Long-term performance testing method, device, readable storage medium and electronic device

Abstract

The present invention discloses a long-term performance test method, device, readable storage medium and electronic device. Based on a preset test time, sequential read and write operations are performed on a memory to be tested with a preset data volume as a unit, and sequential read and write performance data of the sequential read and write operations are recorded. The preset test time is greater than or equal to 30 days. The median of all sequential read and write performance data is calculated, and the difference between each sequential read and write performance data and the median is calculated. A confidence level graph is generated based on all the differences. The test result of the memory to be tested is determined based on the confidence level graph and the median. The median can be used to effectively feedback the trend of performance data distribution concentration. The difference between each performance data and the median is intuitively displayed in the form of a confidence level graph. The test result is determined based on the confidence level graph and the median, which can effectively judge the stability of the long-term performance of the memory, thereby realizing reliable and effective long-term performance testing.

Description

Technical Field

[0001] The present invention relates to the field of performance testing technology, and in particular to a long-term performance testing method, device, readable storage medium and electronic equipment. Background Art

[0002] The existing UFS (Universal Flash Storage) and EMMC (Embedded Multi-MediaCard) performance tests generally use AndroBench (a benchmark application), focusing on short-term performance indicators, while the stability of long-term performance is also a very important indicator. After long-term operation, the memory performance fluctuation should be within an acceptable range. However, there is currently no reliable and effective long-term performance test method. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a long-term performance test method, device, readable storage medium and electronic device, which can realize reliable and effective long-term performance test.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0005] A long-term performance testing method comprises the following steps:

[0006] Performing sequential read and write operations on the memory to be tested in units of preset data volume based on a preset test duration, and recording sequential read and write performance data of the sequential read and write operations, wherein the preset test duration is greater than or equal to 30 days;

[0007] Calculating the median of all the sequential read / write performance data, and calculating the difference between each sequential read / write performance data and the median;

[0008] generating a confidence level map based on all said difference plots;

[0009] A test result of the memory to be tested is determined based on the confidence level map and the median.

[0010] In order to solve the above technical problems, another technical solution adopted by the present invention is:

[0011] A long-term performance testing device, comprising:

[0012] A data reading and writing module, used to perform sequential reading and writing operations on the memory to be tested in units of preset data volume based on a preset test duration, and record sequential reading and writing performance data of the sequential reading and writing operations, wherein the preset test duration is greater than or equal to 30 days;

[0013] A calculation module, used for calculating the median of all the sequential read / write performance data, and calculating the difference between each sequential read / write performance data and the median;

[0014] A confidence level map generation module, used for generating a confidence level map based on all the difference plots;

[0015] A test result determination module is used to determine the test result of the memory to be tested based on the confidence level map and the median.

[0016] In order to solve the above technical problems, another technical solution adopted by the present invention is:

[0017] A computer-readable storage medium stores a computer program, which implements each step of the long-term performance test method when executed by a processor.

[0018] In order to solve the above technical problems, another technical solution adopted by the present invention is:

[0019] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements each step of the above-mentioned long-time performance testing method when executing the computer program.

[0020] The beneficial effects of the present invention are as follows: sequential read and write operations are performed on the memory to be tested in units of preset data volume based on a preset test duration, and sequential read and write performance data of the sequential read and write operations are recorded, the preset test duration is greater than or equal to 30 days, the median of all sequential read and write performance data is calculated, and the difference between each sequential read and write performance data and the median is calculated, a confidence level graph is generated based on all the differences, and the test result of the memory to be tested is determined based on the confidence level graph and the median, the median can be used to effectively feedback the trend of performance data distribution concentration, the difference between each performance data and the median is intuitively displayed in the form of a confidence level graph, and the test result is determined based on the confidence level graph and the median, which can effectively judge the stability of the long-term performance of the memory, thereby achieving reliable and effective long-term performance testing. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A flowchart of a long-term performance test method according to an embodiment of the present invention;

[0022] Figure 2 It is a structural schematic diagram of a long-time performance testing device according to an embodiment of the present invention;

[0023] Figure 3 A schematic diagram of the structure of an electronic device according to an embodiment of the present invention;

[0024] Figure 4This is the final confidence level diagram in the long-term performance testing method of an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to explain the technical content, achieved objectives and effects of the present invention in detail, the following is an explanation in combination with the implementation modes and the accompanying drawings.

