Patent Application Number: 2007243344
Filing Date: April 25, 2007Priority Date: April 25, 2006
Inventors: Pankaj Mehra, Mark Lillibridge, Samuel A. Fineberg, Kave Eshghi
Applicants: Hewlett-Packard Development Company, L.P.
View Prior Art for Claim 9
The method of claim 8 wherein a currently considered component data-storage system responds to a query for a data object by: determining a first number of matches between a second number of received hash values with hash values stored within the currently considered component data storage system; and returning a value based on the determined first number of matches, the value one of the determined first number of matches, a ratio of the determined first number of matches divided by the second number of hash values, and one minus the ratio of the determined first number of matches divided by the second number of hash values.
Title Redundancy Elimination Within Large Collections of Files
Description
Conceptually the idea presented in the prior art is very similar to the one presented in the application.
Both of it is aiming to achieve better storage space and bandwidth by clustering data files with similar content, determined by a similar hash-based approach, and avoid storing redundant data via differential encoding scheme.
United States