SSD (Solid State Disk) staged verification test method and storage equipment

Abstract

The invention relates to an SSD staged verification test method and storage equipment, and belongs to the technical field of storage. The method comprises the following steps: acquiring the random write performance of the full capacity of the SSD as target performance; the user capacity is adjusted according to the target performance, and the target capacity is obtained through testing; clearing the user data of the full capacity; and setting SSD user capacity according to the target capacity, and carrying out a random write performance rapid test to obtain a performance rapid test result. According to the embodiment of the invention, the performance can be quickly evaluated in a research and development stage, and compared with a traditional performance test mode, the test time of an hour / day level can be reduced to a minute level through quick test, so that the test period is shortened.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of storage, in particular to an SSD phased verification test method and a storage device. BACKGROUND

[0002] The performance of a solid state disk (SSD) refers to its comprehensive performance in data reading and writing, response speed, multitasking processing, durability, etc., which determines the speed, stability and application scenarios of the SSD in actual use.

[0003] An SSD is shipped as an empty disk state, and as non-repetitive data is continuously written, the writable space becomes smaller, and when it is reduced to a certain threshold, a garbage collection (GC) task is triggered to release the idle space. When the load of GC recovery and the host write load tend to be balanced, the performance of the SSD will gradually stabilize, and will be maintained in this state for a long time, which is called steady state. In the steady state, the performance of the SSD fluctuates less, and can truly reflect its performance in long-term use. Therefore, when testing the SSD, in order to obtain real performance data, the disk is first preprocessed to reach the steady state, and then subsequent tests are performed.

[0004] In the development stage of the product life cycle, the functional technology may not be perfect, the version iteration is relatively rapid, and multiple tests and improvements are needed, and whether the performance meets the expectation is concerned. If a conventional performance test method is used, the test time is too long to meet the rapid reporting requirement, which affects the development progress. SUMMARY

[0005] Therefore, it is necessary to solve the above technical problems, and embodiments of the present disclosure provide an SSD phased verification test method and a storage device to solve the problem of long test time of random write performance of the SSD.

[0006] In a first aspect, the embodiments of the present disclosure provide an SSD phased verification test method, which comprises: obtaining the random write performance of the full disk capacity of the SSD as a target performance; adjusting the user capacity according to the target performance to obtain a target capacity through testing; clearing the user data of the full disk capacity; setting the user capacity of the SSD according to the target capacity, performing a rapid test of the random write performance, and obtaining a performance rapid test result.

[0007] In some embodiments of the present disclosure, the adjusting the user capacity according to the target performance to obtain a target capacity through testing comprises: adjusting the available capacity of the SSD to the current user capacity, and setting the current user capacity value as a first preset proportion of the full disk capacity; performing a random write performance test on the current user capacity of the SSD; comparing the performance test result of the current user capacity with the target performance, and if consistent, taking the value of the current user capacity as the target capacity.

[0008] In some embodiments of the present disclosure, the method further comprises: comparing the performance test result of the current user capacity with the target performance, and if not consistent, continuing to adjust the current user capacity of the SSD, performing a random write performance test on the current user capacity of the SSD until the performance test result of the current user capacity is consistent with the target performance.

[0009] In some embodiments of the present disclosure, the if not consistent, continuing to adjust the current user capacity of the SSD comprises: if the performance test result is less than the target performance, performing a decreasing process on the current user capacity; and if the performance test result is greater than the target performance, performing an increasing process on the current user capacity.

[0010] In some embodiments of the present disclosure, the adjusting the current user capacity of the SSD comprises: adjusting the current user capacity of the SSD using a short stroke method; wherein the short stroke method is to reduce the physically accessible address range according to a set value under the premise that the actual physical space is unchanged, thereby reducing the user capacity of the SSD for adaptation, and all the dies in the SSD can still be accessed.

[0011] In some embodiments of the present disclosure, the comparing the performance test result of the current user capacity with the target performance, and if consistent, taking the value of the current user capacity as the target capacity comprises: performing a predicted number of random write operations on the current user capacity, and if the performance test result of each time is consistent with the target performance, taking the value of the current user capacity as the target capacity.

