WO2021135280A1

WO2021135280A1 - Data check method for distributed storage system, and related apparatus

Info

Publication number: WO2021135280A1
Application number: PCT/CN2020/110952
Authority: WO
Inventors: 冯龙; 何营; 白战豪
Original assignee: 浪潮电子信息产业股份有限公司
Priority date: 2019-12-31
Filing date: 2020-08-25
Publication date: 2021-07-08
Also published as: CN111176885A

Abstract

A data check method for a distributed storage system, and a related apparatus. The method comprises: reading target data from a hard disk, and calculating a CRC value of data of each preset check interval length in the target data, and obtaining a first CRC value; when the target data are read and written from a database, calculating a second CRC value obtained from the CRC value of the data of each preset check interval length in the target data; respectively comparing each first CRC value with the corresponding second CRC value; and if the first CRC value is inconsistent with the corresponding second CRC value, determining that the target data in the hard disk has an error. According to the data check method, the anomaly position of data can be accurately identified, and an effective data check can be guaranteed.

Description

Data verification method and related device of distributed storage system

This application claims the priority of the Chinese patent application filed to the Chinese Patent Office on December 31, 2019, with the application number 201911411044.2, and the title of the invention "A data verification method and related device for a distributed storage system", all of which The content is incorporated in this application by reference.

Technical field

This application relates to the field of distributed storage technology, in particular to a data verification method of a distributed storage system; it also relates to a data verification device, equipment and computer-readable storage medium of a distributed storage system.

Background technique

Mass distributed storage systems usually consist of thousands of hard disks and dozens or hundreds of storage nodes. Each hard disk is managed by an independent storage engine, that is, managed by an independent process. If there are errors in the stored data due to hard disk hardware errors, firmware defects, power supply temperature, etc., it is usually difficult to obtain such anomalies in a timely and effective manner. In a multi-copy distributed storage system, if the wrong data is not found and recovered in time, it may lead to the risk of data loss or data inconsistency. Therefore, it is particularly important to verify the data and find the wrong data in time. At present, the technical solution for data verification is to calculate the CRC (Cyclic Redundancy Check) check value of the data of multiple copies, and compare the CRC check values between the copies. When the CRC check value is not equal, it is considered that an error has occurred in the data of a certain copy. However, with the above verification method, in the case of two copies, if the CRC check value of the data of the two copies is different, it can only be judged that the data of one copy has an error, but it is impossible to determine which one. There is an error in the data of the copy. In addition, obtaining the check value of the data of the two copies from the two storage nodes for comparison is high in complexity. If a node where a copy is located fails, such as power failure, data verification cannot be effectively performed at this time.

Therefore, how to solve the above technical defects has become an urgent technical problem to be solved by those skilled in the art.

Summary of the invention

The purpose of this application is to provide a data verification method and related device for a distributed storage system, which can accurately identify the location of data abnormalities and ensure the effective execution of data verification.

To solve the above technical problems, this application provides a data verification method for a distributed storage system, including:

Reading the target data from the hard disk, and calculating the CRC check value of the data of each preset check interval length in the target data to obtain the first CRC check value;

When reading and writing the target data from the database, calculating the second CRC check value obtained by calculating the CRC check value of the data of each preset check interval length in the target data;

Respectively comparing each of the first CRC check values with the corresponding second CRC check values;

If the first CRC check value is inconsistent with the corresponding second CRC check value, it is determined that an error has occurred in the target data in the hard disk.

Optionally, when writing the target data, calculating the CRC check value of the data of each preset check interval length in the target data includes:

If the start position and the end position of the write interval corresponding to the target data are integer multiples of the length of the preset check interval, the CRC of the data of each preset check interval length in the target data is directly calculated. Value.

If the start position and/or end position of the write interval of the target data is not an integer multiple of the calculated length of the preset check value, then read the start position from the hard disk before the preset It is assumed that the written data from the position that is an integer multiple of the length of the check interval to the start position, and/or the preset check is read from the end position to the end position from the hard disk The written data at the position that is an integer multiple of the interval length;

Calculate the CRC check value of the data of each preset check interval length in the written data and the target data.

