Block-level deduplication

Patent metadata

Field	Value
Publication number	US-9442806-B1
Application number	US-95737110-A
Country	US
Kind code	B1
Filing date	Nov 30, 2010
Priority date	Nov 30, 2010
Publication date	Sep 13, 2016
Grant date	Sep 13, 2016

Abstract

Various systems and methods can perform block-level deduplication. For example, one method involves sending a chunk of data to a deduplication server for storage in a deduplicated data store. The chunk of data includes multiple blocks. Subsequent to sending the chunk of data to the deduplication server, the method detects that at least one of the blocks has been modified. In response, the method sends associated information as well as the modified blocks, which include at least one but fewer than all of the blocks in the chunk, to the deduplication server. The associated information identifies a location of the included blocks within the chunk of data. The method can be performed by a computing device implementing a deduplication client.

First claim

What is claimed is:

1. A method comprising:
replicating a chunk of data, the replicating comprising
sending the chunk of data to a deduplication server for storage in a deduplicated data store, wherein
the chunk of data comprises a plurality of blocks, and
the chunk of data is identified within the deduplicated data store by a single fingerprint;

subsequent to the sending, determining whether at least one of the plurality of blocks has been modified, thereby creating a modified chunk of data; and
in response to a determination that at least one of the plurality of blocks has been modified, incrementally replicating the modified chunk of data to the deduplicated data store by sending the at least one of the plurality of blocks but fewer than all of the plurality of blocks of the modified chunk of data to the deduplication server, wherein
the sending is performed by a computing device implementing a deduplication client, and
the deduplication server performs deduplication on chunk-sized units of data by comparing the chunk of data identified with the modified chunk of data incrementally replicated to the deduplication data store, wherein
the chunk of data is identified based on the single fingerprint.

2. The method of claim 1 , wherein
the sending the chunk of data comprises sending the chunk of data via a network.

3. The method of claim 1 , wherein
the associated information comprises an identifier of a first version of the chunk of data and an identifier of a second version of the chunk of data,
the sending the chunk of data comprises sending the first version, and
the second version is created subsequent to the sending the chunk of data and in response to the at least one of the plurality of blocks being modified.

4. The method of claim 3 , wherein
the sending the associated information is performed in response to detecting that the second version of the chunk of data is not yet included in the deduplicated data store.

5. The method of claim 1 , wherein
the deduplication comprises storing only the blocks comprising the modified chunk of data with the reference associated with the chunk.

6. The method of claim 1 , further comprising:
calculating the single fingerprint for the chunk of data, wherein
the single fingerprint identifies a value of the chunk of data prior to the modification of the at least one of the plurality of blocks, and
the single fingerprint is not derived from a fingerprint of each block of the plurality of blocks.

7. The method of claim 1 , further comprising:
accessing at least part of a previous version of the chunk of data in the deduplicated data store;
combining at least the part of the previous version of the chunk of data with the at least one of the plurality of blocks to reconstitute a new version of the chunk of data; and
storing the new version of the chunk of data in the deduplicated data store.

8. A non-transitory computer readable storage medium storing program instructions executable to:
replicate a chunk of data, the replicating comprising
sending the chunk of data to a deduplication server for storage in a deduplicated data store, wherein
the chunk of data comprises a plurality of blocks, and
the chunk is identified within the deduplicated data store by a single fingerprint;

subsequent to sending the chunk of data, determine whether at least one of the plurality of blocks has been modified, thereby creating a modified chunk of data; and
in response to a determination that at least one of the blocks has been modified,
incrementally replicate the modified chunk of data to the deduplicated data store by sending the at least one of the plurality of blocks but fewer than all of the plurality of blocks of the modified chunk of data to the deduplication server, wherein
the sending is performed by a computing device implementing a deduplication client, and
the deduplication server performs deduplication on chunk-sized units of data by comparing the chunk of data identified with the modified chunk of data incrementally replicated to the deduplication data store, wherein
the chunk of data is identified based on the single fingerprint.

9. The non-transitory computer readable storage medium of claim 8 , wherein
the sending the chunk of data comprises sending the chunk of data via a network.

10. The non-transitory computer readable storage medium of claim 8 , wherein
the associated information comprises an identifier of a first version of the chunk of a data and an identifier of a second version of the chunk of data,
sending the chunk of data comprises sending the first version, and
the second version is created subsequent to sending the chunk of data and in response to the at least one of the plurality of blocks being modified.

11. The non-transitory computer readable storage medium of claim 10 , wherein
associated information and the at least one of the plurality of blocks is sent in response to detecting that the second version of the chunk of data is not yet included in the deduplicated data store.

12. A system comprising:
one or more processors; and
a memory coupled to the one or more processors, wherein the memory stores program instructions executable by the one or more processors to:
replicate a chunk of data, the replicating comprising
sending the chunk of data to a deduplication server for storage in a deduplicated data store, wherein
the chunk of data comprises a plurality of blocks, and
the chunk of data is identified within the deduplicated data store by a single fingerprint;

subsequent to sending the chunk of data, determine whether at least one of the plurality of blocks has been modified, thereby creating a modified chunk of data; and
in response to determining that at least one of the blocks has been modified, incrementally replicate the modified chunk of data to the deduplicated data store by sending the at least one of the plurality of blocks but fewer than all of the plurality of blocks of the modified chunk of data to the deduplication server, wherein
the sending is performed by a computing device implementing a deduplication client, and
the deduplication server performs deduplication on chunk-sized units of data by comparing the chunk of data identified with the modified chunk of data incrementally replicated to the deduplication data store, wherein
the chunk of data is identified based on the single fingerprint.

13. The system of claim 12 , wherein
the sending the chunk of data comprises sending the chunk of data via a network.

14. The system of claim 12 , wherein
the associated information comprises an identifier of a first version of the chunk of a data and an identifier of a second version of the chunk of data,
sending the chunk of data comprises sending the first version, and
the second version is created subsequent to sending the chunk of data and in response to the at least one of the plurality of blocks being modified.

15. The system of claim 14 , wherein
associated information and the at least one of the plurality of blocks is sent is performed in response to detecting that the second version of the chunk of data is not yet included in the deduplicated data store.

Assignees

• Bardale Trimbak Somnathappa
• Veritas Technologies Llc

Inventors

• Bardale Trimbak Somnathappa

Classifications

• G06F3/0641

  De-duplication techniques · CPC title

• G06F11/1453 Primary

  using de-duplication of the data · CPC title

• G06F3/067

  Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS] · CPC title

• G06F11/1464

  for networked environments · CPC title

• G06F3/0608 Primary

  Saving storage space on storage systems · CPC title