WO2005006176A1

WO2005006176A1 - Disc system

Info

Publication number: WO2005006176A1
Application number: PCT/JP2004/009814
Authority: WO
Inventors: Hidejiro Daikokuya; Mikio Ito; Kazuhiko Ikeuchi
Original assignee: Fujitsu Limited
Priority date: 2003-07-10
Filing date: 2004-07-09
Publication date: 2005-01-20
Also published as: WO2005006174A1

Abstract

An access data string transmitted from a host (10) is sent to a center module (CM) via a channel adapter (CA). Here, it is set whether to perform striping management. When the striping management is performed and data is divided into stripes, each of the stripes divided is sent to device adapters (DA). In the device adapters (DA), it is possible to set what kind of control is to be performed for RAID (5) and whether to perform mirroring or perform nothing. When control of RAID (5) is performed, a parity is added to the data divided into stripes and the data is stored in a physical disc connected to the device adapters (DA).

Description

Technical field

[0001] The present invention relates to

Background art

[0002] At present, various disk systems are being put to practical use. Among them, RAID5 is common.

Light

FIG. 1 is a diagram showing a configuration of a RAID5 disk system.

Rice field

[0003] The host 10 sends a host access data string to the channel adapter CA of the RAID5 system. In the figure, a state in which D1 to D4 are arranged in a row is shown as a host access data string. This is sent to the center module CM, stored in the cache, and then sent to the device adapter DA. The device adapter DA controls RAID5 for the received host access data sequence. That is, the data string is divided into strips D1 to D4, and a process of adding a parity (indicated as P in the figure) is performed. Then, the data string controlled by RAID5 is stored in four physical disks connected to the device adapter DA. As shown in the lower part of Fig. 1, the data should be stored so that D1-D4, which was one data string, is evenly distributed on four physical disks. The parity is also stored in the distributed physical disks.

FIG. 2 and FIG. 4 are diagrams for explaining the problems of the conventional RAID 5.

As shown in Figure 2, in a conventional RAID5 system, a single disk failure causes a loop-down, causing a failure in which all disks on the FC (Fiber Channel) loop including that disk become invisible. In other words, in the conventional RAID5 disk configuration, RAID5 is configured only with disks on a single FC loop, so that loop-down may prevent access to the multiple disks that make up the RAID group, and As a result, normal input / output processing such as read / write may not be possible.

[0005] Therefore, as a countermeasure, there is a system as shown in FIG. In other words, the device adapter has two FC ports, and one loop is connected to each port. One disk at a time. In this case, make up a RAID group with a total of 4 disks connected to different loops. Therefore, the four disks in Fig. 3 form a set. Here, if one of the four disks fails, the other three disks can still be accessed. Therefore, it is possible to recover the data stored on the failed disk by using the intelligence.

FIG. 4 is a diagram illustrating a problem when rebuilding is performed when many disks are connected.

The configuration in Fig. 4 is a RAID5 configuration using 16 physical disks. In the rebuild (redundancy restoration process), data is read from 15 disks, XOR is performed, parity is generated, and then data is written to the spare disk HS. Therefore, the more disks are connected, the more disks that need to be read during rebuilding, causing the problem of slower rebuilding processing.

[0007] As a similar problem, there is a problem that a processing delay occurs at the time of writing. For example, in RAID5, when writing back, when writing in a state where the RAID group loses redundancy due to a disk failure, etc., especially when the disk to which data is to be written has failed, parity XOR the data read from all disks except for the data with the data to be written back, create parity, and write it to the parity disk. Therefore, since reading or writing is performed for all disks, processing is easily delayed.

[0008] As conventional disk systems, there are systems as described in Patent Literature 1, Patent Literature 2, Patent Literature 3, and Patent Literature 4. When a processor accesses a shared memory, a technology has been disclosed in which a newly provided built-in cache is passed. Patent Document 2 discloses a technology in which a host adapter, a disk adapter, and a cache memory for temporary storage are commonly connected to a common bus. Patent Document 3 discloses a technique in which a spindle Z block write-back restoration is performed in an array disk processing device. In Patent Document 4, in a disk array, a virtual disk holding the contents of a disk drive is used. There is disclosed a technique of providing a cache memory that functions as a cache memory.