Optionally, storing the second CRC check value in the database includes:

The second CRC check value and the offset in the object of the data corresponding to the second CRC check value are stored in the database in the form of a map.

Optionally, the reading target data from the hard disk includes:

The target data is read from the hard disk when a read request is received or when an active verification is triggered.

Optionally, when receiving a read request, reading the target data from the hard disk and calculating the CRC check value of the data of each preset check interval length in the target data includes:

Determining the start position and the end position of the read interval corresponding to the target data according to the read request;

If the start position and the end position of the reading interval corresponding to the target data are integer multiples of the length of the preset check interval, directly read and calculate the data of each preset check interval length in the target data CRC check value;

If the start position and/or end position of the read interval of the target data is not an integer multiple of the calculated length of the preset check value, then read the start position from the hard disk before the preset Set the data from the position of an integer multiple of the length of the check interval to the start position and the target data, and/or read the end position to the end position as an integer of the preset check interval length Calculate the CRC check value of the read data and the data of each preset check interval length in the target data.

Optionally, it also includes:

When an error occurs in the target data, the target data is added to the reconstruction queue for data reconstruction.

To solve the above technical problems, this application also provides a data verification device for a distributed storage system, including:

The calculation module is used to read the target data from the hard disk, and calculate the CRC check value of the data of each preset check interval length in the target data to obtain the first CRC check value;

A reading module, which is used to calculate the second CRC check value obtained by calculating the CRC check value of the data of each preset check interval length in the target data when reading and writing the target data from the database;

The comparison module is configured to compare each of the first CRC check values with the corresponding second CRC check values;

The determining module is configured to determine that an error occurs in the target data in the hard disk if the first CRC check value is inconsistent with the corresponding second CRC check value.

Memory, used to store computer programs;

The processor is used to implement the steps of the data verification method of the distributed storage system as described above when the computer program is executed.

In order to solve the above technical problems, the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, realizes the above-mentioned distributed storage system. The steps of the data verification method.

The data verification method of the distributed storage system provided by this application includes reading target data from a hard disk, and calculating the CRC check value of the data of each preset check interval length in the target data, to obtain the first CRC check When the target data is read and written from the database, the second CRC check value obtained by calculating the CRC check value of the data of each preset check interval length in the target data; respectively The first CRC check value is compared with the corresponding second CRC check value; if the first CRC check value is inconsistent with the corresponding second CRC check value, it is determined that the hard disk An error occurred in the target data.

It can be seen that, compared to the technical solution of data verification based on the CRC check value of the data in multiple copies, the data verification method provided in this application calculates the CRC check value of the data to be written whenever data is written. , And stored in the database. When subsequent data verification is performed, the CRC check value of the data to be checked is calculated, and further compared with the corresponding CRC check value stored in the database, so as to determine whether the data has an error. The data verification method adopts the data verification method in which the storage engine independently performs data verification. Data verification can be completed without using the data in the copies of other nodes. It can not only accurately identify the location of abnormal data, but also It can ensure the effective execution of data verification.

The data verification device, equipment, and computer-readable storage medium of the distributed storage system provided in this application all have the above technical effects.

Description of the drawings

In order to more clearly explain the technical solutions in the embodiments of the present application, the following will briefly introduce the prior art and the drawings needed in the embodiments. Obviously, the drawings in the following description are only some of the present application. Embodiments, for those of ordinary skill in the art, without creative work, other drawings can be obtained based on these drawings.

FIG. 1 is a schematic flowchart of a data verification method of a distributed storage system provided by an embodiment of the application;

2 is a schematic diagram of calculating a CRC check value provided by an embodiment of the application;

FIG. 3 is another schematic diagram of calculating a CRC check value provided by an embodiment of the application;

4 is a schematic diagram of a data verification device of a distributed storage system provided by an embodiment of the application;

FIG. 5 is another schematic diagram of calculating a CRC check value provided by an embodiment of the application.

Detailed ways

The core of this application is to provide a data verification method and related device for a distributed storage system, which can accurately identify the location of data abnormalities and ensure the effective execution of data verification.

