Storage system

摘要

Duplicate storage elimination is performed in units of block data generated by dividing a data stream into arbitrary-sized blocks. Further, sub-block data is generated by further dividing the block data into a plurality of pieces of data, and sub-address data based on the data content of each of the pieces of sub-block data is stored in a predetermined storage device. As such, duplicate storage elimination is also performed in sub-block data units based on the sub-address data.

主权项

1. A storage system including a processor, comprising:
a block data deduplication unit implemented by the processor that stores, in a storage device, block data generated by dividing a data stream into arbitrary-sized blocks, the block data being pointed to by address data based on a data content of the block data, and when attempting to store, in the storage device, another piece of block data having a data content identical to the data content of the block data having been stored in the storage device, stores, in the storage device, the address data pointing to the block data having been stored in the storage device as the other piece of block data to thereby perform duplicate storage elimination of the block data; and a sub-block data deduplication unit implemented by the processor that stores, in the storage device, sub-block data generated by further dividing the block data into a plurality of pieces of data, each of the pieces of sub-block data being pointed to by a piece of sub-address data based on a data content of the sub-block data, stores a sub-address data group including pieces of sub address data in a predetermined storage device, and when attempting to store, in the storage device, another piece of sub-block data having a data content identical to the data content of the sub-block data having been stored in the storage device, stores, in the predetermined storage device, the piece of sub-address data pointing to the sub-block data having been stored in the storage device as the other piece of sub-block data to thereby perform duplicate storage elimination of the sub-block data, wherein if a feature value detected from at least one piece of block data in the data stream based on a data content of the block data satisfies a set condition, the sub-block data deduplication unit stores, in the predetermined storage device, the sub-address data group pointing to pieces of sub-block data generated by dividing another piece of block data corresponding to the block data from which the feature value satisfying the set condition is detected, in association with the feature value satisfying the set condition.