CN103810065B - Method and device for testing disk array - Google Patents

Abstract

The invention discloses a method and a device for testing a disk array, which are used to solve the problems in the prior art that the abnormal running state of the disk array cannot be detected and accurate test results cannot be obtained. Including: determining the preset access control policy group; executing the specified operation for each access control policy in the access control policy group in turn until all access control policies are traversed; the specified operation includes: starting from the logic unit to be tested for the disk array In the correspondingly set storage space matrix, determine the matrix elements to be accessed; according to the correspondence between the pre-established matrix elements and the respective data blocks contained in the logic unit to be tested, determine the data blocks to be accessed corresponding to the matrix elements to be accessed; and judge Whether the write data specified for the data block to be accessed matches the data returned after the read operation is performed according to the access control policy; and according to the judgment result, it is determined whether the operation state of the disk array is abnormal.

Description

Method and device for testing disk array

technical field

The invention relates to the technical field of testing, in particular to a method and device for testing a disk array.

Background technique

A disk array includes a controller and a physical disk cabinet. The controller is used to run control software and various algorithms. The cache for caching data is located in the controller; and the physical disk cabinet stores data under the control of the controller. Under normal circumstances, when the disk array receives an IO read request from the client, if the requested data is not hit in the cache memory, then the requested data must be read from the physical disk cabinet of the disk array into the cache, and then the cache Return to the client; when the disk array receives an IO write request from the client, it will write the data to be written into the cache, and return a successful response to the client, and then control the algorithm according to the algorithm, and then at a certain time, the cache will The data to be written is written into a physical disk enclosure in the disk array. According to the operating characteristics of the disk array, the existing disk array test method is: simple simulation IO read and write operations, that is: send the IO write operation command to the disk array, receive the successful response returned by the disk array; Send the IO read operation command for reading the written data, and receive the data returned by the disk array. In the prior art, the above process does not verify whether the written data is consistent with the read data.

In the actual test, in order to obtain a higher test value, the manufacturer of the tested disk array may change the control software of the disk array. For example, for an IO read operation command, even if the cache misses, it will not read data from the physical disk cabinet of the disk array and return it to the client, but directly return other data in the cache to the client.

It can be seen that the existing test method cannot effectively detect the abnormal operating state of the disk array, which will lead to falsely high test values, which do not conform to the actual operating conditions.

In addition, the existing test model is realized by generating random numbers, as shown in FIG. 1 , which is a schematic diagram of implementing tests by generating random numbers in the prior art. Among them, the test model generates an array containing 100 elements, and each element represents a specific access control strategy. According to the generated random number, the access control strategy represented by the corresponding element is determined, and the disk is controlled according to the determined access control strategy. array for testing. In practical applications, such as an online transaction processing OLTP model, which generates an array from 1 to 100, which represents an access control policy group, where "1-20" represents the access control policy as "read in random access mode 8K bytes", the access control strategy represented by "21-65" is "read 4K bytes by random access", and the access control strategy represented by "66-80" is "write 8K bytes by random access", " The access control policy represented by 81-90" is "write 64K bytes in sequential access mode", and the access control policy represented by "91-100" is "read 64K bytes in sequential access mode". It can be seen that in the access control policy set for this OLTP model, 8K byte random read operations account for 20%, 4K byte random read operations account for 45%, 8K byte random write operations account for 15%, and 64K byte random read operations account for 15%. Sequential reads of sections account for 10%, and sequential writes of 64K bytes account for 10%.

In the actual test, the most accurate test results will be obtained only when the proportion of the different access control policies it is based on in the access control policy group meets the specified proportion. However, since there is no way to control the generated random numbers according to the requirements, the access control strategy based on the test reaches such a ratio. For example, when the disk array is tested in the above OLTP model using the method of generating random If 30 random numbers in the random number fall into the range [1, 20], then the access control policy corresponding to "1-20" will account for 30%, so the generated random number points to the access control policy in the access The proportions in the control policy group are bound to be imprecise, and thus do not serve the purpose of testing disk arrays in the above model well.

Contents of the invention

Embodiments of the present invention provide a method and device for testing a disk array to solve the problems in the prior art that the abnormal operation state of the disk array cannot be detected and accurate test results cannot be obtained.

