JP5392580B2 - Disk array device and control method thereof - Google Patents

Description

  The present invention relates to a disk array device and a control method thereof.

  Conventionally, the same device is used as a device constituting a rank (RANK) in a disk array device. That is, the disk array device unifies the writing speed by using HDDs (Hard Disk Drives) having the same rotational speed.

  In recent years, a disk array device has been introduced in which a high-speed device and a low-speed device are mixed to form a rank. For example, an external storage device disclosed in Patent Document 1 is disclosed as a disk array device in which a high-speed device and a low-speed device are mixed to form a rank. The external storage device of Patent Document 1 includes a semiconductor memory and a hard disk. When it is determined that write data can be stored in the semiconductor memory, the write data is compressed and stored in the semiconductor memory, and the write data is stored in the semiconductor memory. If it is determined that the data cannot be stored, the write data is stored in the hard disk.

JP 2009-070489 A

  However, when a high-speed device and a low-speed device are mixed to form a rank, since the writing speed is different, a time difference until the data writing is completed is generated, and it is meaningless to use the high-speed device. In addition, when a rank is configured using only a high-speed device, the writing speed is improved, but there is a problem that the cost is increased.

  The present invention has been made in consideration of the above points, and proposes a disk array device and a control method thereof that can improve access performance.

  In order to solve such a problem, one aspect of the disk array device of the present invention is configured such that a rank is formed by mixing a first device for storing data to be written received from a server device and the first device. When the second device having a lower data processing capacity than the first device and the write target data are stored in the second device, the write target data is compressed and compressed data is compressed. A controller that generates and stores the generated compressed data in the second device, and stores the write target data in the first device when the write target data is stored in the first device. And.

  Further, according to one aspect of the disk array device control method of the present invention, a rank is formed by mixing a first device for storing data to be written received from a server device and the first device. A method for controlling a disk array device, comprising: a second device having a lower data processing capacity than the first device; and a control unit that controls the first device and the second device, When the control unit stores the write target data in a second device, the control unit generates compressed data by compressing the write target data, and stores the generated compressed data in the second device. And when the control unit stores the write target data in the first device, the control unit stores the write target data in the first device. Characterized in that it comprises the steps of, a.

  Therefore, according to the disk array apparatus and the disk array apparatus control method according to an aspect of the present invention, even when ranks are configured using devices having different rotation speeds, a difference in writing speed does not occur. In other words, the disk array apparatus and the disk array apparatus control method according to one aspect of the present invention spends writing time when data is written in a state in which a rank in which the first device and the second device are mixed is configured. The time can be approximately the same as the first device.

  According to the present invention, it is possible to realize a disk array device capable of improving access performance and a control method thereof.

It is a figure which shows an example of a structure of a storage system. It is a flowchart which shows an example of the write-in process procedure of data. It is a flowchart which shows an example of the reading process procedure of data. It is a conceptual diagram with which it uses for description of the Example of the writing process of data.

  Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. Note that the present invention is not limited thereby.

(Constitution)
FIG. 1 is a diagram showing an example of the configuration of the storage system 1 of the present embodiment. The storage system 1 includes, for example, a server device 2 and a disk array device 3. The server device 2 and the disk array device 3 are connected via a predetermined neck work, for example.

  The server device 2 is a computer device that includes information processing resources such as a CPU (Central Processing Unit) and a memory, an information input device, and an information output device, for example. For example, the server device 2 transmits a write request to the disk array device 3 and writes the corresponding data in the disk array device 3. For example, the server device 2 transmits a read request to the disk array device 3 and reads the corresponding data from the disk array device 3.

  As the predetermined network, for example, a local area network (LAN), a storage area network (SAN), the Internet, a dedicated line, a public line, and the like can be used as appropriate.

  The disk array device 3 includes, for example, at least one CPU 11, cache memory 12, disk director 13, low speed / high speed device determination unit 14, compression / decompression processing unit 15, and HDD unit 16. The HDD unit 16 includes, for example, a low speed device 17 and a high speed device 18.

