Methods and systems for vectored data de-duplication
AssigneeQuantum Corporation
InventorsGeorge SALIBA, Theron WHITE
Life of this patent
Estimating the term…
Abstract
The present invention is directed toward methods and systems for data de-duplication. More particularly, in various embodiments, the present invention provides systems and methods for data de-duplication that may utilize a vectoring method for data de-duplication wherein a stream of data is divided into “data sets” or blocks. For each block, a code, such as a hash or cyclic redundancy code may be calculated and stored. The first block of the set may be written normally and its address and hash can be stored and noted. Subsequent block hashes may be compared with previously written block hashes.
Claims21
A method of data de-duplication, comprising:
- comparing a code for a block of data being processed to a code for a stored block of data;
- and
- upon determining that the code for the block of data being processed matches the code for the stored block of data, storing a vector instead of the block of data being processed, where the vector is a link to the stored block of data.
A data de-duplication device, comprising:
- a de-duplication logic configured to:
- compare a code for a block of data being processed to a code for a previously processed block of data;
- and
- upon determining that the code for the block of data being processed matches the code for the previously processed block of data, to store a vector instead of the block of data being processed, where the vector points to the previously processed block of data.
A data de-duplication system, comprising:
- a solid-state data storage device configured to store blocks of data and codes for blocks of data;
- a data de-duplication device comprising:
- a data processing device, configured to:
- determine a code for a block of data being processed;
- compare the code for the block of data being processed to a code for a previously processed block of data;
- and
- upon determining that the code for the block of data being processed matches the code for the previously processed block of data, to store a vector instead of the block of data being processed in the solid-state data storage device, where the vector points to the previously processed block of data.
Dependencies are inferred from the claim text.