Embodiments of the present disclosure disclose methods and devices of data de-duplication. The method of data de-duplication performed at a client comprises: in response to receiving data to be backed up at a client, sampling the data to be backed up to obtain the sampled data; generating a signature for the sampled data; transmitting the signature to a master storage node in a storage cluster including a plurality of storage nodes, to allow the master storage node to select one storage node from the plurality of storage nodes; receiving an indication of the selected storage node from the master storage node; and transmitting, based on the indication, the data to be backed up to the selected storage node. Embodiments of the present disclosure also provide methods of data de-duplication performed at the master storage node and the slave storage node, and corresponding devices.