JP3220581B2 - Array type storage system - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an array type storage system in which a plurality of storage devices are arranged on an array and stores redundant data together with normal input / output data. The present invention relates to an array-type storage device system capable of adding a storage device without performing the operation.

[0002]

2. Description of the Related Art Conventionally, a disk array system has been known as an array type storage device system.

A disk array system is a computer system that achieves a high data transfer speed between a processing device and an external storage device by operating a large number of magnetic disk devices in parallel.

As an example of the configuration of a disk array system, see a paper by Paterson et al. (D. Paterson, G. Gi.
bson, R. Katz, "A Case for Redundant Arrays of Inex
pensive Disks (RAID) ", ACM SIGMOD conference procee
dings, 1988, pp.109-116).

In the above paper, RAID (Redundunt Arra
y of Inexpensive Disks (Raid).

In RAID levels 1 to 5, redundant data is stored in the magnetic disk drive together with normal input / output data.

[0007] By storing redundant data, when the input / output data is lost, the lost input / output data can be recovered using a data recovery function.

In the RAID levels 1 to 5, it is relatively easy to increase the number of magnetic disk drives for each redundant data creation unit.

In such an extension, it is necessary to regard the extended area as a continuous area and add the area immediately after the area before the extension or to logically make it appear to another magnetic disk device to incorporate the extended area. It is possible.

However, in the above-mentioned paper, the disk array
No reference is made to the addition of magnetic disk devices for each unit in the system, particularly to means for adding the magnetic disk devices without stopping the system.

A method of adding a magnetic disk device in a conventional disk array system will be described with reference to FIGS.

FIG. 13 is a diagram showing the data arrangement of a conventional RAID level 5 disk array system before magnetic disk units are added.

In FIG. 13, a magnetic disk drive 4-1 is shown.
4-4 constitute a logical disk, and the data of the logical disk is distributed and stored in the disk devices 4-1 to 4-4 for each block.

In FIG. 12, D0 to D17 indicate blocks of continuous data in the logical disk.

The magnetic disk array devices 4-1 to 4-1
-4, there is a block in which parity data is stored for each row composed of blocks having the same address.

In creating parity data, that is, redundant data, redundant data is created using exclusive OR for each bit of data from a plurality of magnetic disk devices, which is a unit for creating redundant data.

For example, in the parity data block P0 in the first row, the result of the exclusive OR operation for each bit of the data block D0, the data block D1, and the data block D2 is stored.

Here, it is assumed that the magnetic disk device 4-5 is added.

FIG. 14 is a diagram showing the data arrangement of a conventional disk array system after magnetic disk units are added.

The data is distributed and stored in the five magnetic disk array devices 4-1 to 4-5, and the parity is recalculated.

For example, the parity data block P0 'in the first row includes a data block D0 and a data block D1.
And the result of the bitwise other OR of the data block D2 and the data block D3 is stored.

As described above, if an attempt is made to increase the number of magnetic disk units one by one at the RAID level 5, data refilling and regeneration of redundant data are required.

[0023]

SUMMARY OF THE INVENTION
As described using the system as an example, in a conventional array-type storage device system, when a storage device is added, it is necessary to add the storage devices in units of a plurality of storage device groups for distributing data.

For this reason, there has been a problem that the unit of extension becomes large and the cost for increasing the storage capacity increases.

In addition, there is a problem that, when an attempt is made to add storage units for each unit, data must be refilled and redundant data must be recreated.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems of the prior art, and an object of the present invention is to provide an array-type storage device system without stopping the system and refilling data. Another object of the present invention is to provide a technology that enables an increase in the number of storage devices for each unit without performing regeneration of redundant data or redundant data.

The above and other objects and novel features of the present invention will become apparent from the description of the present specification and the accompanying drawings.

