Hard disk test data processing method and system

Abstract

The invention provides a hard disk test data processing method and system, and relates to the technical field of hard disk test.The method comprises the steps that a read-write test is conducted on a hard disk, so that the random read-write speed, the sequential read-write speed and the corresponding response time of the hard disk under different filling capacities are obtained; generating a reading performance comprehensive coefficient, a writing performance comprehensive coefficient and a reading and writing performance comprehensive coefficient in combination with the reading and writing speed and the response time; and when any one of the reading performance comprehensive coefficient, the writing performance comprehensive coefficient and the reading and writing performance comprehensive coefficient is lower than a preset threshold value, sending out a performance alarm signal. According to the method, the read performance comprehensive coefficient, the write performance comprehensive coefficient and the read-write performance comprehensive coefficient are generated by combining the random read-write speed, the sequential read-write speed and the corresponding response time of the hard disk, and the hard disk is comprehensively evaluated by fully combining the read-write speed and the response time, so that the performance evaluation of the hard disk is more comprehensive.

Description

Technical Field

[0001] The present invention relates to the technical field of hard disk testing, and in particular to a hard disk testing data processing method and system. Background Art

[0002] At present, SSD (Solid State Drive) has been widely used in various occasions. Due to its excellent indicators in performance, power consumption, environmental adaptability, etc., it is gradually replacing traditional hard disks. The performance test of solid state drives is a link that must be passed before solid state drives leave the factory. How to improve the test efficiency is a problem that major solid state drive manufacturers are waiting to solve. Therefore, various hard disk test software came into being. The basis of software testing is test requirements, such as software task books, software requirements specifications, software design instructions, software interface communication protocols and other files. Testers decompose test requirements from these files and then design test cases according to the test requirements. Due to the complexity of the software system being tested, testers often need to spend a lot of energy to import test files by themselves, analyze files, sort out test requirements, and subsequently need to count the test results by themselves, which costs a lot of manpower and time costs, and seriously reduces the efficiency of hard disk performance analysis.

[0003] In the prior art, a method, device and medium for processing hard disk test data with the publication number of "CN116521465B" (main classification number of G06F11 / 22) includes: formatting the hard disk to be tested, and performing performance test on the hard disk to be tested based on the test software to obtain initial test parameters; recording the initial response time of the test software for the performance test of the hard disk to be tested; configuring the test software based on the test conditions, and performing performance test on the hard disk to be tested according to the configured test software to obtain multiple test parameters; for each test cycle, recording the response time of the test software for the performance test of the hard disk to be tested; storing the test parameters and response time in a sequential queue; generating a test coordinate axis based on the initial test parameters, the initial response time and the sequential queue; and plotting multiple test parameters and response times to generate a target curve graph. According to this technical solution, the test data of the hard disk can be automatically counted and a curve graph can be generated, which is convenient for the tester to view and analyze.

[0004] However, the prior art still has major defects. For example, when analyzing the read and write performance of the hard disk, the prior art only analyzes and evaluates from a single aspect, such as analyzing the read speed performance of the hard disk from the read speed, analyzing the read response performance of the hard disk from the read response time, etc., that is, the performance evaluation of the hard disk is too one-sided and it is impossible to conduct a comprehensive evaluation of the read performance of the hard disk. Summary of the invention

[0005] The object of the present invention is to provide a hard disk test data processing method and system to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A hard disk test data processing method comprises the following steps:

[0008] S1, performing a read and write test on the hard disk to obtain a random read speed, a sequential read speed, a random write speed, a sequential write speed, a random read response time, a sequential read response time, a random write response time, and a sequential write response time of the hard disk at different filling capacities;

[0009] S2, removing outliers and supplementing missing values ​​from the data obtained in step S1;

[0010] S3, performing data analysis on the random read speed, random read response time, sequential read speed, and sequential read response time processed in step S2 to generate a random read performance coefficient, a sequential read performance coefficient, and a comprehensive read performance coefficient;

[0011] S4, performing data analysis on the random write speed, random write response time, sequential write speed, and sequential write response time processed in step S2 to generate a random write performance coefficient, a sequential write performance coefficient, and a write performance comprehensive coefficient;

[0012] S5, generating a comprehensive read and write performance coefficient according to the comprehensive read performance coefficient and the comprehensive write performance coefficient;

[0013] S6, compare the comprehensive reading performance coefficient ZRXN, the comprehensive writing performance coefficient ZWXN, and the comprehensive reading and writing performance coefficient RWZH with the preset threshold, and issue a performance alarm signal when any one of the comprehensive reading performance coefficient ZRXN, the comprehensive writing performance coefficient ZWXN, and the comprehensive reading and writing performance coefficient RWZH is lower than the preset threshold.

[0014] Furthermore, when testing the hard disk, 20 different filling capacity measurement conditions are set, namely, the filling capacity accounts for 5%, 10%, 15%, ..., 95%, and 100% of the hard disk capacity.

[0015] Furthermore, the random read speed is calibrated as RRS i , the sequential reading speed is calibrated as SRS i , the random write speed is calibrated as RWS i , the sequential writing speed is calibrated as SWS i , the random read response time is calibrated as RRRS i, the sequential read response time is calibrated as SRRS i , the random write response time is calibrated as RWRS i , the sequential write response time is calibrated as SWRS i , the comprehensive coefficient of read performance is calibrated as ZRXN, the comprehensive coefficient of write performance is calibrated as ZWXN, and the comprehensive coefficient of read and write performance is calibrated as RWZH, i represents the number of the hard disk tested at different filling capacities, and i=1, 2, 3, ..., m.