Embodiments of the present invention adopt the following technical solutions:

A method of testing a disk array, comprising:

Determine a preset access control policy group; execute a specified operation for each access control policy in the access control policy group in turn until all access control policies are traversed; wherein the specified operation includes: from the disk array to be In the storage space matrix set corresponding to the test logic unit, determine the matrix element to be accessed; according to the correspondence between the pre-established matrix element and each data block contained in the logic unit to be tested, determine the matrix element corresponding to the matrix element to be accessed The data block to be accessed; and when the type of read-write IO operation specified by the access control policy is a read operation, it is judged that the write data specified for the data block to be accessed and the data returned after the read operation is performed according to the access control policy Whether it matches; according to the judgment result obtained by executing the specified operation for each access control policy, determine whether the operation status of the disk array is abnormal.

A device for testing disk arrays, comprising:

an access control policy group determination unit, configured to determine a preset access control policy group; an execution unit, configured to sequentially perform specified operations on each access control policy in the access control policy group determined by the access control policy group determination unit, Until all access control policies are traversed; wherein, the specified operation includes: determining the matrix elements to be accessed from the storage space matrix corresponding to the logic unit to be tested in the disk array; Test the corresponding relationship of each data block included in the logic unit, determine the data block to be accessed corresponding to the matrix element to be accessed; Whether the write data specified by the access data block matches the data returned after the read operation is performed according to the access control policy; the operating state determination unit is used to determine the result obtained by performing the specified operation for each access control policy, Determine whether the running state of the disk array is abnormal.

The beneficial effects of the embodiments of the present invention are as follows:

According to the solution provided by the embodiment of the present invention, when the data read from the disk array is not the data specified to be written, it can be determined that the disk array has an abnormal operating state through the judgment result, thereby overcoming the problem of not verifying the write in the prior art. Whether the input data is consistent with the read data solves the problem that the abnormal operation status of the disk array cannot be detected in the prior art; on the other hand, by traversing the access control policies in the preset access control policy group, the In order to read each access control policy, in the actual test, the test can be accurately performed according to the proportion of the set access control policy in the access control policy group, and then accurate test results can be obtained.

Description of drawings

Fig. 1 is the schematic diagram that uses the mode of generating random number to realize test in the prior art;

FIG. 2 is a main flowchart of a method for testing a disk array provided by an embodiment of the present invention;

FIG. 3 is a schematic diagram of an access control policy matrix provided by an embodiment of the present invention;

FIG. 4 is a schematic diagram of a traversal access control policy matrix provided by an embodiment of the present invention;

FIG. 5 is a schematic diagram of a specific implementation of the above solution provided by the embodiment of the present invention in practical application;

FIG. 6 is a schematic diagram of an implementation of a storage space matrix in an embodiment of the present invention;

FIG. 7 is a schematic diagram of different access methods for a storage space matrix provided by an embodiment of the present invention;

FIG. 8 is a schematic structural diagram of a device for testing a disk array provided by an embodiment of the present invention.

detailed description

In order to solve the problems in the prior art that the abnormal operating state of the disk array cannot be detected and accurate test results cannot be obtained, the embodiment of the present invention provides a solution for testing the disk array. On the one hand, according to each access control strategy, the solution determines the matrix elements with access from the storage space matrix corresponding to the logic unit to be tested in the disk array, and then according to the pre-established matrix elements and the logic unit to be tested. The corresponding relationship of each data block, determine the data block to be accessed corresponding to the matrix element to be accessed, and then judge whether the write data specified for the data block to be accessed matches the data returned after the read operation is performed according to the access control strategy, and overcome In the prior art, it is impossible to verify whether the written data and the read data are consistent. When the data read from the disk array is not the data specified to be written, it can be determined that there is an abnormality in the disk array through the judgment result. operating state, thereby solving the problem that the abnormal operating state of the disk array cannot be detected in the prior art; on the other hand, by traversing the access control policies in the preset access control policy group, the control of each access control policy is realized. Read, so that in the actual test, the test can be accurately performed according to the proportion of the set access control policy in the access control policy group, and then accurate test results can be obtained.

The main realization principles, specific implementation modes and corresponding beneficial effects that can be achieved of the technical solutions of the embodiments of the present invention will be described in detail below in conjunction with each accompanying drawing.

As shown in Figure 2, it is a main flowchart of a method for testing a disk array provided by an embodiment of the present invention, the method includes the following steps:

Step 21, determining a preset access control policy group.

