Low-power in-out reliability detection method and device of SSD, computer device and storage medium

Abstract

The present application relates to the low-power consumption of SSD, and the method, device, computer equipment and storage medium of reliability detection, the method comprises: obtaining the life data of high-temperature SSD low-power consumption; according to life data, the shape parameter and scale parameter of weibull distribution are calculated; the weibull distribution hypothesis is checked; if the check passes, the use intensity of normal temperature SSD low-power consumption state and high-temperature life test acceleration factor are obtained; according to shape parameter, scale parameter, use intensity and acceleration factor, the low-power consumption of SSD is calculated to get reliability, and the detection result is generated.The present application can accurately evaluate the low-power consumption state in the client field failure probability, estimate the reliability that the product can reach after design improvement, and also give quantitative evaluation to the effect of design improvement.

Description

Technical Field

[0001] This invention relates to the field of low-power on / off reliability technology for SSDs, and in particular to a method, apparatus, computer equipment, and storage medium for detecting low-power on / off reliability of SSDs. Background Technology

[0002] SSDs (Solid State Drives) undergo low-power lifespan testing during R&D or before shipping. This testing assesses whether the overall SSD design will exhibit functional abnormalities during its entire lifespan in low-power conditions, including blue screens, black screens, reboots, crashes, and errors. Low-power lifespan testing typically employs traditional temperature and electrical stress accelerated testing, using an empirical acceleration factor as an equivalent estimate of laboratory and client-side usage conditions. However, this general acceleration factor is not very accurate for specific failure modes. During low-power lifespan testing, a certain sample size N is tested according to the test design. The usual requirement is that all samples N complete the test without failure. However, in the early stages of R&D, some samples (n=r) may encounter errors during testing, leading to a certain failure probability. The failure probability F is often calculated using a simple mathematical formula: F = r / N * 100%. This calculation significantly overestimates the actual failure probability at the client's end.

[0003] For any issues identified during testing, design improvements will be implemented. After the improvements, regression testing is typically conducted. The results of the regression tests usually confirm that the design improvements are positive and effective, and the issue is then closed. However, it's generally impossible to provide an accurate estimate of the probability of failure in a real customer's field. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method, apparatus, computer equipment, and storage medium for low-power advance and retreat reliability testing of SSDs.

[0005] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:

[0006] Firstly, this embodiment provides a low-power reliability detection method for SSDs, including the following steps:

[0007] Obtain lifespan data for high-temperature SSDs that have transitioned to low-power operation;

[0008] Based on lifetime data, the shape and scale parameters of the Weibull distribution were calculated.

[0009] Verify the Weibull distribution hypothesis;

[0010] If the verification passes, the usage intensity of the SSD in low-power state at room temperature and the acceleration factor of the high-temperature life test will be obtained.

[0011] Based on shape parameters, dimensional parameters, usage intensity, and acceleration factor, the low-power transition reliability of the SSD is calculated, and the test results are generated.

[0012] The further technical solution is as follows: In the step of obtaining the lifespan data of SSD low-power state entry and exit, a certain sample size of SSD products in normal working condition are subjected to an ambient temperature of 45°C. At the same time, the test script is adjusted to make the SSD frequently enter and exit the low-power state. The test is conducted in a time-cut-off manner. That is, when functional abnormalities occur, including blue screen, black screen, restart, crash, or error, it is recorded as failure and the test is stopped; or the test is stopped after a certain number of entry and exit cycles are reached. After the test is stopped, the lifespan data of SSD low-power state entry and exit is obtained.

[0013] The further technical solution is as follows: In the step of calculating the shape parameter and scale parameter of the Weibull distribution based on lifetime data, the shape parameter β and scale parameter η of the two-parameter Weibull distribution 2P-weibul are solved by using the maximum likelihood algorithm.

