JP2015161996A - Disk array control device, disk array device, disk array control method and computer program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a disk array control device and the like that hold an access performance capable of dealing with a change in data volume to be stored, and enable reduction in power consumption.SOLUTION: A disk array control device comprises control means that receives a command from a host device to perform a control according to the command, and the control means is configured to: obtain the number of required disk drives on the basis of a data volume stored in a disk array composed of a plurality of disk drives; determine to halt disk drives above the number of required disk drives are halted; and copy data stored in the disk drives determined to halt to disk drives not targeted for a halt.

Description

  The present invention relates to a technical field for controlling a disk array including a plurality of disk drives.

  In recent years, power consumption of computer systems has become a social issue due to the increase in computer systems. In particular, a computer system and a data center owned by a company may require a large amount of power, and there is a strong demand for a technique for reducing the power consumption of individual devices in such a computer system.

  A disk array device has a large number of disk drives, which are rotating bodies, mounted therein. Therefore, the disk array device is a device that consumes particularly large power in the computer system. Therefore, reducing the power consumption of the disk array device can be expected to greatly contribute to the reduction of power consumption in the entire system.

  Regarding the reduction of power consumption of the disk array device, together with the technology to reduce the power consumption of the control unit and the disk drive itself, the disk drives that are not used or are not used frequently are stopped, MAID (Massive Array of Inactive Disks) technology for reducing the power consumption of the array device is known and commercialized. This technology is based on the following characteristics that appear when a large number of disk drives are mounted in a disk array device or when there are a large number of disk array devices. That is, the characteristic is that, in general, only a small part of disk drives are frequently issued with input / output commands, and input / output commands are issued rarely or not at all to many disk drives. This is based on the distribution characteristics of input / output instructions for the disk, which is often the case.

  In the business using the computer system, there is a periodic fluctuation in the business load in each business cycle. In general, there is a temporal distribution characteristic in which a large load is concentrated at the end of the month, the end of the fiscal year, and the end of the fiscal year in balance with accounting.

  The performance of a disk array device is often the bottleneck of the input / output performance of the disk drive itself. Therefore, it is common for a disk array device to have a configuration with many disk drives as high performance is required. is there. For this reason, the disk array device is sized so as to withstand the maximum work load. The disk array device constructed in this way usually operates with excessive performance even when it has adequate performance during busy periods.

  Here, as related technologies existing prior to the application of the present application, for example, there are the following patent documents.

  Patent Document 1 and Patent Document 2 classify data according to requirements (response speed and access pattern) required when accessing data stored in a storage medium, and divide the storage medium storing the data for each classification. Thus, a technique for performing power saving control on each storage medium is disclosed.

  Patent Document 3 discloses a technique for moving data between storages for a plurality of storages so that all the disks constituting one storage are targeted for power saving.

  Patent Document 4 discloses a technique for optimizing data arrangement according to data access frequency and reducing an excess storage area.

  Patent Document 5 discloses a technique for setting a threshold value for the usage status of each data storage medium and rearranging data between the storage media so as not to exceed the threshold value.

Japanese Patent No. 3589654 JP 2010-271901 A Special table 2013-524333 gazette JP 2010-231465 A JP 2007-115232 A

  However, even if the techniques proposed in Patent Document 1 to Patent Document 5 are used, it is not possible to perform power saving control in consideration of access performance that can cope with fluctuations in the amount of data stored in one disk array device. .

  SUMMARY OF THE INVENTION Accordingly, it is a primary object of the present invention to provide a disk array control device and the like that can reduce power consumption while maintaining access performance that can cope with fluctuations in the amount of data to be stored.

  In order to achieve the above object, a disk array control device according to the present invention comprises the following arrangement.

That is, the disk array control device according to the present invention is
A control means for receiving a command from the host device and performing control according to the command;
The control means obtains the number of disk drives required based on the amount of data stored in a disk array comprising a plurality of disk drives, and decides to stop the disk drives exceeding the number of disk drives. The data stored in the disk drive determined to be stopped is copied to a disk drive not to be stopped.

