JP7056874B2 - Controls, disk array devices, control methods, and programs - Google Patents

Description

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

In recent years, with the increase in the capacity of a physical disk, when a failure occurs in the physical disk, the recovery time is extended in proportion to the capacity. Patent Document 1 discloses a technique for shortening the recovery time as a related technique.

Japanese Unexamined Patent Publication No. 2018-120382

In the technique described in Patent Document 1, a spare storage device is incorporated in a pool of physical disks in order to shorten the recovery time that occurs later. However, in the event of a failure, in order to temporarily recover the data of the failed disk to another physical disk, it is necessary to use many other physical disks to restore redundancy, and recovery takes time. It was necessary.

The present invention is to provide a control device, a disk array device, a control method, and a program that solve the above problems.

According to the first aspect of the present invention, it is a control device that controls a storage area pool configured by using a plurality of storage devices, and is a storage area for data to be stored in the storage area pool and the above-mentioned. It is the first storage area information indicating the storage area of any of the spare areas in which data can be stored , and is the identification information of each of the plurality of storage devices and the identification of a plurality of groups provided in the same number of the storage devices. For each storage area identified by information, the data storage area indicates the data recorded in that area, and at least one of the spare areas for each group is different from the other storage devices. The first storage area information indicating that the same data for each group is stored in at least two storage devices, and the second storage area indicating the storage area and the spare area at the time of shrinkage. The data at the time of withdrawal for each storage area specified by the area information, the identification information of each of the plurality of storage devices, and the identification information of a plurality of groups provided in the same number of the storage devices. The second storage area information indicating at least the identification information of the data for each storage area, the acquisition unit for acquiring the data, and the first storage area information and the second storage area information when the shrinkage occurs. Based on this, the data recorded in the first storage area information corresponding to the identification information of the retracted storage device is transferred from the storage area of another storage device in the same group as the storage area of the data to the spare area. The data is rearranged by copying , and when the contracted state is released, the rearranged data is returned to the original arrangement based on the first storage area information and the second storage area information. It is a control device including a control unit for performing control for the purpose.

According to the second aspect of the present invention, it is a disk array device including a plurality of storage devices and the above-mentioned control device.

According to the third aspect of the present invention, in the control device that controls the storage area pool configured by using a plurality of storage devices, the storage area of the data to be stored in the storage area pool and the data in the normal time are stored in the storage area pool. The first storage area information indicating any storage area of the storage area , which is the identification information of each of the plurality of storage devices and the identification information of a plurality of groups provided in the same number of the storage devices. For each storage area specified by, the data storage area indicates the data recorded in that area, and at least one of the spare areas for each group is set in the storage device different from the other groups. The first storage area information indicating that the data for each group is stored in at least two storage devices, and the second storage area information indicating the storage area and the spare area at the time of shrinkage. For each storage area specified by the identification information of each of the plurality of storage devices and the identification information of a plurality of groups provided in the same number of the storage devices, each storage area of the data at the time of shrinkage is obtained. Based on the acquisition step of acquiring at least the second storage area information indicating the identification information of the data, and the first storage area information and the second storage area information when the shrinkage occurs, the said By copying the data recorded in the first storage area information corresponding to the identification information of the retracted storage device from the storage area of another storage device in the same group as the storage area of the data to the spare area. Control for returning the rearranged data to the original arrangement based on the first storage area information and the second storage area information when the data is rearranged and the contracted state is released. It is a control method including a control step to be performed.

According to the fourth aspect of the present invention, it is a control device that controls a storage pool configured by using a plurality of storage devices in a computer that controls a storage area pool configured by using a plurality of storage devices. It is the first storage area information indicating the storage area of either the storage area of the data to be stored in the storage area pool or the spare area in which the data can be stored in the normal time, and is the first storage area information of each of the plurality of storage devices. For each storage area specified by the identification information and the identification information of a plurality of groups provided in the same number in each of the storage devices, the data storage area indicates the data recorded in the area, and the group is shown. With the first storage area information indicating that at least one of the spare areas for each is set in the storage device different from the other groups and the data for each group is stored in at least two storage devices. Second storage area information indicating the storage area and the spare area at the time of withdrawal , identification information of each of the plurality of storage devices, and identification information of a plurality of groups provided in the same number in each of the storage devices. And, for each storage area specified by, the acquisition step of acquiring at least the second storage area information indicating at least the identification information of the data for each storage area of the data at the time of the shrinkage, and the shrinkage occurred. In this case, based on the first storage area information and the second storage area information, the data recorded in the first storage area information corresponding to the identification information of the retracted storage device is stored in the data. The data is rearranged by copying from the storage area of another storage device in the same group as the area to the spare area, and when the contracted state is released, the first storage area information and the second storage area are released. It is a program for executing a control step for performing control for returning the rearranged data to the original arrangement based on the information.

According to the present invention, redundancy can be restored at high speed.

It is a schematic block diagram which shows the structure of the information processing system 100 which concerns on one Embodiment of this invention. It is a figure which shows an example of the map which concerns on one Embodiment of this invention. It is a figure which shows another example of the map which concerns on one Embodiment of this invention. It is a figure which shows an example of the data copy which concerns on one Embodiment of this invention. It is a flowchart which shows an example of the operation at the time of degeneration which concerns on one Embodiment of this invention. It is a flowchart which shows an example of the determination process of the area which performs data writing which concerns on one Embodiment of this invention. It is a figure which shows another example of the map which concerns on one Embodiment of this invention. It is a flowchart which shows another example of the operation at the time of degeneration which concerns on one Embodiment of this invention. It is a figure which shows the minimum structure of the control device which concerns on one Embodiment of this invention.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings.