Patent Document 1: Japanese Patent Application Laid-Open No. 2001-306265

Patent Document 2: Japanese Patent Application Laid-Open No. 7-20994

Patent Document 3: JP-A-11-66693

Patent Document 4: JP-A-7-200190

Disclosure of the invention

[0009] An object of the present invention is to provide a disk system that is excellent in expandability and that can efficiently realize redundancy when a failure occurs.

The disk system according to the present invention is a disk system employing a redundant configuration, comprising: a stripe processing managing means for performing stripe management of a data string according to a setting of whether or not a data string of a host is divided into stripes; A redundancy management means for providing data redundancy and storing the data on a plurality of physical disks based on the setting of whether or not to perform redundancy management on the data from the management means; By separating the redundancy management function, disk systems of various configurations can be configured.

According to the present invention, each of the center module and the device adapter has the functions of managing the striping and managing the redundancy, which are conventionally performed by the device adapter, respectively. Various disk systems can be easily constructed by combining. In addition, by providing a plurality of device adapters DA as redundancy management means, the capacity of the disk system can be easily expanded, and the performance can be improved by distributed processing. In addition, the effect of the write penalty and the like that has occurred in the conventional RAID5 is closed within one device driver (redundancy management means), so that the effect can be prevented from affecting the entire disk system.

[0011] Another disk system according to the present invention is a first striping unit that regards a set of a plurality of physical disks as one virtual disk and distributes a data string from a host to the plurality of virtual disks by striping. A second striping means for generating a parity from the data sequence allocated to each of the virtual disks, and distributing the allocated data sequence and the generated parity to a plurality of physical disks by means of a stripe, and Writing means for writing data allocated to each of the physical disks to the corresponding physical disk.

[0012] According to such a disk system, the first striping means performs the RAID5 control, which is the control of redundancy, on the data sequence allocated to each virtual disk by a plurality of physical devices. Done. Therefore, RAID5 can be further striped, and the degree of freedom in configuration is greatly increased, and performance improvement by distributed processing can be expected. In addition, since the impact of the write penalty is closed within one virtual disk, the extent of the impact can be reduced.

Brief Description of Drawings

FIG. 1 is a diagram showing a configuration of a RAID5 disk system.

FIG. 2 is a diagram illustrating a problem of a conventional RAID5.

FIG. 3 is a diagram illustrating a problem of conventional RAID5.

FIG. 4 is a diagram illustrating a problem of conventional RAID5.

FIG. 5 is a configuration diagram of a disk system according to the embodiment of the present invention.

FIG. 6 is a diagram showing a manner of mapping between a RAID group and a physical disk in the embodiment of the present invention.

FIG. 7 is a diagram showing a configuration of an RLU information table.

FIG. 8 is a configuration example of a DLU information table.

FIG. 9 is a flowchart showing the operation of the center module CM.

FIG. 10 is a flowchart showing an operation of the device adapter DA.

FIG. 11 is a diagram illustrating a configuration of RAID 1 when a disk system according to an embodiment of the present invention is used.

FIG. 12 is a diagram for explaining a configuration of RAIDO + 1 when a disk system according to an embodiment of the present invention is used.

FIG. 13 is a diagram illustrating a configuration of RAID5 when a disk system according to an embodiment of the present invention is used.

FIG. 14 illustrates the configuration of RAIDO + 5 when using the disk system according to the embodiment of the present invention. FIG.

FIG. 15 is a diagram for explaining RAID0 + 5.

FIG. 16 is a diagram explaining rebuilding in the disk system of the embodiment of the present invention.

FIG. 17 is a diagram for explaining read / write when a loop down of the 1FC loop occurs in the disk system of the embodiment of the present invention.

FIG. 18 is a diagram showing information used for managing a cache memory.

FIG. 19 is a diagram showing conversion between RLU and DLU during host read.

FIG. 20 is a diagram showing conversion between RLU and DLU at the time of host write.

FIG. 21 is a configuration diagram of a disk system that performs stripe control and RAID5 control on a CM. BEST MODE FOR CARRYING OUT THE INVENTION

First, the host 10 sends a host access data sequence. The data sequence is received by the channel adapter CA and transferred to the center module CM. The center module performs only stripe control and distributes the data string to the two device adapters DA. Each device adapter DA performs RAID5 control, generates a note, and stores each strip on the four physical disks connected to the device adapter DA.