Usually, the test model includes two test scenarios of OLAP and OLTP, and each test scenario includes read and write IO operations with different proportions, different access methods, and different data volumes. For example, the preset access control policy groups in OLTP and OLAP scenarios may be shown in Table 1. Wherein, in each test mode scenario, an array containing 100 elements may be generated, the array represents an access control strategy group, and each element represents a specific access control strategy. Taking the OLTP scenario in Table 1 as an example, a total of 5 elements can be generated, and each element corresponds to an access control policy IOProfile, as follows:

a) Element.size=8192, Element.random=100, Element.read=100;

b) Element.size=4096, Element.random=100, Element.read=100;

c) Element.size=8192, Element.random=100, Element.read=0;

d) Element.size=65536, Element.random=0, Element.read=100;

e) Element.size=65536, Element.random=0, Element.read=0;

Among them, Element.size indicates the size of the data; Element.random indicates the access mode, Element.random=100 indicates the random access mode, Element.random=0 indicates the sequential access mode; Element.read indicates the operation mode, and Element.read=100 is Read operation, Element.read=0 is write operation. For example, taking the above a) as an example, the access control strategy it represents is to read 8192 bytes (4KB) of data in random access mode.

According to the different proportions of each access control policy in the access control policy group, the number of elements is determined, and the sum of the numbers of all elements is 100.

Table 1:

Step 22, execute specified operations for each access control policy in the access control policy group in turn until all access control policies are traversed.

Wherein, the specified operation includes: determining the matrix elements to be accessed from the storage space matrix corresponding to the logic unit to be tested for the disk array; , determine the data blocks to be accessed corresponding to the elements of the matrix to be accessed; Whether the data returned after the policy executes the read operation matches.

Optionally, in the embodiment of the present invention, the 100 elements contained in the generated array can be organized into a 10*10 matrix, as shown in FIG. 3 , which is a schematic diagram of an access control policy matrix provided in the embodiment of the present invention , by traversing the access control policy matrix, all access control policies are read. As shown in Figure 4, it is a schematic diagram of traversing the access control policy matrix provided by the embodiment of the present invention. According to the access sequence of accessing each matrix element from top to bottom, first access the matrix elements in the first column, and then , and then access the matrix elements in the second column according to the above access sequence, and so on, until all the matrix elements of the access control policy matrix are traversed.

Wherein, during the test process, the test can be stopped only when all the matrix elements of the storage space matrix must be traversed; if the matrix elements of the storage space matrix have not been traversed once, the test cannot be stopped. It should be noted that, during the testing process, the traversal process can be executed multiple times in a loop, that is, the test can only stop when all the matrix elements of the storage space matrix are traversed at least once.

Step 23, according to the judgment result obtained by executing the specified operation for each access control policy, determine whether the operation state of the disk array is abnormal.

On the one hand, according to each access control strategy, the embodiment of the present invention determines the matrix elements to be accessed from the storage space matrix corresponding to the logic unit to be tested in the disk array, and then according to the pre-established matrix elements and the logic unit to be tested The corresponding relationship of each data block included determines the data block to be accessed corresponding to the matrix element to be accessed, and then judges whether the write data specified for the data block to be accessed matches the data returned after the read operation is performed according to the access control policy , through the judgment result, it can be determined whether the disk array has an abnormal operation state, thereby solving the problem that the abnormal operation state of the disk array cannot be detected in the prior art; on the other hand, by traversing the preset access control policy group The unique access control strategy realizes the reading of each access control strategy, enabling precise control of various types of operations and obtaining accurate test results.

As shown in FIG. 5, it is a schematic diagram of a specific implementation of the above-mentioned solution provided in the embodiment of the present invention in practical application. The method includes the following steps:

Step 51, determining a preset access control policy group.

Step 52 , for an access control policy that has not been accessed in the access control policy group, determine matrix elements to be accessed from the storage space matrix corresponding to the logic unit to be tested in the disk array.

During the test, take traversing all the access control policies in the access control policy group as an example, each access control policy will be accessed and only once.

Among them, the access control policy includes IO operation type (read operation or write operation), IO data size and IO access mode. The IO access methods include: an IO random access method and an IO sequential access method. If the data blocks accessed twice before and after are adjacent, then it is considered as sequential access; if the data blocks accessed twice before and after are not adjacent, then it is considered as random access.

