Deduplication of storage device encoded data

A computer-implemented method, comprising:

• storing, by a storage device and through an error correction code engine in a write path of the storage device, host data blocks to a storage medium of the storage device, wherein the stored host data blocks comprise a first encoded comparison data unit encoded by the error correction code engine in the write path;
• returning, by the storage device and to a host system, previously-stored host data blocks responsive to decoding, through an error correction code engine in a read path of the storage device, the stored host data blocks from the storage medium;
• encoding, by the storage device and using the error correction code engine in the write path, a target data unit to generate an encoded target data unit comprised of:
• an input host data block divided into a plurality of symbols;
• and
• at least one parity symbol generated using the plurality of symbols of the input host data block and an error correction code coding algorithm for the error correction code engine in the write path;
• retrieving, by the storage device and for a deduplication operation, a first encoded comparison data unit from the storage medium of the storage device without decoding the first encoded comparison data unit using the error correction code engine in the read path of the storage device, wherein the first encoded comparison data unit comprises:
• a previously-stored host data block divided into a plurality of symbols;
• and
• at least one parity symbol generated prior to storage in the storage medium using the plurality of symbols of the previously-stored host data block and the error correction code coding algorithm for the error correction code;
• comparing, responsive to encoding the target data unit and retrieving the first encoded comparison data unit and using a bit-by-bit exclusive-or comparison, each bit of the encoded target data unit to each corresponding bit of the first encoded comparison data unit;
• determining, based on a number of bits that are not equal between the encoded target data unit and the first encoded comparison data unit, a first similarity value;
• and
• eliminating, responsive to the first similarity value, at least one duplicate data unit selected from:
• the target data unit;
• and
• the first encoded comparison data unit in the storage medium.

A storage device, comprising:

• a storage medium configured to store host data blocks;
• a storage device controller comprising:
• at least one processor;
• and
• at least one operating memory;
• means for storing, through an error correction code engine in a write path of the storage device, the host data blocks to the storage medium, wherein the stored host data blocks comprise a first encoded comparison data unit encoded by the error correction code engine in the write path;
• means for returning, to a host system, previously-stored host data blocks responsive to decoding, through an error correction code engine in a read path of the storage device, the stored host data blocks from the storage medium;
• means for encoding, using the error correction code engine in the write path, a target data unit to generate an encoded target data unit comprised of:
• an input host data block divided into a plurality of symbols;
• and
• at least one parity symbol generated using the plurality of symbols of the input host data block and an error correction code coding algorithm for the error correction code engine in the write path;
• means for retrieving, for a deduplication operation, a first encoded comparison data unit from the storage medium without decoding the first encoded comparison data unit using the error correction code engine in the read path of the storage device, wherein the first encoded comparison data unit comprises:
• a previously-stored host data block divided into a plurality of symbols;
• and
• at least one parity symbol generated prior to storage in the storage medium using the plurality of symbols of the previously-stored host data block and the error correction code coding algorithm for the error correction code engine in the write path;
• means for comparing, responsive to encoding the target data unit and retrieving the first encoded comparison data unit and using a bit-by-bit exclusive-or comparison, each bit of the encoded target data unit to each corresponding bit of the first encoded comparison data unit;
• means for determining, based on a number of bits that are not equal between the encoded target data unit and the first encoded comparison data unit, a first similarity value;
• and
• means for eliminating, responsive to the first similarity value, at least one duplicate data unit selected from:
• the target data unit;
• and
• the first encoded comparison data unit in the storage medium.