[0012] In some embodiments of the present disclosure, the method further comprises, before the setting the user capacity of the SSD according to the target capacity and performing a random write performance test: performing a pre-processing operation on the user capacity of the SSD to make the SSD reach a steady state.

[0013] In some embodiments of the present disclosure, the pre-processing operation comprises: performing a second preset number of sequential write operations under a first load, and performing a third preset number of random write operations under a second load.

[0014] In some embodiments of the present disclosure, the clearing of the user data of the full capacity includes: By executing the erase command, all user data in the SSD is completely cleared.

[0015] In a second aspect, the embodiments of the present disclosure also provide a storage device, comprising a memory and a processor, the processor comprising a plurality of cores, wherein the memory stores a computer program, and when the computer program is executed by the processor, the above-mentioned SSD phased verification test method is realized.

[0016] The present disclosure provides an SSD phased verification test method and a storage device, and the embodiments of the present disclosure provide technical solutions which at least bring the following beneficial effects: The performance can be quickly evaluated in the development phase, and compared with the traditional performance test method, the test time of hours / days level can be reduced to minutes level through the fast test, thereby shortening the test period.

[0017] Due to the quick performance result in a short time, the low-frequency phased verification can be improved to a high-frequency execution times of multiple times per day. In this way, the high-cost equipment is not occupied for a long time, and the test types can be increased in the same time, thereby improving the test coverage.

[0018] The speed of identifying performance problems in the development phase is accelerated, the abnormal points can be quickly diagnosed, the development and iteration efficiency is improved, and the influence on the product is reduced through more search risk points.

[0019] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0021] Figure 1 A flowchart of a SSD phased verification test method provided by the embodiments of the present disclosure is shown in the figure; Figure 2 A flowchart of a SSD phased verification test method provided by the embodiments of the present disclosure is shown in the figure; Figure 3 A flowchart of a method for obtaining the random write performance of the full capacity of the SSD as the target performance, and adjusting the user capacity according to the target performance, and obtaining the target capacity through the test provided by the embodiments of the present disclosure is shown in the figure; Figure 4 A flowchart of a method for setting the user capacity of an SSD as a target capacity, performing a random write performance quick test, and obtaining a performance quick test result is provided for an embodiment of the present disclosure. Figure 5 An IOPS diagram of an SSD phased verification test method is provided for an embodiment of the present disclosure. Figure 6 An IOPS diagram of a conventional performance test method is provided. Figure 7 A structural diagram of a storage device is provided for an embodiment of the present disclosure. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the present disclosure will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present disclosure and do not limit the present disclosure.

[0023] In the embodiments related to the present disclosure, 4KB random write (i.e., 4K random write) is one of the key indicators for measuring the performance of an SSD, and 4KB is the size of each data block for a write operation; random write refers to a random write operation, i.e., the position of the data block on the storage device for each operation is random. Usually measured in IOPS, IOPS refers to the number of input / output operations that an SSD can handle in one second, and a high IOPS indicates faster data processing capability.

[0024] Performance is an important parameter of an SSD, and capacity is also one of the important parameters. The capacity of an SSD is usually measured in GB or TB, which represents the capacity that a user can address and access, i.e., "user capacity". Common capacities of consumer-grade SSDs include 256GB, 512GB, 1TB, 2TB and 4TB, while the capacities of enterprise-grade SSDs can reach 16TB, 32TB, 64TB, 128TB or even higher. Large-capacity SSDs can store more files, applications and data, and can meet the growing demand for data storage, which has also significantly increased the demand.

[0025] Before testing the random write performance, a preprocessing operation is required, and a larger-capacity SSD also means a longer preprocessing time, which poses a challenge to how to quickly test the random write performance of an SSD.

[0026] To address the aforementioned issues, the method provided by the embodiments of this disclosure obtains the random write performance of the entire SSD capacity as a target performance; adjusts the user capacity based on the target performance, and obtains the target capacity through testing; clears user data from the entire capacity; sets the SSD user capacity to the target capacity, performs a quick random write performance test, and obtains the quick performance test results. This method ensures the consistency of random write performance and significantly reduces testing time.