Then this step specifically includes: according to the size of the IO data volume and the rated data storage capacity of a single data block, determining the number of matrix elements to be accessed, and then according to the read pointer and the IO access mode of the storage space matrix, from the storage space matrix Select the above number of matrix elements to be accessed. Wherein, the position pointed by the above-mentioned read pointer is the storage space of the last accessed matrix element in the storage space matrix. Storage space for matrix elements.

The following describes how to set up the storage space matrix:

Assume that the storage space of the disk array is divided into several logical units, and each logical unit (assumed to have a capacity of 100GB) is divided into continuous data blocks in units of 1KB. Then, these 1KB data blocks can form a matrix with M rows and N columns, where M*N*1KB=100GB. Based on the divided data blocks, the schematic diagram of setting the storage space matrix is shown in Figure 6. The specific setting method is: starting from the first data block of the logic unit, the first row of the matrix is sequentially generated, that is, starting from M(0,0 ) to M (0, N-1), a total of N elements; then generate the second row from M (1, 0) to M (1, N-1), and so on, and finally generate a storage space matrix M (M* N).

Optionally, in order to facilitate the read-write verification in the test, the specified write data in each 1KB data block in the logical unit can be the row label and column label of the corresponding matrix element, where the former All 512 bytes are written into the row i value of the matrix element, and all the last 512 bytes are written into the column j value of the matrix element.

It should be noted that the storage space matrix in the embodiment of the present invention may be set in the above-mentioned way, but is not limited to the above-mentioned way. In order to make the test simple and easy, the above-mentioned setting way is preferred.

According to the setting method of the above-mentioned storage space matrix, different access methods to the storage space matrix in the embodiment of the present invention are shown in FIG. 7 . When the IO access mode is the IO sequential access mode, according to the read pointer, starting from the adjacent matrix element on the right side of the matrix element indicated by the read pointer, select the above-mentioned number of waiting arrays arranged from left to right from the storage space matrix in turn. access matrix elements;

When the IO access mode is the IO random access mode, according to the read pointer, starting from the adjacent matrix element below the matrix element indicated by the read pointer, select the above-mentioned number of arrays to be accessed from left to right in the storage space matrix in turn matrix elements.

For example, if the IO data size stipulated in this access control policy is 4KB, and the IO access method is sequential access, then the matrix element to be accessed is determined according to the IO data size of 4KB and the rated data storage size of a single data block of 1KB. The number is 4, then, starting from the adjacent matrix element on the right side of the matrix element indicated by the read pointer, select 4 matrix elements to be accessed from the storage space matrix arranged from left to right in sequence.

It should be noted that if the row where the matrix elements of the storage space matrix are located ends, then continue to select the above-mentioned number of matrix elements to be accessed arranged from left to right from the next row of the storage space matrix. If the row where the matrix element of the storage space matrix is located is the last row of the storage space matrix, continue to select the above-mentioned number of matrix elements to be accessed arranged from left to right from the first row of the storage space matrix.

Step 53: Determine the data block to be accessed corresponding to the matrix element to be accessed according to the pre-established correspondence between the matrix element and each data block included in the logical unit to be tested.

The corresponding relationship is determined according to the setting method of the storage space matrix in step 52 . In the embodiment of the present invention, the corresponding relationship is specifically: the matrix elements in each row of the storage space matrix are arranged in order from left to right, and one by one corresponds to a plurality of consecutive data contained in the logic unit to be tested on the address of the storage space. Each block of data in the block.

Step 54, obtain the specified write data from the determined data block to be accessed.

Wherein, the write data specified for any data block to be accessed may be: the number of the matrix element corresponding to the data block to be accessed in the storage space matrix. In the embodiment of the present invention, the number of the matrix element in the storage space matrix The number is the row label and column label of the matrix element in the storage space matrix.

Step 55, judging whether the IO operation type specified in the access control policy is a read operation, if so, go to step 56, otherwise go to step 59.

Step 56, perform an IO read operation, and return the read data;

Step 57, judge whether the write data specified for the data block to be accessed matches the read data returned after the read operation is performed according to the access control policy, if yes, execute step 510, otherwise execute step 58.

In step 58, the operating status of the disk array is abnormal, the abnormal number is increased by 1, and step 510 is executed.

Step 59, execute the IO write operation, and return a successful response.