In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

Please refer to FIG. 1. FIG. 1 is a schematic flowchart of a data verification method of a distributed storage system according to an embodiment of the application; referring to FIG. 1, the data verification method includes:

S101: Read the target data from the hard disk, and calculate the CRC check value of the data of each preset check interval length in the target data to obtain the first CRC check value;

Specifically, this application provides a data verification method that uses a storage engine to independently perform data verification. After starting the data check, read the data that needs to be checked from the hard disk, that is, the above target data, and then calculate the CRC check value of the data of each preset check interval length in the target data, and obtain one or more The first CRC check value. Among them, there is no data duplication among the data in the target data for calculating the CRC check value. The so-called preset check interval length refers to the length of the data for calculating the CRC check value. For example, the preset check value calculation length is 4KB, which means the calculated CRC check value of data with a length of 4KB. If the length of the target data is 8KB , Then two first CRC check values can be calculated at this time. Of course, the specific value of the length of the preset check interval is not limited in this application, and can be set differently according to actual needs. In addition, the specific calculation method for calculating the CRC check value of the data is not described in detail here in this application, and the existing related technology can be referred to.

S102: When reading and writing target data from the database, calculate the second CRC check value obtained by calculating the CRC check value of each preset check interval length data in the target data;

Specifically, whenever data is written, the CRC check value of each preset check interval length in the data to be written is calculated before the data is written to the hard disk to obtain the second CRC check value, and the calculated second CRC check value is obtained. The CRC check value is stored in the database. On the basis of the first CRC check value calculated by performing step S101, the second CRC check value calculated and stored in the database when the target data is written is further read from the database, and subsequently based on each first CRC check value and The corresponding second CRC check value determines whether the target data has an error.

Wherein, in a specific implementation manner, when writing the target data, calculating the CRC check value of the data of each preset check interval length in the target data includes: if the start position and the end of the write interval corresponding to the target data If the position is an integer multiple of the length of the preset check interval, the CRC check value of the data of each preset check interval length in the target data is directly calculated.

Specifically, this embodiment corresponds to the case where the target data is aligned data. The so-called aligned data refers to data in which the start position and the end position of the writing interval in the data buffer are both integral multiples of the length of the preset check interval. When the target data is aligned data, at this time, the target data is directly divided by the preset check value calculation length as a unit to obtain multiple data fragments, and the CRC check value of each data fragment is calculated.

For example, referring to Figure 2, taking the preset check interval length of 4KB as an example, the start position of the data write interval is 4KB, the end position is 16KB, and the write length is 12KB. The target data is divided into 3 data fragments, and the CRC check value of each data fragment is calculated respectively to obtain 3 first CRC check values: CRC1 to CRC3.

In another specific embodiment, when writing the target data, calculating the CRC check value of the data of each preset check interval length in the target data includes: if the writing interval of the target data is If the starting position and/or ending position is not an integer multiple of the calculated length of the preset check value, then the position that is an integer multiple of the length of the preset check interval before the starting position is read from the hard disk The written data to the starting position, and/or the written data from the ending position to the position that is an integer multiple of the length of the preset check interval after the ending position is read from the hard disk Input data; Calculate the CRC check value of the data of each preset check interval length in the written data and the target data.

Specifically, this embodiment corresponds to the case where the target data is non-aligned data. The so-called non-aligned data refers to data whose starting position and/or ending position of the writing interval in the data buffer is not an integer multiple of the length of the preset check interval. When the target data is unaligned data, the data is first read from the hard disk to the data buffer to fill in the unaligned part. Specifically, if the start position of only the write interval is not an integer multiple of the length of the preset check interval, then the position that is an integer multiple of the preset check interval length before the start position is read from the hard disk to the start position The data has been written. If the end position of the write-only interval is not an integer multiple of the calculated length of the preset check value, the data written from the end position to the position that is an integer multiple of the preset check interval length after the end position is read from the hard disk. If neither the start position nor the end position of the write interval is an integer multiple of the length of the preset check interval, the position that is an integer multiple of the preset check interval length before the start position is read from the hard disk to the start position The written data and the written data from the hard disk from the end position to the position that is an integer multiple of the length of the preset check interval after the end position is read from the hard disk. Furthermore, taking the written data and the target data as a whole, the CRC check value of the data of each preset check interval length is calculated. Among them, it is preferable to read from the hard disk the minimum number of data that can fill in the misaligned part.