[0026] Please refer to Figure 1 , a long-term performance testing method, comprising the steps of:

[0027] Performing sequential read and write operations on the memory to be tested in units of preset data volume based on a preset test duration, and recording sequential read and write performance data of the sequential read and write operations, wherein the preset test duration is greater than or equal to 30 days;

[0028] Calculating the median of all the sequential read / write performance data, and calculating the difference between each sequential read / write performance data and the median;

[0029] generating a confidence level map based on all said difference plots;

[0030] A test result of the memory to be tested is determined based on the confidence level map and the median.

[0031] From the above description, it can be seen that the beneficial effects of the present invention are: based on the preset test time, sequential read and write operations are performed on the memory to be tested in units of preset data volume, and sequential read and write performance data of the sequential read and write operations are recorded, the preset test time is greater than or equal to 30 days, the median of all sequential read and write performance data is calculated, and the difference between each sequential read and write performance data and the median is calculated, a confidence level graph is generated based on all the differences, and the test results of the memory to be tested are determined based on the confidence level graph and the median. The median can be used to effectively feedback the trend of performance data distribution concentration, and the difference between each performance data and the median is intuitively displayed in the form of a confidence level graph. The test results are determined based on the confidence level graph and the median, which can effectively judge the stability of the long-term performance of the memory, thereby achieving reliable and effective long-term performance testing.

[0032] Further, the sequential read and write operations are performed on the memory to be tested based on the preset test duration and in units of preset data volume, and the sequential read and write performance data of the sequential read and write operations are recorded, including:

[0033] Performing a sequential write operation on the memory to be tested in units of a preset data amount until the memory to be tested is filled with sequential data, and recording sequential write performance data of the sequential write operation;

[0034] Performing a sequential read operation on the memory to be tested in units of the preset data amount until the memory to be tested is sequentially read, and recording sequential read performance data of the sequential read operation;

[0035] Determine whether the current test duration reaches the preset test duration. If so, stop the sequential read and write operation. If not, erase all data in the memory to be tested, and return to execute the sequential write operation step of the memory to be tested in units of preset data amount.

[0036] From the above description, it can be seen that by repeating sequential write operations and sequential read operations within the preset test duration, the memory can be effectively tested for a long period of time, and the performance data of the test process can be recorded to facilitate subsequent confirmation of the test results.

[0037] Further, generating a confidence level map based on all the difference values ​​includes:

[0038] Sorting the differences in ascending order to obtain sorted differences;

[0039] Draw and generate a first confidence level map according to the sorted difference values;

[0040] Extracting a preset proportion of differences from the sorted differences in order to obtain grade data;

[0041] Plotting the level data to generate a second confidence level map;

[0042] A final confidence level map is generated according to the first confidence level map and the second confidence level map.

[0043] From the above description, it can be seen that a first confidence level graph is generated based on the sorted differences, a preset proportion of differences are extracted in sequence from the sorted differences to obtain level data, and the level data is plotted to generate a second confidence level graph, and a final confidence level graph is generated based on the first confidence level graph and the second confidence level graph. The confidence level graph can intuitively show the distribution of memory performance fluctuations, which is also convenient for subsequent determination of test results.

[0044] Furthermore, extracting a preset proportion of differences from the sorted differences in order to obtain the grade data includes:

[0045] Extracting a first preset proportion of differences from the sorted differences in order to obtain first level data;

[0046] Extracting a second preset ratio of differences from the sorted differences in order to obtain second level data;

[0047] Extracting a third preset ratio of differences from the sorted differences in order to obtain third level data;

[0048] Extracting a fourth preset ratio of differences from the sorted differences in order to obtain fourth level data;

[0049] The first preset ratio, the second preset ratio, the third preset ratio and the fourth preset ratio decrease in sequence.