Step 510, judge whether to traverse all the access control policies, if yes, the test ends and the test result is obtained; otherwise, return to step 52. Wherein, the test result may be obtained according to the finally determined abnormal number. For example, based on comparing the finally determined abnormal number with the preset abnormal threshold, if the final determined abnormal number is greater than or equal to the preset abnormal threshold, the test result indicates that the disk array is running abnormally; if the final determined abnormal number is less than the preset abnormal threshold If the abnormal threshold is set, the test result indicates that the disk array is running normally.

In the embodiment of the present invention, when the data read from the disk array is not the data specified to be written, it can be determined that the disk array has an abnormal operating state through the judgment result, thereby overcoming the problem of not verifying the written data in the prior art. The defect of whether the data and the read data are consistent solves the problem that the abnormal operation status of the disk array cannot be detected in the prior art; on the other hand, by traversing the access control policies in the preset access control policy group, the The reading of each access control policy makes it possible to accurately test according to the proportion of the set access control policy in the access control policy group in the actual test, and then obtain accurate test results.

Correspondingly, an embodiment of the present invention also provides a device for testing a disk array, as shown in FIG. 8 , which is a schematic structural diagram of the device, including:

An access control policy group determining unit 81, configured to determine a preset access control policy group;

The executing unit 82 is configured to execute specified operations for each access control policy in the access control policy group determined by the access control policy group determining unit 81 in turn until all access control policies are traversed; wherein the specified operations include: Determine the matrix elements to be accessed in the storage space matrix corresponding to the logic unit to be tested; determine the matrix elements to be accessed corresponding to the matrix elements to be accessed according to the corresponding relationship between the matrix elements and each data block contained in the logic unit to be tested Access the data block; and when the read-write IO operation type specified in the access control policy is a read operation, determine whether the write data specified for the data block to be accessed matches the data returned after the read operation is performed according to the access control policy ;

The running state determining unit 83 is configured to determine whether the running state of the disk array is abnormal according to the judgment result obtained by executing the specified operation for each access control policy.

Optionally, the preset access control policy group determined by the access control policy group determining unit 81 is an access control policy matrix, and the access control policy is a matrix element in the access control policy matrix.

Optionally, the write data specified for any data block to be accessed in the execution unit 82 is: the number of the matrix element corresponding to the data block to be accessed in the storage space matrix.

Among them, the access control strategy includes the size of the IO data volume and the IO access mode; then

Execution unit 82 may specifically include:

Quantity determining module 821, is used for determining the quantity of matrix elements to be accessed according to the size of the IO data volume and the rated data storage volume of a single data block;

The selection module 822 is configured to select the number of matrix elements to be accessed from the storage space matrix determined by the quantity determination module according to the read pointer and the IO access mode of the storage space matrix.

Wherein, the IO access method may include: a sequential access method and a random access method; and

The corresponding relationship in 82 in the execution unit specifically includes:

The matrix elements in each row of the storage space matrix correspond to each data block in the plurality of data blocks that are included in the logic unit to be tested and are consecutive on the storage space address one by one in accordance with the arrangement order from left to right; then

Execution unit 82 can be specifically used for:

When the IO access mode is the IO sequential access mode, according to the read pointer, starting from the adjacent matrix element on the right side of the matrix element indicated by the read pointer, select the number of arrays arranged from left to right from the storage space matrix in turn The matrix element to be accessed;

When the IO access mode is the IO random access mode, according to the read pointer, starting from the adjacent matrix element below the matrix element indicated by the read pointer, select the number of waiting arrays arranged from left to right from the storage space matrix in turn. Access matrix elements.

Wherein, the position pointed by the above-mentioned read pointer is the storage space of the last accessed matrix element in the storage space matrix. Storage space for matrix elements.

It should be noted that if the row where the matrix elements of the storage space matrix are located ends, then continue to select the above-mentioned number of matrix elements to be accessed arranged from left to right from the next row of the storage space matrix.

Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Accordingly, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and combinations of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a Means for realizing the functions specified in one or more steps of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the invention have been described, additional changes and modifications to these embodiments can be made by those skilled in the art once the basic inventive concept is appreciated. Therefore, it is intended that the appended claims be construed to cover the preferred embodiment as well as all changes and modifications which fall within the scope of the invention.

Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these modifications and variations.