A disk array control method according to the present invention that achieves the same object,
When a computer receives a command from a host device and controls a disk array composed of a plurality of disk drives according to the command,
The number of disk drives required based on the amount of data stored in the disk array is determined, the disk drive exceeding the number of disk drives is determined to stop, and the disk determined to stop Data stored in the drive is copied to a disk drive that is not a stop target.

  Further, the same object is achieved by a computer program for realizing the disk array control device having the above-described configuration by a computer, and a computer-readable storage medium in which the computer program is stored.

  According to the present invention described above, in the disk array device, it is possible to reduce power consumption while maintaining access performance that can cope with fluctuations in the amount of data to be stored.

1 is a block diagram showing a configuration of a disk array control device according to a first embodiment of the present invention. It is a block diagram which shows the structure of the disk array apparatus concerning the 2nd Embodiment of this invention. It is a figure explaining the address conversion table which stores the address information which concerns on the 2nd Embodiment of this invention. It is a figure explaining the physical address for every disk drive concerning the 2nd Embodiment of this invention. It is a figure explaining the disk array apparatus seen from the high-order apparatus which concerns on the 2nd Embodiment of this invention. It is a flowchart which shows the process at the time of the write command reception in the microprocessor which concerns on the 2nd Embodiment of this invention. It is a flowchart which shows the process at the time of the read command reception in the microprocessor which concerns on the 2nd Embodiment of this invention. It is a flowchart which shows the transfer process from the normal mode in the microprocessor which concerns on the 2nd Embodiment of this invention to a power saving mode. It is a figure explaining the address conversion table after transfering to the power saving mode which concerns on the 2nd Embodiment of this invention. It is a flowchart which shows the transfer process from power saving mode to normal mode in the microprocessor which concerns on the 2nd Embodiment of this invention. It is a figure explaining the address conversion table after transfering to the normal mode which concerns on the 2nd Embodiment of this invention.

  Next, embodiments of the present invention will be described in detail with reference to the drawings.

<First Embodiment>
FIG. 1 is a block diagram showing the configuration of the disk array control apparatus according to the first embodiment of the present invention.

  The disk array control apparatus 100 according to the present embodiment includes a control unit 110 and an address conversion unit 120.

  The disk array control device 100 is connected to the host device 200. The host device 200 issues a command to the disk array control device 100. The host device 200 is, for example, a host computer.

  The disk array control device 100 controls the disk drives 131 to 138 constituting the disk array.

  The control unit 110 receives a command from the host device 200 and performs control according to the command.

  The address conversion unit 120 associates the address information specified by the instruction with the address information used when accessing the disk drives 131 to 138.

  When the host apparatus 200 commands the transition to the power saving state, the control unit 110 obtains the number of disk drives required based on the amount of data stored in the disk drives 131 to 138. Then, the control unit 110 determines to stop the disk drives (131 to 138) exceeding the number of disk drives. In the present application, “stop” refers to stopping power supply to the disk drive. However, the present invention is not limited to this, and “stop” may be to reduce the electric power used in the disk drive by stopping the motor that moves the rotating body. The control unit 110 refers to the information stored in the address conversion unit 120 for data stored in the disk drives (131 to 138) determined to be stopped, and the disk drives (131 to 138) that are not to be stopped. ). After copying, the control unit 110 updates the information held by the address conversion unit 120 in accordance with the contents of the disk drives 131 to 138.

  When the host apparatus 200 is instructed to cancel the power saving state, the control unit 110 operates the stopped disk drives (131 to 138). Then, the control unit 110 refers to the information held by the address conversion unit 120 and distributes and stores the data in the operating disk drives (131 to 138). After the storage, the control unit 110 updates the information held by the address conversion unit 120 in accordance with the contents of the disk drives (131 to 138).

  In this embodiment, eight disk drives are used, but the number of disk drives is not limited to this.

  In the present embodiment, the address conversion unit 120 has been described as being included in the disk array control apparatus 100, but may be outside the disk array control apparatus 100.

  As described above, according to the first embodiment, there is an effect that power consumption can be reduced while maintaining an access performance that can cope with a change in the amount of data to be stored.

