Selective activation of memory to retrieve data in a dispersed storage network

• US 9,201,732 B2
• Filed: 07/30/2014
• Issued: 12/01/2015
• Est. Priority Date: 01/28/2010
• Status: Active Grant

• Current Assignee: Pure Storage, Inc.
• Original Assignee: Cleversafe Incorporated (International Business Machines Corporation)
• Inventors: Resch, Jason K.
• Primary Examiner(s): Faal, Baboucarr
• Application Number:
  US14/446,703
• Publication Number:
  US 20140344617A1
• Time in Patent Office: 489 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/1088 Reconstruction on already foreseen single or plurality of spare disks
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• CPC Class Codes: G06F 2211/1028 Distributed, i.e. distributed RAID systems with parity
• CPC Class Codes: G06F 3/0614 Improving the reliability of storage systems
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]

Abstract

A technique of selectively activating inactive distributed storage units of a dispersed storage network to retrieve a threshold number of data slices that are required to recover the original data, instead of utilizing all of the distributed storage units.

Claims

1. A method of retrieving encoded data slices in a dispersed storage network by selectively activating distributed storage units, comprising:

utilizing a processing unit, having a processor, to determine a number of distributed storage units of a plurality of storage units of the dispersed storage network that are active and available to retrieve encoded data slices of a data segment to recover the data segment, wherein data is initially divided into a set of separate data segments, including the data segment, and the encoded data slices of the data segment are stored in the plurality of distributed storage units, and wherein upon retrieval, only a threshold number of encoded data slices are required to recover the data segment, in which the threshold number of encoded data slices needed to recover the data segment being less than a total number of encoded data slices created and stored in the plurality of distributed storage units;

determining, by use of the processing unit, which of the distributed storage units storing the encoded data slices of the data are active and available to retrieve the threshold number of encoded data slices of the data segment;

determining, by use of the processing unit, which additional distributed storage units are to be made active to obtain the threshold number of the encoded data slices to retrieve, when less than the threshold number of the encoded data slices are available for retrieval, the determining based on an attribute associated with the distributed storage units; and

utilizing the processing unit to selectively activate the additional distributed storage units to retrieve the threshold number of encoded data slices to recover the data segment.

2. The method of claim 1, wherein when determining which of the distributed storage units storing the encoded data slices are active and available indicates that the threshold number of the encoded data slices are available for retrieval from active distributed storage units, retrieving the threshold number of encoded data slices without activating inactive distributed storage units.

3. The method of claim 1, further comprising deactivating selectively activated additional distributed storage units after retrieving the threshold number of the encoded data slices.

4. The method of claim 1, wherein when determining which of the additional distributed storage units are to be made active based on an attribute associated with the distributed storage units, the attribute is a performance characteristic of respective distributed storage units.

5. The method of claim 1, wherein when determining which of the additional distributed storage units are to be made active based on an attribute associated with the distributed storage units, the attribute is energy usage or energy usage history of respective distributed storage units.

6. The method of claim 1, wherein when determining which of the additional distributed storage units are to be made active based on an attribute associated with the distributed storage units, the attribute is a priority order established for respective distributed storage units.

7. The method of claim 1, wherein when determining which of the additional distributed storage units are to be made active based on an attribute associated with the distributed storage units, the attribute is a security level established for respective distributed storage units.

8. The method of claim 1, wherein when determining which of the additional distributed storage units are to be made active based on an attribute associated with the distributed storage units, the attribute is proximity of respective additional distributed storage units to the processing unit.

9. A method of retrieving encoded data slices in a dispersed storage network by selectively activating distributed storage units, comprising:

utilizing a processing unit, having a processor, to determine a number of distributed storage units that are active and available to retrieve encoded data slices of a data segment, in which data is divided into a set of separate data segments, including the data segment, and in which the distributed storage units are configured to receive and store n number of encoded data slices of the data segment by having a respective distributed storage unit store a respective one of the n encoded data slices of the data segment, wherein at least a threshold number k of the n encoded data slices are needed to reconstruct the data segment, where k is less than n;

determining, by use of the processing unit, which of the distributed storage units storing the encoded data slices of the data segment are active for retrieval of the k number of encoded data slices;

determining, by use of the processing unit, which additional distributed storage units are to be made active to obtain the k number of encoded data slices to recover the data segment, when less than the k number of the encoded data slices are available for retrieval, in which the determining is based on an attribute associated with the distributed storage units; and

utilizing the processing unit to selectively activate the additional distributed storage units to retrieve the k number of the encoded data slices to recover the data segment.

10. The method of claim 9, further comprising deactivating selectively activated additional distributed storage units after retrieving respective encoded data slices from the selectively activated additional distributed storage units.

11. The method of claim 9, wherein when determining which of the additional distributed storage units are to be made active based on an attribute associated with the distributed storage units, the attribute is a performance characteristic of respective distributed storage units.

12. The method of claim 9, wherein when determining which of the additional distributed storage units are to be made active based on an attribute associated with the distributed storage units, the attribute is energy usage or energy usage history of respective distributed storage units.

13. The method of claim 9, wherein when determining which of the additional distributed storage units are to be made active based on an attribute associated with the distributed storage units, the attribute is a priority order established for respective distributed storage units.

14. The method of claim 9, wherein when determining which of the additional distributed storage units are to be made active based on an attribute associated with the distributed storage units, the attribute is a security level established for respective distributed storage units.

15. The method of claim 9, wherein when determining which of the additional distributed storage units are to be made active based on an attribute associated with the distributed storage units, the attribute is proximity of respective additional distributed storage units to the processing unit.

16. An apparatus for retrieving encoded data slices in a dispersed storage network by selective activation of inactive distributed storage units, comprising:

an interface to communicate with distributed storage units configured within the dispersed storage network; and

a processor, configured with the interface, to determine a number of distributed storage units of a plurality of storage units of the dispersed storage network that are active and available to retrieve encoded data slices of a data segment to recover the data segment, wherein data is initially divided into a set of separate data segments, including the data segment, and the encoded data slices of the data segment are stored in the plurality of distributed storage units, and wherein only a threshold number of encoded data slices are required to recover the data segment, in which the threshold number of encoded data slices needed to recover the data segment being less than a total number of encoded data slices created and stored in the plurality of distributed storage units, the processor is to determine which of the distributed storage units storing the encoded data slices of the data segment are active and available to retrieve the threshold number of the encoded data slices of the data segment, wherein when less than the threshold number of the encoded data slices are available for retrieval, the processor is to determine which additional distributed storage units are to be made active to obtain the threshold number of encoded data slices to retrieve based on an attribute associated with the distributed storage units, and the processor is to selectively activate the additional distributed storage units to retrieve the threshold number of encoded data slices to recover the data segment.

17. The apparatus of claim 16, wherein the processor deactivates the selectively activated additional distributed storage units after retrieving the threshold number of the encoded data slices.

18. The apparatus of claim 16, wherein the apparatus includes one of the distributed storage units.

19. The apparatus of claim 16, wherein the processor bases the attribute as a performance characteristic of respective distributed storage units.

20. The apparatus of claim 16, wherein the processor bases the attribute on proximity of respective distributed storage units to the processor.