Abstract: A plurality of disc units, an array control unit, and a host controller connecting mechanism for connecting them to a host controller through a system interface are mounted on the same circuit board. The order of interrupts of requests for connecting of disc units is detected, and the disc units are connected to a common bus selectively. Cables for interconnecting constituent elements of the disc array device and supporting mechanisms for the disc units can be dispensed with, and consequently the cost can be reduced. Useless rotation waiting is avoided, improving the data transfer rate. The disc array device can be built in the host device and connected directly to the system bus. Therefore the ease of operation can be improved.

Abstract: A disc array system has a plurality of disc storage devices (i.e., drives) constituting a parity group and mounted in a distributed manner on different boards. Where any one drive in the same parity group develops a fault, the board carrying the faulty drive is withdrawn from the mother board for repair. If the CPU issues a write request for data held in the faulty drive or in any normal data on the same board, the requested data is recovered from the multiple data retained in the other drives constituting the same logical group and mounted on the other boards. The recovered data is sent to the CPU.If the CPU supplies write data to the faulty drive or to any normal drive on the same board, the supplied write data is held temporarily in a cache memory in an array controller.

Abstract: With respect to the disk drives provided power from a single power source in a disk drive system, start up power is first supplied to a first start-up group of the disks, preferably comprising all of the master disks, with the size of the group being selected so that the required current does not exceed the capacity of the power source. When the disk drives of the first group have substantially reached steady state, start-up is conducted with respect to a second start-up group of the disk drives so that the current required during start-up for the second group and the current required for steady state drive of the first start-up group does not exceed the capacity of the power source. With respect to each start-up group, the number of disk drives is the maximum integer value and decreases or remains the same with respect to subsequent start-up groups.

Abstract: A drive unit connected to a disk control unit of a disk array has a logical group formed of a plurality of drives. In the logical group, both original data and duplexed data of the original data are stored. The original data and the duplexed data thereof are stored in different drives. When a plurality of data stored in one drive are to be read, the original data or the duplexed data thereof are read in parallel from the different drives.

Abstract: To a parity group including a plurality of data items and a parity code, at least two dummy data items are added to configure a logical group. The data items, dummy data items, and parity code of each logical group are written in mutually different disk drives. When renewing a data item of a parity group, an old data item and an old parity code are read from the associated drives so as to renew the old data item. According to a new data item for the renewal and the old data item and parity code, there is created a new parity code. The new parity code is written in one of the drives containing dummy data items available at an earliest point of time for the write operation. Prior to the write operation of the new parity code, the new data item is written in a drive containing another dummy data item.

Abstract: A disc array system has a plurality of disc storage devices (i.e., drives) constituting a parity group and mounted in a distributed manner on different boards. Where any one drive in the same parity group develops a fault, the board carrying the faulty drive is withdrawn from the mother board for repair. If the CPU issues a write request for data held in the faulty drive or in any normal data on the same board, the requested data is recovered from the multiple data retained in the other drives constituting the same logical group and mounted on the other boards. The recovered data is sent to the CPU.If the CPU supplies write data to the faulty drive or to any normal drive on the same board, the supplied write data is held temporarily in a cache memory in an array controller.

Abstract: When new data for writing is sent from a host device, old data and old parities are read after a search time respectively, and a new parity is generated with the new data, the old data and the old parities, and the new parity is stored in a cache memory, and when the number of the new parities corresponding to a plurality of write data becomes more than a predetermined value set by a user or when there is a period of time in which no read request or no write request is issued, new parities are collectively written to a drive for storing parities. In this case, a plurality of new parities are written in a series of storing positions, where a plurality of old parities are stored, in a predetermined access order independent of the stored positions of corresponding old parities. At least to a plurality of storing positions in a track, these new parities are written in the order of positions in a track.

Abstract: In a disk array system of RAID (level 5) improving the system performance by distributing data, duplicated fields are allocated in a parity group in order to reduce an overhead of data write. In the data write process, write data is tentatively and duplicately written in the duplicate fields. At this time, a write completion is reported to the CPU. The parity is generated later at a proper timing and written in a SCSI drive. Generating a parity and writing data can be efficiently scheduled.

Abstract: A file system including an input/output unit for inputting data from and outputting data to an external system; a controller connected to the input/output unit for dividing the data into an optional number of parallel data; a management table for storing the number of divisions of the data; a head group for writing the divided parallel data into a storage medium at the same time; and a unit for reading the data from the storage medium while referring to information stored in management device.