FIG. 1 is a schematic diagram showing a configuration of an information processing system 100 according to an embodiment of the present invention.
The control device 100 includes a control device 1, a storage pool 20, and a plurality of hosts 30 (30-1, ... 30-N). The host 30 is connected to the control device 1. Further, the control device 1 is connected to the storage pool 20. In the present embodiment, for convenience of explanation, an example in which one host 30 is provided will be described, but the host 30 may include a plurality of hosts 30 (30-1, ..., 30-N). Further, in the present embodiment, the host 30 (30-1, ... 30-N) will be described as the host 30 when indicating an arbitrary host included in the information processing system 100, or when not particularly distinguished.

The host 30 is a computer provided with a processor such as a CPU (Central Processing Unit). The host 30 is running an OS (Operating System) by a CPU. The OS outputs a read instruction and a write instruction for the logical volume managed by the control device 1 to the control device 1.
The control device 1 configures and controls RAID (Redundant Arrays of Inexpentive Disks) for the physical disks # 1 to # n of the storage pool 20. Further, the control device 1 writes to the drive and reads from the drive for the logical volume according to the read command and the write command by the host 30. Details of the control device 1 will be described later.
The storage pool 20 is composed of a plurality of physical disks (# 1 to # n). The plurality of physical disks # 1 to # n constitute one logical disk that guarantees data redundancy. Further, the physical disk is a storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive).

Next, the control device 1 will be described.
The control device 1 includes a host control unit 11, a physical disk control unit 12, a RAID management unit 13, and a map storage unit 131.

The host control unit 11 analyzes and executes an instruction received from the host 30. Specifically, when the host control unit 11 receives a write instruction, the host control unit 11 analyzes the received instruction. Based on the analysis result, the host control unit 11 outputs an instruction for writing and information indicating the content to be written to the physical disk control unit 12. Further, when the input from the physical disk control unit 12 that the writing is completed is received, the fact that the writing is completed is output to the host 30.
Further, when the host control unit 11 receives the read instruction, the host control unit 11 analyzes the received instruction. Based on the analysis result, the host control unit 11 outputs an instruction to read and information indicating the content to be read to the physical disk control unit 12. When the information read from the physical disk control unit 12 is received, the read contents are output to the host 30.
Further, when the host control unit 11 receives the information from the physical disk control unit 12 that has failed to be written or read, the host control unit 11 outputs the information to the host 30.

The physical disk control unit 12 controls data transfer between the control device 1 and the storage pool 20. Specifically, the physical disk control unit 12 outputs information for inquiring about an area in the storage area pool 20 of data to be written or read to the RAID management unit 13. Hereinafter, the data to be written is also referred to as "write data", and the data to be read is also referred to as "read data". The physical disk control unit 12 performs a process of writing write data to the storage pool 20 based on the information received from the RAID management unit 13. Further, the physical disk control unit 12 performs a process of reading read data from the storage area pool 20 based on the information received from the RAID management unit 13. The physical disk control unit 12 outputs information indicating the processing result to the host control unit 11. The information indicating the processing result is, for example, information indicating the end of writing, information including read data, information in which writing or reading has failed, and the like.

Further, when the physical disk constituting the storage area pool 20 is degenerated, the physical disk control unit 12 acquires the information from the storage area pool 20 and outputs the acquired information to the RAID management unit 13. The occurrence of degeneracy is not limited to the case where the target physical disk fails. For example, the error rate of a physical disk may be monitored, and degeneracy may occur when the monitored information meets certain conditions. In the following, it is assumed that the physical disk in which the degeneracy has occurred cannot be read or written, but the present invention is not limited to this.

The RAID management unit 13 manages the arrangement of data stored in the physical disk of the storage area pool 20 by using a map. The map is information in which an area in which the physical disk of the storage pool 20 stores data is associated with information contained in the area. Here, the area is a unit for recording data on a physical disk.
Further, the RAID management unit 13 responds to an inquiry from the physical disk control unit 12 in the area of write data / read data. Specifically, the RAID management unit 13 receives information inquiring about the area of write data / read data from the physical disk control unit 12. The RAID management unit 13 reads a map from the map storage unit 131, and determines a region of write data / read data based on the read information. The RAID management unit 13 outputs the determined information to the physical disk control unit 12.
Further, the RAID management unit 13 performs a process of determining data to be copied for degeneration recovery when a degeneration occurs in the physical disk constituting the storage pool 20. The RAID management unit 13 outputs the determined information to the physical disk control unit 12.
The details of the processing of the RAID management unit 13 will be described later.

The map storage unit 131 stores the map managed by the RAID management unit 13. The map storage unit 131 stores two types of maps (first map and second map). The first map is a map when degeneration has not occurred in all the physical disks constituting the storage pool 20. The second map is a map when degeneration occurs in any of the physical disks constituting the storage pool 20. The second map is a different map depending on the physical disk in which the degeneration occurred. Therefore, there are as many second maps as there are physical disks constituting the storage pool 20.

Hereinafter, an example in which the storage pool 20 has nine physical disks (# 1 to # 9) will be described. However, this embodiment is not limited to the following description.