[0027] Figure 1 A flow chart of an SSD phased verification test method 100 provided in the first embodiment of the present disclosure is shown as follows: Figure 1 As shown, the following steps are included: In step S101, the random write performance of the entire SSD capacity is obtained as the target performance; In step S102, user capacity is adjusted according to target performance, and the target capacity is obtained through testing; In step S103, clear the user data on the entire disk capacity; In step S104, the SSD user capacity is set according to the target capacity, and a random write performance quick test is performed to obtain a performance quick test result.

[0028] In some embodiments, a SSD phased verification test method provided by the present disclosure is described in detail. Figure 2 A flow chart of an SSD phased verification test method 200 provided in the second embodiment of the present disclosure is shown as follows: Figure 2 As shown, the following steps are included: In step S201 , the random write performance of the entire SSD capacity is tested, and the test performance result of the entire SSD capacity is used as the target performance.

[0029] In step S202 , the available capacity of the SSD is adjusted to the current user capacity using a short stroke method.

[0030] In step S203, a random write performance test is performed on the current user capacity of the SSD.

[0031] In step S204, the current user capacity performance test result is compared with the target performance. If they are consistent, step S205 is executed below; if they are inconsistent, steps S202 to S204 are repeated until the current user capacity performance test result is consistent with the target performance.

[0032] In some embodiments, if the performance test result of the current user capacity is less than the target performance, the shortstroke method is used to reduce the current user capacity; if the performance test result is greater than the target performance, the shortstroke method is used to increase the current user capacity.

[0033] In step S205, the value of the current user capacity is taken as the target capacity.

[0034] In step S206, the user data of the SSD full-disk capacity is cleared.

[0035] By executing the erase command, all user data in the SSD is completely cleared.

[0036] In some embodiments, the sanitize operation is performed to clear the data on the standard capacity disk. The sanitize function is a data security erasing technology, mainly used to completely clear the data in the SSD, ensuring that the data cannot be recovered.

[0037] In step S207, the SSD user capacity is set according to the target capacity.

[0038] In some embodiments, the target capacity is obtained in step S205.

[0039] In step S208, a random write performance test is performed on the set user capacity to obtain a performance test result. The above method will be described in detail in combination with some specific embodiments: Figure 3 The random write performance of the SSD full-disk capacity provided by the third embodiment of the present disclosure is taken as the target performance; the method 300 for testing the target capacity according to the target performance is shown in the flowchart as shown in Figure 3 The method includes the following steps: In step S301, a pre-processing operation is performed on the standard capacity SSD to make the SSD reach a steady state.

[0040] In some embodiments, the standard capacity SSD can be a consumer-grade SSD, and the capacity includes 256GB, 512GB, 1TB, 2TB and 4TB; or an enterprise-grade SSD, and the capacity includes 16TB, 32TB, 64TB, 128TB or even higher.

[0041] In some embodiments, the pre-processing operation includes two workload operations, a second preset number of sequential write operations under a first load, and a third preset number of random write operations under a second load.

[0042] In some embodiments, the first workload operation is to set the parameters of the performance test tool as blocksize=128KB, iodepth=1024, numjobs=1, and perform two sequential write operations on the full capacity; and the second workload operation is to set the parameters of the performance test tool as blocksize=4KB, iodepth=8, numjobs=64, and perform two random write operations on the full capacity.

[0043] Through the above two workload operations, the pre-processing operation on the standard capacity SSD is completed, and the SSD reaches a steady state.

[0044] In step S302, a random write performance test is performed on the standard capacity, and the random write test performance of the standard capacity is taken as the target performance.

[0045] In some embodiments, the current user capacity is the standard capacity of the SSD, i.e., the full capacity.

[0046] In some embodiments, the performance test tool uses FIO. FIO is an I / O tool used for stress testing and verification of SSD hardware. The parameter blocksize is the data block size of each request, iodepth is the IO queue depth of the request, numjobs is the number of threads, and the parameter runtime is the test running time (in seconds).

[0047] In some embodiments, the performance test tool uses FIO. FIO is an I / O tool used for stress testing and verification of SSD hardware. The parameter blocksize is the data block size of each request, iodepth is the IO queue depth of the request, numjobs is the number of threads, and the parameter runtime is the test running time (in seconds).

[0048] In some embodiments, after obtaining the random write performance of the full capacity of the SSD as the target performance, the user capacity is adjusted using the short stroke method according to the target performance, and the target capacity is obtained through testing.

