The invention provides a distributed file system based small file storage method and device. The method comprises the steps of allocating a uniquely corresponding data sub-table to a to-be-stored small file with the associativity, wherein the data sub-table is a preset logic two-dimensional table and comprises a plurality of logic rows and logic columns composed of logic storage units with the preset sizes, and the to-be-stored file comprises batches of small files different in both type and size; storing the small files with the associativity in the to-be-stored small file into the same logic rows or the same logic columns in the data sub-table; and for the small files with the associativity, generating uniquely corresponding file indexes and storing the file indexes into the corresponding logic rows or logic columns. According to the method and device, the file storage pressure of a distributed file system can be remarkably reduced.