  The reason is that the disk array control apparatus 100 according to this embodiment operates many disk drives (131 to 138) when the required performance is high, and operates when the required performance is low. This is to reduce power consumption by reducing the number of disk drives (131 to 138).

  In the above-described embodiment, the control unit 110 and the address conversion unit 120 illustrated in FIG. 1 may be realized by a dedicated device, but a computer capable of realizing the functions of the control unit 110 and the address conversion unit 120 described above. It can also be achieved by executing the program in a CPU (Central Processing Unit) of a computer (information processing apparatus) that is a hardware resource. This also applies to the microprocessor 11, the host device connection unit 12, the array control unit 13, the disk connection unit 14, the physical address register 15, and the address conversion unit 20 shown in FIG. .

<Second Embodiment>
FIG. 2 is a block diagram showing the configuration of the disk array device according to the second embodiment of the present invention.

  The disk array device 1 according to the present embodiment includes a microprocessor 11, a host device connection unit 12, an array control unit 13, a disk connection unit 14, a physical address register 15, an address conversion 20, and disk drives 31 to 31. 38.

  The disk array device 1 is connected to the host device 2. The host device 2 issues a command to the disk array device 1. The host device 2 is, for example, a host computer. The disk array device 1 reads data stored in the disk drives 31 to 38 or writes data to the data disk drives 31 to 38 specified by the command in accordance with an input / output command issued by the host device 2.

  In this embodiment, the disk array device 1 is a RAID (Redundant Arrays of Inexpensive Disks) and has a configuration of RAID10. Therefore, each of the disk drives 31 and 32, the disk drives 33 and 34, the disk drives 35 and 36, and the disk drives 37 and 38 is RAID1, and forms a mirror to store the same contents. The disk array device 1 according to this embodiment has a RAID 10 configuration in which data is striped and stored in the order of disk drives 31 and 32, disk drives 33 and 34, disk drives 35 and 36, and disk drives 37 and 38. ing.

  The microprocessor 11 manages and controls the entire disk array device 1.

  The host device connection unit 12 controls an interface with the host device 2. The host device connection unit 12 receives a command issued by the host device 2, and controls data input and transmission according to the command.

  The array control unit 13 performs RAID control on write data and read data for the disk array device 1. The array control unit 13 performs data striping at the time of writing, and synthesizes the striped data at the time of reading.

  The disk connection unit 14 controls an interface with a large number of disk drives 31 to 38 existing in the disk array device 1.

  The physical address register 15 is a register that stores which address of which disk drive (31 to 38) is accessed.

  The address conversion unit 20 is a part that converts the address to be actually written to the disk drive (31 to 38) based on the write address recognized by the host device 2 and replaces it. As a result, the disk array device 1 virtualizes the write address. That is, the host device 2 can access the data without being aware of where the data to be accessed actually exists.

  The address conversion unit 20 includes an address conversion table 21, a start pointer 22, and an end pointer 23.

  The address conversion table 21 is an area that stores the address that is actually written and the write address that is shown to the host device in association with each other. The address conversion table 21 preferably uses a non-volatile storage medium such as a flash memory in order to preserve its contents.

  FIG. 3 is a diagram for explaining an address conversion table for storing address information according to the second embodiment of the present invention.

  As shown in FIG. 3, the address conversion table 21 includes an entry number 301, a physical address 302, and a virtual address 303. That is, it is assumed that the entry number 301, the physical address 302, and the virtual address 303 are associated with each other in the address conversion table 21 as a table conceptually shown in FIG.

  The entry number 301 is a value that can uniquely identify an entry in the address conversion table 21. In the present embodiment, the entry number 301 is a value that is incremented by 1 such that the first entry of the address conversion table 21 is “1”, the second entry is “2”, and the third entry is “3”. is there.

  A physical address 302 indicates a write position in the disk drive (31 to 38). When the physical address 302 is expressed as “XY”, X indicates the disk drive (31 to 38). X is “1” for disk drives 31 and 32, “2” for disk drives 33 and 34, “3” for disk drives 35 and 36, and “4” for disk drives 37 and 38. And Y represents an address in each disk drive (31 to 38).