FIG. 2 is a diagram showing an example of a map according to an embodiment of the present invention. Map M1 in FIG. 2 shows an example of the above-mentioned first map.
In the example shown in this figure, the map M1 is information showing the structure of the data stored in each area when each of the nine physical disks is divided into nine areas. “# 1” to “# 9” in the first line indicate individual physical disks constituting the storage pool 20. That is, each column constitutes one physical disk. Further, the stripe ST indicates a group including one area of each physical disk. The areas included in each stripe ST have the same position on each physical disk. In the example shown in this figure, each row constitutes one stripe.

Each area is either an area for storing data (also referred to as a "data area") or a spare area (also referred to as a "spare area"). Here, the data includes information stored in the storage pool 20 and an error correction code (parity) related to the information. Further, the spare area is an area in which data is not recorded when the physical disk constituting the storage pool 20 is not degenerated.
When a certain area is a data area, the identifier "Dx" (x is a number from 0 to 35) is indicated in the area. Also, each data is mirrored in two data areas. Here, mirroring means that the same data is stored in a plurality of areas of the physical disk constituting the storage area pool 20.

The mirrored data (hereinafter, also referred to as “mirroring data”) is distributed and stored in two physical disks. That is, the mirroring data is stored in the first physical disk and the second physical disk different from the first physical disk. The combination of the first and second physical disks is different for each mirroring data. Also, the mirroring data is stored in the same stripe.

Further, when a certain area is a spare area, the strip is indicated by the identifier "S". There is one spare area for each physical disk and one for each stripe. Also, the spare area has no data to store, so it is not mirrored.

In the example shown in this figure, for example, stripe 0 of the physical disk # 1 is indicated by the identifier “D0”, indicating that this area is a data area. The same identifier is also shown for stripe 0 of physical disk # 2, indicating that these two areas hold mirroring data. Further, the stripe 0 of the physical disk # 9 displays the identifier “S”, indicating that this area is a spare area.

FIG. 3 is a diagram showing another example of the map according to the embodiment of the present invention. Map M2 in FIG. 3 shows an example of the above-mentioned second map.

In the example shown in this figure, the map M2 is information indicating the structure of the data stored in each area when the physical disk # 3 is degenerated. In map M2, the degenerate physical disk # 3 includes all spare areas. Further, in the map M2, the data stored in the data area of the physical disk # 3 of the map M1 and stored in the data area included in the same stripe is stored in the area that was the spare area in the map M1.

For example, in the case of stripe 0, the spare area exists on the physical disk # 9 in the map M1. Further, in the map M1, the data identified by the identifier “D1” is stored in the stripe 0 of the physical disk # 3. Therefore, in the map M2, the data identified by the identifier “D1” is stored in the stripe 0 of the physical disk # 9. Further, stripe 0 of the physical disk # 3 is a spare area. For stripe 0, there is no change between map M1 and map M2 on other physical disks (# 1, # 2, # 4 to # 8).
Further, for example, in the case of stripe 6, the physical disk # 3 is already a spare area in the map M1. Therefore, the stripe 6 has no change between the map M1 and the map M2 for all physical disks.

As described above, the map M2 can be created by moving the data area existing in the degenerate physical disk to the spare area of the same stripe in the map M1 and arranging the map M2.
Further, even when the degeneracy occurs in another physical disk, the second map can be easily created from the map M1 by the above-mentioned method.

Subsequently, the RAID management unit 13 will explain in detail the process of determining the data to be copied when the degeneracy actually occurs.
FIG. 4 is a diagram showing an example of a data copy according to an embodiment of the present invention. In the example shown in this figure, when the degeneracy occurs in the physical disk # 3, the physical disk control unit 12 indicates the data to be copied by an arrow. For example, the "arrow from D1 to S" indicates that the data stored in the data area identified by the identifier "D1" of the physical disk # 6 is copied to the spare area of the physical disk # 9. The RAID management unit 13 identifies the area to which the arrow is based and the area to which the arrow is located, that is, the copy source and the copy destination.

When the degeneration occurs, the RAID management unit 13 receives information indicating the degenerate physical disk from the physical disk control unit 12. In the following, the case where the degeneracy occurs in the physical disk # 3 will be described, but the present invention is not limited to this. Further, hereinafter, the physical disk in which the degeneracy has occurred is also referred to as a "degenerate disk".

The RAID management unit 13 reads out the second map corresponding to the degenerate disk (# 3) from the map storage unit 131 from the plurality of second maps based on the information received from the physical disk control unit 12. Further, the RAID management unit 13 reads the first map from the map storage unit 131. The RAID management unit 13 determines the data to be moved based on the read first map and the second map. The data contained in the degenerate disk cannot be read from the disk due to degeneration. Therefore, the RAID management unit 13 reads the data from the area where the data is mirrored.

Specifically, first, the RAID management unit 13 refers to the first map and identifies an area in which the data stored in each area of the fault disk is mirrored. For example, in the case of stripe 0, the RAID management unit 13 first refers to the first map and acquires that the identifier of the data stored in the degenerate disk is “D1”. Subsequently, the RAID management unit 13 refers to the first map and identifies another area (mirrored area) in which the acquired identifier is shown. In the case of the identifier "D1", the RAID management unit 13 identifies that the RAID management unit 13 is also arranged in the area of the stripe 0 of the physical disk # 6. That is, this area (stripe 0 of the physical disk # 6) is the copy source area.

