WO2018113322A1

WO2018113322A1 - Method and device for reading data

Info

Publication number: WO2018113322A1
Application number: PCT/CN2017/097682
Authority: WO
Inventors: 罗镇; 孙吉峰
Original assignee: 华为技术有限公司
Priority date: 2016-12-23
Filing date: 2017-08-16
Publication date: 2018-06-28
Also published as: CN106775481B; CN106775481A

Abstract

Provided in the embodiments of the present invention are a method and a device for reading data. The method comprises: acquiring a reading instruction from a host, the reading instruction comprising the identifier of a source logical unit number (LUN) and the first starting address and the first data length of to-be-read data, the source LUN corresponding to a redundant view, the redundant view comprising at least one first record entry, the identifier of a target LUN, which redundantly stores at least part of the data of the source LUN, being stored in each first record entry; if it is determined that the data in the storage space corresponding to the source LUN can't be read, determining, according to the first starting address, the first data length and the redundant view, the identifier of the target LUN corresponding to the to-be-read data; and reading, according to the identifier of the target LUN corresponding to the to-be-read data, first redundant data, and feeding the first redundant data back to the host. The present embodiment can improve the utilization of redundant data of a storage system.

Description

Data reading method and device

Technical field

The embodiments of the present invention relate to the field of storage technologies, and in particular, to a data reading method and device.

Background technique

With the rapid development of computer technology and network technology, the memory that comes with the computer is gradually unable to meet the storage requirements, so a relatively independent storage device is developed. The storage device has its own interface and protocol, and is connected to the host computer through a coaxial cable, a network cable, an optical fiber, or the like.

In the prior art, the storage device can provide disk space to the computer host through a logical unit number (LUN). Specifically, the disk space of the storage device is divided into multiple blocks, and each block corresponds to one LUN. When the storage device receives the read command from the host computer, if there is a disk bad track or data corruption in the block corresponding to a certain LUN, the correct data cannot be read from the corresponding storage location of the LUN. If the mirrored LUN exists on the LUN, check whether the data corresponding to the mirrored LUN meets the data consistency status. If the data is consistent, the data is read from the storage space corresponding to the mirrored LUN and returned to the host. The data is fetched and written into the storage space corresponding to the LUN. If they are inconsistent, the medium error information is returned to the host computer.

However, in the prior art, data can be read from the mirrored LUN only when the data corresponding to the mirrored LUN meets the data consistency status. If there is some data in the storage space corresponding to the LUN, even if the mirrored LUN does not meet the data consistency status, the mirrored LUN does not meet the data consistency status. The correct data cannot be obtained from the mirrored LUN, resulting in the inability to fully utilize the redundant data of the storage system.

Summary of the invention

Embodiments of the present invention provide a data reading method and device to improve utilization of redundant data of a storage system.

In a first aspect, an embodiment of the present invention provides a data reading method, including:

Obtaining a read instruction of the host, where the read command includes an identifier of the source logical unit number LUN, a first start address of the data to be read, and a first data length, where the source LUN corresponds to a redundant view, and the redundancy The remaining view includes at least one first record item, and each of the first record items stores an identifier of a target LUN that performs redundancy storage on at least part of the data in the source LUN;

Determining, according to the first start address, the first data length, and the redundant view, the target LUN corresponding to the data to be read, when the data in the storage space corresponding to the source LUN is unreadable. Optionally, the first record item further stores a second start address and a second data length of the second redundant data; determining an address space corresponding to the first start address and the first data length, and the second The identifier of the target LUN in the corresponding first record entry is the identifier of the target LUN corresponding to the data to be read when the address space corresponding to the first address and the second data length are overlapped.

And reading, according to the identifier of the target LUN corresponding to the data to be read, the first redundant data, and returning the first redundant data to the host.

The source LUN corresponds to a redundant view, and the redundant view includes at least one first record item, where each first record item stores an identifier of a target LUN that performs redundant storage on at least part of the data in the source LUN, so that the source is in the source When the data in the storage space corresponding to the LUN cannot be read, you do not need to determine whether the data in the source LUN is related to the target LUN. The data in the data meets the data consistency. The first record in the redundant view corresponding to the data to be read is obtained, and the identifier of the target LUN corresponding to the data to be read is determined; and the identifier of the target LUN corresponding to the data to be read is determined. The first redundant data is read to improve the utilization of redundant data in the storage system.

In a possible design, the storage space corresponding to the source LUN is divided into a plurality of data blocks, wherein each of the data blocks respectively corresponds to a redundant view;

Determining, according to the first start address, the first data length, and the redundant view, the identifier of the target LUN corresponding to the data to be read, including:

Determining, according to the first start address, the first data length, and an address space of each data block corresponding to the identifier of the source LUN, at least one first target data block corresponding to the data to be read;

And determining, according to the first record item in the redundant view corresponding to each of the first target data blocks, an identifier of the target LUN corresponding to the to-be-read data.

In a possible design, the first record item further stores a second start address and a second data length of the second redundant data, where the second start address and the second data length form The second address space is a subset of the address space of the data block;

Determining, according to the first record item in the redundancy view corresponding to each of the first target data blocks, an identifier of the target LUN corresponding to the data to be read, including:

Determining a first address space according to the first start address and the first data length;

Determining, according to the first address space, the second address space corresponding to the first record item in the redundant view corresponding to each of the first target data blocks, corresponding to the second address space that has an intersection with the first address space a target record entry, and the first address space is a subset of address spaces formed by the plurality of the second address spaces;

And determining, according to each of the target record items, an identifier of the target LUN corresponding to the data to be read.

The storage space corresponding to the source LUN is divided into multiple data blocks, and each data block has a corresponding redundant view. In this way, as long as the target data block corresponding to the data to be read is found, the first record item can be traversed only in the target data block, which reduces the traversal time and improves the efficiency of reading the data.

In a possible design, the priority of each target LUN is also stored in the first record item;

Determining, according to the first address space, the second address space corresponding to the first record item in the redundant view of each of the first target data blocks, determining a second address space that intersects with the first address space Corresponding target records, including:

Determining, according to the first address space and an address space of each data block, the third address space of the data to be read for each first target data block;

For each of the first target data blocks, traversing each of the first records in the redundant view according to a priority of the target LUNs in each of the first entries in the redundant view from high to low Obtaining a target record corresponding to the second address space where the third address space intersects, and the third address space is a subset of the address space formed by at least one of the second address spaces, for the same redundancy Data, the target LUN in the target record item has a higher priority than the target LUN in the other first record item.

The process of inserting a record item in the redundant view will be described in detail below, and those skilled in the art can understand that the process of inserting a record item in the redundant view can be implemented separately without depending on the above possible design, and may also be The design is based on the implementation.

In one possible design, the method further includes:

Obtaining an identifier of the source LUN, a second record to be inserted into the redundant view, where the second record includes a third start address and a third data length of the three redundant data, an identifier of the target LUN corresponding to the third redundant data, and a priority of the target LUN;

Determining, according to the third start address, the third data length, and the address space of each data block corresponding to the identifier of the source LUN, the at least one second target data block corresponding to the third redundant data;

And according to the priority of the target LUN stored in each first record in the redundant view corresponding to each of the second target data blocks, and the priority of the target LUN stored in the second record, The redundant view corresponding to the two target data blocks is processed by inserting the record items.