[0016] Furthermore, the random read speed, random read response time, sequential read speed, and sequential read response time processed in step S2 are analyzed to generate the random read performance coefficient, the sequential read performance coefficient, and the specific logic of the comprehensive read performance coefficient is as follows:

[0017] S31, performing data analysis on the random read speed and random read response time after the processing in step S2, and generating a random read performance coefficient, the calculation formula of which is as follows:

[0018]

[0019] Among them, the random read performance coefficient is calibrated as RRXN, Indicates the average random read speed, RRS zs Indicates the median random read speed, Indicates the mean random read response time, RRRS zs Indicates the median random read response time, RRBZ max Indicates the maximum value of the ratio of random read speed and its corresponding random read response time, RRBZ min Indicates the minimum value of the random read speed and its corresponding random read response time ratio;

[0020] Wherein, λ1, λ2, and λ3 are all preset proportional coefficients, and λ1+λ2+λ3=1, and 0<λ3<λ2<λ1<1;

[0021] S32, performing data analysis on the sequential read speed and sequential read response time after the processing in step S2, and generating a sequential read performance coefficient, the calculation formula of which is as follows:

[0022]

[0023] Among them, the sequential read performance coefficient is calibrated as SRXN, Indicates the average sequential read speed, SRS zs Indicates the median sequential read speed, Represents the mean sequential read response time, SRRS zsIndicates the median sequential read response time, SRBZ max Indicates the maximum value of the ratio of sequential read speed and its corresponding sequential read response time, SRBZ min Indicates the minimum value of the ratio of the sequential read speed and its corresponding sequential read response time;

[0024] Wherein, α1, α2, and α3 are all preset proportional coefficients, and α1+α2+α3=1, and 0<α3<α2<α1<1;

[0025] S33, generating a comprehensive read performance coefficient according to the random read performance coefficient and the sequential read performance coefficient, and the calculation formula is as follows:

[0026] ZRXN=β1*RRXN+β2*SRXN;

[0027] Wherein, β1 and β2 are both preset proportional coefficients, and β1+β2=1, and 0<β1<1, 0<β2<1.

[0028] Furthermore, the value range of λ1 is 0.4-0.6, the value range of λ2 is 0.3-0.4, the value range of λ3 is 0.1-0.2, the value range of α1 is 0.5-0.7, the value range of α2 is 0.2-0.3, and the value range of α3 is 0.1-0.2.

[0029] For hard disks that tend to perform random read operations, the value range of β1 is 0.6-0.8, and the value range of β2 is 0.2-0.4. For hard disks that tend to perform sequential read operations, the value range of β1 is 0.2-0.4, and the value range of β2 is 0.6-0.8. For hard disks that perform both random read and sequential read operations, the values ​​of β1 and β2 are both 0.5.

[0030] Furthermore, the random write speed, random write response time, sequential write speed, and sequential write response time processed in step S2 are analyzed to generate the random write performance coefficient, the sequential write performance coefficient, and the specific logic of the comprehensive write performance coefficient is as follows:

[0031] S41, performing data analysis on the random write speed and random write response time processed in step S2, and generating a random write performance coefficient, the calculation formula of which is as follows:

[0032]

[0033] Among them, the random write performance coefficient is calibrated as RWXN, Indicates the average random write speed, RWS zs Indicates the median random write speed, Indicates the mean random write response time, RWRS zs Indicates the median random write response time, RWBZ max Indicates the maximum value of the ratio of random write speed and its corresponding random write response time, RWBZ min Indicates the minimum value of the ratio of random write speed to its corresponding random write response time;

[0034] Wherein, ω1, ω2, and ω3 are all preset proportional coefficients, and ω1+ω2+ω3=1, and 0<ω3<ω2<ω1<1;

[0035] S42, performing data analysis on the sequential write speed and sequential write response time after the processing in step S2, and generating a sequential write performance coefficient, the calculation formula of which is as follows:

[0036]

[0037] Among them, the sequential write performance coefficient is calibrated as SWXN, Indicates the average sequential write speed, SWS zs Indicates the median sequential write speed, Indicates the mean sequential write response time, SWRS zs Indicates the median sequential write response time, SWBZ max Indicates the maximum value of the ratio of sequential write speed and its corresponding sequential write response time, SWBZ min Indicates the minimum value of the ratio of the sequential write speed and its corresponding sequential write response time;

[0038] Wherein, δ1, δ2, and δ3 are all preset proportional coefficients, and δ1+δ2+δ3=1, and 0<δ3<δ2<δ1<1;

[0039] S43, generating a comprehensive write performance coefficient according to the random write performance coefficient and the sequential write performance coefficient, and the calculation formula is as follows:

[0040] ZWXN=γ1*RWXN+γ2*SWXN;

[0041] Among them, γ1 and γ2 are both preset proportional coefficients, and γ1+γ2=1, and 0<γ1<1, 0<γ2<1.

[0042] Furthermore, the value range of ω1 is 0.4-0.6, the value range of ω2 is 0.3-0.4, the value range of ω3 is 0.1-0.2, the value range of δ1 is 0.5-0.7, the value range of δ2 is 0.2-0.3, and the value range of δ3 is 0.1-0.2;

[0043] For hard disks that tend to perform random write operations, the value range of γ1 is 0.6-0.8, and the value range of γ2 is 0.2-0.4. For hard disks that tend to perform sequential write operations, the value range of γ1 is 0.2-0.4, and the value range of γ2 is 0.6-0.8. For hard disks that perform both random write and sequential write operations evenly, the values ​​of γ1 and γ2 are both 0.5.