[0049] In step S303, it is determined whether it is the first performance test; if so, step S304 is performed; and if not, step S305 is performed.

[0050] In step S304, the current user capacity value is set to a first preset proportion of the full capacity using the short stroke method, and then step S308 is performed.

[0051] In some embodiments, the first preset ratio is 1 / 4. Taking 16 channels as an example, when the first preset ratio is 1 / 4, all LUNs are also used, that is, it is still full configuration of 16 channels, but each LUN only uses 1 / 4 of the number of physical blocks.

[0052] In some embodiments, the short stroke method is to reduce the physically accessible address range according to the set value under the premise that the actual physical space is unchanged, thereby reducing the SSD user capacity for adaptation, and the SSD internal can still access all the Die. Specifically, the short stroke method is defined in section 6.2.1 Short Stroke Extrapolation Method of JESD218B, by artificially reducing the SSD user capacity, so that some flash chips are not written, and the remaining flash chips are recycled (P / E) faster. This method is commonly referred to as "short stroke", similar to the technology of using a hard disk drive to access only a part of the storage disk. The short stroke method is not simply reducing the logical range of writing data. While reducing the logical range of writing data, it cannot distort the normal internal work of the SSD and needs to be able to access all the Die. For example: it may be necessary to reduce the number of free storage blocks, which guarantees that the write amplification factor and the SSD's ability to accommodate bad blocks remain unchanged.

[0053] Wherein, Die refers to an independent flash chip, which is the basic unit of NAND Flash. Each Die contains multiple channels and storage units, responsible for storing and transmitting data.

[0054] In step S305, the performance test result of the current user capacity is compared with the target performance. If the performance test result is less than the target performance, step S306 is executed: the current user capacity is reduced using the short stroke method; if the performance test result is greater than the target performance, step S307 is executed: the current user capacity is increased using the short stroke method. Here, the tested performance can be random write performance.

[0055] In some embodiments, the current user capacity is reduced / increased according to the capacity formula; the capacity formula uses the formula provided in section 4 SSD Capacity of JESD218B: User-addressable LBA count = 21168 + (1953504 x SSD Capacity in Gbytes).

[0056] In step S308, a pretreatment operation is performed on the current user capacity to make the SSD reach a steady state.

[0057] In some embodiments, the pre-processing operation includes two workload operations, sequential write for a preset number of times under a first load, and random write for a preset number of times under a second load.

[0058] In some embodiments, the first workload operation is to set the parameters of the performance test tool as blocksize=128KB, iodepth=1024, numjobs=1, and perform two sequential write operations on the current user capacity; and the second workload operation is to set the parameters of the performance test tool as blocksize=4KB, iodepth=8, numjobs=64, and perform two random write operations on the current user capacity.

[0059] Through the above two workload operations, the pre-processing operation on the current user capacity is completed, and the SSD reaches a steady state.

[0060] In step S309, a random write performance test is performed on the current user capacity of the SSD.

[0061] In some embodiments, the performance test parameters are set as blocksize=4KB, iodepth=8, numjobs=64, and runtime=600, and a random write performance test is performed on the current user capacity.

[0062] In step S310, the performance test result of the current user capacity is compared with the target performance, if inconsistent, steps S305-S310 are performed; if consistent, step S311 is performed.

[0063] In step S311, the first predicted number of random write operations is continued to be performed on the current user capacity.

[0064] In some embodiments, the performance test parameters are set as blocksize=4KB, iodepth=8, numjobs=64, and runtime=600, and a random write performance test is performed on the current user capacity for the predicted number of times.

[0065] In some embodiments, the first preset number is a positive integer greater than or equal to 0, for example, it can be 6 times.

[0066] In step S312, the performance test result of the first predicted number of times is compared with the target performance, if inconsistent, steps S305-S312 are performed; if consistent, step S313 is performed.

[0067] In some embodiments, if the comparison is inconsistent at any time, steps S305-S312 are performed.

[0068] In some embodiments, if each comparison is consistent, step S313 is performed.

[0069] In step S313, the value of the current user capacity is set as the target capacity, and the target capacity is used as the user capacity value for the performance quick test.

[0070] In some embodiments, if the preset number of times is 0, in step S311, the value of the current user capacity is set as the target capacity, and the target capacity is used as the user capacity value for the performance quick test.

