Disk array apparatus capable of dealing with an abnormality occurring in one of disk units without delaying operation of the apparatus

Abstract

In a disk array apparatus which includes disk units so as to have a redundancy and which carries out, in response to a data writing instruction or a data reading instruction from a host computer, a data writing operation or a data reading operation between the disk units and the host computer, detector/memory section ( ) detects, as a faulty unit, one of the disk units in which an abnormality occurs on any one of the data writing operation and the data reading operation. A disconnection managing section ( ) temporarily disconnects the faulty unit as a temporarily disconnected unit to make the disk array apparatus operate in a temporary degenerate mode. An instruction-execution controlling section ( ) forces the disk units except the temporarily disconnected unit to execute the data writing operation or the reading operation between the disk units except the temporarily disconnected unit and the host computer by the use of the redundancy when the disk array apparatus receives, during the temporary degenerate mode, the data writing instruction or the data reading instruction from the host computer. A retry section ( ) carries out retry for the temporarily disconnected unit in parallel to the data writing operation or the data reading operation executed between the disk units except the temporarily disconnected unit and the host computer.