[0028]

In order to achieve the above-mentioned object, the means (1) of the present invention distributes a plurality of storage devices, redundant data and transfer data from a processing device to a plurality of storage devices. Means for reading and transferring necessary data from one or more storage devices in response to a data read request from the processing device, and means for transferring the data on the storage device directly due to a failure or the like. Is
A storage device of an array type comprising a control device having means for restoring data that cannot be accessed using redundant data, wherein the control device stores a logical configuration of the plurality of storage devices before expansion, Means for writing all zero data to the added storage device when a new storage device is added under the control of the control device; and writing all zero data to the added storage device, and Means for storing a new logical configuration of a plurality of storage devices including the added storage device in the storage means.

Further, the means (2) of the present invention is a means for distributing redundant data and transfer data from the processing device to a plurality of storage devices and storing the data, and a method for reading data from the processing device. Means for reading necessary data from one or more storage devices in response to the request and transferring the data to the processing device;
When the data on the storage device cannot be directly accessed due to a failure or the like, in a storage device system of an array type comprising a control device having means for restoring the inaccessible data using redundant data, A storage unit that stores a logical configuration of the plurality of storage devices, a unit that writes all 1 data to the added storage device when a new storage device is added under the control of the control device, Means for writing a new logical configuration of a plurality of storage devices including the newly added storage device to the storage means after writing all data in the storage device.

Further, the means (3) of the present invention is a means for distributing redundant data and transfer data from a processing device to a plurality of storage devices and storing the data, and a method for reading data from the processing device. Means for reading necessary data from one or more storage devices in response to the request and transferring the data to the processing device;
When the data on the storage device cannot be directly accessed due to a failure or the like, in a storage device system of an array type comprising a control device having means for restoring the inaccessible data using redundant data, A storage unit for storing a logical configuration of the plurality of storage devices, and confirming that, when a new storage device is added under the control of the control device, data of all 0s is written in the added storage device. And a new logical configuration of a plurality of storage devices including the added storage device after the addition, after confirming that data of all 0s has been written to the added storage device. Storage means.

Further, the means (4) of the present invention is a means for distributing redundant data and transfer data from the processing device to a plurality of storage devices and storing the data, and a method for reading data from the processing device. Means for reading necessary data from one or more storage devices in response to the request and transferring the data to the processing device;
When the data on the storage device cannot be directly accessed due to a failure or the like, in a storage device system of an array type comprising a control device having means for restoring the inaccessible data using redundant data, A storage unit for storing a logical configuration of the plurality of storage devices, and confirming that, when a new storage device is added under the control of the control device, all one data is written to the added storage device. And a new logical configuration of a plurality of storage devices including the added storage device after the addition, after confirming that all 1 data has been written to the added storage device. Storage means.

Further, the means (5) of the present invention, in the means of the above (1) to (4), the control device is added when a new storage device is added under the control device. The storage device has means for storing part or all of the redundant data.

[0033]

According to the above means, when an additional storage device is added to an array-type storage device system, all the added storage devices are initialized to 0 or 1 in advance, and then the added storage device is initialized. By storing the new logical configuration of a plurality of storage devices including the storage device in the storage means, the newly added storage device is logically incorporated into the array type storage device system, so that the redundant data does not change. Therefore, there is no need to regenerate redundant data.

Further, since the logical disk is constituted by the added storage device itself, it is not necessary to refill data.

Further, it is possible to initialize the additional storage device independently of the input / output operation with the processing device.
In addition, it is possible to incorporate a storage device to be added simply by changing the logical configuration of a plurality of storage devices without refilling data or regenerating redundant data, so that there is no need to stop the system when adding a storage device.

According to the above means, when updating the redundant data, the storage device for storing the redundant data is moved to the added storage device, so that the load can be balanced. Thereby, the performance can be improved.

[0037]

Embodiments of the present invention will be described below in detail with reference to the drawings.

In all the drawings for describing the embodiments, components having the same function are denoted by the same reference numerals, and their repeated description will be omitted.

[0039]

Embodiment 1 FIG. 1 is a block diagram showing a schematic configuration of an array type storage device system which is Embodiment 1 of the present invention.