Next, the RAID management unit 13 refers to the second map and identifies the area where the data contained in the previously specified area is mirrored at the time of degeneration. Specifically, the RAID management unit 13 refers to the second map and identifies the area in which the previously acquired identifier is arranged. For example, in the case of the identifier "D1", it is acquired that the data identified by the identifier is arranged on the stripe 0 of the physical disk # 6 and the physical disk # 9. Subsequently, the RAID management unit 13 specifies that the area mirrored at the time of degeneration is stripe 0 of the physical disk # 9, since the area specified earlier was the physical disk # 6. That is, this area (stripe 0 of the physical disk # 9) is the copy destination area.

The RAID management unit 13 performs the same processing as described above for the other stripes. In the example shown in FIG. 4, the copy source and copy destination specified as a result of such processing are indicated by arrows.
In the example of this figure, each physical disk has one area where reading and writing are performed, and the combinations thereof are all different. Therefore, the physical disk control unit 12 can simultaneously execute reading and writing using a plurality of physical disks at the time of degeneration. That is, for example, the data copy of stripes 0, 2, 5, and 8 can be executed at the same time because the physical disks for reading and writing are all different. The same applies to the data copies of stripes 1, 3, 4, and 7. Therefore, even if a degenerate disk occurs, it is possible to shift to the configuration shown by the map M2 by copying the data for a short time. Since the redundancy of the configuration of the map M1 and the configuration of the map M2 are the same, it is possible to restore the redundancy in a short time.
When the RAID management unit 13 finishes copying the area (D1, D4, D10, D14, D18, D22, D29, D32) that needs to be copied, the RAID management unit 13 shifts the map from the normal map (map M1) to the degenerate map. Change to a map (map M2).

Next, the operation of the RAID management unit 13 at the time of degenerate recovery will be described.
FIG. 5 is a flowchart showing an example of the operation at the time of degeneracy according to the embodiment of the present invention.

The physical disk control unit 12 acquires information indicating that degeneration has occurred in the physical disk (# 3) constituting the storage area pool 20 from the storage area pool 20 (step S101). The physical disk control unit 12 outputs the acquired information to the RAID management unit 13. The control device 1 then proceeds to step S102.

The RAID management unit 13 determines whether or not to perform degenerate recovery (step S102). If the degenerate recovery has not been performed yet, the RAID management unit 13 determines that the degenerate recovery will be performed (step S102: YES). In this case, the RAID management unit 13 advances the process to step S103.

The RAID management unit 13 determines that the degenerate recovery is not performed when the degenerate recovery has already been performed (step S102: NO). In this case, the RAID management unit 13 advances the process to step S104.

The RAID management unit 13 performs degenerate recovery (step S103). Specifically, the RAID management unit 13 decides to change the map that manages the storage pool 20 from the map before degeneration (map M1) to the map at the time of degeneration (map M2). In addition, the RAID management unit 13 specifies information for copying data as the map is changed. The information for performing data copying is information indicating an area (copy source area) containing data that needs to be copied and an area (copy destination area) for copying. The RAID management unit 13 outputs the specified information to the physical disk control unit 12. The physical disk control unit 12 copies the data of the storage pool 20 according to the information received from the RAID management unit 13. When the data copy is completed, the RAID management unit 13 changes the map that manages the storage pool 20 to the map at the time of degeneration (map M2). When the processing is completed, the control device 1 returns the processing to step S101.

The RAID management unit 13 maintains the current map when the degenerate restoration has already been performed (step S104). In this case, since the RAID management unit 13 has already changed the map constituting the storage pool 20 to the map at the time of degeneration (map M2), the operation on the map is continued. Hereinafter, the control device 1 returns to step S102 and repeats the process until the degenerate state is eliminated by exchanging the degenerate physical disk or the like.

When the degenerate state is released, the RAID management unit 13 performs a process for changing the map used by the storage pool 20 from the degenerate map (map M2) to the normal map (map M1). conduct. At this time, the RAID management unit 13 makes a copy made in the reverse direction when shifting to the map at the time of degeneration. That is, copying is performed by exchanging the copy source and the copy destination at the time of map migration at the time of degeneration. After that, the RAID management unit 13 changes the map to a normal map (map M1).

Next, the operation when data is written from the host 30 will be described.
FIG. 6 is a flowchart showing an example of a determination process of a region for writing data according to an embodiment of the present invention.

When the host control unit 11 receives information indicating writing from the host 30, the host control unit 11 outputs the information to the physical disk control unit 12. Based on the input information, the physical disk control unit 12 outputs to the RAID management unit 13 information inquiring which area of the storage area pool 20 the write data is stored (step S201). After that, the process proceeds to step S202.

The RAID management unit 13 identifies an area in which write data is stored based on the information received from the physical disk control unit 12 and the map read from the map storage unit 131 (step S202). After that, the process proceeds to step S203.
For example, if the write data is data stored in "D1", the RAID management unit 13 determines that the area in which the write data is stored is the physical disk # 3 based on the first map (see FIG. 2). It is specified that it is stripe 0 and stripe 0 of physical disk # 6. The map M1 is referred to when the degeneracy has not occurred (normal time), or when the degeneracy has occurred but the data copy has not been completed and the map has not been changed. When the map is changed to the map at the time of degeneration (map M2), the RAID management unit 13 performs the above-mentioned processing based on the second map (for example, see FIG. 3).
Hereinafter, the case where the write data is the data stored in “D1” and the degenerate disk is the physical disk # 3 will be described as a representative, but the present embodiment is not limited to this.