  The CPU 11 is connected to the server apparatus 2 via a network and controls transmission / reception of various requests and data received from the server apparatus 2. The CPU 11 can use various interfaces according to the type of network. Further, the CPU 11 controls the entire disk array device 3. That is, the CPU 11 interprets various requests received from the server device 2 and controls each component.

  Further, the CPU 11 performs, for example, RAID (Redundant Arrays of Independent Disks) control such as RAID 1 or RAID 5 on the low-speed device 17 and the high-speed device 18 of the HDD unit 16, thereby enabling the reliability of the disk array device 3. Performance, availability and performance can also be improved. In this case, the CPU 11 sets one or a plurality of logical disks on a physical storage area (RAID group) provided by the HDD unit 16. Then, when the address of the logical disk is designated from the server device 2, the CPU 11 stores data in units of blocks of a predetermined size in the logical disk.

  The cache memory 12 temporarily holds data received from the server device 2. The cache memory 12 holds various programs used in the disk array device 3 and various tables.

  The disk director 13 is connected to the HDD unit 16 and controls reading and writing of data received from the server device 2 with respect to the HDD unit 16. The disk director 13 can use various interfaces corresponding to types such as fiber channel, SAS (Serial Attached SCSI), SATA (Serial ATA), and the like.

  The low speed / high speed device determination unit 14 determines whether the data received from the server device 2 is stored in the low speed device 17 of the HDD unit 16 or in the high speed device 18.

  The compression / decompression processing unit 15 compresses data stored in the low speed device 17 of the HDD unit 16. The compression method is not particularly limited. Therefore, it is possible to freely select the compression speed and compression rate and use the optimum compression method for the data.

  The low speed device 17 and the high speed device 18 of the HDD unit 16 store data received from the server device 2. The low speed device 17 is a device having a low data processing capability such as a disk device having a low number of times of disk. The high-speed device 18 is a device having a high data processing capability such as a disk device or a semiconductor memory having a high number of disks. The HDD unit 16 includes a rank (RANK) in which the low speed device 17 and the high speed device 18 are mixed.

(Data write processing procedure)
Next, the operation of the storage system 1 of this embodiment will be described in detail. FIG. 2 is a flowchart showing an example of a data write processing procedure of the disk array device 3 of the present embodiment.

  When the CPU 11 receives a data write request from the server device 2, the CPU 11 executes the data write processing procedure shown in FIG. 2 and receives data to be written from the server device 2 (step SP1).

  Subsequently, the CPU 11 performs predetermined data processing on the received data to be written (step SP2). For example, the CPU 11 determines in which rank the low speed device 17 and / or the high speed device 18 stores the data to be written.

  Subsequently, the CPU 11 temporarily stores the received data to be written in the cache memory 12 (step SP3). Subsequently, at a predetermined timing, the CPU 11 reads the data to be written temporarily stored in the cache memory 12 and transmits it to the disk director 13 (step SP4). The disk director 13 performs predetermined processing on the data to be written and transmits the data to be written to the low speed / high speed device determination unit 14.

  Subsequently, the low speed / high speed device determination unit 14 checks whether the data to be written is data stored in the low speed device 17 (step SP5).

  Then, when the data to be written is data to be stored in the low speed device 17 (step SP5: YES), the low speed / high speed device determination unit 14 transmits the data to be written to the compression / decompression processing unit 15. Subsequently, the compression / decompression processing unit 15 compresses the write target data and generates the compressed write target data (step SP6). Subsequently, the compression / decompression processing unit 15 transmits the compressed write target data to the HDD unit 16.

  On the other hand, when the data to be written is not the data to be stored in the low speed device 17 (step SP5: NO), the low speed / high speed device determination unit 14 uses the data to be written as the data to be stored in the low speed device 17. Therefore, the data to be written is transmitted to the HDD unit 16 as it is.

  Eventually, the low-speed device 17 of the HDD unit 16 writes the received compressed data to be written (step SP7), and then ends the data write processing procedure shown in FIG. 2 (step SP8). The high speed device 18 of the HDD unit 16 writes the received data to be written (step SP7), and then ends the data write processing procedure shown in FIG. 2 (step SP8).