[0050] From the above description, it can be seen that the differences between the first preset ratio, the second preset ratio, the third preset ratio and the fourth preset ratio are extracted in sequence from the sorted differences to obtain first-level data, second-level data, third-level data and fourth-level data. By extracting data of different levels, we can further understand the distribution of performance fluctuations.

[0051] Further, the determining the test result of the memory to be tested based on the confidence level graph and the median includes:

[0052] Obtaining the confidence level corresponding to the first level data from the confidence level map;

[0053] Obtaining an absolute error according to the value at the confidence level corresponding to the first level data;

[0054] Calculate the absolute error and the median to obtain a relative error;

[0055] It is determined whether the relative error is less than a preset threshold value. If so, it is determined that the test result of the memory to be tested is a test pass. If not, it is determined that the test result of the memory to be tested is a test fail.

[0056] From the above description, it can be seen that the absolute error is obtained according to the value at the confidence level corresponding to the first-level data, and the relative error is obtained by calculation based on the absolute error and the median. The test result of the memory to be tested is determined based on the relative error, which can accurately reflect the stability of the performance.

[0057] Furthermore, before performing sequential read and write operations on the memory to be tested based on the preset test duration and using the preset data volume as a unit, the method further includes:

[0058] Erase all data in the memory under test.

[0059] From the above description, it can be seen that before the test, all data in the memory to be tested is erased to ensure that the long-term performance test is performed under a clean disk, reduce the impact of other factors on the test results, and improve the reliability of the long-term performance test.

[0060] Further, the calculation based on the absolute error and the median to obtain the relative error includes:

[0061] Relative error = the absolute error / the median.

[0062] From the above description, it can be seen that the relative error is calculated by the absolute error and the median, and the relative error can accurately reflect the performance fluctuation, so as to determine the stability of the memory performance.

[0063] Please refer to Figure 2 Another embodiment of the present invention provides a long-term performance testing device, comprising:

[0064] A data reading and writing module, used to perform sequential reading and writing operations on the memory to be tested in units of preset data volume based on a preset test duration, and record sequential reading and writing performance data of the sequential reading and writing operations, wherein the preset test duration is greater than or equal to 30 days;

[0065] A calculation module, used for calculating the median of all the sequential read / write performance data, and calculating the difference between each sequential read / write performance data and the median;

[0066] A confidence level map generation module, used for generating a confidence level map based on all the difference plots;

[0067] A test result determination module is used to determine the test result of the memory to be tested based on the confidence level map and the median.

[0068] Another embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computer program implements the various steps in the above-mentioned long-term performance testing method.

[0069] Please refer to Figure 3 Another embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements each step of the above-mentioned long-term performance testing method when executing the computer program.

[0070] The long-term performance test method, device, readable storage medium and electronic device of the present invention can be applied to UFS and EMMC, and are described below through specific implementation methods:

[0071] Please refer to Figure 1 and Figure 4 , Embodiment 1 of the present invention is:

[0072] Hardware environment preparation: Select a UFS or eMMC platform with a screen. The UFS or eMMC platform needs to allow users to perform USB (Universal Serial Bus) debugging. Then, start the platform from the UFS or eMMC to enter the Android system. Select the test device through the Android debugging bridge and push the iozone (a file system benchmark tool) script with the long-term performance test method of the present invention to the platform.

[0073] A long-term performance testing method comprises the following steps:

[0074] S0, erase all data in the memory to be tested.

[0075] Wherein, the memory to be tested is UFS or EMMC.

[0076] Performance testing has higher requirements on the cleanliness and independence of the test environment. In order to reduce the impact of other factors on the test results, all disk data is erased to ensure that long-term performance testing is carried out under a clean disk to ensure the reliability of long-term performance testing.