[0015] As is clear from FIG. 5, in the embodiment of the present invention, the center module CM is connected to the device adapter DA, and the group of four physical disks is regarded as a virtual disk, and drive control is performed. After that, the device adapter DA corresponding to each virtual disk performs RAID5 control as redundancy control.

According to the above embodiment of the present invention,

1) The roles are divided between the center module CM that performs stripe control and the device adapter DA that performs RAID5 control, which greatly increases the degree of freedom in configuration.

2) By using multiple device adapters DA that perform RAID5 control, performance improvement can be expected by distributed processing.

3) In general, in RAID5, as the number of constituent disks increases, the number of disks used due to a write penalty in the event of a disk failure increases, but in the embodiment of the present invention, The influence of the write penalty only in the disc can be small. There is an advantage.

[0017] The center module CM includes a processor and a memory that stores programs and data used by the processor. The processor performs necessary processing for the disk system by executing a program using the memory.

[0018] These programs and data are supplied to the center module CM by an information processing device such as the host 10 or a portable recording medium. At this time, the information processing device generates a carrier signal for carrying the supplied program and data, and transmits the carrier signal to the center module CM via an arbitrary transmission medium on the communication network. As the portable recording medium, any computer-readable recording medium such as a memory card, a flexible disk, an optical disk, and a magneto-optical disk can be used.

FIG. 6 is a diagram showing a state of mapping between a RAID group and a physical disk in the embodiment of the present invention.

First, the uppermost layer shows the entire disk system and is called a RAID group. At the next stage, stripe management is performed and data is allocated to virtual logical units. Next, redundancy management is performed, and each data is

[0020] Here, the stripe management is to manage simple striping without redundancy. Redundancy management refers to management of mirroring in RAID1 and stripes including parity in RAID5. Here, the function of performing only stripe management that manages simple striping without redundancy is called RAIDO.

In the disk system according to the embodiment of the present invention, various types of disk systems can be used depending on whether or not stripe management is performed, whether or not redundancy management is performed, and whether or not stripe processing including mirroring power parity is performed in redundancy management. Can be configured.

[0022] Stripe management Redundancy management

RAIDO Yes No

Without RAID1 Mirroring RAIDO + 1 Yes Mirroring

RAID 5 None Stripes with parity

RAID0 + 5 Yes Stripe including parity

The terms used in the following description are defined as follows. First, RLU stands for one RAID group. RLBA is the LBA (Logical Block Address) of the RLU. PLU means a single physical disk. PLBA is the LBA of PL U. A DLU is an LU (logical unit) logically located between the RLU and the PLU, and is obtained by dividing stripes from the RLU and considering the redundancy of the PLU. DLBA is the LBA of DLU.

FIG. 7 is a diagram showing a configuration of the RIJ information table.

The RLU information table is a table that holds information in RLU units. The tape module is mainly held by the center module CM, and a necessary part of the copy is held by the channel adapter CA and the device adapter DA. RLUN is the RLU number. Define

The CM Module ID is the module ID of the CM in the configuration responsible for the RLU.

Current CM Module ID is the module ID of the CM currently in charge of the RLU. Raid Level indicates the RAID level of the RLU, and RAID0, RAID5, etc. are set. RLBA count is the total number of blocks of the RLU. Stripe Depth is the length of one strip when striping. The Stripe Size is, for example, the total length of four strips when one physical strip is hit on each of four physical disks. That is, the total length of the strips equal to the number of physical disks. Others are not so involved in the description of the embodiment of the present invention, and thus the description is omitted.

FIG. 8 is a configuration example of a DLU information table.

This is a table that holds information in DLU units. This table is mainly held by the center module CM, and a necessary part of the table is copied by the channel adapter CA ゃ device adapter DA. DLUN is the DLU number. RLUN is the RLU number to which the DLU belongs. The Member Disk Number is a number indicating the DLU number of the stripe constituting the DLU. Start DLBA is the first LBA of DLU. Block Co tint is the total number of blocks of the DLU. Stripe Depth and Stripe Size are as described above. is there. Member Disk Count is the number of disks used by the DLU. DA ID xx is the module ID of the DA connected to the DLU. PLU in Use xx is the PLU number that makes up the current DLU. Defined PLU xx is the PLU number when there is no disk failure when this configuration was created.

FIG. 9 is a flowchart showing the operation of the center module CM.

