System and method for efficiently creating off-site data volume back-ups

• US 20110167221A1
• Filed: 04/01/2010
• Published: 07/07/2011
• Est. Priority Date: 01/06/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: StorSimple, Inc. (Microsoft Corporation)
• Inventors: Pangal, Gururaj, Kulangara, Kuriakose George, Parikh, Urshit, Testardi, Richard, Cometto, Maurilio
• Granted Patent: US 8,452,932 B2
• Time in Patent Office: Days
• US Class Current: 711/117
• CPC Class Codes: G06F 11/1448 Management of the data involved in backup or backup restore
• 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 12/0808 with cache invalidating means G06F12/0815 takes precedence
• CPC Class Codes: G06F 12/122 of the least frequently used [LFU] type, e.g. with individual count value
• CPC Class Codes: G06F 2201/84 Using snapshots, i.e. a logical point-in-time copy of the data
• CPC Class Codes: G06F 3/0608 Saving storage space on storage systems
• CPC Class Codes: G06F 3/0641 De-duplication techniques
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]

Abstract

Data back-ups are a critical task of any information technology department. Data back-ups are typically performed using some type of back-up tape systems. Internet based data storage systems now offer data storage services at low prices. To take advantage of such services, a system and method for efficiently back-up data volumes is disclosed. The data back-up system divides data volumes into fingerprinted data slices. Redundant data slices are then removed. Unique fingerprinted data slices are then copied to an internet based storage provider.

Claims

1. A method of backing-up an active data volume in a data storage system, said method comprising:

creating a snapshot volume of said active data volume;

creating a fingerprint data map of said snapshot volume, said fingerprint data map comprising an ordered list of data slice fingerprints, each of said data slice fingerprints comprising a statistically unique fingerprint of an associated data slice in said snapshot volume;

copying unique data slices of said associated data slices to a back-up storage system; and

storing said fingerprint data map in said back-up storage system.

2. The method of backing-up an active data volume as set forth in claim 1 wherein said back-up storage system comprises a back-up area at a cloud data storage provider.

3. The method of backing-up an active data volume as set forth in claim 2 wherein a subset of said unique slices are already stored with said a cloud data storage provider.

4. The method of backing-up an active data volume as set forth in claim 1 wherein said snapshot volume comprises an ordered set of fixed length data chunks and each of said fixed length data chunks comprises a set of ordered set of said associated data slices.

5. The method of backing-up an active data volume as set forth in claim 1 wherein a subset of said data slice fingerprints and said associated data slices already exist in said back-up storage system.

6. The method of backing-up an active data volume as set forth in claim 1 wherein copying said unique data slices to said back-up storage system comprises:

copying said unique data slices to a main storage area of a cloud data storage provider; and

requesting said cloud data storage provider to back-up of said unique data slices.

7. The method of backing-up an active data volume as set forth in claim 1 wherein said data storage system comprises a tiered data system with multiple data tiers, said method further comprising:

storing a data tier identifier for each of said associated data slices in said back-up storage system, said data tier identifier identifying which of said multiple data tiers said associated data slice was residing in.

8. The method of backing-up an active data volume as set forth in claim 1 wherein said snapshot volume comprises a set of data chunks and creating said fingerprint data map of said snapshot volume comprises:

dividing a first set of data chunks into a first set of data slices, creating a first set of data slice fingerprints for said first set of data slices, and placing said first set of fingerprints in said fingerprint data map; and

copying a second set of existing data slice fingerprints for a second set of existing data slices from a second set of data chunks in said snapshot volume.

9. A method of backing-up an active data volume in a data storage system as claimed in claim 1, said method further comprising:

dividing said snapshot volume into said associated data slices.

10. The method of backing-up an active data volume as set forth in claim 1 wherein said associated data slices comprise variable length data slices.

11. A data storage system for storing digital data, said data storage comprising:

an active data volume;

a snapshot system for creating a snapshot volume of said active data volume;

a clone volume creation system, said clone volume creation system for creating a fingerprint data map of said snapshot volume, said fingerprint data map comprising an ordered list of data slice fingerprints, each of said data slice fingerprints comprising a statistically unique fingerprint of an associated data slice in said snapshot volume;

a back-up system, said back-up system copying unique data slices of said associated data slices to a back-up storage system and storing said fingerprint data map in said back-up storage system.

12. The data storage system as set forth in claim 11 wherein said data storage system divides data volumes into data chunks and said data storage system comprises a tiered data system with data stored in multiple data tiers, said data storage system further comprising:

a first data tier comprising a first set of data chunks, said first set of data chunks stored in a first tier memory system; and

a second data tier comprising a set of second tier data slices stored in a second tier memory system, said second tier slices may be combined to create data chunks in a second set of data chunks.

13. The data storage system as set forth in claim 12, said data storage system further comprising:

a third data tier comprising a set of third tier data slices, said third tier data slices stored in bulk storage, said third tier slices may be combined with said second tier slices to create data chunks in a second set of data chunks.

14. The data storage system as set forth in claim 11 wherein said back-up storage system comprises a back-up area at a cloud data storage provider.

15. The data storage system as set forth in claim 14 wherein a subset of said unique slices are already stored with said a cloud data storage provider.

16. The data storage system as set forth in claim 11 wherein said snapshot volume comprises an ordered set of fixed length data chunks and each of said fixed length data chunks comprises a set of ordered set of said associated data slices.

17. The data storage system as set forth in claim 11 wherein a subset of said data slice fingerprints and said associated data slices already exist in said back-up storage system.

18. The data storage system as set forth in claim 11 wherein said back-up system copies said unique data slices to a main storage area of a cloud data storage provider and requesting said cloud data storage provider to back-up of said unique data slices

19. The data storage system as set forth in claim 12 wherein said back-up system stores a data tier identifier for each of said associated data slices in said back-up storage system, said data tier identifier identifying which of said multiple data tiers said associated data slice was residing in

20. A data storage system as claimed in claim 11, said data storage system further comprising:

a data volume divider, said data volume divider dividing said snapshot volume into said associated data slices.

21. The data storage system as set forth in claim 11 wherein said associated data slices comprise variable length data slices.

22. A method of restoring a back-up into a tiered data storage system, said method comprising:

copying a set of backed-up data slices into a low tier of said tiered data storage system, each of said backed-up data slices having unique data fingerprints;

creating a new volume in said tiered data storage system, said new volume comprising an ordered list of said backed-up data slices; and

exposing said new volume to hosts.

creating a fingerprint data map of said snapshot volume, said fingerprint data map

23. The method of restoring a back-up into a tiered data storage system, said method comprising:

moving each of said backed-up data slices to a data tier where the backed-up data slice existed when a back-up operation was performed.