The RAID management unit 13 determines whether or not the map is being changed (step S203). If the map has not been changed, the RAID management unit 13 determines that the map is not being changed (step S203: NO). In this case, the RAID management unit 13 advances the process to step S205.
The RAID management unit 13 determines that the map is being changed if the information indicating that the degeneration has occurred is acquired from the physical disk control unit 12 and the map at the time of degeneration has not been changed. (Step S203: YES). In this case, the RAID management unit 13 advances the process to step S204.

The RAID management unit 13 tentatively determines the state (also referred to as "physical disk state") of the area (hereinafter, also referred to as "target area") in which the write data is stored before and after the change (step S204).
There are three physical disk states: "read / write possible", "write possible", and "access inaccessible". "Read / write possible" indicates that data can be read from the area and data can be written to the area. "Writable" indicates that data can be written to the area, but data cannot be read from the area. "Inaccessible" indicates that reading and writing cannot be performed due to reasons such as degeneration or data copying.

The RAID management unit 13 reads out the changed map and specifies the target area in the changed map. Specifically, the RAID management unit 13 specifies that "D1" is stored in the stripe 0 of the physical disk # 6 and the stripe 0 of the physical disk # 9 based on the map M2 which is the changed map. do. Subsequently, the RAID management unit 13 compares the target areas before and after the change, and provisionally determines the physical disk state. After that, the process proceeds to step S205.
Specifically, the RAID management unit 13 sets the area included in both the target areas before and after the change as "read / write possible". Further, the RAID management unit 13 sets the area to be "lightable" for the area included only before and after the change. In the above example, stripe 0 of the physical disk # 6 is included both before and after the change, so that it is “read / write possible”. Further, since the stripe 0 of the physical disk # 3 and the stripe 0 of the physical disk # 9 are included only before or after the change, both areas are "writable".

When the RAID management unit 13 provisionally determines the physical disk state, the RAID management unit 13 proceeds to the process in step S205.

The RAID management unit 13 determines whether or not the storage pool 20 has been degraded or restored (step S205). When the RAID management unit 13 receives the information indicating the degeneration from the physical disk control unit 12, the RAID management unit 13 determines that the degeneration has occurred in the storage pool 20 (step S205: YES), and proceeds to the process in step S206. .. Further, the RAID management unit 13 has acquired information indicating that degeneration has occurred from the physical disk control unit 12, and if the map at the time of degeneration has not been changed, the map has been changed. That is, it is determined that recovery is being performed (step S205: YES). In this case as well, the RAID management unit 13 advances the process to step S206.

On the other hand, the RAID management unit 13 indicates that the degeneration has occurred again when the information indicating that the degeneration has occurred has not been received from the physical disk control unit 12, or after receiving the information indicating that the degeneration has been released. When the information is not received from the physical disk control unit 12, it is determined that neither degeneration nor restoration has occurred (step S205: NO). In this case, the RAID management unit 13 advances the process to step S207.

Among the physical disk states tentatively determined in step S204, the RAID management unit 13 sets the physical disk state included in the physical disk whose degeneration / recovery is in progress to "inaccessible" (step S206). In the above example, the physical disk # 3 is a degenerate physical disk. Therefore, the RAID management unit 13 changes the stripe 0 of the physical disk # 3 to "inaccessible" and completes the setting of the physical disk state. Further, for example, when the data of the stripe 0 of the physical disk # 6 is mirrored to the stripe 0 of the physical disk # 9, the RAID management unit 13 changes both physical disk states to "inaccessible" and changes the physical disk to "inaccessible". Complete the state setting. When the RAID management unit 13 completes the setting of the physical disk state, the RAID management unit 13 outputs the physical disk state to the physical disk control unit 12 and ends the process.

When neither degeneration nor restoration is performed, the RAID management unit 13 completes the setting in the physical disk state tentatively determined in step S204 (step S207). When the RAID management unit 13 completes the setting of the physical disk state, the RAID management unit 13 outputs the physical disk state to the physical disk control unit 12 and ends the process.

The physical disk control unit 12 executes a process of writing write data to the "write possible" area based on the information received from the RAID management unit 13. In the case of the above example, if the data is not copied, the physical disk control unit 12 writes to the stripe 0 of the physical disk # 6 and the stripe 0 of the physical disk # 9.

Further, when the data is read to the host 30, the RAID management unit 13 performs the same processing as when the above-mentioned writing is performed. In this case, the physical disk control unit 12 reads read data from the "readable" area based on the information received from the RAID management unit 13. In the case of the above example, if the data is not copied, the physical disk control unit 12 reads the read data from the stripe 0 of the physical disk # 6.

As described above, the control device 1 according to the embodiment of the present invention is a control device that controls a storage area pool configured by using a plurality of storage devices, and the storage area pool is degenerated. If not, the first storage area information (for example, the first map: FIG. 2) indicating the storage area of the data to be stored in the storage pool and the spare area in which the data can be stored, and the case where the contraction occurs. , The second storage area information indicating the storage area and the spare area (for example, the second map: FIG. 3), the acquisition unit (for example, the RAID management unit 13) for acquiring the storage area, and the contraction when the contraction occurs. A control unit (for example, a physical disk control unit 12) that controls for rearranging the data based on the first storage area information and the second storage area information is provided.