  FIG. 4 is a diagram illustrating physical addresses for the respective disk drives (31 to 38) according to the second embodiment of the present invention. 4 is rearranged for each disk drive (31 to 38) based on FIG. If the data is set in the ascending order of the entry numbers 301, the disk array device 1 can store the data in the disk drives (31 to 38) in a distributed manner.

  A virtual address 303 indicates a write position on the virtual disk recognized by the host device 2. FIG. 5 is a diagram for explaining the disk array device viewed from the host device according to the second embodiment of the present invention.

  The disk array device 1 shows the eight disk drives 31 to 38 constituting the RAID 10 as one virtual disk as shown in FIG. The address designated when the host device 2 writes data to the disk drives 31 to 38 of the disk array device 1 is a virtual address, and is the virtual address 303 of the address conversion table 21.

  The start pointer 22 is a pointer that indicates the first entry that stores the virtual address 303 in the address conversion table 21. Specifically, the start pointer 22 is an entry number 301 included in the entry. The initial value of the start pointer 22 is “1”.

  The end pointer 23 is a pointer indicating an entry for storing the virtual address 303 in the address conversion table 21 next. Specifically, the end pointer 23 is an entry number 301 included in the entry. The initial value of the end pointer 23 is “1”.

  That is, the start pointer 22 and the end pointer 23 are values of the entry number 301 included in an entry in the address conversion table 21. These return to “1” next to the entry number 301 included in the last entry in the address conversion table 21, and indicate the first entry in the address conversion table 21.

  In the disk array device 1, a case where the disk drives 31 to 38 are in an operating state and data is distributed and stored in all the disk drives 31 to 38 is referred to as “normal mode”. The normal mode is a state suitable for high-performance processing.

  Further, the disk array device 1 obtains the number of required disk drives (31 to 38) based on the data storage amount, and stops and operates the disk drives (31 to 38) exceeding that number. This is referred to as “power saving mode”.

  In the present embodiment, RAID 10 has been described as an example, but stripe-type RAID such as RAID 30 and RAID 50 can be handled in the same manner. Further, the number of disk drives is not limited to this.

  Next, the operation of the disk array device 1 in this embodiment will be described.

  FIG. 6 is a flowchart showing processing upon receipt of a write command in the microprocessor 11 according to the second embodiment of the present invention.

  First, the host device 2 issues a data write command to the disk array device 1. The write command includes data to be written to the disk array device 1 and an address to which the data is written (hereinafter referred to as “write address”). The microprocessor 11 receives the issued write command through the higher-level device connection unit 12 (step S101). Subsequently, the microprocessor 11 confirms whether the write address specified by the received write command matches the virtual address 303 of the address conversion table 21 (step S102).

  If it matches the virtual address 303 of the address conversion table 21 (“Yes” in step S103), the microprocessor 11 stores the physical address 302 included in the entry with the matching virtual address 303 in the physical address register 15 ( Step S106).

  If it does not match the virtual address 303 in the address conversion table 21 (“No” in step S103), the microprocessor 11 determines that data has not been written to the write address specified by the received write command. Therefore, the microprocessor 11 stores the physical address 302 included in the entry corresponding to the end pointer 23 in the physical address register 15 in the address conversion table 21. Next, the microprocessor 11 writes the write address designated by the host device 2 to the virtual address 303 included in the entry (step S104). Then, the microprocessor 11 increments the end pointer 23 to indicate the next entry in the address conversion table 21 (step S105).

  Next, the microprocessor 11 instructs the array controller 13 to start writing in RAID 10 (step S107). The microprocessor 11 writes the write data designated by the host device 2 to the write position in the disk drive (31 to 38) indicated by the physical address register 15 by the disk connection unit 14 (steps S108 and S109). When the writing to the disk drives (31 to 38) is completed, the microprocessor 11 reports the end of the write command to the host device 2 through the host device connection unit 12 (step S110).

  FIG. 7 is a flowchart showing processing upon receipt of a read command in the microprocessor 11 according to the second embodiment of the present invention.