In a possible design, the priority of the target LUN stored in each of the first records in the redundant view corresponding to each of the second target data blocks and the target stored in the second record Priority of the LUN, the processing of inserting the record entry into the redundant view corresponding to each of the second target data blocks, including:

Determining, according to the third start address, the third data length, and an address space of each data block, a third record of the third redundant data for each second target data block, the third The record entry includes a fourth start address, a fourth data length, an identifier of the target LUN corresponding to the third redundant data, and a priority of the target LUN;

For each second target data block, traversing each of the redundant views according to a priority of each first record in the redundant view corresponding to the second target data block from highest to lowest a record item is inserted before the first record item until the priority of the target LUN in the third record item is higher than the priority of the target LUN in the first record item.

The process of deleting a record item in the redundant view will be described in detail below. Those skilled in the art can understand that the process of deleting a record item in the redundant view can be implemented separately without depending on the above possible design, and may also be The design is based on the implementation.

In one possible design, the method further includes:

Obtaining the write information of the newly written data of the storage space corresponding to the source LUN, where the write information includes an identifier of the source LUN, a fourth start address of the newly written data, and a fourth data length;

Determining, according to the fourth start address, the fourth data length, and the address space of each data block corresponding to the identifier of the source LUN, the at least one third target data block corresponding to the newly written data. ;

And according to the fifth start address and the fifth data length, the fourth start address, and the fourth data length in each fourth record item in the redundant view corresponding to each of the third target data blocks, The redundant view corresponding to each of the third target data blocks performs processing for deleting the record items.

In a possible design, the fifth start address and the fifth data length and the fourth start in each fourth record item in the redundant view corresponding to each of the third target data blocks The address and the fourth data length are processed by deleting the record of the redundant view corresponding to each of the third target data blocks, including:

Determining, according to the fourth start address, the fourth data length, and an address space of each data block, a sixth start address and a sixth data length of the new write data for each third target data block. And a fourth address space;

Traversing each fourth record item in the redundant view, if the fifth address space corresponding to the fourth record item and the fourth address space have an intersection, according to the fifth start address, the fifth The data length, the sixth start address, and the sixth data length are processed by deleting the record item in the redundant view corresponding to the third target data block.

In a possible design, the redundant view corresponding to the third target data block is deleted according to the fifth start address, the fifth data length, the sixth start address, and the sixth data length The processing of records, including:

Establishing a first decomposition space R1 and a second decomposition space R2 according to the fifth start address, the fifth data length, the sixth start address, and the sixth data length;

The starting address and data length of the R1 are as follows:

R1_lba=D5; R1_len=D6-D5;

The starting address and data length of the R2 are as follows:

R2_lba=D6+L6; R2_len=D5+L5-D6-L6, wherein R1_lba is a starting address of the first decomposition space, the R1_len is a data length of the first decomposition space, and the R2_lba For the start address of the second decomposition space, the R2_len is the data length of the second decomposition space, the D5 is the fifth start address, the D6 is the sixth start address, and the L5 is a fifth data length, wherein the L6 is a sixth data length;

And processing the deleted record item on the redundant view corresponding to the third target data block according to the data length of the R1 and the data length of the R2.

In a possible design, the processing of deleting a record item in the redundant view corresponding to the third target data block according to the data length of the R1 and the data length of the R2 includes:

If the data length of the R1 is greater than 0, and the data length of the R2 is greater than 0, the fourth record is deleted, and the fifth record and the sixth record are inserted, and the start of the fifth record The address is D5, the data length is D6-D5, the starting address in the sixth record is D6+L6, and the data length is D5+L5-D6-L6;

If the data length of the R1 is greater than 0, and the data length of the R2 is less than or equal to 0, the fourth record is deleted, and the sixth record is inserted, and the start address in the sixth record is D6+ L6, the data length is D5+L5-D6-L6;

If the data length of the R1 is less than or equal to 0, and the data length of the R2 is greater than 0, the fourth record is deleted, and the fifth record is inserted, and the start address in the fifth record is D5. The data length is D6-D5.

In a second aspect, an embodiment of the present invention provides a storage device, including:

a receiving module, configured to acquire a read command of the host, where the read command includes an identifier of the source logical unit number LUN, a first start address of the data to be read, and a first data length, where the source LUN corresponds to redundancy View, the redundant view includes at least one first record item, and each of the first record items stores an identifier of a target LUN that performs redundancy storage on at least part of the data in the source LUN;

a processing module, configured to determine, according to the first start address, the first data length, and the redundant view, the data to be read, when the data in the storage space corresponding to the source LUN is unreadable The identifier of the target LUN is read, and the first redundant data is read according to the identifier of the target LUN corresponding to the data to be read;

And a sending module, configured to return the first redundant data to the host.

In a possible design, the storage space corresponding to the source LUN is divided into a plurality of data blocks, wherein each of the data blocks corresponds to a redundant view; the processing module is specifically configured to:

The processing module is specifically configured to:

In one possible design, the processing module is further configured to:

Obtaining an identifier of the source LUN, a second record to be inserted into the redundant view, where the second record includes a third start address and a third data length of the third redundant data, and the third redundancy The identifier of the target LUN corresponding to the data and the priority of the target LUN;

In one possible design, the processing module is specifically configured to:

In one possible design, the processing module is further configured to:

In one possible design, the processing module is specifically configured to:

The starting address and data length of the R1 are as follows:

R1_lba=D5; R1_len=D6-D5;

The starting address and data length of the R2 are as follows:

In one possible design, the processing module is specifically configured to:

In a third aspect, the embodiment of the present invention further provides a storage device, where the storage device includes at least one processor and a memory; the memory stores a computer to execute an instruction; and the at least one processor executes the computer execution of the memory storage The instructions cause the storage device to be as described above in the first aspect and the data reading method of the various possible designs of the first aspect.

In a fourth aspect, the embodiment of the present invention further provides a computer readable storage medium, where the computer readable storage medium stores computer execution instructions, when the at least one processor of the storage device executes the computer execution instruction, the storage device performs the above Various data reading methods that may be provided by the design.

In a fifth aspect, an embodiment of the present invention further provides a computer program product, the computer program product comprising computer execution instructions, the computer execution instructions being stored in a computer readable storage medium. At least one processor of the storage device can read the computer-executable instructions from a computer readable storage medium, and the at least one processor executes the computer-executable instructions to cause the storage device to implement the data reading method provided by various possible designs in the foregoing method embodiments .

The data reading method and device provided in this embodiment have a redundant view corresponding to the source LUN, and the redundant view includes At least one first record item, each of the first record items stores an identifier of the target LUN that is used to store at least part of the data in the source LUN, so that the data in the storage space corresponding to the source LUN cannot be read. The data of the source LUN is not required to be consistent with the data in the target LUN. The first record in the redundant view corresponding to the data to be read is obtained, and the target LUN corresponding to the data to be read is determined. The first redundant data is read according to the identifier of the target LUN corresponding to the data to be read, thereby improving the utilization of redundant data in the storage system.

DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings to be used in the description of the embodiments will be briefly described below.