First, in step S10, the presence or absence of stripe management is determined. If it is determined in step S10 that stripe management is performed, the stripe is divided in step S11. Then, using the RLU information table, the set of RLUN and RLBA is converted into at least one or more corresponding set of DLUN and DLBA. If it is determined in step S10 that there is no stripe management, in step S12, a set of RLUN and RLBA is converted one-to-one to a corresponding set of DLUN and DLBA using the RLU information table. .

In step S13, the type of redundancy management is determined. If it is determined in step S13 that there is no redundancy management, in step S16, a set of DLUN and DLBA is paired with a corresponding set of PLUN and PLBA using the DLU information table. Convert and proceed to step S17.

[0027] If it is determined in step S13 that the redundancy management is mirroring, mirroring is considered in step S15. Using the DLU information table, the pair of DLUN and DLBA is converted into two corresponding pairs of PLUN and PLBA, and the process proceeds to step S17.

[0028] In step S13, when it is determined that the redundancy management is a stripe including parity, in step S14, a pair of DLUN and DLBA is designated as the device adapter DA, and the device adapter DA is started, and the process ends. I do.

[0029] In step S17, a pair of PLUN and PLBA is specified for the device adapter DA and activated, and the process ends.

FIG. 10 is a flowchart showing the operation of the device adapter DA.

In step S20, the type of the specified LUN is determined. At the judgment of step S20

If it is determined that the type is a pair of PLUN and PLBA, in step S21 Executes the process (read, write, etc.) on the disk according to the specified pair of PLUN and PLBA, and ends the process. If it is determined that the type of step S20 is a combination of DLUN and DLBA, in step S22, the conventional RAID5 control is performed. In the RAID 5 control process, the DLU information table is used to convert a DLUN / DLBA pair into at least one or more corresponding PLUN / PLBA pairs, and read / write to each disk. , And the process ends.

FIG. 11 is a diagram for explaining the configuration of RAID 1 when the disk system according to the embodiment of the present invention is used.

Since the LUN has no stripe, there is only one DLUN corresponding to the RLUN. In mirroring, two DLUNs are provided because two disks are used. Since the LBA has no stripe, RLBA = DLBA. In mirroring, only the same information is written to both disks, so DLBA = PLBA.

In FIG. 11, the RAID group RLU has a one-to-one relationship with the virtual logical unit DLU, and the virtual logical unit DLU mirrors two physical disks PLU to store data.

FIG. 12 is a diagram for explaining the configuration of RAID0 + 1 when the disk system according to the embodiment of the present invention is used.

Four virtual logical units DLU are mapped to the RAID group RLU. This mapping is realized by performing striping. Each of the virtual logical units DLU is provided with two physical disks PLU, and performs mirroring to store the data. The diagram below FIG. 12 is a diagram showing how data is stored. There are four DLUs, # 0 # 3, and two PLUs are associated with each. The data is divided by striping and D0, Dl, ..., Dl5 from the beginning. These stripes are stored laterally, that is, in the direction of different virtual logical units, one stripe at a time.

FIG. 13 is a diagram for explaining the configuration of RAID5 when the disk system according to the embodiment of the present invention is used.

As shown on the left of Fig. 13, the RAID group RLU and virtual logical unit DLU Is one-to-one. In addition, the correspondence between the DLU and the physical disk PLU is one-to-many (in this case, one-to-four), and the DLU performs RAID5 control, and as shown in the right of FIG. The data is stored in each physical disk together with the notice by performing redundancy control on the data divided into stripes.

FIG. 14 is a diagram illustrating the configuration of RAID0 + 5 when the disk system according to the embodiment of the present invention is used.

As described in the upper part of FIG. 14, two virtual logical units DLU correspond to the RAID group RLU, and between them, mapping is performed by striping. Between the DLU and the physical disk PLU, four PLUs correspond to one DLU and are mapped by RAID5 control. As shown in the lower part of Fig. 14, data is first divided into two DLUs by striping, and each is divided into four physical disks by RAID5 control. At this time, since the RAID5 control performs redundancy management, parity is generated. The Stripe Size of the DLU information table is equal to the Stripe Depth of the RLU information table.

FIG. 15 is a diagram illustrating RAID0 + 5.