[0077] S1, performing sequential read and write operations on the memory to be tested in units of preset data volume based on a preset test duration, and recording sequential read and write performance data of the sequential read and write operations, wherein the preset test duration is greater than or equal to 30 days, specifically including S11-S13:

[0078] S11. Perform a sequential write operation on the memory to be tested with a preset data amount as a unit until the memory to be tested is fully written, and record sequential write performance data of the sequential write operation.

[0079] In an optional implementation, the preset data volume is 1 GB, so that the performance change per GB can be checked. Specifically, a sequential write operation is performed on the memory to be tested, and 1 GB of data is sequentially written each time until the memory to be tested is filled, and sequential write performance data of the sequential write operation is recorded.

[0080] S12, performing a sequential read operation on the memory to be tested in units of the preset data amount until the memory to be tested is completely sequentially read, and recording sequential read performance data of the sequential read operation.

[0081] In an optional implementation, sequential read and write operations are performed by sending an iozone command, where the iozone command is i0 for testing sequential write performance, and i1 for testing sequential read performance.

[0082] S13, judging whether the current test duration reaches the preset test duration, if so, stopping the sequential read and write operation, if not, erasing all data in the memory to be tested, and returning to execute S11.

[0083] S2. Calculate the median of all the sequential read / write performance data, and calculate the difference between each sequential read / write performance data and the median.

[0084] Because of the long-term testing, most performance test data should be stable near a value, and a few performance data will fluctuate greatly. Therefore, the median of all sequential read and write performance data is calculated. Based on the median, the difference between each sequential read and write performance data and the median is calculated to understand the performance fluctuations.

[0085] S3, generating a confidence level map based on all the difference values, specifically including S31-S35:

[0086] S31, sorting the difference values ​​in ascending order to obtain sorted difference values, such as Figure 4 The cylindrical part of the .

[0087] S32, generating a first confidence level map according to the sorted difference values, such as Figure 4 The curve in .

[0088] If the memory performance is more stable, the first confidence level graph is more concentrated on the left side, that is, it is expected that most points can be stabilized below a value.

[0089] S33, extracting a preset proportion of differences from the sorted differences in order to obtain grade data, specifically including S331-S334:

[0090] S331 . Extract a first preset ratio of differences from the sorted differences in order to obtain first level data.

[0091] S332: Extract a second preset ratio of differences from the sorted differences in order to obtain second level data.

[0092] S333. Extract a third preset ratio of differences from the sorted differences in order to obtain third level data.

[0093] S334. Extracting a fourth preset ratio of differences from the sorted differences in order to obtain fourth level data.

[0094] The first preset ratio, the second preset ratio, the third preset ratio and the fourth preset ratio decrease in sequence.

[0095] Among them, the first preset ratio is 95%, the second preset ratio is 90%, the third preset ratio is 85%, and the fourth preset ratio is 80%.

[0096] S34, plotting the level data to generate a second confidence level graph, such as Figure 4 The 4 vertical lines in the .

[0097] Specifically, a second confidence level graph is generated based on the first level data, the second level data, the third level data and the fourth level data, so that the distribution of performance fluctuations can be intuitively understood, that is, it can be seen within which error range 80% of the data fluctuations fall, within which error range 85% of the data fluctuations fall, within which error range 90% of the data fluctuations fall, and within which error range 95% of the data fluctuations fall.

[0098] S35, generating a final confidence level map according to the first confidence level map and the second confidence level map, such as Figure 4 shown.

[0099] If we see from the final confidence level graph that the gaps between the confidence levels of the four levels of data are very small, it means that the performance fluctuations are very close. If the values ​​are very small, it means that the performance is relatively stable. This allows us to intuitively observe the performance of the memory.

[0100] S4, determining the test result of the memory to be tested based on the confidence level graph and the median, specifically including S41-S44:

[0101] S41. Obtain the confidence level corresponding to the first level data from the confidence level map.

[0102] S42. Obtain an absolute error according to the value at the confidence level corresponding to the first level data.

[0103] S43, calculating according to the absolute error and the median to obtain a relative error, specifically:

[0104] Relative error = the absolute error / the median.