Thereby, the control device 1 can determine the data to be rearranged in a short time based on the first storage area information and the second storage area information. Therefore, the relocation can be completed in a short time, and the redundancy can be restored at high speed.

Further, regarding the control device 1 according to the embodiment of the present invention, the first storage area information is information indicating that the same data is stored for each of the storage areas provided in the two storage devices. Therefore, the information is such that the combination of the storage devices including the storage area is different for each storage area.
As a result, the data to be rearranged is distributed to a plurality of physical disks that are storage devices to be mirrored. This makes it possible to perform relocation using a large number of physical disks at the same time, and the relocation can be completed in a short time. Therefore, the redundancy can be restored at high speed.

Further, with respect to the control device 1 according to the embodiment of the present invention, at least one of the storage devices is the spare area, and the second storage area information is stored in the storage device in the first storage area information. This is information in which a data area is distributed and rearranged in other storage devices.
As a result, if the data is copied to the spare area before the relocation and the relocation is completed, the redundancy can be recovered without performing other processing. As a result, the redundancy can be restored only by the relocation process. Therefore, the redundancy can be restored at high speed.

Further, the control unit (for example, the physical disk control unit 12 and the RAID management unit 13) of the control device 1 according to the embodiment of the present invention is said to be based on the first storage area information and the second storage area information. The data having different storage areas before and after the occurrence of the degeneracy is determined to be the relocation data that needs to be relocated in the recovery from the degeneration, and the control for relocating the relocation data is performed.
Thereby, the control device 1 can quickly determine the storage area of the data required for relocation based on the two storage area information. Therefore, the redundancy can be restored at high speed.

Further, the control device 1 according to the embodiment of the present invention is a combination of a storage device in which the rearranged data is included in the first storage area information and a storage device in which the rearrangement data is included in the second storage area information. However, it differs depending on the storage area of the rearranged data.
As a result, the control device 1 can simultaneously execute the processes required for relocation for the above-mentioned combinations of different physical disks. Therefore, the relocation can be completed in a short time, and the redundancy can be restored at high speed.

In the above-described embodiment, an example in which the spare area is equivalent to one physical disk in total has been described, but the spare area is not limited to this. Hereinafter, an example in which the spare area is equivalent to two physical disks in total will be described.

FIG. 7 is a diagram showing another example of the map according to the embodiment of the present invention. In the example shown in this figure, the storage pool 20 has 10 physical disks (# 1 to # 10). Further, the map M3 in this figure is an example of the above-mentioned first map.

In the example shown in this figure, each physical disk is managed by stripes divided into ten. Also, each physical disk has two spare areas, and each stripe also has two spare areas. The combination of stripes that includes the spare area of each physical disk is different for all physical disks. Also, the combination of physical disks including the spare area of each stripe is different for all stripes.
Also, as with map M1, all data areas are mirrored. Also, the combinations of physical disks that include the mirrored area are all different.

In the example shown in this figure, there are a total of two spare areas. Therefore, as the second map, the map storage unit 131 possesses the second map in advance not only when there is one degenerate disk but also for all combinations when there are two degenerate disks. As a result, even when two degenerate disks are generated, the redundancy can be restored in a short time by performing the same processing as in the case of one.

Further, in the above-described embodiment, an example in which all physical disks are incorporated into the storage pool 20 from the beginning has been described, but the present invention is not limited to this. For example, if degeneration does not occur, there may be a physical disk (hereinafter, also referred to as “spare disk”) that is not included in the storage pool 20. In this case, the degeneracy can be eliminated by incorporating a spare disk instead of the degenerate disk when the degeneration occurs. In this case, if there is a spare disk, priority is given to the process of exchanging the roles of the degenerate disk and the spare disk. Hereinafter, the operation of the RAID management unit 13 at the time of degeneration when a spare disk is present will be described with reference to the drawings.

FIG. 8 is a flowchart showing another example of the operation at the time of degeneracy according to the embodiment of the present invention. In the following description, an example in which the physical disk # 3 of the physical disks constituting the storage pool 20 is degenerated will be described, but the embodiment of the present invention is not limited to this.

The physical disk control unit 12 acquires information from the storage pool 20 indicating that degeneration has occurred in the physical disk (# 3) constituting the storage pool 20 (step S301). The physical disk control unit 12 outputs the acquired information to the RAID management unit 13. The control device 1 then proceeds to step S302.

The RAID management unit 13 determines whether or not to perform degenerate recovery using a spare disk (step S302). The RAID management unit 13 acquires information about the spare disk from the physical disk control unit 12. The information about the spare disk includes information indicating the number of spare disks and information indicating the number of spare disks incorporated in the storage pool 20.
If there is a spare disk that can be embedded based on the information acquired by the RAID management unit 13, it is determined that the degenerate recovery using the spare disk is performed (step S302: YES), and the process proceeds to step S303.
Based on the information about the spare disk acquired from the physical disk control unit 12, the RAID management unit 13 determines that the degenerate recovery using the spare disk is not performed if there is no embedded spare disk (step S302: NO). ), The process proceeds to step S304.