The CM performs stripe control and transfers data mapped to each DLU to four DAs. Each DA performs redundancy management and transfers the mapped data to four physical disks. In the above example, the CM transfers data to two DAs. However, the CM can be added in units of DAs and the physical disks under the DAs, so that performance can be improved by distributed processing. Also, as described above, in the disk system according to the embodiment of the present invention, a disk system having various configurations other than RAID0 + 5 can be configured. The role is shared with DAs who perform

FIG. 16 is a diagram for explaining rebuilding in the disk system according to the embodiment of the present invention.

If a DA has four FC ports, build a RAID5 by combining four physical disks connected to different FC ports, and then build a RAID0 + 5 by combining the four RAID5s to rebuild any DLU. Up to three discs when reading Limited.

FIG. 17 is a diagram for explaining reading / writing when a loop down of the 1FC loop occurs in the disk system of the embodiment of the present invention.

If the DA has four FC ports, RAID0 + 5 is set up in the same way as in Fig. 16, so that any DLU can be read-Z-written using the remaining three disks when a 1FC loop loop-down occurs Thus, RZ can be used for read and Z write.

The outline of RAID0 + 5 is that existing RAID5 is regarded as one virtual disk, a plurality of virtual disks are prepared, and striping is performed.

RAID0 + 5 first prepares Stripe Size / Stripe Depth (value defined as the redundancy management layer) for controlling RAID5, and separates this from Stripe Size / Stripe for striping this RAID5. This is realized by preparing Depth (value defined as stripe management layer). Access to this RAID group is performed by dividing the result of the division into stripes according to the definition of the stripe management layer into each physical disk according to the definition of the redundancy management layer.

Next, the internal operation of RAID0 + 5 will be described in more detail with reference to FIGS.

As shown in Fig. 18, the CM divides the cache memory into strip-size units, and lists information indicating whether each unit is in use and information indicating whether there is write data. Having it manages the cache memory.

In FIG. 18, for simplicity, information indicating whether or not each divided unit is in use and information indicating whether or not there is write data are described like a flag on a list entry. However, in practice, it is possible to perform processing in a unit smaller than a strip by using a method such as a bitmap representation in a block unit.

FIG. 19 shows conversion between RLU and DLU during host read. If there is no cache data in the CM's cache memory at the time of host read, the CM prepares the cache memory area divided into strip units by the number of strips requested to be read. Then, the RLU address list is created by giving information indicating that each strip is in use and listing the addresses of each strip. This RLU address list allows multiple A data string spanning the strip is represented.

Next, in order to cause the DA to perform staging from the disk, conversion between RLU and DLU is performed.

At this time, for the read-requested area, it is determined which DLU each strip belongs to, using the Stripe Size and Stripe Depth of the RLU information table. Then, with respect to the RLU address list, the addresses of the strips belonging to each DLU are collected for each DLU while maintaining the order in the list, and a list of entry numbers of the RLU address list is created for each DLU. The list for each DLU created in this way represents a continuous area as a DLBA.

Next, the CM requests a staging process from each DA in charge of the DLU for the list for each DLU, and the DA requested to perform the staging process performs a conversion between the DLU and the PLU.

The DA processes the requested list for each DLU according to the normal RAID5 control, and uses the Stripe Size and Stripe Depth of the DLU information table to transfer the data read from each disk to the cache memory address of the corresponding strip. .

Next, the CM notifies the CA of the address list of the RLU, and the CA transfers data in the cache memory to the host according to the address list. Thus, the host read is completed.

FIG. 20 shows conversion between RLU and DLU during host write. If there is no cache data in the cache memory of the CM at the time of host write, the CM prepares the cache memory area divided into strip units by the number of strips for which a write request was made. Then, the RLU address list is created by giving information indicating that each strip is in use and listing the addresses of each strip. The RLU address list represents a data string that spans multiple strips.

Next, the CM notifies the CA of the address list of the RLU, and the CA transfers the data written from the host to the cache memory according to the address list. Then, the CM has information indicating that there is write data for each strip. This completes the host write.

After that, the DA writes back the data in the cache memory. CM is Convert between RLU and DLU to make DA write back.

At this time, first, for the area requested to be written, it is determined which DLU each strip belongs to using the Stripe Size and Stripe Depth of the RLU information table. Then, in the same way as in the case of FIG. 19, a list of entry numbers of the RLU address list is created for each DLU.

Next, the CM requests a write-back process to each DA in charge of the DLU for the list for each DLU, and the DA requested to perform the write-back process performs conversion between DLU and PLU.