  First, the host device 2 issues a data read command to the disk array device 1. The read command includes an address from which data is read (hereinafter referred to as “read address”). The microprocessor 11 receives the issued read command by the higher-level device connection unit 12 (step S201). Subsequently, the microprocessor 11 checks whether or not the read address specified by the read command received from the host device 2 matches the virtual address 303 of the address conversion table 21 (step S202).

  If it matches the virtual address 303 of the address translation table 21 (“Yes” in step S203), the microprocessor 11 stores the physical address 302 included in the entry with the matching virtual address 303 in the physical address register 15 ( Step S205). Next, the microprocessor 11 instructs the array controller 13 to start reading with RAID 10 (step S206). The microprocessor 11 reads from the read position in the disk drive (31 to 38) indicated by the physical address register 15 by the disk connection unit 14 (step S207). The microprocessor 11 transfers the read data to the host device 2 through the host device connection unit 12 (step S208).

  If it does not match the virtual address 303 of the address conversion table 21 (“No” in step S203), the microprocessor 11 determines that an instruction to read from a portion where there is no written data is given. The microprocessor 11 sends zero data as read data to the host device 2 (step S204).

  When the transfer of the read data to the host device 2 is completed, the microprocessor 11 reports the end of the read command to the host device 2 through the host device connection unit 12 (Step S209).

  When a low load is expected due to a business cycle or the like, the disk array device 1 operating in the normal mode receives an instruction from the host device 2 to shift to the power saving mode.

  FIG. 8 is a flowchart showing a transition process from the normal mode to the power saving mode according to the second embodiment of the present invention.

  As an initial state, it is assumed that the disk array device 1 has the disk drives 31 to 38 in the operating state, and the address conversion table 21, the start pointer 22, and the end pointer 23 have the contents shown in FIG.

  When it is predicted that the low load state will continue, the host device 2 confirms that the device capacity is free, and determines that it can shift to the power saving mode if there is a free state of 25% or more. Here, the configuration of the disk array device 1 of the present embodiment is a RAID 10 configuration of 2 × 4 units, and when 2 × 3 units are used, the storage capacity is reduced by 25%. The criterion for judgment was that there was free space. If the disk array device 1 has 50% or more free capacity, the disk array device 1 can be reduced to 2 × 2. The criterion for determining the disk capacity used here is an example, and the present invention is not limited to this.

  Here, a case will be described in which the disk drives 37 and 38 are stopped in order to configure the disk array device 1 in a 2 × 3 configuration.

  When the host device 2 determines that it is possible to shift to the power saving mode, it issues a command to shift to the power saving mode to the disk array device 1.

  The microprocessor 11 receives the migration command issued from the host device 2 (step S301). The microprocessor 11 reads the physical address 302 included in the entry corresponding to the end pointer 23 of the address conversion table 21. The microprocessor 11 confirms whether the read physical address 302 is the disk drive (37, 38) to be stopped (steps S302, S303). In the present embodiment, the physical addresses of the disk drives 37 and 38 to be stopped are values starting with “4”.

  If the disk drive is to be stopped (37, 38) (“Yes” in step S303), the microprocessor 11 increments the end pointer 23 (step S304) and repeats from step S302.

  When the disk drive (37, 38) is not to be stopped (“No” in step S303), the microprocessor 11 reads the physical address 302 included in the entry corresponding to the start pointer 22 of the address conversion table 21 (step S303). S305). The microprocessor 11 reads data from the disk drive (31 to 36) indicated by the physical address 302. Then, the microprocessor 11 issues an instruction for writing the read data to the disk drive indicated by the physical address 302 included in the entry corresponding to the end pointer 23 to the array control unit 13 (step S306).

  The microprocessor 11 uses the disk connector 14 to transfer the target data between the disk drives (step S307). Next, the microprocessor 11 copies the virtual address 303 included in the entry corresponding to the start pointer 22 to the virtual address 303 included in the entry corresponding to the end pointer 23 (step S308). Thereafter, the microprocessor 11 clears the virtual address 303 included in the entry corresponding to the start pointer 22 (step S309). Next, the microprocessor 11 increments the start pointer 22 and the end pointer 23 (step S310). The microprocessor 11 repeats the processing from step S302 to step S310 for the number of entries in which the virtual address 303 is registered in the address conversion table 21, that is, for the number of data stored in the address conversion table ( Step S311).