(Data read processing procedure)
FIG. 3 is a flowchart showing an example of a data read processing procedure of the disk array device 3 of the present embodiment.

  When the CPU 11 receives a data read request from the server device 2, the CPU 11 executes the data read processing procedure shown in FIG. 3, and reads data to be read from the low speed device 17 to be read or the high speed device 18 to be read of the HDD unit 16. Send a read command.

  Subsequently, when the read target low-speed device 17 receives a read command of the read target data, the low speed device 17 reads the compressed read target data (step SP1). Further, when the read target high-speed device 18 receives a read command for the read target data, the high speed device 18 reads the read target data (step SP11). Subsequently, the read target low speed device 17 or the read target high speed device 18 transmits the compressed read target data or the read target data to the low speed / high speed device determination unit 14.

  Subsequently, the low speed / high speed device determination unit 14 determines whether the data read from the HDD unit 16 (the low speed device 17 to be read or the high speed device 18 to be read) is the data to be read. Check (step SP12).

  The low-speed / high-speed device determination unit 14 then compresses the compressed read data into a compression / decompression processing unit when the data read from the HDD unit 16 is compressed data to be read (step SP12: YES). 15 to send. Subsequently, the compression / decompression processing unit 15 decompresses the compressed read target data and generates decompressed read target data (read target data) (step SP13). Subsequently, the compression / decompression processing unit 15 transmits the generated read target data to the disk director 13 (step SP14). The disk director 13 performs predetermined processing on the data to be read and transmits the data to be read to the CPU 11.

  Subsequently, the CPU 11 performs predetermined data processing on the received data to be read (step SP15).

  Subsequently, the CPU 11 temporarily stores the received data to be read in the cache memory 12 (step SP16). Subsequently, the CPU 11 reads the data to be read temporarily stored in the cache memory 12 at a predetermined timing and transmits it to the server device 2 (step SP17), and then the data read processing shown in FIG. The procedure ends (step SP18).

(Example)
Next, an embodiment when data is written in the storage system 1 will be described in detail. FIG. 4 is a conceptual diagram for explaining an embodiment of specific processing at the time of data writing in the disk array device 3. The horizontal axis in FIG. 4 represents the passage of time.

  In FIG. 4, the rank is configured by using one rotation speed 7200 [rpm] as the low speed device 17 and one device having 15000 [rpm] as the high speed device 18. In this case, for example, the disk array device 3 simultaneously writes data to be written to the low speed device 17 and the high speed device 18. As for the writing speed, the high-speed device 18 is about twice as fast as the low-speed device 17 because of the high rotation speed.

  Further, it is assumed that data to be written to the low speed device 17 and the high speed device 18 are A, B, and C, respectively, and the data amounts to be written to the low speed device 17 and the high speed device 18 are AV, BV, and CV, respectively. Further, in FIG. 5, input means that the low-speed device 17 and the high-speed device 18 capture data, compression means that the low-speed device 17 and the high-speed device 18 compress data, and Write means low-speed. The device 17 and the high-speed device 18 write data. Further, in FIG. 5, A input, B input, and C input are referred to as input time, A compression, B compression, and C compression are referred to as compression time, and A light, B light, and C light are referred to as write time.

  In this case, the total amount of data X written to the high speed device 18 is as follows.

  If the compression rate of data in the compression / decompression processing unit 15 is 50 [%], the total amount of data Y written to the low-speed device 17 is as follows.

  Here, assuming that the compression time is 50 [%] of the input time and the compression time of the data A is AT, the data B input processing and compression processing are completed during the data A compression time and write time. To do. Therefore, the writing of data B starts immediately after the writing of data A is completed. Similarly, the writing of data C starts immediately after the writing of data B is completed.

  Accordingly, the total amount of data Y written to the low-speed device 17 is ½ of the total amount of data X written to the high-speed device 18, so that the entire write time is substantially the same.