[0071] Figure 4 The flowchart of the method 400 for setting the SSD user capacity as the target capacity and performing the random write performance quick test to obtain the performance quick test result is shown in FIG. 4. Figure 4 As shown in FIG. 4, the method 400 includes the following steps: In step S401, the SSD user capacity is set according to the target capacity.

[0072] In some embodiments, the short stroke method is used to set the SSD user capacity according to the target capacity by using a capacity formula. The capacity formula uses the formula provided in Chapter 4 of JESD218B SSD Capacity: User-addressable LBA count = 21168 + (1953504 x SSD Capacity in Gbytes).

[0073] In step S402, a pre-processing operation is performed on the SSD user capacity to make the SSD reach a steady state.

[0074] In some embodiments, the pre-processing operation includes two workload operations. The second preset number of times of sequential write operations is performed under a first load, and the third preset number of times of random write operations is performed under a second load.

[0075] In some embodiments, the first workload: the parameters of the performance test tool are set as blocksize = 128KB, iodepth = 1024, and numjobs = 1, and two sequential write operations are performed on the SSD user capacity; and the second workload: the parameters of the performance test tool are set as blocksize = 4KB, iodepth = 8, and numjobs = 64, and two random write operations are performed on the SSD user capacity.

[0076] Through the above two workload operations, the pre-processing operation on the SSD user capacity is completed, and the SSD reaches a steady state.

[0077] In step S403, the SSD user capacity is subjected to a random write performance test.

[0078] In some embodiments, the performance test parameters are set as blocksize=4KB, iodepth=8, numjobs=64, runtime=600, and the SSD user capacity is subjected to a random write performance test.

[0079] In step S404, the performance test result of the random write performance test is recorded, and it is analyzed whether the current version is abnormal.

[0080] Figure 5 For the IOPS schematic diagram of the embodiments of the present disclosure, from the performance curve diagram of the random write, the random write performance consistency of the test method exceeds 95%, and there is no large abnormal jitter in the random write performance curve, etc., and the data result can be guaranteed.

[0081] Comparison Figure 6 The time from pre-processing to steady state and the sum of the random write performance in the IOPS schematic diagram without using the test method of the present disclosure is multiplied after using the test method of the present disclosure. As shown in FIGS. 1 and 2, Figure 6 and Figure 5 For the user capacity disk of 16T, from the start of pre-processing to the steady state, Figure 5 the time for starting the random write test is reduced to one fourth of the time for using the Figure 6 conventional test method, and the time length consumed by the pre-processing is also greatly shortened, thereby improving the test efficiency.

[0082] According to the method of the present disclosure, the following technical effects are achieved: In the research and development stage, the performance is quickly evaluated, and compared with the conventional performance test method, the test time of hours / days level is reduced to minutes level, thereby shortening the test period.

[0083] Due to the rapid performance result obtained in a short time, the low-frequency stage verification can be improved to a high-frequency execution times of multiple times per day. In this way, the high-cost equipment is not occupied for a long time, and the test types can be increased in the same time, thereby improving the test coverage.

[0084] The speed of identifying the performance problem in the development stage is accelerated, the abnormal point can be quickly diagnosed, the development and iteration efficiency is improved, and the influence on the product is reduced through more search risk points.

[0085] It should be understood that, although Figures 1-4The steps in the flowcharts are shown in sequence according to the arrows, but the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the steps are not strictly limited in sequence, and the steps can be executed in other sequences. Moreover, Figures 1-4 At least part of the steps in the flowcharts can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of the steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or steps in other steps.

[0086] It can be understood that the same / similar parts between each embodiment of the method in the specification can be referred to each other, and each embodiment focuses on the difference from other embodiments, and the related part can be referred to the description of other method embodiments.

[0087] The embodiment of the disclosure also provides a storage device, which comprises a processor and a memory, and the processor comprises a plurality of cores, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method of any one of the above embodiments can be implemented, and the execution mode and beneficial effects are similar, which will not be repeated here.