Abstract: When a CPU serving as a higher rank apparatus issues an input command to a secondary storage device having a plurality of disk drives, a predetermined number of disk drives each being less in the number of input/output commands to be processed and having a free capacity are selected from the plurality of disk drives so that identical data are multiply written in the selected disk drives. A data address management table for managing data stored in the respective disk drives, a free area management table for managing free areas in the respective disk drives and a disk drive management table for managing the number of input/output commands to be processed in each of the disk drives are generated in a controller in the secondary storage device. Processors in the controller select a predetermined number of optimum disk drives by referring to these tables in response to the input command given from the CPU.

Abstract: In a data processing system to which a large number of disk drive units are connected, data in the whole or part area of a file are multiplexed and distributed into a plurality of disk drive units when the file is opened, and the multiplex data of the file are deleted when the file is closed. Among the multiplex data, data shortest in access time or striped data shortest in transfer time is selected to be accessed. When data multiplexing is applied only to the part area, the data storage capacity of the system can be reduced more remarkably.

Abstract: A storage data reconstruction system including a plurality of storage units for storing therein divided data units for storing therein ECC data corresponding to the divided data; a spare storage unit for storing therein reconstructed data; an I/O-reconstruction control circuit; a timer; a data reconstructing table for a storage unit which has failed; and a circuit for reconstructing faulty data. When a failure occurs in any of the storage units, the failure is detected by an error check, a state of the failure is discriminated, a preferred processing suitable for the state of the failure is selected from a processing of a normal access or read/write, and a data reconstruction processing, and the selected processing is carried out, or the frequency of the processing of the normal access or read/write and the data reconstruction processing, or the ratio of the amount of the data reconstruction processing within a unit time, is set.

Abstract: In a disk array system for RAID (level 5) to improve a process performance by dispersing data, the overhead during data writing operation is reduced. Even when write data are used to rewrite data #1 to data #4, which have already been written at address SADR 2, SADR 2, SADR1 and SADR 3 within drives as data belonging to mutually different parity groups, these data are considered as new write data, and then these new write data are written in parallel into, for instance, an empty region in the drive at the address SADR 4. The updated old data or the updated old parity data are not read out. The invalidation flags for the updated old data are registered into an address conversion table. The subsequent data readout operation is carried out from a newly written region. When all of data within the original parity group are invalidated, the region holding this group is used as an empty region. The valid data within the parity group, which have been partially invalidated, are replaced at a proper timing.

Abstract: An array disk system includes a plurality of disk drives having disk-like recording media each having a surface divided into a plurality of zones and the data capacity per track is varied in each zone. The plurality of disk drives are divided into a plurality of groups. Reading/writing heads of the disk drives are positioned to access tracks having different zones on the disks in each zone on the basis of a cylinder address designated by a host system. Data transferred from the host system is divided in accordance with a ratio of data capacities of the tracks to be accessed and is recorded in each of the disk drives simultaneously.

Abstract: An array disk subsystem including a command selector for separating a signal from a host into a data item and a command, a data dividing unit for subdividing the data item, an ECC generator for producing an ECC for each of the obtained subdata items, a group of data disks for respectively storing thereon the subdata items and the ECCs, a command interpreting unit for interpreting the command, an I/O counter for counting I/O commands in the command, a backup processor for requesting a backup command based on count information of the I/O counter, and a backup unit responsive to the backup command for sequentially reading the subdata items and the ECCs from the data disks to record therein the subdata items and the ECCs.

Abstract: An error correction circuit which includes a specification circuit for specifying erroneous portions in a first data set reproduced from a recording medium, a register for storing the reproduced first data set including the erroneous portions thus specified and a reproducing circuit responsive to the reproduced first data set for reproducing again the first data set from the recording medium to obtain retry data, when there exist erroneous portions in the reproduced first data set stored in the register. The correction circuit also includes a data replace circuit, connected to receive the retry data, for replacing information at the specified erroneous portions in the reproduced first data set stored in the register by information at corresponding portions in the retry data.

Abstract: A parallel transfer type disk system comprising: a means for parallel dividing input digital data; a plurality of magnetic disks for recording each of said divided digital data, said magnetic disks including a plurality of magnetic heads for allocating said divided digital data to a plurality of tracks on a plurality of magnetic recording disks for simultaneous recording of the data, and a magnetic head driving means including a head selection means for driving said magnetic heads; a means for detecting defective track among said plurality of tracks from each of track signals; and a means for temporarily recording digital data allocated to a defective track and then recording the data on a predetermined track, or for simultaneously recording digital data allocated to said defective track and digital data allocated to tracks other than said defective track on a predetermined group of replacement tracks on said plurality of recording media, when existence of said defective track has been detected by said detect