Selecting a store for deduplicated data

• US 10,496,490 B2
• Filed: 05/16/2013
• Issued: 12/03/2019
• Est. Priority Date: 05/16/2013
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Inventors: Chandrasekharan, Kaushik, Camble, Peter Thomas, Todd, Andrew, Pelly, Simon, Bhagwat, Deepavali Mahendra
• Primary Examiner(s): Lewis, Cheryl
• Application Number:
  US14/787,763
• Publication Number:
  US 20160110260A1
• Time in Patent Office: 2,392 Days
• CPC Class Codes: G06F 11/1453 using de-duplication of the data
• CPC Class Codes: G06F 11/1464 for networked environments
• CPC Class Codes: G06F 11/1466 to make the backup process non-disruptive
• CPC Class Codes: G06F 11/1469 Backup restoration techniques
• CPC Class Codes: G06F 16/137 Hash-based content-based indexing of textual data G06F16/31
• CPC Class Codes: G06F 16/1752 based on file chunks
• CPC Class Codes: G06F 2201/80 Database-specific techniques

Abstract

A technique includes communicating signatures of samples of first data associated with an object to at least some stores of a plurality of stores on which the object is distributed, and in response to the communication, receiving responses indicating numbers of the samples stored on the respective at least some of the plurality of stores and regulating on which store of the plurality of stores deduplicated data associated with the first data is stored based at least in part on the numbers and a pattern of data storage on the stores.

Claims

1. A method comprising:

communicating, by a processor, a subset of signatures of first data associated with an object to a plurality of stores on which the object is distributed;

in response to the communication, receiving, from each of the plurality of stores, a response including a number of signatures stored on the store that match the subset of signatures;

selecting, by the processor, one of the plurality of stores to send remaining signatures of the first data based at least in part on the number of matched signatures stored on each of the plurality of stores and a pattern of data storage on the stores;

sending the remaining signatures to the selected store;

receiving, from the selected store, information indicating which of the remaining signatures match a respective signature on the selected store; and

based on the received indication, sending, to the selected store for storage, chunks of the first data that are not stored on the selected store.

2. The method of claim 1, wherein selecting one of the plurality of stores to send the remaining signatures is further based on a determination of whether the selected store stores most recently deduplicated data associated with the object.

3. The method of claim 1, further comprising:

determining whether the first data comprises seeding data by determining whether the number of the matched signatures stored on the selected store exceeds a predetermined threshold number.

4. The method of claim 1, wherein selecting of one of the plurality of stores to send the remaining signatures is further based on storage capacity of each of the plurality of nodes.

5. The method of claim 3, wherein selecting one of the plurality of stores to send the remaining signatures is further based on determinations of whether the first data comprises seeding data, whether the selected store is a current bid winner and an immediately previous bid winner.

6. The method of claim 1, wherein selecting one of the plurality of stores to send the remaining signatures is further based on whether the first data is at a beginning of backup data for a system.

7. The method of claim 1, further comprising suspending the communication of the subset of signatures to the plurality of nodes based on a prediction of future bidding activity.

8. The method of claim 1, wherein selecting the store to send the remaining signatures of the first data is further based on a number of times the store having the largest number of matched signatures changes.

9. The method of claim 1, wherein the plurality of stores comprises independent computer systems or independent storage systems.

10. The method of claim 1, wherein the plurality of stores comprises independent nodes.

11. A system comprising:

a processor; and

a memory storing instructions that when executed cause the processor to;

designate first data associated with an object to be backed up, the object being stored on a plurality of stores in a distributed fashion;

communicate a subset of signatures of the first data to the plurality of stores;

receive responses from the plurality of stores, each response from each store indicating a number of signatures stored on the store that match the subset of signatures;

select one of the plurality of stores to send remaining signatures of the first data based on the number of matched signatures stored on each of the plurality of stores and a pattern of data storage on the stores;

send the remaining signatures to the selected store;

receive, from the selected store, information indicating which of the remaining signatures match a respective signature on the selected store; and

based on the received information, send, to the selected store for storage, chunks of the first data that are not stored on the selected store.

12. The system of claim 11, wherein the instructions, when executed, cause the processor to determine whether the selected store is a store that stores most recently deduplicated data associated with the object.

13. The system of claim 11, wherein the processor is to select one of the plurality of stores to send the remaining signatures of the first data further based on a determination of whether the first data comprises seeding data.

14. The system of claim 13, wherein the processor is to compare the number of matched signatures stored on the selected store to a bid threshold to determine whether the first data comprises seeding data.

15. An article comprising a computer readable non-transitory storage medium to stored instructions that when executed by a computer cause the computer to:

communicate a subset of signatures of first data associated with an object to a plurality of stores on which the object is distributed;

in response to the communication, receive, from each of the plurality of stores, a response including a number of signatures stored on the respective store that match the subset of signature;

select one of the plurality of stores to send remaining signatures of the first data based on the number of matched signatures stored on each of the plurality of stores and a pattern of data storage on the stores;

send the remaining signatures to the selected store;

receive, from the selected store, information indicating which of the remaining signatures match a respective signature on the selected store; and

based on the received indication, send, to the selected store for storage, chunks of the first data that are not stored on the selected store.

16. The article of claim 15, the storage medium storing instructions that when executed by the computer cause the computer to select one of the plurality of stores to send the remaining signatures of the first data further based on a determination of whether the first data comprises seeding data.

17. The article of claim 16, the storage medium storing instructions that when executed by the computer cause the computer to compare the number of the matched signatures stored on the selected node to a bid threshold to determine whether the first data comprises seeding data.