A data transfer device calculates a compression performance value which represents a quantity of data that can be compressed per unit time and a transfer performance value which represents a quantity of data that can be transferred per unit time, and calculates, based on these values, a compression ratio which represents a ratio of data to be compressed and then transferred to total data to be transferred. The data transfer device extracts, from a storage unit which stores data, the data to be transferred, and then compresses part of the extracted data based on the compression ratio, and transfers the compressed data and remaining data to another device. The compression and transfer processes are performed in parallel.