Data deduplication in a removable storage device
AssigneeSpectra Logic Corporation
InventorMatthew Thomas Starr
Life of this patent
Estimating the term…
Abstract
An apparatus and associated methodology contemplate a data storage system having a removable storage device operably transferring user data between the data storage system and another device via execution of a plurality of input/output commands. A commonality factoring module executes computer instructions stored in memory to assign commonality information to the user data. A deduplication module executes computer instructions stored in memory to combine a plurality of files of the user data (user data files) with at least one file of corresponding commonality information (commonality information file), the combined files forming a sequential data stream.
Claims23
A data storage system comprising:
- a removable storage device operably transferring user data between the data storage system and another device via execution of a plurality of input/output (I/O) transfers;
- a commonality factoring (CF) module executing computer instructions stored in memory to assign commonality information to the user data;
- and
- a deduplication module executing computer instructions stored in memory to combine a plurality of files of the user data (user data files) with at least one file of corresponding commonality information (commonality information file), the combined files forming a sequential data stream.
A method comprising:
- transferring user data between a data storage system and another device via execution of a plurality of input/output (I/O) transfers;
- performing commonality factoring (CF) to assign commonality information to the transferred user data;
- and
- deduplicating the user data by combining a plurality of files of the user data (user data files) with at least one file of corresponding commonality information (commonality information file) into a sequential data stream.
A data storage library comprising:
- a frame;
- a shelf system supported by the frame to queue a plurality of tape cartridges;
- a plurality of tape drives each adapted to engage one of the tape cartridges in a data transfer relationship;
- a transport system selectively moving the tape cartridges between the queue in the shelf and the data transfer relationship in one of the plurality of tape drives;
- and
- a controller accessing instructions stored in memory that when executed deduplicate the user data by interleaving a plurality of files of the user data (user data files) with a respective plurality of files of corresponding commonality information (commonality information files) into a sequential data stream.
Dependencies are inferred from the claim text.