1 is a schematic structural diagram 1 of a storage device according to an embodiment of the present invention;

2 is a schematic flowchart 1 of a data reading method according to an embodiment of the present invention;

3 is a corresponding relationship diagram between a data block and a redundant view according to an embodiment of the present invention;

4 is a schematic flowchart 2 of a data reading method according to an embodiment of the present invention;

FIG. 5 is a schematic flowchart of inserting a redundant view record item according to an embodiment of the present invention;

FIG. 6 is a schematic flowchart 1 of deleting a redundant view record item according to an embodiment of the present invention;

FIG. 7 is a schematic flowchart 2 of deleting a redundant view record item according to an embodiment of the present invention;

FIG. 8 is a schematic structural diagram 2 of a storage device according to an embodiment of the present disclosure;

FIG. 9 is a schematic structural diagram 3 of a storage device according to an embodiment of the present invention.

detailed description

The technical solutions in the embodiments of the present invention will be clearly and completely described in the following with reference to the accompanying drawings.

FIG. 1 is a schematic structural diagram 1 of a storage device according to an embodiment of the present invention. The storage device provided in this embodiment is relatively independent from the computer host, has its own interface and protocol, and is connected to the computer host through a coaxial cable, a network cable, an optical fiber, or the like. The storage device can provide disk space to the host computer through a logical unit number (LUN). As shown in FIG. 1, the storage device of this embodiment includes software and hardware.

The software of the storage device contains the operating system and software modules. Among them, the operating system provides the basic operating system for the software to run. The software module can implement functions such as reading and repairing data.

The hardware of the storage device includes multiple hard disks, interface cards, a central processing unit (CPU), and memory. The multiple hard disks can provide the hard disk storage space corresponding to the LUN. An interface card is used to connect to a host computer or other storage device. Other storage devices store redundant data such as remote replication. The CPU and memory provide the basic hardware platform required for the operating system and software modules.

FIG. 1 shows a possible structure of the storage device of the embodiment. For other storage devices, as long as the components such as the hard disk and the CPU are provided, the protection scope of the present invention belongs to the present invention. For other structures, this embodiment will not be described herein.

Based on the technical problem that the redundant data of the storage system cannot be fully utilized in the prior art, the storage space corresponding to the source LUN is divided into multiple data blocks, and the storage information of the redundant data of each data block is redundant. The view mode is organized. When some data blocks of the source LUN are damaged, the target LUN is found through the redundant view, and the data is read from the target LUN and automatically repaired. The data consistency status is not required, and the storage system is improved. rate. The data reading method provided by the embodiment of the present invention is described in detail below by using a detailed embodiment.

2 is a schematic flowchart 1 of a data reading method according to an embodiment of the present invention. The execution body of this embodiment is the above-described storage device. As shown in Figure 1, the method includes:

S101. Acquire a read instruction of the host, where the read instruction includes an identifier of the source logical unit number LUN, a first start address of the data to be read, and a first data length.

The source LUN corresponds to a redundant view, and the redundant view includes at least one first record item, and each of the first record items stores redundant storage of at least part of the data in the source LUN. The identity of the target LUN.

When the host reads the data stored in the storage device, the storage device receives the read instruction of the host, where the read command includes the identifier of the source LUN and the first start address and the first data length of the data to be read. The ID of the source LUN can be, for example, the number of the LUN, such as LUN_0, LUN_1, and LUN_N.

In this embodiment, the source LUN corresponds to a redundant view. The redundant view includes at least one first record item, and each of the first record items stores an identifier of a target LUN that performs redundant storage on at least part of the data in the source LUN. The data stored in the storage space corresponding to the target LUN may be redundant data such as mirroring, cloning, active-active, copy, snapshot, synchronous remote replication, and asynchronous remote replication.

A person skilled in the art can understand that all the data in the source LUN can be stored in the target LUN, and some data in the source LUN can be stored. The target LUN can be one or more, for example, the mirror corresponds to a target LUN, and the synchronization is performed. The remote replication corresponds to a target LUN. In this embodiment, the number of target LUNs and the type of redundant data are not particularly limited.

S102. Determine, according to the first start address, the first data length, and the redundant view, a target corresponding to the data to be read, when the data in the storage space corresponding to the source LUN is unreadable. ID of the LUN.

If the disk corresponding to the source LUN has bad sectors or data errors, the storage device cannot read the correct data from the storage space to the host. At this time, the first record corresponding to the data to be read is determined in the redundant view according to the first start address and the first data length, and the first record corresponding to the data to be read is obtained for reading. ID of the target LUN corresponding to the data taken.

In a specific example, the first record item stores an identifier of the target LUN, a second start address of the second redundant data, and a second data length.

If the first start address of the data to be read, the address space corresponding to the first data length, and the address space corresponding to the second start address and the second data length corresponding to the second redundant data, the first record entry The identifier of the target LUN in the target entry is the identifier of the target LUN corresponding to the data to be read.

In a specific implementation process, if the redundant data corresponding to a target record item is not all of the data to be read but a part of the data to be read, the first record item may be traversed until the data to be read is obtained. a plurality of target records, wherein the redundant data corresponding to the plurality of target records can be integrated into the complete data to be read, and the identifiers of the target LUNs in the plurality of target records are all corresponding to the data to be read. ID of the target LUN.

S103. Read first redundant data according to the identifier of the target LUN corresponding to the data to be read, and return the first redundant data to the host.

Specifically, the target LUN corresponding to the data to be read is at least one, and the redundant data is read from the storage space corresponding to each target LUN according to the identifier of the target LUN corresponding to the data to be read, thereby completing the to-be-read The reading of the first redundant data corresponding to the data.

In the prior art, the address is generally represented by hexadecimal, for example 0x1000, and the data length is represented by sector sectors. In the present embodiment, for convenience of explanation, the decimal is taken as an example to illustrate that the hexadecimal is similar to this. For example, if the starting address of the data to be read is 50 and the data length is 250, the ending address is 300. The ID of the target LUN corresponding to the data to be read is LUN_1, LUN_3, and LUN_4, and the data to be read exists. The intersections are [50, 70], [70, 230], [230, 230]; finally, the data of [50, 70] is read from the address space corresponding to LUN_1, and is read from the address space corresponding to LUN_3. [70,200] data, read [200,300] data from LUN_4. Among them, in [50, 70], 50 represents the starting address, 70 represents the ending address, and the like. Those skilled in the art can understand that multiple target record items can also correspond to the identifier of one target LUN.

After the first redundant data is read, the first redundant data is returned to the host, and the first redundant data is written into the corresponding source LUN to complete the repair of the source LUN.

The data reading method provided in this embodiment has a redundant view corresponding to the source LUN, and the redundant view includes at least one first record item, and each of the first record items stores redundancy for at least part of the data in the source LUN. The identifier of the target LUN is stored. When the data in the storage space corresponding to the source LUN cannot be read, the data in the source LUN does not need to be consistent with the data in the target LUN. The first record item in the redundant view corresponding to the data determines the identifier of the target LUN corresponding to the data to be read; and reads the first redundant data according to the identifier of the target LUN corresponding to the data to be read, thereby improving the storage system. Utilization of redundant data.

The specific implementation process of the data reading method provided by the embodiment of the present invention is described in detail below by using a detailed embodiment.