[0014] The further technical solution is as follows: In the step of obtaining the usage intensity of the low-power state of the SSD at room temperature and the acceleration factor of the high-temperature life test if the verification is passed, an ambient temperature of 25°C is adopted for a certain sample of SSD products in normal working state. When the APST characteristic of the SSD is in the open state, the power state of the SSD automatically switches from the power state in working mode, i.e., one of the states from PS0 to PS2, to the low-power state in non-working mode, i.e., PS3 or PS4. When the SSD is in PS3, a timer interrupt is set. When the timer expires, the interrupt is triggered to wake up the SSD. Then the SSD checks whether there are any new NVME instructions and actions to be performed. If not, it enters PS3 again. After entering and exiting PS3 multiple times, the usage intensity of the low-power state of the SSD at room temperature is obtained. By conducting tests under three temperature stresses at the set ambient temperature until the sample fails, the acceleration factor of the high-temperature life test is obtained.

[0015] Secondly, this embodiment provides a low-power reliability detection device for SSDs, including: a first acquisition unit, a calculation unit, a verification unit, a second acquisition unit, and a calculation generation unit;

[0016] The first acquisition unit is used to acquire lifespan data of the high-temperature SSD with low power consumption transition;

[0017] The computing unit is used to calculate the shape parameters and scale parameters of the Weibull distribution based on the lifetime data.

[0018] The verification unit is used to verify the Weibull distribution hypothesis;

[0019] The second acquisition unit is used to acquire the usage intensity of the SSD in low power consumption state at room temperature and the acceleration factor of high temperature life test if the verification passes.

[0020] The calculation and generation unit is used to calculate the low-power advance and retreat reliability of the SSD based on shape parameters, scale parameters, usage intensity and acceleration factor, and generate the detection results.

[0021] The further technical solution is as follows: In the first acquisition unit, an ambient temperature of 45°C is adopted for a certain sample of SSD products in normal working state. At the same time, the test script is adjusted to make the SSD frequently enter and exit the low power state. The test is carried out in a time-cut-off manner. That is, when functional abnormalities such as blue screen, black screen, restart, crash or error occur, it is recorded as failure and the test stops; or the test stops when a certain number of entry and exit is reached; after the test stops, the lifespan data of SSD low power entry and exit is obtained.

[0022] The further technical solution is as follows: In the computing unit, the shape parameter β and scale parameter η of the two-parameter Weibull distribution 2P-weibul are solved by using the maximum likelihood algorithm.

[0023] The further technical solution is as follows: In the second acquisition unit, by taking a certain sample of SSD products in normal working condition at an ambient temperature of 25°C, when the APST characteristic of the SSD is in the open state, the power state of the SSD automatically switches from the power state in working mode, i.e., one of PS0 to PS2, to the low power state in non-working mode, i.e., PS3 or PS4. When the SSD is in PS3, a timer interrupt is set. When the timer expires, the interrupt is triggered to wake up the SSD. Then the SSD checks whether there are any new NVME instructions and actions that need to be performed. If not, it enters PS3 again. After entering and exiting PS3 multiple times, the usage intensity of the SSD in the low power state at room temperature is obtained. By conducting tests under three temperature stresses at the set ambient temperature until the sample fails, the high temperature life test acceleration factor is obtained.

[0024] Thirdly, this embodiment provides a computer device, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the low-power advance / backward reliability detection method for SSDs as described above.

[0025] Fourthly, this embodiment provides a storage medium storing a computer program, the computer program including program instructions, which, when executed by a processor, can implement the low-power forward / backward reliability detection method for SSDs as described above.

[0026] The advantages of this invention compared to existing technologies are: it can accurately assess the failure probability of low-power states at the customer site, predict the reliability that the product can achieve after design improvements, and also provide a quantitative evaluation of the effect of design improvements, thus better meeting the needs.

[0027] The present invention will be further described below with reference to the accompanying drawings and specific embodiments. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 A flowchart illustrating the low-power reliability detection method for SSDs provided in this embodiment of the invention;

[0030] Figure 2 A schematic diagram of the probability Weibull algorithm provided in an embodiment of the present invention;

[0031] Figure 3 A schematic diagram of temperature-accelerated lifetime distribution provided for an embodiment of the present invention;

[0032] Figure 4 A schematic block diagram of a low-power advance / retreat reliability detection device for SSDs provided in an embodiment of the present invention;

[0033] Figure 5 A schematic block diagram of a computer device provided for an embodiment of the present invention. Detailed Implementation

