IP Library Granted Patent US 11,543,964
Granted Patent B1
US 11,543,964 · App. 17/248,885 · Granted Jan 3, 2023

Efficient rebuilding of an encoded data slice

Inventors: Jason K. Resch (Chicago, IL); Greg R. Dhuse (Chicago, IL)
Assignee: Pure Storage, Inc.
G06F3/0604G06F3/064G06F3/067G06F3/0629G06F3/0644G06F11/1076G06F11/1092G06F3/0619G06F3/0643G06F2211/1028
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,543,964
App. No.
17/248,885
Granted
Jan 3, 2023
Kind
B1
Abstract

A method includes determining whether an encoded data slice (EDS) of an “x” number of EDSs associated with a set of EDSs requires rebuilding, where the “x” number of EDSs is stored in a set of storage units of the storage network and the encoded data slice is stored in a first storage unit of the set of storage units. When the encoded data slice requires rebuilding, the method continues by identifying one of a “z” number of EDSs to replace the encoded data slice, where the “z” number of EDSs are not currently stored in the set of storage units. The method continues by constructing the one of the “z” number of EDSs from a decode threshold number of EDSs of the “x” number of EDSs and sending the one of the “z” number of EDSs to a second storage unit of the set of storage units.

Claims (61)

1. A method for execution by a computing device within a storage network, the method comprises:

determining whether an encoded data slice of “x” number of encoded data slices associated with a set of encoded data slices requires rebuilding, wherein:

a data segment of a data object is dispersed storage error encoded to produce the “x” number of encoded data slices,

the set of encoded data slices includes a pillar width number of encoded data slices,

the “x” number of encoded data slices is stored in a set of storage units of the storage network and the encoded data slice is stored in a first storage unit of the set of storage units,

“x” is equal to or greater than a write threshold number of encoded data slices of the set of encoded data slices and is less than or equal to the pillar width number,

a “z” number of encoded data slices corresponds to encoded data slices of the set of encoded data slices that are not currently stored in the set of storage units, and

“z” is equal to the pillar width number minus “x”; and

when the encoded data slice requires rebuilding:

identifying one of the “z” number of encoded data slices of the set of encoded data slices to replace the encoded data slice;

constructing the one of the “z” number of encoded data slices from a decode threshold number of encoded data slices of the “x” number of encoded data slices to produce a new one of the “x” number of encoded data slices; and

sending the new one of the “x” number of encoded data slices to a second storage unit of the set of storage units for storage therein.

2. The method of claim 1 , wherein determining a current “x” number comprises:

receiving, from storage units of the set of storage units, favorable listing responses to a listing request for the “x” number of encoded data slices, wherein a first favorable listing response of the favorable listing responses indicates a corresponding storage unit is storing a corresponding encoded data slice of the “x” number of encoded data slices.

3. The method of claim 2 further comprises:

determining an additional encoded data slice of the set of encoded data slices is stored in the set of storage units, wherein the additional encoded data slice was not included in the favorable listing responses; and

updating the “x” number based on the additional encoded data slice.

4. The method of claim 1 , wherein determining a current “x” number comprises:

receiving the “x” number.

5. The method of claim 1 , wherein determining a current “x” number comprises:

obtaining the “x” number by performing a lookup in a lookup table.

6. The method of claim 1 , wherein the identifying the one of the “z” number of encoded data slices comprises:

identifying a storage unit of the set of storage units that is mapped to store a respective encoded data slice of the “z” number of encoded data slices.

7. The method of claim 6 , wherein the identifying the storage unit is based on determining the storage unit has been recently restored.

8. The method of claim 6 , wherein the identifying the storage unit is based on determining the storage unit has been recently upgraded.

9. The method of claim 6 , wherein the identifying the storage unit is based on determining the storage unit has not been used previously for the set of encoded data slices.