In this embodiment, in order to improve the efficiency of the storage device traversing the first record item and acquiring the target record item, the storage space corresponding to the source LUN may be divided into multiple data blocks, and each data block has its own corresponding Redundant view. In this way, as long as the target data block corresponding to the data to be read is found, the first record item can be traversed only in the target data block, which reduces the traversal time. Correspondingly, S102 in FIG. 1 can be implemented by S1021 and S1022 as follows.

S1021, determining, according to the first start address, the first data length, and an address space of each data block corresponding to the identifier of the source LUN, at least one first target data block corresponding to the data to be read;

Determining, according to the first start address of the data to be read and the first data length, a first address space corresponding to the data to be read. Then, according to the address space of each data block corresponding to the identifier of the source LUN, at least one first target data block corresponding to the data to be read is obtained. The identifier of the source LUN corresponds to an address space of each of the plurality of data blocks in which the storage space is divided.

Those skilled in the art can understand that when the length of the data to be read is short and is just in one data block, there is only one first target data block, when the data to be read is long, or just spans two When there are one or more data blocks, there are multiple first target data blocks.

For example, the first address space is [50, 300], the data length of each data block is 200, and the start address of the data block starts from 0, and the address space of each of the plurality of data blocks is [0, 200], [201, 400], [401, 600], etc., the first address space corresponds to two consecutive data blocks of address space [0, 200], [200, 400].

S1022: Determine, according to the first record item in the redundancy view corresponding to each of the first target data blocks, an identifier of the target LUN corresponding to the data to be read.

As can be seen from the above, the first record item stores an identifier of the target LUN corresponding to the storage space in which the data in the data block is redundantly stored.

If the data in the data block is continuously stored by the storage space corresponding to a target LUN, there may be only one first record in the redundant view. If the data in the data block is distributed, the redundant view includes a plurality of first entries.

Specifically, the first address space may be determined according to the first start address and the first data length; and the second address space corresponding to the first record item in the redundant view corresponding to each first target data block according to the first address space , OK And a target record item corresponding to the second address space that has an intersection with the first address space; and determining, according to each target record item, an identifier of the target LUN corresponding to the data to be read.

The redundant data in the storage space corresponding to the target LUN in each of the first target records is part or all of the data to be read, that is, the data to be read is redundantly stored in one or more target LUNs. Therefore, the target record corresponding to the second address space in which the first address space exists is determined, and the identifiers of all the target LUNs corresponding to the storage space where the redundant data of the data to be read is located are obtained.

For example, the first address space is [50, 300] spanning two consecutive blocks of data. The second address space that intersects the first address space is [30, 70], [60, 200], [200, 310], and the identifiers of the corresponding target LUNs are LUN_1, LUN_3, and LUN_4. It can be seen that the first address space is a subset of consecutive address spaces formed by the above three second address spaces, indicating that the complete data to be read can be obtained.

In the specific implementation process, based on the foregoing embodiment, the priority of each target LUN is also stored in the first record item. FIG. 3 is a corresponding relationship diagram between a data block and a redundant view according to an embodiment of the present invention. As shown in FIG. 3, the storage space corresponding to a single LUN is divided into a plurality of 16 MB data blocks, and each data block corresponds to a plurality of records of the redundant view of the data block. In the present embodiment, for the sake of distinction, the record item is referred to as a first record item. The contents of the entry are described in detail below.

LBA (logical block address): the starting address of redundant data;

LEN(length): the data length of the redundant data;

Target LUN ID: ID of the target LUN corresponding to this entry.

PRI (priority): The priority of the restoration of this entry can be expressed by numbers or letters, for example, the priority is A, and the priority is B.

Among them, the starting address and the data length form an address space of redundant data. In this embodiment, each record item is different, and may be the same priority, but the address space is different, or the address space has an intersection, but the priority of the target LUN is different. However, the address space corresponding to each record item is a subset or a complete set of the address space formed by the start address and the data length of the data block.

The priority is determined in principle based on the relationship between the target LUN and the source LUN. In this embodiment, the target LUN includes mirroring, cloning, active-active, copy, snapshot, synchronous remote replication, asynchronous remote replication, and the like. The recovery priority is from high to low for Mirroring > Clone > Active & Active > Copy > Snapshot > Synchronous Remote Replication > Asynchronous Remote Replication. This example is only an example of the priority. In the specific implementation process, the priority can be set according to the relationship between the target LUN and the source LUN and the performance of the target LUN. This embodiment will not be repeated here.

Therefore, the optimal recovery path can be used to recover data and read data based on the priority.

In a specific implementation process, the third address space for each first target data block is determined according to the first address space and the address space corresponding to each data block. The description of the above embodiment will be continued as an example.

The first address space is [50, 300], and the data length of each data block is 200. The first address space corresponds to two consecutive data blocks of address space [0, 200], [200, 400]. It can be seen that the third address space of the data to be read for the two first target data blocks is [50, 200], [200, 300], respectively. Then, for each first target data block, a target record item is acquired. Here, the third address space [50, 200] will be described in detail as an example. In this embodiment, each of the first entries in the redundant view is arranged in descending order of priority of the target LUN. That is, the first record corresponding to the target LUN with the highest priority is ranked first, and the first record corresponding to the target LUN with the lower priority is the first record. The entries are ranked lower. Therefore, according to the order of priority of the target LUNs in each of the first records in the redundant view, each first record item in the redundant view is traversed, and a second intersection with the third address space is obtained. a target record corresponding to the address space, and the third address space is a subset of the address space formed by the at least one second address space. For the same redundant data, the target LUN in the target record has a higher priority than the other first records. The priority of the target LUN in the entry. The details will be described below with reference to the embodiment shown in FIG.

FIG. 4 is a schematic flowchart 2 of a data reading method according to an embodiment of the present invention. As shown in FIG. 4, the method includes:

S201. Obtain a first first record item in the redundant view.

S202, determining whether the remaining address space of the third address space and the second address space corresponding to the first record have an intersection, and if so, executing step 203, if not, executing step 206;

S203, determining whether the third address space is a subset of the address space formed by the plurality of second address spaces, and if so, executing step 204; if not, executing step 206;

S204. The read redundant data is normal.

S205. Return redundant data to the host, and repair the source LUN.

S206. Obtain a next first record item in the redundant view.

S207, determining whether the next first record item is empty; if not, executing step 202, and if so, executing step 208;

S208. Return a media error to the host.

Specifically, the first first record in the redundant view is obtained, that is, the record with the highest priority. If the second address space corresponding to the first record item is [20, 40], and there is no intersection with the remaining address space [50, 200] of the third address space, the next first record item is obtained, that is, the priority is An advanced record item; if the second address space corresponding to the first record item is [30, 100], there is an intersection [50, 100] with the remaining address space [50, 200] of the third address space, but the third If the address space [50, 200] is not a subset of the second address space [30, 100], the next first record item is obtained; if the second address space corresponding to the next first record item is [80, 200], There is an intersection [101, 200] with the remaining address space [101, 200] of the third address space, and the third address space [50, 200] is a child of the address space [30, 100] formed by at least one second address space. The set reads the redundant data, that is, sequentially reads the redundant data of the intersection portion from the second address space. Then, the redundant data is returned to the host. If all the first entries are traversed, and the third address space is not a subset of the address space formed by the at least one second address space, the media error is returned to the host and cannot be read. Take data.