[0034] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0035] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0036] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0037] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0038] Please see Figure 1 The specific embodiment shown in this invention discloses a low-power forward / backward reliability detection method for SSDs, comprising the following steps:

[0039] S1, obtains lifespan data of high-temperature SSDs with low power consumption transitions;

[0040] In step S1, a certain sample size of SSD products in normal working condition are subjected to an ambient temperature of 45°C. At the same time, the test script is adjusted to make the SSD frequently enter and exit low power mode. The test is conducted in a time-cut-off manner. That is, when functional abnormalities such as blue screen, black screen, restart, crash or error occur, it is recorded as failure and the test is stopped; or the test is stopped after a certain number of times it enters and exits. After the test is stopped, the lifespan data of the SSD's low power entry and exit are obtained.

[0041] Specifically, the high-temperature accelerated life test life data obtained are shown in Table 1:

[0042] Table 1

[0043] Quantity (pieces) Status (F / S) Lifespan (times) 1 F 2700 1 F 6000 400 S 10000 1 F 24000 1 F 25000 1 F 42000 1 F 44000 1 F 81000 1500 S 90000 800 S 270000

[0044] S2, based on lifetime data, calculate the shape and scale parameters of the Weibull distribution;

[0045] In step S2, the shape parameter β and scale parameter η of the two-parameter Weibull distribution 2P-weibul are solved by using the maximum likelihood algorithm.

[0046] Specifically, 2P-Weibull two-parameter Weibull analysis is widely used in the aerospace and automotive industries and is a powerful tool for reliability analysis, with numerous proven case studies demonstrating its broad applicability. The Weibull probability plotting method is used to initially determine whether lifetime data conforms to a two-parameter Weibull distribution. Weibull probability plotting can be implemented using Excel or commercial software such as Minitab or Weibull++. This embodiment uses Weibull++ as an example. Figure 2It can be seen that the failure points exhibit a good linear relationship, and it is preliminarily determined that the Weibull distribution is appropriate. The shape parameter β and scale parameter η are solved using the maximum likelihood estimation method, and the results are as follows... Figure 2 As shown, β=0.52, η=9.8E+09.

[0047] Specifically, the maximum likelihood estimation method solves for the two-parameter shape parameter β and the scale parameter η:

[0048] Weibull cumulative fault distribution function:

[0049] The Weibull reliability function is:

[0050] Taking the logarithm of both sides of the reliability function, we get -ln(t) = (t / η) β Taking the logarithm of both sides again yields a linear relationship.

[0051] Therefore, if the failure time follows a Weibull distribution, the double logarithm of 1 / (1-F(t)) has a linear relationship with ln(t).

[0052] Specifically, the maximum likelihood estimation method solves for the shape parameter β and the scale parameter η.

[0053] Definition of multiple right-truncation likelihood function:

[0054] and

[0055] Take the logarithm of both sides to convert the product into addition and subtraction calculations;

[0056]

[0057] Then the maximum likelihood estimate of η is the solution to the corresponding expression when the partial differential of L is zero.

[0058] The two-parameter Weibull fault density function Reliability function

[0059] Substituting into formula (2), we obtain the log-likelihood expression for the two-parameter Weibull distribution:

[0060]

[0061] To obtain the maximum likelihood estimate, let its partial derivative with respect to η be zero:

[0062]

[0063] but,

[0064] So,

[0065] Let its partial derivative with respect to β be zero:

[0066]

[0067] Right now

[0068] Continue to transform,

[0069] Substituting formula (5) into (7), the expression within the square brackets can be eliminated. Substituting formula (6) into (7), we can obtain an expression for estimating β that does not contain η:

[0070]

[0071] Equation (8) can only be solved by numerical methods, such as Newton's method. It can be solved with the help of EXCEL, or with commercial software such as Minitab or Weibull++, to obtain the result β=0.52, η=9.8E+09.