The DA processes the requested list for each DLU according to the normal RAID5 control, and transfers the data written by the host from the cache memory address of the corresponding strip using the Stripe Size and Stripe Depth of the DLU information table. And temporarily store it in DA. Then, using the data written from the host or the data written from the host, the data on the disk, and the parity, a new parity is created, and the data written from the host and the new parity are written to the disk.

Next, the CM causes each strip to have information indicating no write data. This completes the write-back processing.

In the embodiment described above, stripe management is performed by CM, and RAID5 control (redundancy management) is performed by DA. It is also possible to perform both stripe management and redundancy management on a single CM. .

FIG. 21 is a configuration diagram of a disk system equipped with such a CM.

In this case, the CM first performs stripe control of the data string transmitted from the host 10 to divide the data string into two DLUs. Next, RAID5 control is performed for each DLU, a notice is generated, and each strip is stored on four physical disks.

Industrial applicability

The present invention has excellent expandability as a storage device of a computer system, has a large degree of freedom in configuration, and can limit the influence of a factor of performance degradation to maintain the performance of the entire system. A disk system can be provided.

Claims

The scope of the claims

[1] A disk system adopting a redundant configuration,

Stripe processing management means for performing stripe management of the data string according to the setting as to whether or not the data string from the host is divided into stripes;

Redundancy management means for giving data redundancy and storing the data on a plurality of physical disks based on a setting as to whether or not to perform redundancy management on the data from the stripe processing management means. And disk system.

[2] The device according to claim 1, wherein a plurality of the redundancy management means are provided.

[3] The disk system according to claim 1, wherein the capacity of the disk system is increased by increasing the number of the redundancy management means and the number of physical disks connected to the redundancy management means. .

4. The disk system according to claim 1, wherein the redundancy management means executes a RAID5 process as a redundancy management method.

[5] The stripe processing management means notifies the redundancy management means of the redundancy management method to the redundancy management means by setting a redundancy management method.

6. The disk system according to claim 5, wherein the redundancy management method includes control of stripes including notice and mirroring.

7. The disk system according to claim 1, wherein the stripe management is performed by designating a size and a depth of the stripe.

[8] A disk system configuration method employing a redundant configuration,

Providing a stripe processing management means for performing stripe management of the data string according to a setting as to whether or not the data string from the host is divided into stripes;

Providing redundancy management means for giving redundancy to the data and storing the data on a plurality of physical disks based on a setting as to whether or not to perform redundancy management on the data from the stripe processing management means. A method of configuring a disk system.

[9] The device according to claim 8, wherein a plurality of the redundancy management means are provided. Configuration method.

10. The disk system according to claim 8, wherein the capacity of said disk system is increased by increasing the number of said redundancy management means and the number of physical disks connected to said redundancy management means. Configuration method.

11. The disk system configuration method according to claim 8, wherein said redundancy management means executes RAID5 processing as a redundancy management method.

12. The disk system according to claim 8, wherein the stripe processing management unit notifies the redundancy management method to the redundancy management unit by setting a redundancy management method. Configuration method.

13. The disk system configuration method according to claim 12, wherein the redundancy management method includes control of stripes including notices and mirroring.

14. The method according to claim 8, wherein the stripe management is performed by designating a size and a depth of the stripe.

[15] A first striping means for distributing a data string from a host to a plurality of virtual disks by striping by regarding a set of a plurality of physical disks as one virtual disk, and distributing the data string to each of the plurality of virtual disks Second striping means for generating parity from the allocated data sequence, and distributing the allocated data sequence and the generated parity to the plurality of physical disks by striping;

A writing unit for writing data allocated to each of the plurality of physical disks to a corresponding physical disk.

[16] The first striping unit allocates the data string to the plurality of virtual disks according to a stripe size and a stripe depth held in a first information table. 16. The disk system according to claim 15, wherein the data sequence and the parity are distributed to the plurality of physical disks according to the stripe size and the stripe depth held in the information table.

[17] A set of multiple physical disks is regarded as one virtual disk, and a data string from the host is distributed to multiple virtual disks by striping.

Parity is generated from the data sequence allocated to each of the plurality of virtual disks And

Distributing the allocated data sequence and the generated parity to the plurality of physical disks by striping,

A data storage method characterized by writing data allocated to each of the plurality of physical disks to a corresponding physical disk.