Data processing method and distributed file system applying same

The invention discloses a data processing method and a distributed file system applying the same. The method comprises the following steps of: when a master management node is effective, receiving a data request sent from the client side by the master management node; forwarding the request to a data node; synchronizing file metadata information stored per se to a slave management node; maintaining periodicity heart communication with the slave management node; when the master management node becomes invalid, sending the data node state information stored per se to the slave management node by the data node; and converting the slave management node into the current master management node. From the above technical scheme, the master and the slave management nodes are adopted by the data processing method disclosed by the embodiment of the invention, and the master management node synchronizes the file metadata information stored per se to the slave management node; and thus, when the master management node becomes invalid, the slave management node can replace the master management node to continuously work to guarantee the operation reliability of the distributed file system and provide system disaster tolerance performance.