[0072] S3, verifying the Weibull distribution hypothesis;

[0073] In step S3, the Weibull distribution hypothesis is verified using the Mann statistical test method. The worksheet for the Mann statistical test method is shown in Table 2. The analysis conclusions are as follows:

[0074] M=(ι4+ι5+ι6) / (ι1+ι2+ι3)=1.68, significant factor α=0.10; F 0.10,6,6 =3.05, because M <F 0.10,6，6 Therefore, we accept the hypothesis that the Weibull distribution is a sufficient distribution model.

[0075] Table 2

[0076] i <![CDATA[t i ]]> <![CDATA[lnt i ]]> Zi Mi <![CDATA[ln(t i+1 / t i )]]> <![CDATA[ι i ]]> 1 2700 7.9010 -8.8015 1.0988 0.7985 0.7267 2 6000 8.6995 -7.7027 0.5110 1.3863 2.7130 3 24000 10.0858 -7.1917 0.3366 0.0408 0.1213 4 25000 10.1266 -6.8551 0.2515 0.5188 2.0631 5 42000 10.6454 -6.6036 0.2008 0.0235 0.1172 6 43000 10.6690 -6.4028 0.1672 0.6332 3.7873 7 81000 11.3022 -6.2356 - - -

[0077] Specifically, the Mann statistical test for the Weibull distribution, used to evaluate the goodness of fit of the Weibull distribution, takes the following form:

[0078]

[0079] Where r is the number of records that failed; [x] represents the integer part of x;

[0080]

[0081] If M>F α，2k2，2k1Then abandon H0:F(t)=F0(t).

[0082] S4. If the verification passes, obtain the usage intensity of the SSD in low power consumption state at room temperature and the acceleration factor of the high temperature life test.

[0083] Among them, all existing NVMe-PCIe SSDs (hereinafter referred to as SSDs) support APST (Autonomous Power State Transitions) features.

[0084] In step S4, a certain sample size of SSDs in normal working condition are subjected to an ambient temperature of 25°C. When the APST feature of the SSD is enabled, the SSD's power state automatically switches from the working mode power state (one of PS0 to PS2) to the low-power non-working mode (PS3 or PS4). In PS3, a timer interrupt is set, which triggers the interrupt to wake up the SSD when the timer expires. The SSD then checks for new NVMe instructions and actions to be performed. If no new instructions are found, it re-enters PS3. This process of entering and exiting PS3 multiple times is used to obtain the usage intensity of the SSD in the low-power state at room temperature. By conducting tests under three different temperature stresses at the set ambient temperature until the samples fail, the high-temperature life test acceleration factor is obtained.

[0085] Specifically, in this embodiment, the host is set to be powered on and the display is never turned off and the computer is never put into hibernation. This can simulate the maximum usage of the client entering and leaving the PS3 state, and the usage intensity of the SSD in the low power state at room temperature is obtained as 400K.

[0086] Specifically, accelerated life testing was conducted at ambient temperatures of 45°C and 35°C. The actual ambient temperature under customer conditions can be assumed to be 25°C. Here, tests were performed under three different temperature stresses until the sample failed. The test data are shown in Table 3, and the data processing results are as follows: Figure 3 As shown, the actual acceleration factor is 7.5, and the corresponding activation energy is 0.82 eV, which is consistent with the default activation energy of 0.8 eV commonly used in electronic products.

[0087] Table 3

[0088] Temperature (°C) Lifespan (number of cycles) 45 8000 45 13000 45 9000 45 8200 45 7000 35 16000 35 24000 35 52000 35 48000 35 36000 25 100000 25 90000 25 30000 25 40000 25 60000

[0089] Specifically, the Arrhenius model, which accelerates temperature, is... Where μ(T) l ) for in T l Degradation rate under temperature stress level, T lLet E be the accelerating stress-absolute temperature (K) of the l-th sample, where A is the frequency factor; a The activation energy is expressed in eV, and k is the Boltzmann constant, 8.6171 x 10⁻⁵ eV / K. The strategy for analyzing accelerated life data is as follows: a. Examine the data graphically; one useful and intuitive way to demonstrate the data is to examine a scatter plot of the acceleration factor versus the failure time variable; b. Fit a distribution to the data at different levels of the acceleration factor; here, a Weibull distribution is used; c. Fit the overall model using a seemingly reasonable relationship between the failure time variable and the acceleration factor; d. Compare the model in step c with the individual analyses in step S2 to assess whether the overall model is misfit.