[0044] Furthermore, the calculation formula of the comprehensive coefficient of read-write performance is as follows:

[0045] RWZH=τ1*ZRXN+τ2*ZWXN

[0046] Among them, τ1 and τ2 are both preset proportional coefficients, and τ1+τ2=1, and 0<τ1<1, 0<τ2<1.

[0047] Furthermore, the comprehensive coefficient of read performance ZRXN, the comprehensive coefficient of write performance ZWXN, and the comprehensive coefficient of read-write performance RWZH are compared with the preset threshold, and the specific logic of issuing a performance alarm signal when any one of the comprehensive coefficient of read performance ZRXN, the comprehensive coefficient of write performance ZWXN, and the comprehensive coefficient of read-write performance RWZH is lower than the preset threshold is:

[0048] The preset thresholds include a read performance threshold TTH1, a write performance threshold TTH2, and a read-write performance threshold TTH3. When the read performance comprehensive coefficient ZRXN is less than the read performance threshold TTH1, a read performance alarm signal is issued; when the write performance comprehensive coefficient ZWXN is less than the write performance threshold TTH2, a write performance alarm signal is issued; and when the read-write performance comprehensive coefficient RWZH is less than the read-write performance threshold TTH3, a read-write performance alarm signal is issued.

[0049] A hard disk test data processing system, used for the hard disk test data processing method, comprises:

[0050] A data acquisition module, used for performing a read and write test on the hard disk to obtain the random read speed, sequential read speed, random write speed, sequential write speed, random read response time, sequential read response time, random write response time, and sequential write response time of the hard disk at different filling capacities;

[0051] A data preprocessing module is used to remove outliers and supplement missing values ​​from the data obtained in step S1;

[0052] The read performance analysis module is used to analyze the random read speed, random read response time, sequential read speed, and sequential read response time after the processing in step S2, and generate a random read performance coefficient, a sequential read performance coefficient, and a comprehensive read performance coefficient.

[0053] A write performance analysis module, used to perform data analysis on the random write speed, random write response time, sequential write speed, and sequential write response time after processing in step S2, and generate a random write performance coefficient, a sequential write performance coefficient, and a comprehensive write performance coefficient;

[0054] A read / write performance analysis module, used to generate a comprehensive read / write performance coefficient according to a comprehensive read performance coefficient and a comprehensive write performance coefficient;

[0055] The performance evaluation module is used to compare the comprehensive reading performance coefficient ZRXN, the comprehensive writing performance coefficient ZWXN, and the comprehensive reading and writing performance coefficient RWZH with the preset threshold value, and to issue a performance alarm signal when any one of the comprehensive reading performance coefficient ZRXN, the comprehensive writing performance coefficient ZWXN, and the comprehensive reading and writing performance coefficient RWZH is lower than the preset threshold value.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] The hard disk test data processing method and system of the present invention generates a comprehensive reading performance coefficient, a comprehensive writing performance coefficient, and a comprehensive reading and writing performance coefficient by combining the random reading and writing speeds, sequential reading and writing speeds, and corresponding response times of the hard disk, and fully combines the reading and writing speeds and response times to comprehensively evaluate the hard disk, making the performance evaluation of the hard disk more comprehensive and improving the effect of the hard disk performance evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a flowchart of the hard disk test data processing method of the present invention;

[0059] Figure 2 This is a module unit diagram of the hard disk test data processing system of the present invention. DETAILED DESCRIPTION

[0060] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0061] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0062] Embodiment 1:

[0063] See also Figure 1 The present invention provides a method for processing hard disk test data according to an embodiment, comprising the following steps:

[0064] S1, performing a read and write test on the hard disk to obtain the random read speed, sequential read speed, random write speed, sequential write speed, and corresponding response time of the hard disk at different filling capacities;

[0065] The response time includes the random read response time corresponding to the random read test of the hard disk at different filling capacities, the sequential read response time corresponding to the sequential read test, the random write response time corresponding to the random write test, and the sequential write response time corresponding to the sequential write test;

[0066] Among them, the random read speed is calibrated as RRS i , the sequential read speed is calibrated as SRS i , the random write speed is marked as RWS i , the sequential write speed is calibrated as SWS i , the random read response time is calibrated as RRRS i , the sequential read response time is calibrated as SRRS i , the random write response time is calibrated as RWRS i , the sequential write response time is calibrated as SWRS i , i represents the number of the hard disk tested at different filling capacities, and i=1, 2, 3, ..., m, and m represents the total number of times the hard disk is filled with different capacities, and m≥5, m∈N + ;

[0067] As an implementation mode, when testing a hard disk, 20 different filling capacity measurement conditions are set, namely, 5%, 10%, 15%, ..., 95%, and 100% of the hard disk capacity;

[0068] It should be noted that when testing the hard disk, fio software can be used as the testing software. Using fio software to perform random read test, sequential read test, random write test, and sequential write test on the hard disk, and obtaining the corresponding random read speed and random read response time, sequential read speed and sequential read response time, random write speed and random write response time, sequential write speed and sequential write response time is existing technology and will not be elaborated here.

[0069] S2, removing outliers and supplementing missing values ​​from the data obtained in step S1;

[0070] It should be noted that the data processing for removing outliers and supplementing missing values ​​of the collected data is to ensure the accuracy of subsequent data analysis. Specifically, existing methods can be used for processing. For example, outliers can be identified through standard deviation and removed, so as to better filter out outliers statistically, thereby improving the accuracy of subsequent data analysis. After removing outliers, missing values ​​are supplemented by interpolation to further ensure the accuracy of subsequent data analysis. Among them, linear interpolation method can be used to supplement missing values ​​by interpolation, which will not be elaborated here.