A person skilled in the art can understand that the redundant data acquired according to the priority is used to obtain the optimal path of the redundant data, that is, the complete redundant data corresponding to the data to be read can be obtained in the shortest time.

On the basis of the foregoing embodiment, the redundant data is obtained from the target LUN according to the redundant view, because the data of the storage space corresponding to the source LUN is synchronized to the storage space corresponding to the target LUN. In this process, the record corresponding to the redundant data is inserted into the redundant view.

The following describes a specific implementation process of inserting a record item corresponding to redundant data into a redundant view by using a specific embodiment.

FIG. 5 is a schematic flowchart of inserting a redundant view record item according to an embodiment of the present invention. As shown in FIG. 5, the method includes:

S301. Obtain an identifier of the source LUN, and a second record to be inserted into the redundant view.

When the data in the storage space corresponding to the source LUN is synchronized to the storage space corresponding to the target LUN, obtain the data. The identifier of the source LUN and the second record to be inserted into the redundant view. The second record item includes a third start address and a third data length of the third redundant data, an identifier of the target LUN corresponding to the third redundant data, and a priority of the target LUN.

S302. Determine, according to the third start address, the third data length, and an address space of each data block corresponding to the identifier of the source LUN, at least one second target data block corresponding to the third redundant data.

The implementation of determining the at least one second target data block in step 302 is similar to the implementation of determining the at least one first target data block in step 102, and details are not described herein again.

S303, according to the priority of the target LUN stored in each first record in the redundant view corresponding to each of the second target data blocks, and the priority of the target LUN stored in the second record, The redundant view corresponding to the second target data block performs processing of inserting the record item.

Specifically, determining, according to the third start address, the third data length, and the address space of each data block, the third record of the third redundant data for each second target data block, where the third record includes The starting address, the fourth data length, the identifier of the target LUN corresponding to the third redundant data, and the priority of the target LUN, according to the priority of each first record in the redundant view for any second target data block Levels from high to low, traversing each of the first entries in the redundant view until the priority of the target LUN in the third entry is higher than the priority of the target LUN in the first entry, Three entries are inserted before the first entry.

In a specific implementation process, when the address space corresponding to the third start address and the third data length in the second record item spans multiple data blocks, the second record item needs to be split into a plurality of third record items. When the third start address in the second record and the address space corresponding to the third data length correspond to only one data block, the second record item is equivalent to the third record item.

When the second record item is split into a plurality of third record items, the address space formed by the third start address and the third data length in the second record item is split into multiple according to the address space of the data block. Address spaces to form a plurality of third entries. In each third entry, the identity of the target LUN and the priority of the target LUN are the same as the second entry in the split.

For the second target data block, each first record item in the redundant view is traversed according to the order of priority of each first record item in the redundant view corresponding to the second target data block from high to low. For example, the priority of the target LUN in the third entry is 3, and the priority of each first entry in the redundant view is 1st, 2nd, 3rd, 4th, and 5th. When traversing to the first record item having the priority level of 4, the third record item is inserted before the first record item.

A person skilled in the art can understand that if there is a first record item with a priority level of 3, it is determined whether the third record item has an intersection with the first record item, and if there is an intersection, the merge process can be performed. For example, if the address space corresponding to the first record with priority level 3 is [50, 100] and the address space corresponding to the third record item is [80, 120], the merge processing is performed, and the above two items are merged into [50, 120], that is, the inserted record item has a data start address of 50 and a data length of 70.

After the host writes the data to the source LUN, the data is synchronized to the target LUN. The source LUN and the target LUN are in the previous cycle before the data is newly written to the source LUN. Synchronous, therefore, there is a historical redundant record record that the target LUN is redundant data of the source LUN. Because the data is newly written, the source LUN data has changed but has not been synchronized to the target LUN, so the target LUN is The data at this location is no longer redundant data, but erroneous data, so when writing data in the source LUN, you need to delete the entries in the redundant view.

The specific process of deleting the entries in the redundant view is described in detail below.

FIG. 6 is a schematic flowchart 1 of deleting a redundant view record item according to an embodiment of the present invention. As shown in FIG. 6, the method includes:

S401. Obtain write information of newly written data in a storage space corresponding to the source LUN.

When the data is newly written in the storage space corresponding to the source LUN, the write information is obtained. The write information includes an identifier of the source LUN, a fourth start address of the newly written data, and a fourth data length.

S402. Determine, according to the fourth start address, the fourth data length, and the address space of each data block corresponding to the identifier of the source LUN, the at least one third target corresponding to the newly written data. data block.

The implementation of determining the at least one third target data block in step 402 is similar to the implementation of determining the at least one first target data block in step 102, and details are not described herein again.

Then, according to the fifth start address and the fifth data length, the fourth start address, and the fourth data length in each fourth record item in the redundant view corresponding to each third target data block, each third target The redundant view corresponding to the data block performs the processing of deleting the record item. For details, refer to step 403 and step 404.

S403. Determine, according to the fourth start address, the fourth data length, and an address space of each data block, a sixth start address and a sixth of the new write data for each third target data block. Data length and fourth address space.

The implementation manner of determining the fourth address space in this embodiment is similar to the implementation manner of the third address space, and details are not described herein again.

S404, traversing each fourth record item in the redundant view, if the fifth address space corresponding to the fourth record item and the fourth address space have an intersection, according to the fifth start address, And a fifth data length, a sixth start address, and a sixth data length, and performing processing for deleting the record item on the redundant view corresponding to the third target data block.

In a specific implementation process, if the fifth address space in the fourth record item and the fifth address space formed by the fifth data length have an intersection, the partial data corresponding to the fourth record item is the address space before the update. Redundant data is not redundant data corresponding to newly written data, so it needs to be deleted.

The specific implementation process of step 404 can be seen in FIG. 7. FIG. 7 is a schematic flowchart 2 of deleting a redundant view record item according to an embodiment of the present invention. As shown in FIG. 7, the method includes:

S501. Obtain a first fourth record item in the redundant view.

S502, determining whether there is an intersection of the fourth address space corresponding to the fourth record space and the fourth record item; if yes, executing S502, if not; executing S507;

S503, establishing a first decomposition space R1 and a second decomposition space R2 according to the fifth start address, the fifth data length, the sixth start address, and the sixth data length;

Among them, the starting address and data length of R1 are as follows:

R1_lba=D5; R1_len=D6-D5;

Among them, the starting address and data length of R2 are as follows:

R2_lba=D6+L6; R2_len=D5+L5-D6-L6, the R1_lba is the starting address of the first decomposition space, the R1_len is the data length of the first decomposition space, and the R2_lba is The starting address of the second decomposition space, the R2_len is the data length of the second decomposition space, the D5 is the fifth start address, the D6 is the sixth start address, and the L5 is the fifth Data length, the L6 is a sixth data length;

S504. If the data length of the R1 is greater than 0, and the data length of the R2 is greater than 0, deleting the fourth record item, and inserting the fifth record item and the sixth record item, where the fifth record item is Start address is D5, data length Degree is D6-D5, the starting address in the sixth record item is D6+L6, and the data length is D5+L5-D6-L6;

S505. If the data length of the R1 is greater than 0, and the data length of the R2 is less than or equal to 0, deleting the fourth record item, and inserting a sixth record item, where the start address in the sixth record item is D6+L6, the data length is D5+L5-D6-L6;

S506. If the data length of the R1 is less than or equal to 0, and the data length of the R2 is greater than 0, delete the fourth record item, and insert a fifth record item, where the start address in the fifth record item is D5, the data length is D6-D5;

S507. Obtain a next fourth record item in the redundant view.