  In other words, in terms of the overall time, the low-speed device 17 takes twice as long as the writing speed than the high-speed device 18, but the data amount is halved by compression, so the writing time is does not change. Although it takes extra time by the compression time, the compression time is much smaller than the write time and can be ignored.

(Operation and effect)
In this manner, in the disk array device 3 of the present embodiment, when the compression / decompression processing unit 15 stores the write target data in the low speed device 17, the write target data is compressed to generate compressed data. While the generated compressed data is stored in the low speed device 17, the low speed / high speed device determination unit 14 stores the write target data in the high speed device 18 when storing the write target data in the high speed device 18.

  Therefore, the disk array device 3 of the present embodiment can reduce the amount of data written to the low speed device 17 by compressing the data transmitted to the low speed device 17, so that the low speed device 17 and the high speed device 18 are mixed. When writing data in a state in which ranks are configured, the time spent for writing time can be made substantially the same as that of a high-speed device.

  Further, for example, the high speed device 18 requires a spindle motor, a precision positioning head mechanism, and a control circuit, and the cost per unit becomes high. Therefore, the disk array apparatus 3 of the present embodiment uses the low speed device 17. , Can reduce the cost.

  A part or all of the above-described embodiment can be described as in the following supplementary notes, but is not limited thereto.

(Supplementary Note 1) Data processing capability as compared with the first device for storing the write target data received from the server apparatus and the first device mixed with the first device to form a rank When the second device with low data and the write target data are stored in the second device, the write target data is compressed to generate compressed data, and the generated compressed data is stored in the second device. And a controller that stores the write target data in the first device when storing the write target data in the first device. .

(Supplementary Note 2) When the data to be read is the compressed data read from the second device, the control unit generates the data to be read by decompressing the compressed data, and the generated read When the target data is transmitted to the server device, and the read target data is read target data read from the first device, the read target data is transmitted to the server device. 2. The disk array device according to appendix 1, which is characterized.

(Additional remark 3) Data processing capability compared with the 1st device which stores the data of the write object received from the server apparatus, and the said 1st device which mixes with the said 1st device, and comprises a rank And a control unit that controls the first device and the second device, wherein the control unit stores the write target data in the first A first step of compressing the data to be written to generate compressed data and storing the generated compressed data in the second device when the data is stored in the second device; A second step of storing the write target data in the first device when the target data is stored in the first device. A control method for Kuarei device.

DESCRIPTION OF SYMBOLS 1 ... Storage system, 2 ... Server apparatus, 3 ... Disk array apparatus, 11 ... CPU, 12 ... Cache memory, 13 ... Disk director, 14 ... Low speed / high speed device discrimination part, 15 ... Compression / Decompression processing unit, 16 ... HDD unit, 17 ... Low speed device, 18 ... High speed device

Claims (3)

A first device for storing data to be written received from the server device;
A second device having a data processing capacity lower than that of the first device, the rank being mixed with the first device;
RAID (Redundant Arrays of Independent Disks) control is performed on the first device and the second device, and the data to be written to the first device and the second device that are RAID-controlled. the when store, while store data to be written to said first device to said first device, said first device against to have the same writing time the write time of the write target data said second generating compressed data by compressing the data to be written for Deibasu, you store the generated compressed data to the second device control section,
A disk array device comprising: The controller is
When the read target data is the compressed data read from the second device, the compressed data is decompressed to generate read target data, and the generated read target data is transmitted to the server device. On the other hand, when the data to be read is the data to be read read from the first device, the data to be read is transmitted to the server device. Disk array device. A first device for storing data to be written received from the server device;
A second device having a data processing capacity lower than that of the first device, the rank being mixed with the first device;
A control unit for controlling the first device and the second device;
Have,
A method for controlling a disk array device, wherein RAID (Redundant Arrays of Independent Disks) control is performed on the first device and the second device ,
Wherein the control unit, the said write target data to the first device and the second device to be RAID control when store, the data to be written to said first device said first device one to store the compression of the first device against generates compressed data by compressing the data to be written to said second device to have the same writing time the write time of the data to be written, to produce method of controlling a disk array device and executes the steps you store the data to the second device.

Images