[0105] S44, determining whether the relative error is less than a preset threshold value, if so, determining that the test result of the memory to be tested is a test pass, if not, determining that the test result of the memory to be tested is a test fail.

[0106] In an optional implementation, the preset threshold is 2%.

[0107] Please refer to Figure 2 , Embodiment 2 of the present invention is:

[0108] A long-term performance testing device, comprising:

[0109] A data reading and writing module, used to perform sequential reading and writing operations on the memory to be tested in units of preset data volume based on a preset test duration, and record sequential reading and writing performance data of the sequential reading and writing operations, wherein the preset test duration is greater than or equal to 30 days;

[0110] A calculation module, used for calculating the median of all the sequential read / write performance data, and calculating the difference between each sequential read / write performance data and the median;

[0111] A confidence level map generation module, used for generating a confidence level map based on all the difference plots;

[0112] A test result determination module is used to determine the test result of the memory to be tested based on the confidence level map and the median.

[0113] Embodiment 3

[0114] A computer-readable storage medium stores a computer program, which can implement various steps of the long-term performance testing method in embodiment 1 when executed by a processor.

[0115] Embodiment 4

[0116] Please refer to Figure 3 , an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements each step of the long-term performance testing method in Embodiment 1 when executing the computer program.

[0117] In summary, the present invention provides a long-term performance test method, device, readable storage medium and electronic device, which perform sequential read and write operations on the memory to be tested based on a preset test time and a preset data volume as a unit, and record the sequential read and write performance data of the sequential read and write operations, the preset test time is greater than or equal to 30 days, calculates the median of all sequential read and write performance data, and calculates the difference between each sequential read and write performance data and the median, draws and generates a confidence level map based on all the differences, determines the test result of the memory to be tested based on the confidence level map and the median, and uses the median to effectively feedback the trend of performance data distribution concentration, and sets The confidence level graph method can intuitively display the difference between each performance data and the median. Determining the test results based on the confidence level graph and the median can effectively judge the stability of the long-term performance of the memory, thereby realizing reliable and effective long-term performance testing. In addition, a first confidence level graph is generated based on the sorted differences, and a preset proportion of differences are sequentially extracted from the sorted differences to obtain level data. The level data is plotted to generate a second confidence level graph, and a final confidence level graph is generated based on the first confidence level graph and the second confidence level graph. The confidence level graph can intuitively show the distribution of memory performance fluctuations, which is also convenient for subsequent determination of test results.

[0118] In the above embodiments provided in the present application, it should be understood that the disclosed methods, devices, computer-readable storage media, and electronic devices can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple components or modules can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or components or modules, which can be electrical, mechanical or other forms.

[0119] The components described as separate components may or may not be physically separated, and the components shown as components may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the components may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0120] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each component may exist physically separately, or two or more modules may be integrated into one module. The above integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0121] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0122] It should be noted that, for the convenience of description, the aforementioned method embodiments are all described as a series of action combinations, but those skilled in the art should be aware that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0123] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0124] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent transformations made using the contents of the present invention's specification and drawings, or directly or indirectly applied in related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A long-term performance testing method, characterized in that: Includes steps: Performing sequential read and write operations on the memory to be tested in units of preset data volume based on a preset test duration, and recording sequential read and write performance data of the sequential read and write operations, wherein the preset test duration is greater than or equal to 30 days; Calculating the median of all the sequential read / write performance data, and calculating the difference between each sequential read / write performance data and the median; generating a confidence level map based on all said difference plots; Determine a test result of the memory to be tested based on the confidence level map and the median; The generating a confidence level map based on all the difference values ​​comprises: Sorting the differences in ascending order to obtain sorted differences; Draw and generate a first confidence level map according to the sorted difference values; Extracting a preset proportion of differences from the sorted differences in order to obtain grade data; Plotting the level data to generate a second confidence level map; Generating a final confidence level map according to the first confidence level map and the second confidence level map; The step of extracting a preset proportion of differences from the sorted differences in order to obtain the grade data comprises: Extracting a first preset proportion of differences from the sorted differences in order to obtain first level data; Extracting a second preset ratio of differences from the sorted differences in order to obtain second level data; Extracting a third preset ratio of differences from the sorted differences in order to obtain third level data; Extracting a fourth preset ratio of differences from the sorted differences in order to obtain fourth level data; The first preset ratio, the second preset ratio, the third preset ratio and the fourth preset ratio decrease in sequence; The step of determining the test result of the memory to be tested based on the confidence level graph and the median comprises: Obtaining the confidence level corresponding to the first level data from the confidence level map; Obtaining an absolute error according to the value at the confidence level corresponding to the first level data; Calculate the absolute error and the median to obtain a relative error; It is determined whether the relative error is less than a preset threshold value. If so, it is determined that the test result of the memory to be tested is a test pass. If not, it is determined that the test result of the memory to be tested is a test fail.

