispersed storage processing unit the report including the number of compromised encoded data slices associated with the dispersed storage unit.

18. The dispersed storage network of claim 17, wherein the dispersed storage processing unit includes:

a second memory; and

a second computer processor;

wherein the second memory includes instructions for causing the second computer processor to use the report for quota enforcement.

19. The dispersed storage network of claim 17, wherein the dispersed storage processing unit includes:

a second memory; and

a second computer processor;

wherein the second memory includes instructions for causing the second computer processor to use the report for storage location selection.

20. The dispersed storage network of claim 17, wherein the dispersed storage processing unit includes:

a second memory; and

a second computer processor;

wherein the second memory includes instructions for causing the second computer processor to use the report for allotment enforcement.