  When these series of processes are completed, the address conversion table 21, the start pointer 22, and the end pointer 23 have the contents shown in FIG. FIG. 9 is a diagram illustrating the address conversion table after shifting to the power saving mode according to the second embodiment of the present invention. As shown in FIG. 9, the data stored in the disk drives 37 and 38 is copied to the disk drives 31 to 36. Next, the microprocessor 11 issues a stop instruction to the disk drives 37 and 38 to be stopped (step S312). As a result, the disk array device 1 can reduce the power consumed by the disk drives 37 and 38. This state of the disk array device 1 is the power saving mode.

  Next, transition processing from the power saving mode to the normal mode when a high load is expected will be described with reference to FIG. FIG. 10 is a flowchart showing a transition process from the power saving mode to the normal mode according to the second embodiment of the present invention.

  As an initial state, in the disk array device 1, the disk drives 31 to 36 are in an operating state, and the disk drives 37 and 38 are in a stopped state. The address conversion table 21, the start pointer 22, and the end pointer 23 are assumed to have the contents shown in FIG.

  When the host device 2 determines to shift to the normal mode, it issues a command to shift to the normal mode to the disk device 1.

  The microprocessor 11 receives the instruction to shift to the normal mode issued from the host device 2 (step S401). The microprocessor 11 activates the disk drives 37 and 38 that have been stopped (step S402). Next, the microprocessor 11 reads the physical address 902 included in the entry corresponding to the start pointer 22 of the address conversion table 21, and confirms whether it is a stopped disk drive (37, 38) (step S403). , S404). In the present embodiment, the physical address of the disk drive to be stopped is a value starting with “4”.

  If the disk drive has been stopped (37, 38) (“Yes” in step S404), the microprocessor 11 increments the start pointer 22 (step S405) and repeats the processing from step S403.

  If the disk drive is not stopped (37, 38) (“No” in step S404), the microprocessor 11 reads the physical address 902 included in the entry corresponding to the end pointer 23 of the address conversion table 21 (step S404). S406). Next, the microprocessor 11 reads data from the disk drive indicated by the physical address 902 included in the entry corresponding to the starter 22. Then, the microprocessor 11 issues an instruction to write the read data to the disk drive indicated by the physical address 902 included in the entry corresponding to the end pointer 23 to the array control unit 13 (step S407).

  The microprocessor 11 uses the disk connector 14 to transfer the target data between the disk drives (step S408). Next, the microprocessor 11 copies the virtual address 903 included in the entry corresponding to the start pointer 22 to the virtual address 903 included in the entry corresponding to the end pointer 23 (step S409). Thereafter, the microprocessor 11 clears the virtual address 903 included in the entry corresponding to the start pointer 22 (step S410). Next, the microprocessor 11 increments the start pointer 22 and the end pointer 23 (step S411). The microprocessor 11 repeats the processing from step S403 to step S411 for the number of entries in which the virtual address 303 is registered in the address translation table 21, that is, for the number of data stored in the address translation table (step S412).

  When these series of processes are completed, the address conversion table 21, the start pointer 22, and the end pointer 23 have the contents shown in FIG. FIG. 11 is a diagram for explaining an address conversion table after shifting to the normal mode according to the second embodiment of the present invention. As shown in FIG. 11, the disk array device 1 distributes and stores data in all the disk drives 31 to 38. This state of the disk array device 1 is the normal mode.

  The disk array device 1 repeats the transition to the power saving mode and the transition to the normal mode depending on the load status. Thus, the disk array device 1 reduces power consumption when a low load is expected, and changes to a high-performance state when a high load is expected.

  As described above, the second embodiment has an effect that the disk array device can reduce power consumption while maintaining access performance that can cope with fluctuations in the amount of data to be stored.

  The reason is that the disk array device 1 according to the present embodiment shifts data to some of the disk drives (31 to 38) and vacates disk drives (31 to 38) when a low load is expected. ) To reduce power consumption. Further, when a high load is expected, a large load can be dealt with by operating many disk drives (31-38) and recording data in a distributed manner.