For example, referring to Figure 3, taking the preset check interval length of 4KB as an example, the start position of the data write interval is 3KB, the end position is 15KB, and the write length is 12KB. The start position and the end position are not integral multiples of the length of the preset check interval, so first read the written data from 0KB to 3KB and the written data from 15KB to 16KB from the hard disk, and then use 0KB The data from position to 16KB is a whole data, and the whole data is divided into 4 data fragments, and the second CRC check value of the data from 0KB to 4KB is calculated, and the second of the data from 4KB to 8KB is calculated. The CRC check value, the second CRC check value of the data from the 8KB position to the 12KB position, and the second CRC check value of the data from the 12KB position to the 16KB position, thereby obtaining four second CRC check values: CRC1 to CRC4.

After the second CRC check value is calculated, the calculated second CRC check value is further stored in the database, and the target data is written to the hard disk.

The storing of the second CRC check value in the database includes: the second CRC check value and the offset of the data corresponding to the second CRC check value in the object are stored in the database in the form of a map.

Specifically, the data on the hard disk includes business data and database data that records index information and metadata information. Business data is stored on the hard disk in units of objects, and the metadata, index information, and extended attributes of the objects are stored in the database. As shown in Fig. 4, in order to meet the requirement of data self-verification, this embodiment adds content called verification data to the object metadata to record the verification information of the data stored on the disk for a certain object. When an object writes data, the second CRC check value of the data of each preset check interval length is calculated and recorded in the Key-Value database, where Key is the object name and Value is the object element Data information. And the CRC check value of the object and the offset of the data corresponding to the CRC check value in the object are recorded in the database in the form of a map. The organization of the map is as follows:

Key: offset; characterizes the offset of the data corresponding to the CRC check value in the object.

Value; Check value; CRC check value calculated according to the data in the [offset, CRC_LENGTH] interval in the object. CRC_LENGTH is the length of the preset check interval.

S103: Compare each first CRC check value with a corresponding second CRC check value;

S104: If the first CRC check value is inconsistent with the corresponding second CRC check value, it is determined that an error occurs in the target data in the hard disk.

Specifically, after the first CRC check value of the target data is calculated and the second CRC check value of the target data is read, the first CRC check value of each data segment of the target data is respectively compared with the first CRC check value of each data segment The two CRC check values are compared; if the first CRC check value of one or some data fragments is inconsistent with the corresponding second CRC check value, it is determined that the target data has an error. On the contrary, if the first CEC check value of each data segment is consistent with the corresponding second CRC check value, there is no error in the target data.

Further, the above-mentioned reading of target data from the hard disk includes: reading the target data from the hard disk when a read request is received or when an active verification is triggered.

Specifically, the timing for data verification in this embodiment includes performing data verification on the target data when reading target data (at this time the target data is target read data) after receiving a read request, and triggering active verification. Then, read the target data and perform data verification.

Among them, when receiving the read request, read the target data from the hard disk, and calculate the CRC check value of the data of each preset check interval length in the target data, including: determining the start of the read interval corresponding to the target data according to the read request Position and end position; if the start position and end position of the reading interval corresponding to the target data are integer multiples of the preset check interval length, directly read and calculate the data of each preset check interval length in the target data CRC check value; if the start position and/or end position of the read interval of the target data is not an integer multiple of the calculated length of the preset check value, the length of the preset check interval is set before the start position is read from the hard disk Data and target data from positions that are integer multiples of the position to the start position, and/or data and target data from positions that are integer multiples of the length of the preset check interval after reading the end position to the end position; calculate the read data and The CRC check value of the data of each preset check interval length in the target data.

Specifically, after receiving the read request, it is judged whether the target data is aligned data according to the read request. If the target data is aligned data, the data of the corresponding offset length is directly read from the hard disk, and each preset calibration in the target data is calculated. The CRC check value of the data of the length of the check interval. If the target data is non-aligned data, at this time, in addition to reading the target data from the hard disk, other data is also read from the hard disk, so that the target data and the additionally read data together constitute aligned data. Furthermore, the target data and the additionally read data are taken as a whole data, and the CRC check value of each preset check interval length is calculated.