S508, determining whether the next fourth record item is empty, and if so, executing S509, if not, executing S502;

S509, the return parameter is wrong.

Those skilled in the art can understand that S504 and S506 are one of the relationships, that is, the three cases cannot exist at the same time, and only one of the three can exist. The three cases are respectively illustrated by examples.

The traversal process of this embodiment traverses each record item in the redundant view until all record item traversal is completed.

For S504, the newly written data is for the starting address of the data block D6=50, the data length L6=100, the fourth address space [50, 150]; the starting address of the fourth record item D5=20, the data length L5 =150, the fifth address space [20, 170], delete the fourth record item, insert the fifth record item, the start address of the fifth record item is 20, the data length is 30, and the sixth record item is inserted, the sixth The starting address of the entry is 150 and the data length is 20.

For S505, the newly written data is for the starting address of the data block D6=50, the data length L6=100, the fourth address space [50, 150]; the starting address of the fourth record item D5=70, the data length L5 =130, the fifth address space [70, 200], delete the fourth record item, insert the sixth record item, the start address of the sixth record item is 150, and the data length is 50.

For S506, the newly written data is for the starting address of the data block D6=50, the data length L6=100, the fourth address space [50, 150]; the starting address of the fourth record item D5=20, the data length L5 = 60, the fifth address space [20, 80], delete the fourth record item, insert the fifth record item, the start address of the fifth record item is 20, and the data length is 30.

In summary, the data reading method provided by the embodiment of the present invention can avoid the problem that the upper layer error causes the service interruption due to bad sectors or partial erroneous data of the hard disk, and the LUN is dispersed in the storage system through the redundant view mode. The redundant data blocks in various places are organized, and the data can be read in a small range to complete the automatic repair of bad track data or error data, thereby improving the data reliability of the source LUN.

The solution provided by the embodiment of the present invention is introduced for the functions implemented by the storage device. It can be understood that the storage device includes corresponding hardware structures and/or software modules for performing the respective functions in order to implement the above functions. The embodiments of the present invention can be implemented in a combination of hardware or hardware and computer software in combination with the elements and algorithm steps of the various examples described in the embodiments disclosed herein. Whether a function is implemented in hardware or computer software to drive hardware depends on the specific application and design constraints of the solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the technical solutions of the embodiments of the present invention.

The embodiment of the present invention may divide the function module into the storage device according to the foregoing method example. For example, each function module may be divided according to each function, or two or more functions may be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of a software function module. It should be noted that the division of the module in the embodiment of the present invention is schematic, and is only a logical function division, and the actual implementation may have another division manner.

FIG. 8 is a schematic structural diagram 2 of a storage device according to an embodiment of the present invention. As shown in FIG. 8, the storage device 10 includes a receiving module 11, a processing module 12, and a sending module 13. among them

The receiving module 11 is configured to acquire a read command of the host, where the read command includes an identifier of the source logical unit number LUN, a first start address of the data to be read, and a first data length, where the source LUN corresponds to redundancy. The redundant view includes at least one first record item, and each of the first record items stores an identifier of a target LUN that performs redundancy storage on at least part of the data in the source LUN;

The processing module 12 is configured to determine, according to the first start address, the first data length, and the redundant view, that the data to be read is determined when the data in the storage space corresponding to the source LUN is unreadable The identifier of the target LUN corresponding to the data, and the first redundant data is read according to the identifier of the target LUN corresponding to the data to be read;

The sending module 13 is configured to return the first redundant data to the host.

Optionally, the storage space corresponding to the source LUN is divided into multiple data blocks, where each of the data blocks respectively has a redundant view; the processing module 12 is specifically configured to:

Optionally, the first record item further stores a second start address and a second data length of the second redundant data, and the second start address and the second address formed by the second data length Space is a subset of the address space of the data block;

The processing module 12 is specifically configured to:

Optionally, the priority of each target LUN is also stored in the first record item;

The processing module 12 is specifically configured to:

Optionally, the processing module 12 is further configured to:

Optionally, the processing module 12 is specifically configured to:

Optionally, the processing module 12 is further configured to:

Optionally, the processing module 12 is specifically configured to:

The starting address and data length of the R1 are as follows:

R1_lba=D5; R1_len=D6-D5;

The starting address and data length of the R2 are as follows:

R2_lba=D6+L6; R2_len=D5+L5-D6-L6, the D5 is the fifth start address, the D6 is the sixth start address, the L5 is the fifth data length, and the L6 is the first Six data lengths;

Optionally, the processing module 12 is specifically configured to:

If the data length of the R1 is greater than 0, and the data length of the R2 is greater than 0, the fourth record is deleted, and the fifth record and the sixth record are inserted, and the start of the fifth record The address is D5 and the data length is D6-D5, the starting address in the sixth record is D6+L6, and the data length is D5+L5-D6-L6;

The storage device provided in this embodiment may be used to perform the technical solution of the foregoing method embodiment, and the implementation principle and the technical effect are similar.

In a specific implementation of the foregoing storage device, the receiving module and the sending module may be implemented as a communication interface, and the processing module may be implemented as a processor, and the data and program code may be stored in the memory, and controlled by the processor according to the corresponding program instruction. .

FIG. 9 is a schematic structural diagram 3 of a storage device according to an embodiment of the present invention. As shown in FIG. 9, the storage device 20 includes at least one processor 21, a memory 22, and a communication interface 23. The at least one processor 21, the memory 22, and the communication interface 23 are each connected by a bus 24; the memory 22 stores computer execution instructions; the at least one processor 21 executes computer execution instructions stored by the memory 22. The process of the storage device 20 obtaining the read command of the host through the communication interface 43, executing the above-described method embodiment according to the read command, and returning correct data to the host.

In the specific implementation of the foregoing storage device, it should be understood that the processor 21 may be a central processing unit (English: Central Processing Unit, CPU for short), or may be other general-purpose processors, digital signal processors (English: Digital Signal Processor) , referred to as: DSP), ASIC (English: Application Specific Integrated Circuit, referred to as: ASIC). The general purpose processor may be a microprocessor or the processor or any conventional processor or the like. The steps of the method disclosed in the embodiments of the present invention may be directly implemented as a hardware processor, or may be performed by a combination of hardware and software modules in the processor.

The memory 22 may be any one or any combination of the following: a solid state drive (SSD), a mechanical hard disk, a magnetic disk, a disk array, and the like.

The communication interface 23 may be an interface such as an interface card that establishes a connection with the host.

The bus 24 may include an address bus, a data bus, a control bus, etc., for convenience of representation, the bus is indicated by a thick line in FIG. The bus may be any one or any combination of the following: an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, and an extended industry standard structure ( Extended Industry Standard Architecture (EISA) bus and other devices for wired data transmission.

In addition, the embodiment of the present invention further provides a computer readable storage medium, where the computer readable storage medium stores computer execution instructions, and when at least one processor of the storage device executes the computer execution instruction, the storage device executes the foregoing various It is possible to design a data reading method.