[0090] S5 calculates the low-power reliability of the SSD based on shape parameters, scale parameters, usage intensity, and acceleration factor, and generates the test results.

[0091] In step S5, the reliability of the SSD in low-power state is evaluated using a two-parameter Weibull failure probability function. Based on the usage intensity of the SSD in low-power state at room temperature and the acceleration factor of the high-temperature life test, the usage intensity of the SSD in low-power state after one year is obtained as t = 400 / 7.5 = 53.3K. Substituting the value of t into the two-parameter Weibull cumulative failure distribution function... (β and η have been calculated above), so the client unreliability caused by this low-power failure mode can be obtained, F = 0.5%.

[0092] After step S5, products that do not meet the criteria are redesigned and subjected to regression testing. Since the unreliability index evaluated in step S5 exceeds the design baseline, new design improvements are required to eliminate this defect. The regression test results are shown in Table 4.

[0093] Table 4

[0094] Quantity (pieces) Status (F / S) Lifespan (times) 1 S 15000 1 S 16000 400 S 10000 1 S 50000 1 S 55000 1 S 82000 1 S 83000 1 S 27000 1500 S 90000 800 S 270000

[0095] In this study, Weibayes analysis was applied to evaluate the reliability index of the redesigned sample. Although the defect was theoretically eliminated, the reliability in actual use still needed to be estimated. Since the defect nature remained unchanged, β = 0.52 was fixed, and η was solved. Weibayes analysis was performed on the data using maximum likelihood estimation, yielding η = 9.1 + E11. The improved unreliability was calculated to be F = 0.06%, thus the design improvement efficiency was (0.5 - 0.06) / 0.5 = 88%.

[0096] This invention can accurately assess the failure probability of low-power states in the customer field, predict the reliability that the product can achieve after design improvements, and also provide a quantitative evaluation of the effect of design improvements, so as to better meet the requirements.

[0097] Please see Figure 4 As shown, the present invention also discloses a low-power reliability detection device for SSDs, comprising: a first acquisition unit 10, a calculation unit 20, a verification unit 30, a second acquisition unit 40, and a calculation and generation unit 50.

[0098] The first acquisition unit 10 is used to acquire lifespan data of the high-temperature SSD with low power consumption.

[0099] The computing unit 20 is used to calculate the shape parameters and scale parameters of the Weibull distribution based on the lifetime data.

[0100] The verification unit 30 is used to verify the Weibull distribution hypothesis;

[0101] The second acquisition unit 40 is used to acquire the usage intensity and acceleration factor of the room temperature SSD in low power state if the verification passes.

[0102] The calculation and generation unit 50 is used to calculate the low-power advance and retreat reliability of the SSD based on shape parameters, scale parameters, usage intensity and acceleration factor, and generate the detection results.

[0103] In the first acquisition unit 10, a certain sample size of SSD products in normal working condition are subjected to an ambient temperature of 45°C. At the same time, the test script is adjusted to make the SSD frequently enter and exit the low power state. The test is conducted in a time-cut-off manner. That is, when functional abnormalities such as blue screen, black screen, restart, crash or error occur, it is recorded as failure and the test is stopped; or the test is stopped after a certain number of entry and exit times. After the test is stopped, the lifespan data of the SSD low power entry and exit are statistically obtained.

[0104] In the computing unit 20, the shape parameter β and scale parameter η of the two-parameter Weibull distribution 2P-weibul are solved by using the maximum likelihood algorithm.

[0105] In the second acquisition unit 40, an ambient temperature of 25°C is applied to a certain sample size of SSD products in normal working condition. When the APST characteristic of the SSD is turned on, the power state of the SSD automatically switches from the power state in working mode, i.e., one of PS0 to PS2, to the low-power state in non-working mode, i.e., PS3 or PS4. When the SSD is in PS3, a timer interrupt is set. When the timer expires, the interrupt is triggered to wake up the SSD. Then the SSD checks for new NVMe instructions and the actions that need to be performed. If there are no new instructions, it enters PS3 again. After entering and exiting PS3 multiple times, the usage intensity of the SSD in the low-power state at room temperature is obtained. By conducting tests under three temperature stresses at the set ambient temperature until the sample fails, the high-temperature life test acceleration factor is obtained.