The RAID management unit 13 maintains the current map and carries out reconstruction using a spare disk (step S303). Specifically, the RAID management unit 13 decides to use the map as it is without changing the map currently used. Further, the RAID management unit 13 uses the spare disk as a degenerate disk (# 3), and outputs information indicating data reconstruction to the physical disk control unit 12. The information indicating the data reconstruction is information indicating the copy source and copy destination (area in the spare disk) of the data to be copied to each area of the spare disk. Here, the copy source is an area in which the data stored in the degenerate disk is mirrored. For example, in the example of FIG. 2, in the case of stripe 0, the area in which the data contained in the degenerate disk is mirrored is the physical disk # 6 (both have the same identifier “D1”). Therefore, the RAID management unit 13 outputs to the physical disk control unit 12 information indicating that the data stored in the physical disk # 6 is used as the copy source for the stripe 0.

The RAID management unit 13 performs the above-mentioned processing for all stripes. As a result, since the copy source discs are all different for each stripe, data can be read from a plurality of physical discs in the actual copy process.
The physical disk control unit 12 copies data to a spare disk according to the information input from the RAID management unit 13. When the data copy is completed, the physical disk control unit 12 outputs information indicating that the degeneration has been released to the RAID management unit 13, and ends the process.

Since the processing from step S304 to step S306 is the same as the processing from step S102 to step S104 in FIG. 5, description thereof will be omitted here.

In this way, if there is a spare disk, the control device 1 can perform recovery using the spare disk, and if there is no spare disk, copy the data to the spare area by the method described above. Therefore, the redundancy can be restored in a short time.

FIG. 9 is a diagram showing a minimum configuration of a control device according to an embodiment of the present invention.
As shown in this figure, the control device 100 includes at least an acquisition unit 101 and a control unit 102.
The acquisition unit 101 has the first storage area information indicating the storage area of the data to be stored in the storage pool and the spare area in which the data can be stored when the degeneration has not occurred in the storage pool, and the degeneration has occurred. In this case, the storage area and the second storage area information indicating the spare area are acquired.
The control unit 102 controls to rearrange the data based on the first storage area information and the second storage area information when degeneration occurs.

In the above-described embodiment, when degeneration occurs in the physical disk of the storage pool 20, data is copied from another non-degenerate physical disk to recover the redundancy. Is not limited. For example, if there is data that can be read from the degenerate disk, the data may be read from the degenerate disk and copied.

Further, in the above-described embodiment, the example in which the RAID management unit 13 specifies the mirroring destination of the data by referring to the second map at the time of degeneration has been described, but the present invention is not limited to this. For example, the RAID management unit 13 may determine an area that is a spare area in the first map as a mirroring destination. In this case, the RAID management unit 13 determines a spare area existing in the same stripe as the copy source stripe as the mirroring destination.

Further, in the above-described embodiment, an example in which the control device 1 and the storage pool 20 have different configurations has been described, but the present invention is not limited to this. For example, the control device 1 and the storage pool 20 may be the same. Further, a device for executing the process performed by the host control unit 11 and a device for executing the process performed by the RAID management unit 13 may be provided outside the control device 1.

A part of the control device 1 in the above-described embodiment, for example, the host control unit 11, the physical disk control unit 12, the RAID management unit 13, and the like may be realized by a computer. In that case, a program for realizing this function may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read by a computer system and executed. The "computer system" referred to here is a computer system built in the control device 1, and includes hardware such as an OS (Operating System) and peripheral devices.

Further, the "computer-readable recording medium" refers to a portable medium such as a flexible disk, a magneto-optical disk, a ROM, or a CD-ROM, and a storage device such as a hard disk built in a computer system. Further, a "computer-readable recording medium" is a medium that dynamically holds a program for a short time, such as a communication line when a program is transmitted via a network such as the Internet or a communication line such as a telephone line. In that case, a program may be held for a certain period of time, such as a volatile memory inside a computer system serving as a server or a client. Further, the above-mentioned program may be for realizing a part of the above-mentioned functions, and may be further realized by combining the above-mentioned functions with a program already recorded in the computer system.

Further, a part or all of the control device 1 in the above-described embodiment may be realized as an integrated circuit such as an LSI (Large Scale Integration). Each functional unit of the control device 1 may be individually made into a processor, or a part or all of them may be integrated into a processor. Further, the method of making an integrated circuit is not limited to the LSI, and may be realized by a dedicated circuit or a general-purpose processor. Further, when an integrated circuit technology that replaces an LSI appears due to advances in semiconductor technology, an integrated circuit based on this technology may be used.

Although one embodiment of the present invention has been described in detail with reference to the drawings, the specific configuration is not limited to the above, and various design changes and the like are made without departing from the gist of the present invention. It is possible to do. Further, one aspect of the present invention can be variously modified within the scope of the claims, and the technical aspects of the present invention can also be obtained by appropriately combining the technical means disclosed in the different embodiments. Included in the range. Further, the elements described in each of the above-described embodiments and modifications are included, and a configuration in which elements having the same effect are replaced with each other is also included.