In FIG. 1, 1 is a processing device, 2 is a disk array control device as a control device, 20 is a CPU, 21
Is a host interface, 4-1 to 4-5 are magnetic disk devices as storage devices, 23-1 to 23-5 are disk interfaces, 22 is a buffer, 24 is control storage, 24
1 is a configuration management table.

The disk array control device 2 is connected to the processing device 1 via the host interface 21 and to the magnetic disk devices 4-1 to 4-5 via the disk interfaces 23-1 to 23-5. Is done.

The buffer 22 is used as a data buffer between the processing device 1 and the magnetic disk devices 4-1 to 4-5, a cache, and a temporary storage device for generating parity data.

The control storage 24 is a storage device for storing various control tables and codes required for controlling a plurality of magnetic disk devices, such as a configuration management table 241 for managing the logical configuration of the disk array.

FIG. 2 is a diagram showing the configuration management table 241 according to the first embodiment.

As shown in FIG. 2, the configuration management table 24
1, the number of the corresponding magnetic disk device, the number of data blocks, the block number where parity data as redundant data is stored, and the like are described for each logical disk device.

The disk array control device 2 includes the processing device 1
It analyzes input / output requests from the CPUs and issues input / output requests to the magnetic disk devices 4-1 to 4-5 as necessary.
And the disk array controller 2 and between the disk array controller 2 and the magnetic disk devices 4-1 to 4-5.

When any one of the magnetic disk devices 4-1 to 4-5 fails, data and parity data are read from magnetic disk devices other than the failed magnetic disk device in response to an input request from the processing device 1. Data recovery for recovering the contents of the failed magnetic disk device and transferring it to the processing device, and reconstructing data for recovering the contents of the failed magnetic disk device and writing the data to the replacement magnetic disk device are performed.

FIG. 3 is a diagram showing the data arrangement in the magnetic disk according to the first embodiment.

In the first embodiment, a magnetic disk device for storing parity data is fixed, and a magnetic disk device is added.

In FIG. 3, before the expansion, data of the logical disks 0 to 2 are stored in the magnetic disk devices 4-1 to 4-3, respectively, and parity data is stored in the magnetic disk device 4-4.

Here, the case where the magnetic disk device 4-5 is added as the logical disk 3 is considered.

In this case, the magnetic disk drives 4-5 are all initialized to 0 in advance.

The initialization may be performed by an external device or by the disk array controller 2.

When the initialization is performed by the external device, the entire surface of the magnetic disk device 4-5 is read in order to confirm whether or not the initialization has been performed correctly.

When it is confirmed that the magnetic disk device 4-5 is connected and initialized normally, the configuration management table 241 for managing the logical configuration of the plurality of magnetic disk devices is changed to change the magnetic disk device 4-5. As a logical disk 3 in the storage system.

Next, the contents of the data block / parity data block when the magnetic disk device is added will be described. Here, an example using even parity is shown, but the same applies to odd parity.

The magnetic disk device 4 according to the first embodiment
The change in parity at the time of addition of −5 will be described with reference to FIGS. 4 and 5.

FIG. 4 is a diagram showing the parity when the magnetic disk 4-5 is added in the first embodiment.

In FIG. 4, the data block 41-4 of the magnetic disk device 4-4 is a parity data block, and the data blocks 41-1 to 41-3 of the magnetic disk devices 4-1 to 4-3 before expansion. After the expansion, the parity data of the data blocks 41-1 to 3-3 of the magnetic disk devices 4-1 to 4-3 and the data block 41-5 of the magnetic disk device 4-5 are stored.

As shown in FIG. 4, the data block 41-
The values of the first bytes of 1 to 41-3 are 00001111 and 00, respectively.
Since these are 110011 and 01010101, these even parity values, 01101001, are stored in the first byte of the parity data block 41-4 before expansion.

If the magnetic disk unit 4-5 is added, the contents of the data block 41-5 are all zero because the magnetic disk unit 4-5 has been initialized to zero.

