PESSIMISTIC READS AND OTHER SMART-READ ENHANCEMENTS WITH SYNCHRONIZED VAULTS

• US 20180089027A1
• Filed: 12/04/2017
• Published: 03/29/2018
• Est. Priority Date: 12/31/2014
• Status: Active Grant

• Current Assignee: Pure Storage, Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Gray, Adam M., Dhuse, Greg R., Baptist, Andrew D., Khadiwala, Ravi V., Leggette, Wesley B., Horan, Scott M., Borich, Franco V., Cilfone, Bart R., Scholl, Daniel J., Resch, Jason K.
• Granted Patent: US 10,642,687 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• CPC Class Codes: G06F 11/20 using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
• CPC Class Codes: G06F 16/1844 Management specifically adapted to replicated file systems
• CPC Class Codes: G06F 2211/1028 Distributed, i.e. distributed RAID systems with parity
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/0635 by changing the path, e.g. traffic rerouting, path reconfiguration
• CPC Class Codes: G06F 3/064 Management of blocks
• CPC Class Codes: G06F 3/0644 Management of space entities, e.g. partitions, extents, pools
• CPC Class Codes: G06F 3/0653 Monitoring storage devices or systems
• 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 method for execution by one or more processing modules of one or more computing devices of a dispersed storage network (DSN). The method begins by determining to recover a data object from one or more storage vaults of a plurality of storage vaults where the data object has been synchronously stored amongst the plurality of storage vaults. The method continues, for each storage vault, by determining a slice retrieval performance level and selecting two or more storage vaults of the plurality of storage vaults for retrieval based on the slice retrieval performance levels. The method continues by identifying a plurality of data segments for retrieval where the data object was divided into the plurality of data objects and assigning a storage vault for retrieval to produce assignment information and facilitating recovery of each data segment of the plurality of data segments from the selected two or more storage vaults.

Claims

1. A method for execution by one or more processing modules of one or more computing devices of a dispersed storage network (DSN), the method comprises:

determining to recover a data object from one or more storage vaults of a plurality of storage vaults where the data object has been synchronously stored amongst the plurality of storage vaults;

for each storage vault, determining a slice retrieval performance level;

selecting two or more storage vaults of the plurality of storage vaults for retrieval based on the slice retrieval performance levels;

identifying a plurality of data segments for retrieval where the data object was divided into the plurality of data segments;

for each data segment, assigning a storage vault for retrieval to produce assignment information; and

facilitating recovery of each data segment of the plurality of data segments from the selected two or more storage vaults based on the assignment information.

2. The method of claim 1, wherein the determining to recover includes receiving a retrieval request and identifying the plurality of storage vaults based on the retrieval request.

3. The method of claim 2, wherein the retrieval request includes any of:

performing a lookup or receiving identities of the storage vaults.

4. The method of claim 1, wherein the determining a slice retrieval performance level includes at least one of performing a lookup, initiating a test, or interpreting test results.

5. The method of claim 1, wherein the selecting two or more storage vaults includes determining a number based on a performance requirement and the slice retrieval performance levels, and identifying most favorably performing storage units.

6. The method of claim 1, wherein the identifying a plurality of data segments includes accessing at least one of a DSN directory or a dispersed hierarchical index to determine the plurality of data segments.

7. The method of claim 1, wherein the assigning is based on one or more of:

a retrieval performance goal, a slice retrieval performance level, or a number of storage vaults for the retrieval.

8. The method of claim 1, wherein the facilitating includes sending read slice requests for data segments assigned to each of the selected two or more storage vaults, receiving read slice responses, dispersed storage error decoding received encoded data slices to reproduce a plurality of data segments, and aggregating the plurality of data segments to produce recovered data.

9. A computing device of a group of computing devices of a dispersed storage network (DSN), the computing device comprises:

an interface;

a local memory; and

a processing module operably coupled to the interface and the local memory, wherein the processing module functions to;

determine to recover a data object from one or more storage vaults of a plurality of storage vaults where the data object has been synchronously stored amongst the plurality of storage vaults;

for each storage vault, determine a slice retrieval performance level;

select two or more storage vaults of the plurality of storage vaults for retrieval based on the slice retrieval performance levels;

identify a plurality of data segments for retrieval where the data object was divided into the plurality of data segments;

for each data segment, assign a storage vault for retrieval to produce assignment information; and

facilitate recovery of each data segment of the plurality of data segments from the selected two or more storage vaults based on the assignment information.

10. The computing device of claim 9, wherein the determine to recover includes receiving a retrieval request and identifying the plurality of storage vaults based on the retrieval request.

11. The computing device of claim 10, wherein the retrieval request includes any of:

performing a lookup or receiving identities of the storage vaults.

12. The computing device of claim 9, wherein the determine a slice retrieval performance level includes at least one of performing a lookup, initiating a test, or interpreting test results.

13. The computing device of claim 9, wherein the select two or more storage vaults includes determining a number based on a performance requirement and the slice retrieval performance levels, and identifying most favorably performing storage units.

14. The computing device of claim 9, wherein the identify a plurality of data segments includes accessing at least one of a DSN directory or a dispersed hierarchical index to determine the plurality of data segments.

15. The computing device of claim 9, wherein the assign a storage vault is based on one or more of:

a retrieval performance goal, a slice retrieval performance level, or a number of storage vaults for the retrieval.

16. The computing device of claim 9, wherein the facilitate recovery includes sending read slice requests for data segments assigned to each of the selected two or more storage vaults, receiving read slice responses, dispersed storage error decoding received encoded data slices to reproduce a plurality of data segments, and aggregating the plurality of data segments to produce recovered data.

17. A system comprises:

an interface;

a local memory; and

a processing module operably coupled to the interface and the local memory, wherein the processing module functions to;

determine to recover a data object from one or more storage vaults of a plurality of storage vaults where the data object has been synchronously stored amongst the plurality of storage vaults;

for each storage vault, determine a slice retrieval performance level;

select two or more storage vaults of the plurality of storage vaults for retrieval based on the slice retrieval performance levels;

identify a plurality of data segments for retrieval where the data object was divided into the plurality of data segments;

for each data segment, assign a storage vault for retrieval to produce assignment information; and

facilitate recovery of each data segment of the plurality of data segments from the selected two or more storage vaults based on the assignment information.

18. The system of claim 17, wherein the determine a slice retrieval performance level includes at least one of performing a lookup, initiating a test, or interpreting test results.

19. The system of claim 17, wherein the select two or more storage vaults includes determining a number based on a performance requirement and the slice retrieval performance levels, and identifying most favorably performing storage units.

20. The system of claim 17, wherein the assign a storage vault is based on one or more of:

a retrieval performance goal, a slice retrieval performance level, or a number of storage vaults for the retrieval.