[0106] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the low-power advance and retreat reliability detection device and each unit of the above-mentioned SSD can be referred to the corresponding description in the foregoing method embodiments. For the sake of convenience and brevity, it will not be repeated here.

[0107] The aforementioned low-power reliability detection device for SSDs can be implemented as a computer program, which can, for example... Figure 5 It runs on the computer device shown.

[0108] Please see Figure 5 , Figure 5 This is a schematic block diagram of a computer device 500 provided in an embodiment of this application; the computer device 500 can be a terminal or a server, wherein the terminal can be an electronic device with communication functions such as a smartphone, tablet computer, laptop computer, desktop computer, personal digital assistant, and wearable device. The server can be a standalone server or a server cluster composed of multiple servers.

[0109] See Figure 5 The computer device 500 includes a processor 502, a memory, and a network interface 505 connected via a system bus 501. The memory may include a non-volatile storage medium 503 and internal memory 504.

[0110] The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions that, when executed, cause the processor 502 to perform a low-power on / off reliability detection method for an SSD.

[0111] The processor 502 provides computing and control capabilities to support the operation of the entire computer device 500.

[0112] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a low-power forward and backward reliability detection method for SSD.

[0113] This network interface 505 is used for network communication with other devices. Those skilled in the art will understand that... Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 500 to which the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0114] The processor 502 is used to run a computer program 5032 stored in the memory to perform the following steps:

[0115] Step S1: Obtain the lifespan data of the high-temperature SSD with low power consumption transition;

[0116] Step S2: Based on the lifetime data, calculate the shape parameters and scale parameters of the Weibull distribution;

[0117] Step S3: Verify the Weibull distribution hypothesis;

[0118] Step S4: If the verification passes, obtain the usage intensity and acceleration factor of the room temperature SSD in low power state.

[0119] Step S5: Calculate the low-power advance / retreat reliability of the SSD based on shape parameters, scale parameters, usage intensity, and acceleration factor, and generate the test results.

[0120] It should be understood that in the embodiments of this application, the processor 502 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0121] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program includes program instructions and can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0122] Therefore, the present invention also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions, which, when executed by a processor, can implement the aforementioned low-power on / off reliability detection method for SSDs. The storage medium stores a computer program, which includes program instructions, which, when executed by a processor, can implement the aforementioned method. The program instructions include the following steps:

[0123] Step S1: Obtain the lifespan data of the high-temperature SSD with low power consumption transition;

[0124] Step S2: Based on the lifetime data, calculate the shape parameters and scale parameters of the Weibull distribution;

[0125] Step S3: Verify the Weibull distribution hypothesis;

[0126] Step S4: If the verification passes, obtain the usage intensity and acceleration factor of the room temperature SSD in low power state.

[0127] Step S5: Calculate the low-power advance / retreat reliability of the SSD based on shape parameters, scale parameters, usage intensity, and acceleration factor, and generate the test results.

[0128] The storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0129] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0130] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0131] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the device of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0132] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0133] The above embodiments are preferred implementations of the present invention. In addition, the present invention can be implemented in other ways. Any obvious substitutions without departing from the concept of the present technical solution are within the protection scope of the present invention.

Claims

1. A low-power reliability detection method for SSDs, characterized in that, Includes the following steps: Obtain lifespan data for high-temperature SSDs that have transitioned to low-power operation; Based on lifetime data, the shape and scale parameters of the Weibull distribution were calculated. Verify the Weibull distribution hypothesis; If the verification passes, the usage intensity of the SSD in low-power state at room temperature and the acceleration factor of the high-temperature life test will be obtained. Based on shape parameters, dimensional parameters, usage intensity, and acceleration factor, the low-power transition reliability of the SSD is calculated, and the test results are generated. In the step of obtaining the lifespan data of SSD low-power state transition during high-temperature testing, a certain sample size of SSD products in normal working condition are subjected to an ambient temperature of 45°C. At the same time, the test script is adjusted to make the SSD frequently enter and exit the low-power state. The test is conducted in a time-cutoff manner, that is, when functional abnormalities such as blue screen, black screen, restart, crash, or error occur, it is recorded as failure and the test is stopped; or the test is stopped after a certain number of transitions are reached. After the test is stopped, the lifespan data of SSD low-power state transition is obtained. In the step of calculating the shape and scale parameters of the Weibull distribution based on lifetime data, the shape parameter β and scale parameter η of the two-parameter Weibull distribution 2P-weibull are solved by using the maximum likelihood algorithm.