Therefore, the data blocks 41-1 to 41-
The parity of 3 and 41-5 does not change, and there is no need to update the data block 41-4, which is the parity data block.

Next, a change in parity when data is written to the data block 41-5 after the addition of the magnetic disk device 4-5 will be examined.

FIG. 5 is a diagram showing a change in parity at the time of writing to the additional magnetic disk device 4-5 in the first embodiment.

As shown in FIG. 5, the magnetic disk drive 4-
5 to the data lock 41-5, the first byte of the data block 41-5 is changed from 00000000 to 010101.
Suppose it has changed to 01.

Since the data block 41-4 is a parity data block of the data blocks 41-1 to 41-3 and 41-5, the leading byte of the data block 41-4 contains these even-number parity values 001111100. It is memorized.

Similarly, a new parity value is calculated and stored for the subsequent bytes of the data block 41-4.

The updated parity is stored in the data block 41.
-1 to 41-3 and 41-5, or the exclusive OR of the pre-update data and pre-update parity data of the data block 41-5 and the post-update data of the data block 41-5 is calculated. It may be calculated.

When the updated parity is calculated by the latter method, the data block 41-5 and the data block 4 in FIG.
5 is the data before update 00000000, the parity data before update 01101001, the data after update 41010101 from the data block 41-5 in FIG. 5, and the exclusive OR of these is 00.
111100 is stored in the first byte of the parity data block 41-4.

As described above, any method may be used for calculating the parity.

It is also possible to initialize the additional magnetic disk unit 4-5 to 1.

However, in that case, the magnetic disk device 4-5
It is necessary to change the parity used before and after the expansion from even parity to odd parity.

That is, assuming that the magnetic disk device 4-5 is initialized to 1, the first byte of the data block 41-5 becomes 11111111.

In this case, as shown in FIG. 4, the values of the first bytes of the data blocks 41-1 to 41-3 are 00
001111, 00110011, and 01010101, and these even-numbered parity values of 01101001 are stored in the first byte of the parity data block 41-4 before expansion.

Therefore, if the odd parity is used after the magnetic disk drive 4-5 initialized to 1 is added, the parity of the data blocks 41-1 to 41-3 and 41-5 does not change. There is no need to update a certain data block 41-4.

[0076]

Embodiment 2 FIG. 6 is a diagram showing a data arrangement in a magnetic disk according to Embodiment 2.

In the second embodiment, the parity data is distributed and stored in the magnetic disk devices 4-1 to 4-4, and the number of magnetic disk devices is increased.

The system configuration of the second embodiment is the same as that of the first embodiment.

In FIG. 6, the magnetic disk devices 4-1 to 4-1
4-4 stores data and parity data of the logical disks 0 to 3, respectively.

Here, the case where the magnetic disk device 4-5 is added as the logical disk 4 is considered.

As in the case of FIG. 3, all the magnetic disk drives 4-5 are initialized to 0 in advance, and the configuration management table 241 is changed to change the magnetic disk drives 4-5 to the logical disk 4 as in the case of FIG. As a disk array.

For example, in the data block 42-3 of the magnetic disk device 4-3, a magnetic disk device 4-
1, 4-2, 4-4 data blocks 42-1, 42-
2 and 42-4, and the parity of the data blocks 42-1, 42-2, 42-4, and 42-5 of the magnetic disk devices 4-1, 4-2, 4-4, and 4-5 after expansion. The data is stored.

However, since the magnetic disk device 4-5 is initialized to 0, the contents of the data block 42-5 are all 0, and the contents of the data block 42-3 storing the parity data do not change.

After the expansion, the magnetic disk drives 4-1 and 4-1
4-2, 4-4, and 4-5 data blocks 42-1 and 4-4
When any of 2-2, 42-4, and 42-5 is updated, their parity data is calculated and stored in the data block 42-3.

In the second embodiment, it is also possible to initialize the additional magnetic disk unit 4-5 to 1, as in the first embodiment.