[0071] S3, performing data analysis on the random read speed, random read response time, sequential read speed, and sequential read response time processed in step S2, and generating a random read performance coefficient, a sequential read performance coefficient, and a comprehensive read performance coefficient, as follows:

[0072] S31, performing data analysis on the random read speed and random read response time after the processing in step S2, and generating a random read performance coefficient, the calculation formula of which is as follows:

[0073]

[0074] It should be noted that the random read performance coefficient is calibrated as RRXN. Indicates the average random read speed, the average random read speed The larger the value, the better the random read performance of the hard disk. zs Indicates the median random read speed, random read speed median RRS zs The larger the value, the better the random read performance of the hard disk. Indicates the mean random read response time. The smaller it is, the better the random read performance of the hard disk is.zs Indicates the median random read response time, median random read response time RRRS zs The smaller it is, the better the random read performance of the hard disk is. max Indicates the maximum value of the ratio of random read speed and its corresponding random read response time, the maximum value of the ratio of random read speed and its corresponding random read response time RRBZ max The larger the value, the better the random read performance of the hard disk. min Indicates the minimum value of the ratio of random read speed and its corresponding random read response time, the minimum value of the ratio of random read speed and its corresponding random read response time RRBZ min The larger it is, the better the random read performance of the hard disk is;

[0075] It should be noted that the average random read speed Median random read speed RRS zs , Mean random read response time Median random read response time RRRS zs , the maximum value of the random read speed and its corresponding random read response time ratio RRBZ max , and the minimum value of the random read speed and its corresponding random read response time ratio RRBZ min , can be obtained through existing data processing software, which will not be described in detail here;

[0076] It should be noted that λ1, λ2, and λ3 are all preset proportional coefficients, and λ1 represents The weight in the calculation of random read performance coefficient, λ2 represents The weight in the calculation of random read performance coefficient, λ3 represents ln(RRRS max +RRRS min ) is the weight of the random read performance coefficient calculation, and λ1+λ2+λ3=1, and 0<λ3<λ2<λ1<1, and the specific values ​​of λ1, λ2, and λ3 are generally determined by those skilled in the art according to actual conditions;

[0077] As an implementation mode, the value range of λ1 is 0.4-0.6, the value range of λ2 is 0.3-0.4, and the value range of λ3 is 0.1-0.2;

[0078] It should be noted that the random read speed RRS i The larger the value, the higher the random read response time. i The smaller it is, the better the random read performance of the hard disk is. and ln(RRRS max +RRRS min) is larger, so the random read performance coefficient RRXN of the hard disk is larger;

[0079] S32, performing data analysis on the sequential read speed and sequential read response time after the processing in step S2, and generating a sequential read performance coefficient, the calculation formula of which is as follows:

[0080]

[0081] It should be noted that the sequential read performance coefficient is calibrated as SRXN. Indicates the average sequential read speed. The larger the value, the better the sequential read performance of the hard disk. zs Indicates the median sequential read speed, SRS zs The larger the value, the better the sequential read performance of the hard disk. Indicates the mean sequential read response time. The smaller the value, the better the sequential read performance of the hard disk. zs Indicates the median sequential read response time, the median sequential read response time SRRS zs The smaller the SRBZ, the better the sequential read performance of the hard disk. max Indicates the maximum value of the ratio of sequential read speed and its corresponding sequential read response time, SRBZ max The larger the value, the better the sequential read performance of the hard disk. min Indicates the minimum value of the ratio of sequential read speed and its corresponding sequential read response time, the minimum value of the ratio of sequential read speed and its corresponding sequential read response time SRBZ min The larger it is, the better the sequential read performance of the hard disk is;

[0082] It should be noted that the average sequential read speed Median sequential read speed SRS zs , Mean sequential read response time Median Sequential Read Response Time (SRRS) zs , the maximum value of the sequential read speed and its corresponding sequential read response time ratio SRBZ max , and the minimum value of the sequential read speed and its corresponding sequential read response time ratio SRBZ min , can be obtained through existing data processing software, which will not be described in detail here;

[0083] It should be noted that α1, α2, and α3 are all preset proportional coefficients, α1 represents The weight in the calculation of the sequential read performance coefficient, α2 represents The weight in the calculation of the sequential read performance coefficient, α3 represents ln(SRRS max +SRRS min ) is the weight of the sequential read performance coefficient calculation, and α1+α2+α3=1, and 0<α3<α2<α1<1, and the specific values ​​of α1, α2, and α3 are generally determined by those skilled in the art according to actual conditions;

[0084] As an implementation mode, the value range of α1 is 0.5-0.7, the value range of α2 is 0.2-0.3, and the value range of α3 is 0.1-0.2;

[0085] It should be noted that the sequential read speed SRS i The larger the value, the higher the sequential read response time (SRRS). i The smaller it is, the better the sequential read performance of the hard disk is. and ln(SRRS max +SRRS min ) is larger, so the sequential read performance coefficient SRXN of the hard disk is larger;

[0086] S33, generating a comprehensive read performance coefficient according to the random read performance coefficient and the sequential read performance coefficient, and the calculation formula is as follows:

[0087] ZRXN=β1*RRXN+β2*SRXN;

[0088] It should be noted that the comprehensive coefficient of read performance is calibrated as ZRXN, β1 and β2 are both preset proportional coefficients, β1 represents the weight of the random read performance coefficient RRXN in the calculation of the comprehensive coefficient of read performance, β2 represents the weight of the sequential read performance coefficient SRXN in the calculation of the comprehensive coefficient of read performance, and β1+β2=1, and 0<β1<1, 0<β2<1, and the specific values ​​of β1 and β2 are generally determined by those skilled in the art according to actual conditions;

[0089] As an implementation mode, for a hard disk that is biased toward random read work, the value range of β1 is 0.6-0.8, and the value range of β2 is 0.2-0.4; for a hard disk that is biased toward sequential read work, the value range of β1 is 0.2-0.4, and the value range of β2 is 0.6-0.8; for a hard disk that is evenly biased toward random read work and sequential read work, the values ​​of β1 and β2 are both 0.5;

[0090] It should be noted that the larger the random read performance coefficient RRXN and the sequential read performance coefficient SRXN are, the faster the hard disk read speed is and the shorter the read response time is, that is, the better the hard disk read performance is, and the larger the comprehensive read performance coefficient ZRXN is.

