Method for achieving uniform data distribution in cloud storage system

The invention discloses a method for achieving uniform data distribution in a cloud storage system. The method comprises the steps: A, a client transmits a write request to a metadata service node, wherein the write request comprising a required storage space, basic file information and which data block to be written at present, B, the metadata service node selects one from all available store service nodes randomly with a Hash algorithm and then randomly selects a disk from the selected store service node with the Hash algorithm, the metadata service node stores identifications of the selected store service node and the disk as position distribution information, C, the metadata service node transmits the position distribution information to the client, D, the client writes the position distribution information into a disk in a corresponding position, E, the client judges whether the current data block is overwritten, Step A is re-executed if so, and Step F is executed if not, and F, the client judges whether to accomplish a write process, the process is finished if so, and Step A is re-executed if not.