In this case, for the reasons described above, it is necessary to change the parity used before and after the addition of the magnetic disk drive 4-5 from even parity to odd parity.

[0087]

Embodiment 3 Next, a description will be given of an embodiment in which parity data is distributed and arranged on an additional magnetic disk.

FIG. 7 is a diagram showing a data arrangement in a magnetic disk according to the third embodiment.

In the third embodiment, the magnetic disk drive 4-5
Before the expansion, the parity data is transferred to the magnetic disk drive 4-1.
４−4-4 are distributed and stored, and the magnetic disk drive 4
After the addition of -5, the parity data is distributed and stored in the magnetic disk devices 4-1 to 4-5.

The system configuration of the third embodiment is the same as that of the first embodiment.

The data and parity data of the logical disks 0 to 3 are stored in the magnetic disk devices 4-1 to 4-4, respectively, and the data and the parity data of the logical disk 4 are stored in the added magnetic disk device 4-5. It is memorized.

Since the magnetic disk units 4-5 are all initialized to 0 in advance, when the data blocks of the magnetic disk units 4-5 are used as data of the logical disk 4, the parity data does not change at the time of expansion.

When the parity data is transferred to the magnetic disk device 4-5 due to the addition, the parity data block originally allocated to another magnetic disk device becomes an unused block and is not updated. However, it is included in the calculation of the parity data.

For example, before the magnetic disk device 4-5 is added, the data block 43-1 of the magnetic disk device 4-1 is used.
Are the parity data of the data blocks 43-2 to 43-4 of the magnetic disk devices 4-2 to 4-4, and after the magnetic disk device 4-5 is added, the data blocks 43-2 to 43-4 of the magnetic disk device 4-5. 5 is the data block 43-2 to 4
The data block 43-1 is an unused block, and the data block 43-1 is an unused block.

Data block 4 that has become an unused block
By including 3-1 in the parity data calculation, the initial value of the data block 43-5 serving as the parity data block can be set to 0.

Thus, it is not necessary to regenerate the parity data block allocated to the data block of the magnetic disk drive 4-5.

In the third embodiment, the magnetic disk device 4
The change in parity at the time of addition of −5 will be described with reference to FIGS. 8 and 9.

FIG. 8 is a diagram showing the parity when the magnetic disk 4-5 is added in the third embodiment.

In FIG. 8, even parity values of the data blocks 43-2 to 43-4 of the magnetic disk devices 4-2 to 4-4 are stored in the data block 43-1 of the magnetic disk device 4-1 before expansion. Have been.

Therefore, the data blocks 43-2 to 43-
The first byte of 4 is 00001111, 00110011, 010101
When 01, the value of the first byte of the data block 43-1 is
01100001.

Here, a case is considered where the data block 43-5 of the magnetic disk device 4-5 is used as a parity data block.

Assuming that the data block 43-5 is an even parity of the data blocks 43-2 to 43-4, 01101001 must be stored in the first byte of the data block 43-5.

However, when the unused data block 43-1 is included in the parity data calculation and the parity data of the data blocks 43-1 to 43-4 is calculated, the parity data value becomes 0, The initial value of 43-5 can be set to 0.

As a result, even when parity data is stored and arranged in a distributed manner in the added magnetic disk device, the entirety can be initialized to zero.

FIG. 9 is a diagram showing a change in parity at the time of writing to a magnetic disk device in the third embodiment.

In FIG. 9, it is assumed that the first byte of data block 43-2 has been changed from 000011111 to 01010101.

Since the parity data block after the addition is the data block 43-5, the data block 43-5 including the unused data block 43-1 is included.
-1 to 43-4 are calculated, and the value of the first byte of the data block 43-5 is calculated as shown in FIG.
01011010.

As shown in the data block 43-1 in FIG. 7, the area where the parity data is no longer required to be stored because the parity data has been moved to the added magnetic disk device 4-5 is regarded as an unused block. It may be used, or another logical disk may be allocated and used.