[0091] S4, performing data analysis on the random write speed, random write response time, sequential write speed, and sequential write response time processed in step S2, and generating a random write performance coefficient, a sequential write performance coefficient, and a write performance comprehensive coefficient, as follows:

[0092] S41, performing data analysis on the random write speed and random write response time processed in step S2, and generating a random write performance coefficient, the calculation formula of which is as follows:

[0093]

[0094] It should be noted that the random write performance coefficient is calibrated as RWXN. Indicates the average random write speed, the average random write speed The larger the value, the better the random write performance of the hard disk. zs Indicates the median random write speed, median random write speed RWS zs The larger it is, the better the random write performance of the hard disk is. Indicates the mean random write response time. The smaller it is, the better the random write performance of the hard disk is. zs Indicates the median random write response time, random write response time median RWRS zs The smaller it is, the better the random write performance of the hard disk is. max Indicates the maximum value of the ratio of random write speed and its corresponding random write response time, the maximum value of the ratio of random write speed and its corresponding random write response time RWBZ max The larger the value, the better the random write performance of the hard disk. min Indicates the minimum value of the ratio of random write speed and its corresponding random write response time, the minimum value of the ratio of random write speed and its corresponding random write response time RWBZ min The larger it is, the better the random write performance of the hard disk is;

[0095] It should be noted that the average random write speed Random write speed median RWS zs , Mean random write response time Random write response time median RWRS zs, the maximum value of the random write speed and its corresponding random write response time ratio RWBZ max , and the minimum value of the ratio of random write speed and its corresponding random write response time RWBZ min , can be obtained through existing data processing software, which will not be described in detail here;

[0096] It should be noted that ω1, ω2, and ω3 are all preset proportional coefficients, ω1 represents The weight in the calculation of random write performance coefficient, ω2 represents The weight in the calculation of random write performance coefficient, ω3 represents ln(RWRS max +RWRS min ) is the weight of random write performance coefficient calculation, and ω1+ω2+ω3=1, and 0<ω3<ω2<ω1<1, and the specific values ​​of ω1, ω2, and ω3 are generally determined by those skilled in the art according to actual conditions;

[0097] As an implementation mode, the value range of ω1 is 0.4-0.6, the value range of ω2 is 0.3-0.4, and the value range of ω3 is 0.1-0.2;

[0098] It should be noted that the random write speed RWS i The larger the value, the higher the random write response time RWRS i The smaller it is, the better the random write performance of the hard disk is. and ln(RWRS max +RWRS min ) is larger, so the random write performance coefficient RWXN of the hard disk is larger;

[0099] S42, performing data analysis on the sequential write speed and sequential write response time after the processing in step S2, and generating a sequential write performance coefficient, the calculation formula of which is as follows:

[0100]

[0101] It should be noted that the sequential write performance coefficient is calibrated as SWXN. Indicates the average sequential write speed. The larger the value, the better the sequential write performance of the hard disk. zs Indicates the median sequential write speed, median sequential write speed SWS zs The larger the value, the better the sequential write performance of the hard disk. Indicates the mean sequential write response time. The smaller the size, the better the sequential write performance of the hard disk. zsIndicates the median sequential write response time, the median sequential write response time SWRS zs The smaller it is, the better the sequential write performance of the hard disk is. max Indicates the maximum value of the ratio of sequential write speed and its corresponding sequential write response time, the maximum value of the ratio of sequential write speed and its corresponding sequential write response time SWBZ max The larger the value, the better the sequential write performance of the hard disk. min Indicates the minimum value of the ratio of sequential write speed and its corresponding sequential write response time, the minimum value of the ratio of sequential write speed and its corresponding sequential write response time SWBZ min The larger the value, the better the sequential write performance of the hard disk.

[0102] It should be noted that the average sequential write speed Sequential write speed median SWS zs , Mean sequential write response time Sequential write response time median SWRS zs , the maximum value of the sequential write speed and its corresponding sequential write response time ratio SWBZ max , and the minimum value of the ratio of the sequential write speed and its corresponding sequential write response time SWBZ min , can be obtained through existing data processing software, which will not be described in detail here;

[0103] It should be noted that δ1, δ2, and δ3 are all preset proportional coefficients, δ1 represents The weight in the calculation of the sequential write performance coefficient, δ2 represents The weight in the calculation of the sequential write performance coefficient, δ3 represents ln(SWRS max +SWRS min ) is the weight of the sequential write performance coefficient calculation, and δ1+δ2+δ3=1, and 0<δ3<δ2<δ1<1, and the specific values ​​of δ1, δ2, and δ3 are generally determined by those skilled in the art according to actual conditions;

[0104] As an implementation mode, the value range of δ1 is 0.5-0.7, the value range of δ2 is 0.2-0.3, and the value range of δ3 is 0.1-0.2;

[0105] It should be noted that the sequential write speed SWS i The larger the value, the higher the sequential write response time SWRS. i The smaller it is, the better the sequential write performance of the hard disk is. and ln(SWRS max +SWRS min) is larger, so the sequential write performance coefficient SWXN of the hard disk is larger;