2. A long-term performance testing method according to claim 1, characterized in that: The sequential read and write operations are performed on the memory to be tested based on the preset test duration and in units of preset data volume, and the sequential read and write performance data of the sequential read and write operations are recorded, including: Performing a sequential write operation on the memory to be tested in units of a preset data amount until the memory to be tested is filled with sequential data, and recording sequential write performance data of the sequential write operation; Performing a sequential read operation on the memory to be tested in units of the preset data amount until the memory to be tested is sequentially read, and recording sequential read performance data of the sequential read operation; Determine whether the current test duration reaches the preset test duration. If so, stop the sequential read and write operation. If not, erase all data in the memory to be tested, and return to execute the sequential write operation step of the memory to be tested in units of preset data amount.

3. A long-term performance testing method according to claim 1, characterized in that: Before performing sequential read and write operations on the memory to be tested based on the preset test duration and the preset data volume as a unit, the method further includes: Erase all data in the memory under test.

4. A long-term performance testing method according to claim 1, characterized in that: The relative error obtained by calculating according to the absolute error and the median includes: Relative error = the absolute error / the median.

5. A long-term performance testing device, characterized in that: include: A data reading and writing module, used to perform sequential reading and writing operations on the memory to be tested in units of preset data volume based on a preset test duration, and record sequential reading and writing performance data of the sequential reading and writing operations, wherein the preset test duration is greater than or equal to 30 days; A calculation module, used for calculating the median of all the sequential read / write performance data, and calculating the difference between each sequential read / write performance data and the median; A confidence level map generation module, used for generating a confidence level map based on all the difference plots; A test result determination module, used to determine the test result of the memory to be tested based on the confidence level map and the median; The generating a confidence level map based on all the difference values ​​comprises: Sorting the differences in ascending order to obtain sorted differences; Draw and generate a first confidence level map according to the sorted difference values; Extracting a preset proportion of differences from the sorted differences in order to obtain grade data; Plotting the level data to generate a second confidence level map; Generating a final confidence level map according to the first confidence level map and the second confidence level map; The step of extracting a preset proportion of differences from the sorted differences in order to obtain the grade data comprises: Extracting a first preset proportion of differences from the sorted differences in order to obtain first level data; Extracting a second preset ratio of differences from the sorted differences in order to obtain second level data; Extracting a third preset ratio of differences from the sorted differences in order to obtain third level data; Extracting a fourth preset ratio of differences from the sorted differences in order to obtain fourth level data; The first preset ratio, the second preset ratio, the third preset ratio and the fourth preset ratio decrease in sequence; The step of determining the test result of the memory to be tested based on the confidence level graph and the median comprises: Obtaining the confidence level corresponding to the first level data from the confidence level map; Obtaining an absolute error according to the value at the confidence level corresponding to the first level data; Calculate the absolute error and the median to obtain a relative error; It is determined whether the relative error is less than a preset threshold value. If so, it is determined that the test result of the memory to be tested is a test pass. If not, it is determined that the test result of the memory to be tested is a test fail.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step in a long-term performance testing method as described in any one of claims 1 to 4 is implemented.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the processor implements the various steps in the long-term performance testing method as described in any one of claims 1 to 4.

Images