A computer program product is also provided in an embodiment of the invention, the computer program product comprising computer executed instructions stored in a computer readable storage medium. At least one processor of the storage device can read the computer-executable instructions from a computer readable storage medium, and the at least one processor executes the computer-executable instructions to cause the storage device to implement the data reading method provided by various possible designs in the foregoing method embodiments .

One of ordinary skill in the art will appreciate that all or part of the steps to implement the various method embodiments described above may be accomplished by hardware associated with the program instructions. The aforementioned program can be stored in a computer readable storage medium. The course When the sequence is executed, the steps including the foregoing method embodiments are performed; and the foregoing storage medium includes various media that can store program codes, such as a ROM, a RAM, a magnetic disk, or an optical disk.

Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, and are not intended to be limiting; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that The technical solutions described in the foregoing embodiments may be modified, or some or all of the technical features may be equivalently replaced; and the modifications or substitutions do not deviate from the technical solutions of the embodiments of the present invention. range.

Claims

A data reading method, comprising:

Obtaining a read instruction of the host, where the read command includes an identifier of the source logical unit number LUN, a first start address of the data to be read, and a first data length, where the source LUN corresponds to a redundant view, and the redundancy The remaining view includes at least one first record item, and each of the first record items stores an identifier of a target LUN that performs redundancy storage on at least part of the data in the source LUN;

Determining, according to the first start address, the first data length, and the redundant view, the target LUN corresponding to the data to be read, when the data in the storage space corresponding to the source LUN is unreadable. Identification

And reading, according to the identifier of the target LUN corresponding to the data to be read, the first redundant data, and returning the first redundant data to the host.
The method according to claim 1, wherein the storage space corresponding to the source LUN is divided into a plurality of data blocks, wherein each of the data blocks respectively corresponds to a redundant view;

Determining, according to the first start address, the first data length, and the redundant view, the identifier of the target LUN corresponding to the data to be read, including:

Determining, according to the first start address, the first data length, and an address space of each data block corresponding to the identifier of the source LUN, at least one first target data block corresponding to the data to be read;

And determining, according to the first record item in the redundant view corresponding to each of the first target data blocks, an identifier of the target LUN corresponding to the to-be-read data.
The method according to claim 2, wherein the first record item further stores a second start address and a second data length of the second redundant data, the second start address and the The second address space formed by the second data length is a subset of the address space of the data block;

Determining, according to the first record item in the redundancy view corresponding to each of the first target data blocks, an identifier of the target LUN corresponding to the data to be read, including:

Determining a first address space according to the first start address and the first data length;

Determining, according to the first address space, the second address space corresponding to the first record item in the redundant view corresponding to each of the first target data blocks, corresponding to the second address space that has an intersection with the first address space a target record entry, and the first address space is a subset of address spaces formed by the plurality of the second address spaces;

And determining, according to each of the target record items, an identifier of the target LUN corresponding to the data to be read.
The method according to claim 3, wherein the first record item further stores a priority of each target LUN;

Determining, according to the first address space, the second address space corresponding to the first record item in the redundant view of each of the first target data blocks, determining a second address space that intersects with the first address space Corresponding target records, including:

Determining, according to the first address space and an address space of each data block, the third address space of the data to be read for each first target data block;

For each of the first target data blocks, traversing each of the first records in the redundant view according to a priority of the target LUNs in each of the first entries in the redundant view from high to low Obtaining a target record corresponding to the second address space where the third address space intersects, and the third address space is a subset of the address space formed by at least one of the second address spaces, for the same redundancy Data, the target LUN in the target record item has a higher priority than the target LUN in the other first record item.
The method of claim 2, wherein the method further comprises:

Obtaining an identifier of the source LUN, a second record to be inserted into the redundant view, where the second record includes a third start address and a third data length of the third redundant data, and the third redundancy The identifier of the target LUN corresponding to the data and the priority of the target LUN;

Determining, according to the third start address, the third data length, and the address space of each data block corresponding to the identifier of the source LUN, the at least one second target data block corresponding to the third redundant data;

And according to the priority of the target LUN stored in each first record in the redundant view corresponding to each of the second target data blocks, and the priority of the target LUN stored in the second record, The redundant view corresponding to the two target data blocks is processed by inserting the record items.
The method according to claim 5, wherein the priority of the target LUN stored in each of the first entries in the redundant view corresponding to each of the second target data blocks and the second record The priority of the target LUN stored in the item, and the processing of inserting the record item into the redundant view corresponding to each of the second target data blocks, including:

Determining, according to the third start address, the third data length, and an address space of each data block, a third record of the third redundant data for each second target data block, the third The record entry includes a fourth start address, a fourth data length, an identifier of the target LUN corresponding to the third redundant data, and a priority of the target LUN;

For each second target data block, traversing each of the redundant views according to a priority of each first record in the redundant view corresponding to the second target data block from highest to lowest a record item is inserted before the first record item until the priority of the target LUN in the third record item is higher than the priority of the target LUN in the first record item.
The method of claim 2, wherein the method further comprises:

Obtaining the write information of the newly written data of the storage space corresponding to the source LUN, where the write information includes an identifier of the source LUN, a fourth start address of the newly written data, and a fourth data length;

Determining, according to the fourth start address, the fourth data length, and the address space of each data block corresponding to the identifier of the source LUN, the at least one third target data block corresponding to the newly written data. ;

And according to the fifth start address and the fifth data length, the fourth start address, and the fourth data length in each fourth record item in the redundant view corresponding to each of the third target data blocks, The redundant view corresponding to each of the third target data blocks performs processing for deleting the record items.
The method according to claim 7, wherein the fifth starting address and the fifth data length of each of the fourth entries in the redundant view corresponding to each of the third target data blocks are The fourth start address and the fourth data length are processed, and the redundant view corresponding to each of the third target data blocks is deleted, including:

Determining, according to the fourth start address, the fourth data length, and an address space of each data block, a sixth start address and a sixth data length of the new write data for each third target data block. And a fourth address space;

Traversing each fourth record item in the redundant view, if the fifth address space corresponding to the fourth record item and the fourth address space have an intersection, according to the fifth start address, the fifth The data length, the sixth start address, and the sixth data length are processed by deleting the record item in the redundant view corresponding to the third target data block.
The method according to claim 8, wherein said according to said fifth starting address, said fifth number And processing the deletion record item in the redundant view corresponding to the third target data block according to the length, the sixth start address, and the sixth data length, including:

Establishing a first decomposition space R1 and a second decomposition space R2 according to the fifth start address, the fifth data length, the sixth start address, and the sixth data length;

The starting address and data length of the R1 are as follows:

R1_lba=D5; R1_len=D6-D5;

The starting address and data length of the R2 are as follows:

R2_lba=D6+L6; R2_len=D5+L5-D6-L6, wherein R1_lba is a starting address of the first decomposition space, the R1_len is a data length of the first decomposition space, and the R2_lba For the start address of the second decomposition space, the R2_len is the data length of the second decomposition space, the D5 is the fifth start address, the D6 is the sixth start address, and the L5 is a fifth data length, wherein the L6 is a sixth data length;

And processing the deleted record item on the redundant view corresponding to the third target data block according to the data length of the R1 and the data length of the R2.
The method according to claim 9, wherein the processing of deleting a record item is performed on the redundant view corresponding to the third target data block according to the data length of the R1 and the data length of the R2, include:

If the data length of the R1 is greater than 0, and the data length of the R2 is greater than 0, the fourth record is deleted, and the fifth record and the sixth record are inserted, and the start of the fifth record The address is D5, the data length is D6-D5, the starting address in the sixth record is D6+L6, and the data length is D5+L5-D6-L6;

If the data length of the R1 is greater than 0, and the data length of the R2 is less than or equal to 0, the fourth record is deleted, and the sixth record is inserted, and the start address in the sixth record is D6+ L6, the data length is D5+L5-D6-L6;

If the data length of the R1 is less than or equal to 0, and the data length of the R2 is greater than 0, the fourth record is deleted, and the fifth record is inserted, and the start address in the fifth record is D5. The data length is D6-D5.
A storage device, comprising:

a receiving module, configured to acquire a read command of the host, where the read command includes an identifier of the source logical unit number LUN, a first start address of the data to be read, and a first data length, where the source LUN corresponds to redundancy View, the redundant view includes at least one first record item, and each of the first record items stores an identifier of a target LUN that performs redundancy storage on at least part of the data in the source LUN;

a processing module, configured to determine, according to the first start address, the first data length, and the redundant view, the data to be read, when the data in the storage space corresponding to the source LUN is unreadable The identifier of the target LUN is read, and the first redundant data is read according to the identifier of the target LUN corresponding to the data to be read;

And a sending module, configured to return the first redundant data to the host.
The storage device according to claim 11, wherein the storage space corresponding to the source LUN is divided into a plurality of data blocks, wherein each of the data blocks respectively has a redundant view; Used for:

Determining, according to the first start address, the first data length, and an address space of each data block corresponding to the identifier of the source LUN, at least one first target data block corresponding to the data to be read;

And determining, according to the first record item in the redundant view corresponding to each of the first target data blocks, an identifier of the target LUN corresponding to the to-be-read data.
The storage device according to claim 12, wherein said first record entry further stores a second start address and a second data length of the second redundant data, wherein the second address space formed by the second start address and the second data length is a subset of an address space of the data block;

The processing module is specifically configured to:

Determining a first address space according to the first start address and the first data length;

Determining, according to the first address space, the second address space corresponding to the first record item in the redundant view corresponding to each of the first target data blocks, corresponding to the second address space that has an intersection with the first address space a target record entry, and the first address space is a subset of address spaces formed by the plurality of the second address spaces;

And determining, according to each of the target record items, an identifier of the target LUN corresponding to the data to be read.
The storage device according to claim 13, wherein the first record item further stores a priority of each target LUN;

The processing module is specifically configured to:

Determining, according to the first address space and an address space of each data block, the third address space of the data to be read for each first target data block;

For each of the first target data blocks, traversing each of the first records in the redundant view according to a priority of the target LUNs in each of the first entries in the redundant view from high to low Obtaining a target record corresponding to the second address space where the third address space intersects, and the third address space is a subset of the address space formed by at least one of the second address spaces, for the same redundancy Data, the target LUN in the target record item has a higher priority than the target LUN in the other first record item.
The storage device according to claim 12, wherein the processing module is further configured to:

Obtaining an identifier of the source LUN, a second record to be inserted into the redundant view, where the second record includes a third start address and a third data length of the third redundant data, and the third redundancy The identifier of the target LUN corresponding to the data and the priority of the target LUN;

Determining, according to the third start address, the third data length, and the address space of each data block corresponding to the identifier of the source LUN, the at least one second target data block corresponding to the third redundant data;

And according to the priority of the target LUN stored in each first record in the redundant view corresponding to each of the second target data blocks, and the priority of the target LUN stored in the second record, The redundant view corresponding to the two target data blocks is processed by inserting the record items.
The storage device according to claim 15, wherein the processing module is specifically configured to:

Determining, according to the third start address, the third data length, and an address space of each data block, a third record of the third redundant data for each second target data block, the third The record entry includes a fourth start address, a fourth data length, an identifier of the target LUN corresponding to the third redundant data, and a priority of the target LUN;

For each second target data block, traversing each of the redundant views according to a priority of each first record in the redundant view corresponding to the second target data block from highest to lowest a record item is inserted before the first record item until the priority of the target LUN in the third record item is higher than the priority of the target LUN in the first record item.
The storage device according to claim 12, wherein the processing module is further configured to:

Obtaining the write information of the newly written data of the storage space corresponding to the source LUN, where the write information includes an identifier of the source LUN, a fourth start address of the newly written data, and a fourth data length;

Corresponding to the fourth start address, the fourth data length, and the identifier of the source LUN of the newly written data. Determining, by the address space of each data block, at least one third target data block corresponding to the newly written data;

And according to the fifth start address and the fifth data length, the fourth start address, and the fourth data length in each fourth record item in the redundant view corresponding to each of the third target data blocks, The redundant view corresponding to each of the third target data blocks performs processing for deleting the record items.
The storage device according to claim 17, wherein the processing module is specifically configured to:

Determining, according to the fourth start address, the fourth data length, and an address space of each data block, a sixth start address and a sixth data length of the new write data for each third target data block. And a fourth address space;

Traversing each fourth record item in the redundant view, if the fifth address space corresponding to the fourth record item and the fourth address space have an intersection, according to the fifth start address, the fifth The data length, the sixth start address, and the sixth data length are processed by deleting the record item in the redundant view corresponding to the third target data block.
The storage device according to claim 18, wherein the processing module is specifically configured to:

Establishing a first decomposition space R1 and a second decomposition space R2 according to the fifth start address, the fifth data length, the sixth start address, and the sixth data length;

The starting address and data length of the R1 are as follows:

R1_lba=D5; R1_len=D6-D5;

The starting address and data length of the R2 are as follows:

R2_lba=D6+L6; R2_len=D5+L5-D6-L6, wherein R1_lba is a starting address of the first decomposition space, the R1_len is a data length of the first decomposition space, and the R2_lba For the start address of the second decomposition space, the R2_len is the data length of the second decomposition space, the D5 is the fifth start address, the D6 is the sixth start address, and the L5 is a fifth data length, wherein the L6 is a sixth data length;

And processing the deleted record item on the redundant view corresponding to the third target data block according to the data length of the R1 and the data length of the R2.
The storage device according to claim 19, wherein the processing module is specifically configured to:

If the data length of the R1 is greater than 0, and the data length of the R2 is greater than 0, the fourth record is deleted, and the fifth record and the sixth record are inserted, and the start of the fifth record The address is D5, the data length is D6-D5, the starting address in the sixth record is D6+L6, and the data length is D5+L5-D6-L6;

If the data length of the R1 is greater than 0, and the data length of the R2 is less than or equal to 0, the fourth record is deleted, and the sixth record is inserted, and the start address in the sixth record is D6+ L6, the data length is D5+L5-D6-L6;

If the data length of the R1 is less than or equal to 0, and the data length of the R2 is greater than 0, the fourth record is deleted, and the fifth record is inserted, and the start address in the fifth record is D5. The data length is D6-D5.
A storage device, characterized in that the storage device comprises at least one processor and a memory;

The memory stores a computer execution instruction;

The at least one processor executes the computer-executed instructions stored in the memory such that the storage device performs the data reading method of any one of claims 1 to 10.