In the second embodiment, it is also possible to initialize the additional magnetic disk unit 4-5 to 1, as in the first embodiment.

In this case, for the reasons described above, it is necessary to change the parity used before and after the addition of the magnetic disk drive 4-5 from even parity to odd parity.

In each of the embodiments described above, the configuration in which the physical magnetic disk device and the logical disk correspond one-to-one has been described. However, the added magnetic disk device constitutes a different logical disk from that before the expansion. Or, if it is configured as an extension area of the logical disk before expansion, the physical magnetic disk device and the logical disk need not necessarily correspond one-to-one.

For example, as shown in FIG. 10, one logical disk is formed from the magnetic disk devices 4-1 to 4-3, and another logical disk is formed from the added magnetic disk device 4-5. It is also possible.

As shown in FIG. 11, the magnetic disk devices 4-1 to 4-3 are divided to form a plurality of logical disks, and the additional magnetic disk device 4-5 is connected to another logical disk. Can also be configured.

Further, when a plurality of magnetic disk devices are added at the same time, one logical disk can be constructed from a plurality of disk devices added at the same time.

In FIG. 12, one logical disk is constituted by the added magnetic disk devices 4-5 to 4-6.

Of course, it is also possible to divide the additional magnetic disk device to form a plurality of logical disks.

Although the present invention has been described in detail with reference to the embodiments, it is needless to say that the present invention is not limited to the above embodiments and can be variously modified without departing from the scope of the invention.

[0118]

As described above, according to the present invention,
When an additional storage device is added to an array-type storage device system, all the added storage devices are set to 0 in advance.
Alternatively, after initializing to 1, the new logical configuration of the plurality of storage devices including the added storage device is stored in the storage means, so that the newly added storage device is logically converted to an array type storage device system. Because of the incorporation, the redundant data does not change, and there is no need to regenerate the redundant data.

Further, since the logical disk is constituted by the added storage device itself, it is not necessary to refill data.

Further, it is possible to initialize the additional storage device independently of the input / output operation with the processing device.
In addition, it is possible to incorporate a storage device to be added simply by changing the logical configuration of a plurality of storage devices without refilling data or regenerating redundant data, so that there is no need to stop the system when adding a storage device.

As a result, the data availability associated with the expansion can be improved, and the cost required for expanding the storage capacity can be reduced because the required capacity can be increased.

According to the above means, when updating the redundant data, the storage device for storing the redundant data is moved to the added storage device, so that the load can be balanced. Thereby, the performance can be improved.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a schematic configuration of an array-type storage device system according to a first embodiment of the present invention.

FIG. 2 illustrates a configuration management table according to the first embodiment.

FIG. 3 is a diagram illustrating a data arrangement in a magnetic disk according to the first embodiment.

FIG. 4 is a diagram illustrating parity when a magnetic disk is added in the first embodiment.

FIG. 5 is a diagram illustrating a change in parity at the time of writing to an additional magnetic disk device in the first embodiment.

FIG. 6 is a diagram illustrating a data arrangement in a magnetic disk according to the second embodiment.

FIG. 7 is a diagram illustrating a data arrangement in a magnetic disk according to a third embodiment.

FIG. 8 is a diagram illustrating parity when a magnetic disk is added in the third embodiment.

FIG. 9 is a diagram illustrating a change in parity at the time of writing to a magnetic disk device in the third embodiment.

FIG. 10 is a diagram showing an example of configuring a logical disk from a plurality of magnetic disk devices in the present invention.

FIG. 11 is a diagram showing an example in which a plurality of magnetic disk devices are divided to form a plurality of logical disks in the present invention.

FIG. 12 is a diagram showing an example of configuring a logical disk from a plurality of additional magnetic disk devices in the present invention.

FIG. 13 is a diagram showing a data arrangement before a magnetic disk device is added to a conventional disk array system.

FIG. 14 is a diagram showing a data arrangement after a magnetic disk device is added to a conventional disk array system.