1, 1a ... Information processing system, 10 ... Smart meter, 11, 21, 31 ... Communication unit, 12, 22, 22a, 34, 34a ... Storage unit, 13 ... Power measurement unit , 14 ... Control unit, 20 ... Server, 221 ... Teacher data storage unit, 222 ... Learning model storage unit, 223 ... Smart meter information storage unit, 224 ... Luggage information storage unit , 225 ... Time information storage unit, 226 ... Prediction information storage unit, 227 ... Map information storage unit, 228 ... Delivery information storage unit, 23, 23a, 35, 35a ... Processing unit, 231 ... 231a, 351 and 351a ... Information acquisition unit 232 ... Learning unit 233 ... Time acquisition unit 234 ... Prediction unit 235, 235a ... Delivery destination determination unit 236, 353 , 353a ... Output processing unit, 30, 30a ... Delivery terminal, 32 ... Position information acquisition unit, 33 ... Input unit, 341 ... Display-related information storage unit, 342 ... Position information Storage unit, 343 ... Delivery information storage unit, 352 ... Display processing unit, 36 ... Display unit

Claims (8)

A control device that controls a storage pool configured using multiple storage devices.
First storage area information indicating a storage area of either a data storage area to be stored in the storage area pool or a spare area in which the data can be stored in a normal time, and identification information of each of the plurality of storage devices. For each storage area specified by the identification information of a plurality of groups provided in the same number in each of the storage devices, the data recorded in the data storage area is shown for each group. With the first storage area information indicating that at least one of the spare areas is set in the storage device different from the other groups and the same data is stored in at least two storage devices for each group. Second storage area information indicating the storage area and the spare area at the time of withdrawal , identification information of each of the plurality of storage devices, and identification information of a plurality of groups provided in the same number in each of the storage devices. And, for each storage area specified by, the acquisition unit for acquiring at least the second storage area information indicating at least the identification information of the data for each storage area of the data at the time of shrinkage, and
When the shrinkage occurs, based on the first storage area information and the second storage area information, the data recorded in the first storage area information corresponding to the identification information of the shrinkage storage device is stored. , The data is rearranged by copying from the storage area of another storage device in the same group as the data storage area to the spare area, and when the contracted state is released, the first storage area information is used. A control unit that controls to return the rearranged data to the original arrangement based on the second storage area information.
A control device equipped with. The first storage area information is information indicating that the same data is stored for each of the storage areas provided in the two storage devices, and the storage area is included in each storage area. The combination of the storage devices is different information.
The control device according to claim 1. In the second storage area information, at least one of the storage devices is the spare area, and the data area stored in the storage device in the first storage area information is dispersed and regenerated in the other storage devices. Information to be placed,
The control device according to any one of claims 1 and 2. Based on the first storage area information and the second storage area information, the control unit relocates the data having different storage areas before and after the occurrence of the degeneration, and the relocation data that needs to be rearranged in the recovery from the degeneration. Is determined, and control for rearranging the rearranged data is performed.
The control device according to any one of claims 1 to 3. The combination of the storage device in which the relocation data is included in the first storage area information and the storage device in which the relocation data is included in the second storage area information is different for each storage area of the relocation data.
The control device according to claim 4. With multiple storage devices
The control device according to any one of claims 1 to 5.
A disk array device equipped with. In a control device that controls a storage pool configured by using multiple storage devices,
First storage area information indicating a storage area of either a data storage area to be stored in the storage area pool or a spare area in which the data can be stored in a normal time, and identification information of each of the plurality of storage devices. For each storage area specified by the identification information of a plurality of groups provided in the same number in each of the storage devices, the data recorded in the data storage area is shown for each group. The first storage area information indicating that at least one of the spare areas is set in the storage device different from the other groups and the data for each group is stored in at least two storage devices, and the regression. Second storage area information indicating the storage area and the spare area at the time , the identification information of each of the plurality of storage devices, the identification information of a plurality of groups provided in the same number of the storage devices, and the identification information of the plurality of groups. For each storage area specified in, the acquisition step of acquiring at least the second storage area information indicating at least the identification information of the data for each storage area of the data at the time of shrinkage, and the acquisition step.
When the shrinkage occurs, based on the first storage area information and the second storage area information, the data recorded in the first storage area information corresponding to the identification information of the shrinkage storage device is stored. When the data is rearranged by copying from the storage area of another storage device in the same group as the data storage area to the spare area and the contracted state is released, the first storage area information and A control step that controls to return the rearranged data to the original arrangement based on the second storage area information, and
Control methods, including. For computers that control storage pools that are configured with multiple storage devices,
A control device that controls a storage pool configured using multiple storage devices.
First storage area information indicating a storage area of either a data storage area to be stored in the storage area pool or a spare area in which the data can be stored in a normal time, and identification information of each of the plurality of storage devices. For each storage area specified by the identification information of a plurality of groups provided in the same number in each of the storage devices, the data recorded in the data storage area is shown for each group. The first storage area information indicating that at least one of the spare areas is set in the storage device different from the other groups and the data for each group is stored in at least two storage devices, and the regression. Second storage area information indicating the storage area and the spare area at the time , the identification information of each of the plurality of storage devices, the identification information of a plurality of groups provided in the same number of the storage devices, and the identification information of the plurality of groups. For each storage area specified in, the acquisition step of acquiring at least the second storage area information indicating at least the identification information of the data for each storage area of the data at the time of shrinkage, and the acquisition step.
When the shrinkage occurs, based on the first storage area information and the second storage area information, the data recorded in the first storage area information corresponding to the identification information of the shrinkage storage device is stored. When the data is rearranged by copying from the storage area of another storage device in the same group as the data storage area to the spare area and the contracted state is released, the first storage area information and A control step that controls to return the rearranged data to the original arrangement based on the second storage area information, and
A program to execute.

Images