Cloud storage is one of the underlying services in cloud computing. However, there are some critical issues in file storage which should be resolved urgently, such as the blocking file storage. In order to solve the shortages of hot file storage and parallel computing support issues in fixed-blocking storage, we propose a smart-blocking file storage method in this paper. By setting up 6 grouping factors, the method can determine whether the file should be blocked or not automatically depending on the size of the file and the client bandwidth. The proposed method can block the file into similar size sub-blocks as large as possible when the file is judged to be blocked. Normally the size of the last sub-block is smaller than other similar sub-blocks. But the gap maintains within the size of the next smaller grouping factor. The Metadata server can address the hot files when the file is blocked. In addition, the proposed method also defines the file uniformity and the system uniformity to quantitatively describe the uniformity of sub-blocks in the file and in the whole system. Analysis and simulation demonstrate the proposed method has better system uniformity in file storage, the node load balance caused by hot file, and a large number of file fragments reduction.