[Description of Signs] 1 ... Processing device, 2 ... Disk array control device, 21 ... Host interface, 22 ... Buffer memory, 23-1
23-5: disk interface, 24: control storage, 241: configuration management table, 4-1 to 4-6: magnetic disk drive, 41-1 to 41-5: data block,
43-1 to 43-5 ... data blocks.

──────────────────────────────────────────────────続 き Continuing on the front page (72) Inventor Takao Sato 1099 Ozenji Temple, Aso-ku, Kawasaki City, Kanagawa Prefecture Hitachi, Ltd.System Development Laboratory (72) Inventor Akira Yamamoto 1099 Ozenji Temple, Aso-ku, Kawasaki City, Kanagawa Hitachi, Ltd. (56) References JP-A-7-141121 (JP, A) JP-A-4-233025 (JP, A) JP-A-5-224822 (JP, A) (58) Fields surveyed ( Int.Cl. ⁷ , DB name) G06F 3/06

Claims (5)

(57) [Claims] A plurality of storage devices, means for distributing redundant data and transfer data from the processing device to the plurality of storage devices and storing the data, and storing necessary data in response to a data read request from the processing device. It comprises a control unit having means for transferring data from at least one storage device to the read processing device, and means for restoring inaccessible data using redundant data when data on the storage device cannot be directly accessed due to a failure or the like. In the array-type storage device system, the control device is configured to store the logical configuration of the plurality of storage devices before the addition, and when the storage device is newly added under the control device, the storage device is added. Means for writing all 0s data to the storage device, and writing all the 0s data to the added storage device, and then storing the added storage device after the addition. Means for storing a new logical configuration of a plurality of storage devices including the storage device in the storage means. 2. A plurality of storage devices, means for distributing redundant data and transfer data from a processing device to the plurality of storage devices and storing the data, and storing necessary data in response to a data read request from the processing device. It comprises a control unit having means for transferring data from more than one storage device to the read processing device, and means for restoring inaccessible data using redundant data when data on the storage device cannot be directly accessed due to a failure or the like. In the array type storage device system, the control device is configured to store the logical configuration of the plurality of storage devices before the expansion, and the storage device is added when a new storage device is added under the control device. Means for writing all one data to the storage device, and additional storage device after writing all the one data to the additional storage device Storage system array format, characterized in that it comprises a means for storing a new logical configuration of a plurality of storage devices in the storage means, including. 3. A plurality of storage devices, means for distributing redundant data and transfer data from the processing device to the plurality of storage devices and storing them, and storing necessary data in response to a data read request from the processing device. It comprises a control unit having means for transferring data from at least one storage device to the read processing device, and means for restoring inaccessible data using redundant data when data on the storage device cannot be directly accessed due to a failure or the like. In the array type storage device system, the control device is configured to store the logical configuration of the plurality of storage devices before the expansion, and the storage device is added when a new storage device is added under the control device. Means for confirming that all zero data has been written to the storage device;
Means for storing, in the storage means, a new logical configuration of a plurality of storage devices including the added storage device after the addition, after confirming that all data of 0 is written in the added storage device; An array type storage device system comprising: 4. A plurality of storage devices, means for distributing redundant data and transfer data from a processing device to the plurality of storage devices and storing the data, and storing necessary data in response to a data read request from the processing device. It comprises a control unit having means for transferring data from at least one storage device to the read processing device, and means for restoring inaccessible data using redundant data when data on the storage device cannot be directly accessed due to a failure or the like. In the array type storage device system, the control device is configured to store the logical configuration of the plurality of storage devices before the expansion, and the storage device is added when a new storage device is added under the control device. Means for confirming that all one data has been written to the storage device;
Means for storing, in the storage means, a new logical configuration of a plurality of storage devices including the added storage device after the addition, after confirming that all 1 data has been written to the added storage device; An array type storage device system comprising: 5. An array-type storage device system according to claim 1, wherein the control device is added when a new storage device is added under the control device. An array-type storage device system comprising means for storing a part or all of redundant data in a specified storage device.