10. The method of claim 6 , wherein the identifying the storage unit is based on determining the storage unit is within a performance range of other storage units in the set of storage units.

11. The method of claim 1 , wherein the constructing the one of the “z” number of encoded data slices comprises:

retrieving the decode threshold number of encoded data slices;

dispersed storage error decoding the decode threshold number of encoded data slices to reconstruct the data segment; and

dispersed storage error encoding the reconstructed data segment to produce the one of the “z” number of encoded data slices.

12. The method of claim 11 , wherein the dispersed storage error encoding comprises:

arranging the reconstructed data segment into a data matrix;

obtaining an encoding matrix;

selecting a row of the encoding matrix that corresponds to the one of the “z” number of encoded data slices; and

matrix multiplying the selected row of the encoding matrix with the data matrix to produce the one of the “z” number of encoded data slices.

13. A computing device of a storage network comprises:

memory;

an interface; and

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

determine whether an encoded data slice of “x” number of encoded data slices associated with a set of encoded data slices requires rebuilding, wherein:

a data segment of a data object is dispersed storage error encoded to produce the “x” number of encoded data slices,

the set of encoded data slices includes a pillar width number of encoded data slices,

the “x” number of encoded data slices is stored in a set of storage units of the storage network and the encoded data slice is stored in a first storage unit of the set of storage units,

“x” is equal to or greater than a write threshold number of encoded data slices of the set of encoded data slices and is less than or equal to the pillar width number,

a “z” number of encoded data slices corresponds to encoded data slices of the set of encoded data slices that are not currently stored in the set of storage units, and

“z” is equal to the pillar width number minus “x”; and

when the encoded data slice requires rebuilding:

identify one of the “z” number of encoded data slices of the set of encoded data slices to replace the encoded data slice;

construct the one of the “z” number of encoded data slices from a decode threshold number of encoded data slices of the “x” number of encoded data slices to produce a new one of the “x” number of encoded data slices; and

send, via the interface, the new one of the “x” number of encoded data slices to a second storage unit of the set of storage units for storage therein.

14. The computing device of claim 13 , wherein the processing module is operable to determine a current “x” number by:

receiving, via the interface and from storage units of the set of storage units, favorable listing responses to a listing request for the “x” number of encoded data slices, wherein a first favorable listing response of the favorable listing responses indicates a corresponding storage unit is storing a corresponding encoded data slice of the “x” number of encoded data slices.

15. The computing device of claim 14 , wherein the processing module is further operable to:

determine an additional encoded data slice of the set of encoded data slices is stored in the set of storage units, wherein the additional encoded data slice was not included in the favorable listing responses; and

update the “x” number based on the additional encoded data slice.

16. The computing device of claim 13 , wherein the processing module is further operable to determine a current “x” number by obtaining the “x” number by performing a lookup in a lookup table.

17. The computing device of claim 13 , wherein the processing module is further operable to identify one of the “z” number of encoded data slices by identifying a storage unit of the set of storage units that is mapped to store a respective encoded data slice of the “z” number of encoded data slices.

18. The computing device of claim 17 , wherein the processing module is operable to identify the storage unit based on determining the storage unit has been recently restored.

19. The computing device of claim 17 , wherein the processing module is operable to identify the storage unit based on determining the storage unit has been recently upgraded.

20. The computing device of claim 17 , wherein the processing module is operable to identify the storage unit based on determining the storage unit has not been used previously for the set of encoded data slices.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 12, 2021
From: RESCH, JASON K.; DHUSE, GREG R.
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 055246/0111 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 12, 2021
From: INTERNATIONAL BUSINESS MACHINES CORPORATION
To: PURE STORAGE, INC.
Reel/Frame 055291/0137 →
Continuity (4)
Continuation 16396399 · Apr 26, 2019
Continuation In Part 15405004 · Jan 12, 2017
Continuation 14088897 · Nov 25, 2013
Provisional Application 61748916 · Jan 4, 2013