Abstract: A data allocator which allocates data and redundant data for recovering the data. The data allocator has k storage groups, each of which includes m array files. Each array file includes multiple memory areas for storing the data and the redundant data on a block basis. A redundant group is formed which consists of k memory areas, each of which is selected from the same row of each one of k storage groups, and one of the k memory areas stores the redundant data and the remaining (k-1) memory areas store the data. The redundant data are uniformly allocated to m.sup.k sets of memory areas (D.sub.ij1, D.sub.2j2, . . . , D.sub.kjk) of the same rows of the storage groups, where j.sub.i (j.sub.i =1-m) is the number of the array file in each of the storage groups, and D.sub.kjk is the memory area belonging to k-th storage group and j.sub.k -th array file of the k-th storage group.