A storage array includes a plurality of hard disks, where each of the hard disks is divided into a plurality of chunks, and a plurality of chunks of different hard disks form a chunk group by using a redundancy algorithm. The storage array obtains fault information of a faulty area in a first hard disk, and determines a faulty chunk storing the lost data according to the fault information. The storage array recovers the data in the faulty chunk by using another chunk in a chunk group to which the faulty chunk belongs and stores the recovered data in a recovered chunk. The recovered chunk is located in a second hard disk which is not a hard disk for forming the chunk group.