Claims (10)

1. A method for testing disk arrays, comprising: Determine the preset access control policy group; Executing specified operations for each access control policy in the access control policy group in turn until all access control policies are traversed; Wherein, the specifying operation includes: determining the matrix elements to be accessed from the storage space matrix corresponding to the logic unit to be tested in the disk array; Block correspondence, determine the data block to be accessed corresponding to the matrix element to be accessed, the correspondence between the pre-established matrix element and each data block included in the logic unit to be tested specifically includes: the storage space The matrix elements in each row of the matrix correspond to each data block in the plurality of data blocks that are included in the logic unit to be tested and are continuous on the storage space address one by one in accordance with the order of arrangement from left to right; and in the access When the read-write IO operation type specified in the control policy is a read operation, it is judged whether the write data specified for the data block to be accessed matches the data returned after the read operation is performed according to the access control policy; According to the judgment result obtained by executing the specified operation for each access control policy, it is determined whether the operation state of the disk array is abnormal. 2. The method according to claim 1, wherein the preset access control policy group is an access control policy matrix, and the access control policies are matrix elements in the access control policy matrix. 3. The method according to claim 1, wherein the write data specified for any data block to be accessed is: the number of the matrix element corresponding to the data block to be accessed in the storage space matrix. 4. the method for claim 1 is characterized in that, described access control policy comprises IO data amount size and IO access mode; Then From the storage space matrix, determine the matrix elements to be accessed, specifically including: Determine the number of matrix elements to be accessed according to the size of the IO data volume and the rated data storage capacity of a single data block; Selecting the number of matrix elements to be accessed from the storage space matrix according to the read pointer of the storage space matrix and the IO access mode. 5. The method of claim 4, wherein, Described IO access mode comprises: sequential access mode and random access mode; Then According to the read pointer of the storage space matrix and the IO access mode, select the number of matrix elements to be accessed from the storage space matrix, specifically including: When the IO access mode is the IO sequential access mode, according to the read pointer, starting from the adjacent matrix element on the right side of the matrix element indicated by the read pointer, select from left to right in the storage space matrix in turn said number of matrix elements to be accessed permuted; When the IO access mode is the IO random access mode, according to the read pointer, starting from the adjacent matrix element below the matrix element indicated by the read pointer, select from the storage space matrix and arrange from left to right The stated number of matrix elements to be accessed. 6. A device for testing disk arrays, comprising: An access control policy group determining unit, configured to determine a preset access control policy group; An executing unit, configured to sequentially execute specified operations for each access control policy in the access control policy group determined by the access control policy group determination unit until all access control policies are traversed; wherein the specified operations include: In the storage space matrix corresponding to the logical unit to be tested in the disk array, determine the matrix elements to be accessed; To access the data block to be accessed corresponding to the matrix element, the corresponding relationship in the execution unit specifically includes: the matrix elements in each row of the storage space matrix correspond to the to-be-tested data blocks one by one according to the order of arrangement from left to right Each data block in a plurality of data blocks that are contained in the logical unit and that are continuous on the address of the storage space; and when the type of read-write IO operation specified by the access control policy is a read operation, it is judged that the specified data block for the data block to be accessed Whether the written data matches the data returned after the read operation is performed according to the access control policy; The running state determining unit is configured to determine whether the running state of the disk array is abnormal according to a judgment result obtained by executing the specified operation for each access control policy. 7. The device according to claim 6, wherein the preset access control policy group determined by the access control policy group determination unit is an access control policy matrix, and the access control policy is a matrix element in the access control policy matrix. 8. The device according to claim 6, wherein the write data specified for any data block to be accessed in the execution unit is: the matrix element corresponding to the data block to be accessed is in the storage space matrix number in . 9. The device according to claim 6, wherein the access control policy comprises an IO data size and an IO access mode; then Execution units specifically include: Quantity determination module, used to determine the number of matrix elements to be accessed according to the size of the IO data volume and the rated data storage capacity of a single data block; The selecting module is configured to select the number of matrix elements to be accessed determined by the number determining module from the storage space matrix according to the read pointer of the storage space matrix and the IO access mode. 10. The device according to claim 9, wherein the IO access methods include: sequential access methods and random access methods; The execution unit is specifically used for: When the IO access mode is the IO sequential access mode, according to the read pointer, starting from the adjacent matrix element on the right side of the matrix element indicated by the read pointer, select from left to right in the storage space matrix in turn said number of matrix elements to be accessed permuted; When the IO access mode is the IO random access mode, according to the read pointer, starting from the adjacent matrix element below the matrix element indicated by the read pointer, select from the storage space matrix and arrange from left to right The stated number of matrix elements to be accessed.