[0106] S43, generating a comprehensive write performance coefficient according to the random write performance coefficient and the sequential write performance coefficient, and the calculation formula is as follows:

[0107] ZWXN=γ1*RWXN+γ2*SWXN;

[0108] It should be noted that the comprehensive write performance coefficient is calibrated as ZWXN, γ1 and γ2 are both preset proportional coefficients, γ1 represents the weight of the random write performance coefficient RWXN in the calculation of the comprehensive write performance coefficient, γ2 represents the weight of the sequential write performance coefficient SWXN in the calculation of the comprehensive write performance coefficient, and γ1+γ2=1, and 0<γ1<1, 0<γ2<1, and the specific values ​​of γ1 and γ2 are generally determined by those skilled in the art according to actual conditions;

[0109] As an implementation mode, for a hard disk that tends to work with random writes, the value range of γ1 is 0.6-0.8, and the value range of γ2 is 0.2-0.4. For a hard disk that tends to work with sequential writes, the value range of γ1 is 0.2-0.4, and the value range of γ2 is 0.6-0.8. For a hard disk that has a uniform random write and sequential write performance, the values ​​of γ1 and γ2 are both 0.5.

[0110] It should be noted that the larger the random write performance coefficient RWXN and the sequential write performance coefficient SWXN, the faster the write speed of the hard disk and the shorter the write response time, that is, the better the write performance of the hard disk, and the larger the comprehensive write performance coefficient ZWXN.

[0111] S5, generating a comprehensive read and write performance coefficient according to the comprehensive read performance coefficient and the comprehensive write performance coefficient, and the calculation formula is as follows:

[0112] RWZH=τ1*ZRXN+τ2*ZWXN

[0113] It should be noted that the comprehensive coefficient of read and write performance is calibrated as RWZH, τ1 and τ2 are both preset proportional coefficients, τ1 represents the weight of the comprehensive coefficient of read performance ZRXN in the calculation of the comprehensive coefficient of read and write performance, τ2 represents the weight of the comprehensive coefficient of write performance ZWXN in the calculation of the comprehensive coefficient of read and write performance, and τ1+τ2=1, and 0<τ1<1, 0<τ2<1, and the specific values ​​of τ1 and τ2 are generally determined by those skilled in the art according to actual conditions;

[0114] As an implementation mode, for a hard disk that is biased toward reading, the value range of τ1 is 0.6-0.8, and the value range of τ2 is 0.2-0.4; for a hard disk that is biased toward writing, the value range of τ1 is 0.2-0.4, and the value range of τ2 is 0.6-0.8; for a hard disk that is evenly distributed in reading and writing, the values ​​of τ1 and τ2 are both 0.5;

[0115] It should be noted that the larger the comprehensive coefficient of read performance ZRXN and the comprehensive coefficient of write performance ZWXN, the better the read performance and write performance of the hard disk, and the larger the comprehensive coefficient of read and write performance RWZH.

[0116] S6, comparing the comprehensive reading performance coefficient ZRXN, the comprehensive writing performance coefficient ZWXN, and the comprehensive reading and writing performance coefficient RWZH with a preset threshold, and issuing a performance alarm signal when any one of the comprehensive reading performance coefficient ZRXN, the comprehensive writing performance coefficient ZWXN, and the comprehensive reading and writing performance coefficient RWZH is lower than the preset threshold, as follows:

[0117] The preset thresholds include a read performance threshold TTH1, a write performance threshold TTH2, and a read-write performance threshold TTH3. When the read performance comprehensive coefficient ZRXN is less than the read performance threshold TTH1, a read performance alarm signal is issued; when the write performance comprehensive coefficient ZWXN is less than the write performance threshold TTH2, a write performance alarm signal is issued; and when the read-write performance comprehensive coefficient RWZH is less than the read-write performance threshold TTH3, a read-write performance alarm signal is issued;

[0118] It should be noted that the specific values ​​of the read performance threshold TTH1, the write performance threshold TTH2, and the read / write performance threshold TTH3 are generally determined by those skilled in the art according to actual conditions. The specific acquisition method can be: initialize the hard disk that has passed the test, and obtain the random read speed and random read response time, sequential read speed and sequential read response time, random write speed and random write response time, sequential write speed and sequential write response time of the hard disk after initialization through the test software, and use the ratio of the random read speed to the random read response time, and the ratio of the sequential read speed to the sequential read response time to obtain the random read speed and random read response time. The ratio of the read response time is added together, divided by two and multiplied by 0.8 as the read performance threshold TTH1, and the ratio of the random write speed and the random write response time, and the ratio of the sequential write speed and the sequential write response time are added together, divided by two and multiplied by 0.8 as the write performance threshold TTH2, and the read performance threshold TTH1 and the write performance threshold TTH2 are added together and divided by two as the read-write performance threshold TTH3. Of course, the specific values ​​of the read performance threshold TTH1, the write performance threshold TTH2, and the read-write performance threshold TTH3 can also be obtained by other methods, which will not be repeated here.

[0119] Embodiment 2:

[0120] See also Figure 2 The present invention provides a hard disk test data processing system according to an embodiment of the present invention, which is used in the hard disk test data processing method, and comprises:

[0121] A data acquisition module, used for performing a read and write test on the hard disk to obtain the random read speed, sequential read speed, random write speed, sequential write speed, random read response time, sequential read response time, random write response time, and sequential write response time of the hard disk at different filling capacities;

[0122] A data preprocessing module is used to remove outliers and supplement missing values ​​from the data obtained in step S1;

[0123] The read performance analysis module is used to analyze the random read speed, random read response time, sequential read speed, and sequential read response time after the processing in step S2, and generate a random read performance coefficient, a sequential read performance coefficient, and a comprehensive read performance coefficient.