  As a result, for example, when there is a peak of work load at the end of every month, it is operated in the power saving mode from the beginning of the month to the middle of the month and in the normal mode at the end of the month to handle high loads. Operation that optimizes power and performance becomes possible.

  In this embodiment, since the disk array device 1 virtualizes the disk area shown to the host device 2, even if the physical storage location of the stored data is changed by changing the mode, The host measure 2 can access the stored data without being affected by it.

DESCRIPTION OF SYMBOLS 1 Disk array apparatus 2 Host apparatus 11 Microprocessor 12 Host apparatus connection part 13 Array control part 14 Disk connection part 15 Physical address register 20 Address conversion part 21 Address conversion table 22 Start pointer 23 End pointer 31-38 Disk drive 100 Disk array control Device 110 Control unit 120 Address conversion unit 131 to 138 Disk drive 200 Host device 301 Entry number 302 Physical address 303 Virtual address 901 Entry number 902 Physical address 903 Virtual address

Claims (10)

A control means for receiving a command from the host device and performing control according to the command;
The control means obtains the number of disk drives required based on the amount of data stored in a disk array comprising a plurality of disk drives, and decides to stop the disk drives exceeding the number of disk drives. And copying data stored in the disk drive determined to be stopped to a disk drive not to be stopped. Address conversion means for associating address information specified by the instruction with address information used when accessing the disk array;
When instructed from the host device to shift to a power saving state, the control means obtains the number of disk drives required based on the amount of data stored in the disk array, and calculates the number of disk drives. The disk drive exceeding the disk drive is determined to be stopped, and the data stored in the disk drive determined to be stopped is referred to the information held by the address conversion unit, and the disk not to be stopped 2. The disk array control apparatus according to claim 1, wherein the information stored in the address conversion unit is updated in accordance with the contents of the disk drive after copying to a drive. The control means includes
When the host device is instructed to release the power saving state, the disk drive that has been stopped is operated, and the information stored in the address conversion unit is referred to the disk drive that is operating. 3. The disk array control apparatus according to claim 1, wherein the data is distributed and stored, and the information is updated according to the contents of the disk drive after the storage.   4. The disk array controller according to claim 1, wherein the disk drives controlled by the disk array controller have a RAID configuration. The disk array control device according to any one of claims 1 to 4,
A disk array device comprising the disk array. When a computer receives a command from a host device and controls a disk array composed of a plurality of disk drives according to the command,
Obtain the number of disk drives required based on the amount of data stored in the disk array,
Decide to stop the disk drives that exceed the number of disk drives,
A disk array control method, comprising: copying data stored in the disk drive determined to be stopped to a disk drive not to be stopped. When the host device is instructed to shift to the power saving state, obtain the number of disk drives required based on the amount of data stored in the disk array,
Decide to stop the disk drives that exceed the number of disk drives,
The data stored in the disk drive decided to be stopped is not a stop target with reference to the information associating the address information specified by the instruction with the address information used when accessing the disk array. Copy to disk drive,
7. The disk array control method according to claim 6, wherein the information is updated in accordance with the contents of the disk drive after copying. When the host device is instructed to release the power saving state, the stopped disk drive is operated, and the data is distributed and stored in the operating disk drives with reference to the information, 8. The disk array control method according to claim 6, wherein the information is updated in accordance with the contents of the disk drive after storage. Obtain the number of disk drives required based on the amount of data stored in the disk array consisting of multiple disk drives, and decide to stop the disk drives that exceed the number of disk drives, and stop A computer program for causing a computer to realize a function of copying data stored in the disk drive determined by the method to a disk drive not to be stopped. A function for holding information associating address information specified by an instruction from a host device and address information used when accessing a disk array including a plurality of disk drives;
When the host device is instructed to shift to a power saving state, the number of disk drives required is calculated based on the amount of data stored in the disk array, and the disk drives exceeding the number of disk drives are obtained. Determines to stop, and causes the computer to realize a function of copying data stored in the disk drive determined to stop to a disk drive that is not a stop target with reference to the information. The computer program according to claim 9.

Images