For example, referring to Figure 5, taking the preset check interval length of 4KB as an example, the start position of the reading interval corresponding to the target data is 3KB, and the end position is 15KB, that is, data from 3KB to 15KB needs to be read. Since the start position and the end position of the read interval are not integer multiples of the length of the preset check interval, at this time, in addition to reading the data from the 3KB position to the 15KB position from the hard disk, the 0KB position is also read from the hard disk. The data to the 3KB position, and the data from the 15KB position to the 16KB position, and the data from the 0KB position to the 16KB position as a whole data, calculate the CRC check value of the data of each 4KB length.

Further, in the case that the target data is non-aligned data, the target data and the additionally read data are taken as a whole data, and the first CRC check value is calculated, and each calculated first CRC check value is related to the corresponding When the second CRC check values are consistent, the additional read data is cut from the data buffer, and only the target data is returned to the client.

For the method of triggering active verification, the verification period can be pre-configured, that is, the above-mentioned preset period, for example, data verification is triggered every other week. Therefore, according to the preset period, when the check time is reached, the data check is triggered, the objects in the database are traversed, the target data, which is the target data, is read, and the first CRC check value of the target data is calculated. Read the second CRC check value stored in the database, and compare the second CRC check value with the corresponding first CRC check value. For the method of calculating the first CRC check value of the object data, reference may be made to the above-mentioned embodiment, which is not repeated in this application.

Further, when an error occurs in the target data, the target data is added to the reconstruction queue for data reconstruction. Specifically, when it is verified that there is an error in the data, the data reconstruction process of the distributed storage system is triggered, and the erroneous data is added to the data reconstruction queue as missing data to perform data reconstruction. According to the redundancy rules of the distributed storage system, normal data is read from other copies and written to the local storage engine to restore the local data. Among them, the data reconstruction process can use the original reconstruction process of the distributed storage system, which will not be repeated in this application.

To sum up, the data verification method provided by this application calculates the CRC check value of the data to be written every time data is written, and stores it in the database, and then calculates the data to be verified during subsequent data verification. The CRC check value is further compared with the corresponding CRC check value stored in the database to determine whether the data has an error. The data verification method adopts the data verification method in which the storage engine independently performs data verification. Data verification can be completed without using the data in the copies of other nodes. It can not only accurately identify the location of abnormal data, but also It can ensure the effective execution of data verification.

The present application also provides a data verification device of a distributed storage system, and the device described below may correspond to the method described above with reference to each other. The data verification device includes:

This application also provides a data verification device for a distributed storage system, the data verification device comprising: a memory and a processor; wherein the memory is used to store a computer program; the processor is used to execute the computer program to implement the following steps :

Read the target data from the hard disk, and calculate the CRC check value of the data of each preset check interval length in the target data to obtain the first CRC check value; when reading and writing the target data from the database, calculate The second CRC check value obtained from the CRC check value of the data of each preset check interval length in the target data; respectively compare each of the first CRC check values with the corresponding second CRC check values Value comparison; if the first CRC check value is inconsistent with the corresponding second CRC check value, it is determined that the target data in the hard disk has an error.

For the introduction of the equipment provided in this application, please refer to the embodiment of the above method, which will not be repeated in this application.

This application also provides a computer-readable storage medium with a computer program stored on the computer-readable storage medium, and when the computer program is executed by a processor, the following steps are implemented:

Read the target data from the hard disk, and calculate the CRC check value of the data of each preset check interval length in the target data to obtain the first CRC check value; when reading and writing the target data from the database, calculate The second CRC check value obtained from the CRC check value of the data of each preset check interval length in the target data; respectively compare each of the first CRC check values with the corresponding second CRC check values The value is compared; if the first CRC check value is inconsistent with the corresponding second CRC check value, it is determined that an error occurs in the target data in the hard disk.

The computer-readable storage medium may include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk, etc., which can store program codes Medium.

For the introduction of the computer-readable storage medium provided by the present invention, please refer to the foregoing method embodiments, and the present invention will not be repeated here.

Because the situation is complex, it is impossible to enumerate one by one. Those skilled in the art should be aware that there can be multiple examples based on the basic principles of the embodiments provided in this application in combination with the actual situation. All are within the scope of this application.