[0124] A write performance analysis module, used to perform data analysis on the random write speed, random write response time, sequential write speed, and sequential write response time after processing in step S2, and generate a random write performance coefficient, a sequential write performance coefficient, and a comprehensive write performance coefficient;

[0125] A read / write performance analysis module, used to generate a comprehensive read / write performance coefficient according to a comprehensive read performance coefficient and a comprehensive write performance coefficient;

[0126] The performance evaluation module is used to compare the comprehensive reading performance coefficient ZRXN, the comprehensive writing performance coefficient ZWXN, and the comprehensive reading and writing performance coefficient RWZH with the preset threshold value, and to issue a performance alarm signal when any one of the comprehensive reading performance coefficient ZRXN, the comprehensive writing performance coefficient ZWXN, and the comprehensive reading and writing performance coefficient RWZH is lower than the preset threshold value.

[0127] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0128] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0129] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0130] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A hard disk test data processing method, characterized in that: The steps include: S1, performing a read and write test on the hard disk to obtain a random read speed, a sequential read speed, a random write speed, a sequential write speed, a random read response time, a sequential read response time, a random write response time, and a sequential write response time of the hard disk at different filling capacities; S2, removing outliers and supplementing missing values ​​from the data obtained in step S1; S3, performing data analysis on the random read speed, random read response time, sequential read speed, and sequential read response time processed in step S2 to generate a random read performance coefficient, a sequential read performance coefficient, and a comprehensive read performance coefficient; S4, performing data analysis on the random write speed, random write response time, sequential write speed, and sequential write response time processed in step S2 to generate a random write performance coefficient, a sequential write performance coefficient, and a write performance comprehensive coefficient; S5, generating a comprehensive read and write performance coefficient according to the comprehensive read performance coefficient and the comprehensive write performance coefficient; S6, comparing the comprehensive reading performance coefficient, the comprehensive writing performance coefficient, and the comprehensive reading and writing performance coefficient with a preset threshold, and issuing a performance alarm signal when any one of the comprehensive reading performance coefficient, the comprehensive writing performance coefficient, and the comprehensive reading and writing performance coefficient is lower than the preset threshold.

2. A hard disk test data processing method according to claim 1, characterized in that: When testing the hard disk, 20 different filling capacity measurement conditions are set, namely, 5%, 10%, 15%, ..., 95%, and 100% of the hard disk capacity.

3. The hard disk test data processing method according to claim 1, characterized in that: The random read speed is denoted as RRS i , the sequential reading speed is calibrated as SRS i , the random write speed is calibrated as RWS i , the sequential writing speed is calibrated as SWS i , the random read response time is calibrated as RRRS i , the sequential read response time is calibrated as SRRS i , the random write response time is calibrated as RWRS i , the sequential write response time is calibrated as SWRS i , the comprehensive coefficient of read performance is calibrated as ZRXN, the comprehensive coefficient of write performance is calibrated as ZWXN, and the comprehensive coefficient of read and write performance is calibrated as RWZH, i represents the number of the hard disk tested at different filling capacities, and i=1, 2, 3, ..., m.

4. A hard disk test data processing method according to claim 3, characterized in that: The specific logic of performing data analysis on the random read speed, random read response time, sequential read speed, and sequential read response time after processing in step S2 to generate the random read performance coefficient, the sequential read performance coefficient, and the comprehensive read performance coefficient is as follows: S31, performing data analysis on the random read speed and random read response time after the processing in step S2, and generating a random read performance coefficient, the calculation formula of which is as follows: Among them, the random read performance coefficient is calibrated as RRXN, Indicates the average random read speed, RRS zs Indicates the median random read speed, Indicates the mean random read response time, RRRS zs Indicates the median random read response time, RRBZ max Indicates the maximum value of the ratio of random read speed and its corresponding random read response time, RRBZ min Indicates the minimum value of the random read speed and its corresponding random read response time ratio; Wherein, λ1, λ2, and λ3 are all preset proportional coefficients, and λ1+λ2+λ3=1, and 0<λ3<λ2<λ1<1; S32, performing data analysis on the sequential read speed and sequential read response time after the processing in step S2, and generating a sequential read performance coefficient, the calculation formula of which is as follows: Among them, the sequential read performance coefficient is calibrated as SRXN, Indicates the average sequential read speed, SRS zs Indicates the median sequential read speed, Represents the mean sequential read response time, SRRS zs Indicates the median sequential read response time, SRBZ max Indicates the maximum value of the ratio of sequential read speed and its corresponding sequential read response time, SRBZ min Indicates the minimum value of the ratio of the sequential read speed and its corresponding sequential read response time; Wherein, α1, α2, and α3 are all preset proportional coefficients, and α1+α2+α3=1, and 0<α3<α2<α1<1; S33, generating a comprehensive read performance coefficient according to the random read performance coefficient and the sequential read performance coefficient, and the calculation formula is as follows: ZRXN=β1*RRXN+β2*SRXN; Wherein, β1 and β2 are both preset proportional coefficients, and β1+β2=1, and 0<β1<1, 0<β2<1.

5. A hard disk test data processing method according to claim 4, characterized in that: The value range of λ1 is 0.4-0.6, the value range of λ2 is 0.3-0.4, the value range of λ3 is 0.1-0.2, the value range of α1 is 0.5-0.7, the value range of α2 is 0.2-0.3, and the value range of α3 is 0.1-0.2; For hard disks that tend to perform random read operations, the value range of β1 is 0.6-0.8, and the value range of β2 is 0.2-0.