2. The low-power forward / backward reliability detection method for SSDs according to claim 1, characterized in that, If the verification passes, the steps for obtaining the usage intensity of the low-power state of the SSD at room temperature and the acceleration factor of the high-temperature life test are as follows: A certain sample size of SSD products in normal working condition are subjected to an ambient temperature of 25°C. When the APST characteristic of the SSD is enabled, the SSD's power state automatically switches from the power state in working mode (one of PS0 to PS2) to the low-power state in non-working mode (PS3 or PS4). In PS3, a timer interrupt is set. When the timer expires, the interrupt is triggered to wake up the SSD. The SSD then checks for new NVMe instructions and required actions. If none are found, it re-enters PS3. This process of entering and exiting PS3 multiple times is used to obtain the usage intensity of the SSD in the low-power state at room temperature. The high-temperature life test acceleration factor is obtained by testing the samples under three different temperature stresses until failure, conducted at a set ambient temperature.

3. A low-power reliability detection device for SSDs, characterized in that, include: The unit comprises a first acquisition unit, a calculation unit, a verification unit, a second acquisition unit, and a calculation and generation unit. The first acquisition unit is used to acquire lifespan data of the high-temperature SSD with low power consumption transition; The computing unit is used to calculate the shape parameters and scale parameters of the Weibull distribution based on the lifetime data. The verification unit is used to verify the Weibull distribution hypothesis; The second acquisition unit is used to acquire the usage intensity of the SSD in low power consumption state at room temperature and the acceleration factor of high temperature life test if the verification passes. The calculation and generation unit is used to calculate the low-power advance and retreat reliability of the SSD based on shape parameters, scale parameters, usage intensity and acceleration factor, and generate the detection results. In the first acquisition unit, a certain sample size of SSD products in normal working condition are subjected to an ambient temperature of 45°C. At the same time, the test script is adjusted to make the SSD frequently enter and exit low power consumption state. The test is conducted in a time-cut-off manner. That is, when functional abnormalities such as blue screen, black screen, restart, crash or error occur, it is recorded as failure and the test is stopped; or the test is stopped after a certain number of times it enters and exits. After the test is stopped, the lifespan data of the SSD's low power consumption entry and exit are statistically obtained. In the computing unit, the shape parameter β and scale parameter η of the two-parameter Weibull distribution 2P-weibull are solved by using the maximum likelihood algorithm.

4. The low-power forward / backward reliability detection device for SSD according to claim 3, characterized in that, In the second acquisition unit, by subjecting a certain sample size of SSD products in normal working condition to an ambient temperature of 25°C, when the APST characteristic of the SSD is enabled, the power state of the SSD automatically switches from the power state in working mode (one of PS0 to PS2) to the low-power state in non-working mode (PS3 or PS4). When the SSD is in PS3, a timer interrupt is set, which triggers the interrupt to wake up the SSD when the timer expires. Then the SSD checks for new NVMe instructions and the actions that need to be performed. If there are none, it re-enters PS3. After repeatedly entering and exiting PS3, the usage intensity of the SSD in the low-power state at room temperature is obtained. By conducting tests under three temperature stresses at a set ambient temperature until the sample fails, the high-temperature life test acceleration factor is obtained.

5. A computer device, characterized in that, The computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the low-power advance / backward reliability detection method for SSD as described in any one of claims 1-2.

6. A storage medium, characterized in that, The storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions can implement the low-power forward / backward reliability detection method for the SSD as described in any one of claims 1-2.

Images