The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments can be referred to each other.

The technical solutions provided by this application are described in detail above. Specific examples are used in this article to describe the principles and implementations of the application, and the descriptions of the above examples are only used to help understand the methods and core ideas of the application. It should be pointed out that for those of ordinary skill in the art, without departing from the principles of this application, several improvements and modifications can be made to this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

It should also be noted that in this specification, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply these entities or operations. There is any such actual relationship or sequence between operations. Moreover, the terms "including", "including" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes those that are not explicitly listed Other elements of, or also include elements inherent to this process, method, article or device. Without more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, method, article, or device that includes the element.

Claims

A data verification method for a distributed storage system is characterized in that it comprises:

Reading the target data from the hard disk, and calculating the CRC check value of the data of each preset check interval length in the target data to obtain the first CRC check value;

When reading and writing the target data from the database, calculating the second CRC check value obtained by calculating the CRC check value of the data of each preset check interval length in the target data;

Respectively comparing each of the first CRC check values with the corresponding second CRC check values;

If the first CRC check value is inconsistent with the corresponding second CRC check value, it is determined that an error has occurred in the target data in the hard disk.
The data verification method according to claim 1, wherein when writing the target data, calculating the CRC check value of the data of each preset check interval length in the target data comprises:

If the start position and the end position of the write interval corresponding to the target data are integer multiples of the length of the preset check interval, the CRC of the data of each preset check interval length in the target data is directly calculated. Value.
The data verification method according to claim 1, wherein when writing the target data, calculating the CRC check value of the data of each preset check interval length in the target data comprises:

If the start position and/or end position of the write interval of the target data is not an integer multiple of the calculated length of the preset check value, then read the start position from the hard disk before the preset It is assumed that the written data from the position that is an integer multiple of the length of the check interval to the start position, and/or the preset check is read from the end position to the end position from the hard disk The written data at the position that is an integer multiple of the interval length;

Calculate the CRC check value of the data of each preset check interval length in the written data and the target data.
The data check method according to claim 1, wherein storing the second CRC check value in the database comprises:

The second CRC check value and the offset in the object of the data corresponding to the second CRC check value are stored in the database in the form of a map.
The data verification method according to claim 1, wherein said reading the target data from the hard disk comprises:

The target data is read from the hard disk when a read request is received or when an active verification is triggered.
The data verification method according to claim 5, wherein the target data is read from the hard disk when a read request is received, and the CRC check value of the data of each preset check interval length in the target data is calculated ,include:

Determining the start position and the end position of the read interval corresponding to the target data according to the read request;

If the start position and the end position of the reading interval corresponding to the target data are integer multiples of the length of the preset check interval, directly read and calculate the data of each preset check interval length in the target data CRC check value;

If the start position and/or end position of the read interval of the target data is not an integer multiple of the calculated length of the preset check value, then read the start position from the hard disk before the preset Set the data from the position of an integer multiple of the length of the check interval to the start position and the target data, and/or read the end position to the end position as an integer of the preset check interval length Calculate the CRC check value of the read data and the data of each preset check interval length in the target data.
The data verification method according to claim 1, further comprising:

When an error occurs in the target data, the target data is added to the reconstruction queue for data reconstruction.
A data verification device of a distributed storage system is characterized in that it comprises:

The calculation module is used to read the target data from the hard disk, and calculate the CRC check value of the data of each preset check interval length in the target data to obtain the first CRC check value;

A reading module, which is used to calculate the second CRC check value obtained by calculating the CRC check value of the data of each preset check interval length in the target data when reading and writing the target data from the database;

The comparison module is configured to compare each of the first CRC check values with the corresponding second CRC check values;

The determining module is configured to determine that an error occurs in the target data in the hard disk if the first CRC check value is inconsistent with the corresponding second CRC check value.
A data verification device for a distributed storage system, which is characterized in that it comprises:

Memory, used to store computer programs;

The processor is configured to implement the steps of the data verification method of the distributed storage system according to any one of claims 1 to 7 when the computer program is executed.
A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the distributed storage system according to any one of claims 1 to 7 is realized The steps of the data verification method.