4. For hard disks that tend to perform sequential read operations, the value range of β1 is 0.2-0.4, and the value range of β2 is 0.6-0.

8. For hard disks that perform both random read and sequential read operations equally, the values ​​of β1 and β2 are both 0.

5.

6. The hard disk test data processing method according to claim 3, characterized in that: The specific logic of performing data analysis on the random write speed, random write response time, sequential write speed, and sequential write response time after processing in step S2 to generate the random write performance coefficient, the sequential write performance coefficient, and the comprehensive write performance coefficient is as follows: S41, performing data analysis on the random write speed and random write response time processed in step S2, and generating a random write performance coefficient, the calculation formula of which is as follows: Among them, the random write performance coefficient is calibrated as RWXN, Indicates the average random write speed, RWS zs Indicates the median random write speed, Indicates the mean random write response time, RWRS zs Indicates the median random write response time, RWBZ max Indicates the maximum value of the ratio of random write speed and its corresponding random write response time, RWBZ min Indicates the minimum value of the ratio of random write speed to its corresponding random write response time; Wherein, ω1, ω2, and ω3 are all preset proportional coefficients, and ω1+ω2+ω3=1, and 0<ω3<ω2<ω1<1; S42, performing data analysis on the sequential write speed and sequential write response time after the processing in step S2, and generating a sequential write performance coefficient, the calculation formula of which is as follows: Among them, the sequential write performance coefficient is calibrated as SWXN, Indicates the average sequential write speed, SWS zs Indicates the median sequential write speed, Indicates the mean sequential write response time, SWRS zs Indicates the median sequential write response time, SWBZ max Indicates the maximum value of the ratio of sequential write speed and its corresponding sequential write response time, SWBZ min Indicates the minimum value of the ratio of the sequential write speed and its corresponding sequential write response time; Wherein, δ1, δ2, and δ3 are all preset proportional coefficients, and δ1+δ2+δ3=1, and 0<δ3<δ2<δ1<1; S43, generating a comprehensive write performance coefficient according to the random write performance coefficient and the sequential write performance coefficient, and the calculation formula is as follows: ZWXN=γ1*RWXN+γ2*SWXN; Among them, γ1 and γ2 are both preset proportional coefficients, and γ1+γ2=1, and 0<γ1<1, 0<γ2<1.

7. A hard disk test data processing method according to claim 6, characterized in that: The value range of ω1 is 0.4-0.6, the value range of ω2 is 0.3-0.4, the value range of ω3 is 0.1-0.2, the value range of δ1 is 0.5-0.7, the value range of δ2 is 0.2-0.3, and the value range of δ3 is 0.1-0.2; For hard disks that tend to perform random write operations, the value range of γ1 is 0.6-0.8, and the value range of γ2 is 0.2-0.

4. For hard disks that tend to perform sequential write operations, the value range of γ1 is 0.2-0.4, and the value range of γ2 is 0.6-0.

8. For hard disks that perform both random write and sequential write operations evenly, the values ​​of γ1 and γ2 are both 0.

5.

8. The hard disk test data processing method according to claim 3, characterized in that: The calculation formula of the comprehensive coefficient of read and write performance is as follows: RWZH=τ1*ZRXN+τ2*ZWXN Among them, τ1 and τ2 are both preset proportional coefficients, and τ1+τ2=1, and 0<τ1<1, 0<τ2<1.

9. The hard disk test data processing method according to claim 3, characterized in that: The specific logic of comparing the comprehensive coefficient of read performance, the comprehensive coefficient of write performance, and the comprehensive coefficient of read-write performance with the preset threshold, and issuing a performance alarm signal when any one of the comprehensive coefficient of read performance, the comprehensive coefficient of write performance, and the comprehensive coefficient of read-write performance is lower than the preset threshold is: The preset thresholds include a read performance threshold TTH1, a write performance threshold TTH2, and a read-write performance threshold TTH3. When the read performance comprehensive coefficient ZRXN is less than the read performance threshold TTH1, a read performance alarm signal is issued; when the write performance comprehensive coefficient ZWXN is less than the write performance threshold TTH2, a write performance alarm signal is issued; and when the read-write performance comprehensive coefficient RWZH is less than the read-write performance threshold TTH3, a read-write performance alarm signal is issued.

10. A hard disk test data processing system, used in the hard disk test data processing method according to any one of claims 1 to 9, characterized in that: include: A data acquisition module, used for performing a read and write test on the hard disk to obtain the random read speed, sequential read speed, random write speed, sequential write speed, random read response time, sequential read response time, random write response time, and sequential write response time of the hard disk at different filling capacities; A data preprocessing module is used to remove outliers and supplement missing values ​​from the data obtained in step S1; The read performance analysis module is used to analyze the random read speed, random read response time, sequential read speed, and sequential read response time after the processing in step S2, and generate a random read performance coefficient, a sequential read performance coefficient, and a comprehensive read performance coefficient. A write performance analysis module, used to perform data analysis on the random write speed, random write response time, sequential write speed, and sequential write response time after processing in step S2, and generate a random write performance coefficient, a sequential write performance coefficient, and a comprehensive write performance coefficient; A read / write performance analysis module, used to generate a comprehensive read / write performance coefficient according to a comprehensive read performance coefficient and a comprehensive write performance coefficient; The performance evaluation module is used to compare the comprehensive reading performance coefficient ZRXN, the comprehensive writing performance coefficient ZWXN, and the comprehensive reading and writing performance coefficient RWZH with the preset threshold value, and to issue a performance alarm signal when any one of the comprehensive reading performance coefficient ZRXN, the comprehensive writing performance coefficient ZWXN, and the comprehensive reading and writing performance coefficient RWZH is lower than the preset threshold value.

Images