DISTRIBUTED RDC CHUNK STORE

• US 20100318759A1
• Filed: 06/15/2009
• Published: 12/16/2010
• Est. Priority Date: 06/15/2009
• Status: Abandoned Application

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Hamilton, James R., Virk, Navjot, Murphy, Elissa E. S.
• Application Number:
  US12/484,548
• Publication Number:
  US 20100318759A1
• Time in Patent Office: Days
• US Class Current: 711/171
• CPC Class Codes: G06F 11/1451 by selection of backup contents
• CPC Class Codes: G06F 11/1453 using de-duplication of the data
• CPC Class Codes: G06F 11/1456 Hardware arrangements for backup
• CPC Class Codes: G06F 11/1464 for networked environments
• CPC Class Codes: G06F 2201/83 the solution involving signatures

Abstract

The claimed subject matter provides a system and/or a method that facilitates differential transfer and storage of data for network-based backup architectures. A differential compression component can segment a portion of backup information into one or more blocks. In addition, signatures can be generated for each of the one or more blocks. The differential compression component can identify unique blocks from the one or more blocks based upon the generated signatures and signatures of chunks stored in a distributed chunk store. Moreover, a storage component can transfer the unique blocks of the portion of backup information to the distributed chunk store once identified.

Claims

1. A system that facilitates differential transfer of data in a backup system, comprising:

a processor coupled to a memory that retains computer-executable instructions, the processor executes;

a differential compression component that segments a portion of information into one or more blocks and generates respective signatures for each of the one or more blocks, the differential compression component identifies unique blocks from the one or more blocks based at least in part on the generated signatures and signatures of chunks stored in a distributed chunk store; and

a storage component that transfers identified unique blocks of the portion of information to the distributed chunk store.

2. The system of claim 1, further comprising a segmentation component that employs a fingerprint function to identify boundaries between the one or more blocks of the portion of information.

3. The system of claim 2, wherein boundaries are byte positions corresponding to local maxima of the fingerprint function.

4. The system of claim 1, further comprising a hash component that utilizes a hash function to generate signatures for each of the one or more blocks.

5. The system of claim 4, wherein the hash function is a cryptographically secure hash function.

6. The system of claim 1, further comprising an index lookup component that queries an index associated with the distributed chunk store to identify which of the one or more blocks are stored.

7. The system of claim 6, wherein the index lookup component queries the index with the generated signatures to determine if blocks with matching signatures is stored by the distributed chunk store.

8. The system of claim 7, wherein the storage component transfers blocks corresponding to non-matching signatures to the distributed chunk store.

9. The system of claim 1, wherein the differential compression component increases a reference count to a non-unique block stored in the distributed chunk store that corresponds to at least one of the one or more blocks of the portion of information.

10. The system of claim 1, wherein the storage component includes an indexing component that maintains an index, the indexing component at least one of adds, deletes, or modifies entries in the index when blocks are transferred by the storage component.

11. The system of claim 10, wherein the index comprises a listing of relationships between blocks stored in the distributed chunk store and signatures of the blocks.

12. The system of claim 1, wherein the distributed chunk store includes a set of storage locations.

13. The system of claim 12, wherein the set of storage locations include one or more of peers or cloud storage locations.

14. The system of claim 1, wherein the differential compression component employs remote differential compression.

15. A method for differentially storing and transferring backup information in a distributed backup environment, comprising:

employing a processor executing computer-executable instructions stored on a computer-readable storage medium to implement the following acts;

querying an index associated with a distributed chunk store with a set of signatures, the set of signatures correspond to a respective set of segments of a portion of backup information;

identifying unique segments from the set of segments based at least in part on results of the query; and

transferring the identified unique segments to the distributed chunk store.

16. The method of claim 15, further comprising utilizing a fingerprint function on the portion of backup information to identify cut points at which to segment the portion of backup information.

17. The method of claim 16, wherein the cut points are byte positions at which the fingerprint is a local maximum over a window.

18. The method of claim 15, further comprising employing a hash function one each segment in the set of segments to generate the respective set of signatures.

19. The method of claim 15, wherein the distribute chunk store includes a plurality of storage locations, the plurality of storage locations include one or more peer machines or cloud storage locations.

20. A system that facilitates differential transfer and storage of backup data in a backup environment, comprising:

at least one processor that executes computer-executable code stored in memory to effect the following;

means for segmenting a portion of backup data into a set of chunks, the means for segmenting divides the portion of backup data along boundary points identified with a fingerprint function;

means for generating a set of signatures corresponding to the set of chunks, the means for generating employs a hash function on each chunk in the set of chunks to create a respective signature;

means for querying a distribute chunk store with the set of signatures to identify unique chunks in the set of chunks, wherein a unique chunk is a block of backup data absent from the distributed chunk store; and

means for transferring unique chunks to the distributed chunk store.