[0088] Figure 7 is a structural schematic diagram of a storage device provided by the embodiment of the disclosure, as Figure 7 shown, the storage device can include a processor 710 and a memory 720, wherein the memory 720 stores a computer program, and when the computer program is executed by the processor 710, the method provided by any one of the above embodiments can be implemented, and the execution mode and beneficial effects are similar, which will not be repeated here.

[0089] Of course, in order to simplify, Figure 7 only some of the components related to the application in the storage device are shown in the figure, and components such as buses, input / output interfaces, input devices and output devices are omitted. In addition, according to the specific application, the storage device can also include any other appropriate components. The embodiment of the disclosure provides a computer readable storage medium, the storage medium stores a computer program, and when the computer program is executed by the processor, the method of any one of the above embodiments can be implemented, and the execution mode and beneficial effects are similar, which will not be repeated here.

[0090] The computer readable storage medium can be a combination of one or more computer readable media. The computer readable media can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0091] The computer programs can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++, or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer device, partly on the user's computer device, as a stand-alone software package, partly on the user's computer device and partly on a remote computer device or entirely on the remote computer device or server. The embodiments are not related to a specific computer language or

[0092] Moreover, while operations are depicted in a particular order, this should not be understood as requiring the operations to be performed in the particular order shown or in sequential order, and that some operations can be performed in parallel or in any order. Also, while the above discussion discusses several implementations, it should be appreciated that not all of the features of the implementations are necessarily required, that implementations can be directed to substantially any combination of the features described, and that various configurations might be devised using some or all of the features. Similarly, while operations are depicted in the above contexts as being performed by one component, it should be appreciated that various configurations might be devised to perform the described operations using other suitable components.

[0093] The above descriptions are only specific embodiments of the present disclosure to enable a person skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A phased verification test method for SSD, characterized in that: The method comprises: Get the random write performance of the entire SSD capacity as the target performance; Adjusting user capacity according to the target performance and obtaining the target capacity through testing; Clear all user data on the disk; The SSD user capacity is set according to the target capacity, and a random write performance quick test is performed to obtain a performance quick test result.

2. The method according to claim 1, characterized in that The adjusting the user capacity according to the target performance and obtaining the target capacity through testing includes: Adjust the available capacity of the SSD to the current user capacity, and set the current user capacity value to the first preset ratio of the total disk capacity; Perform random write performance tests on the current user capacity of the SSD; The performance test result of the current user capacity is compared with the target performance. If they are consistent, the value of the current user capacity is used as the target capacity.

3. The method according to claim 2, characterized in that The method further comprises: Compare the performance test results of the current user capacity with the target performance. If they are inconsistent, continue to adjust the current user capacity of the SSD and perform random write performance tests on the current user capacity of the SSD until the performance test results of the current user capacity are consistent with the target performance.

4. The method according to claim 3, characterized in that If the information is inconsistent, then the current user capacity of the SSD is adjusted as follows: If the performance test result is less than the target performance, the current user capacity is reduced; if the performance test result is greater than the target performance, the current user capacity is increased.

5. The method according to claim 4, characterized in that Adjusting the current user capacity of the SSD includes: Use the short stroke method to adjust the current user capacity of the SSD; The short stroke method reduces the physically accessible address range according to the set value while keeping the actual physical space unchanged, thereby reducing the SSD user capacity for adaptation, while all dies can still be accessed inside the SSD.

6. The method according to claim 2, characterized in that The step of comparing the performance test result of the current user capacity with the target performance and, if they are consistent, using the value of the current user capacity as the target capacity includes: A first predicted number of random write operations are performed on the current user capacity. If the performance test results of each time are consistent with the target performance, the value of the current user capacity is used as the target capacity.

7. The method according to any one of claims 1 to 6, characterized in that Before setting the SSD user capacity according to the target capacity and performing a random write performance quick test, the method further includes: Perform pre-processing operations on the user capacity of the SSD to make the SSD reach a steady state.

8. The method according to claim 7, characterized in that The pre-processing operation includes: A second preset number of sequential write operations are performed under the first load, and a third preset number of random write operations are performed under the second load.

9. The method according to claim 8, characterized in that The method of clearing user data of the entire disk capacity includes: By executing the erase command, all user data in the SSD is completely cleared.

10. A storage device, characterized in that: include: A memory and a processor, wherein the processor includes multiple cores, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the SSD phased verification test method according to any one of claims 1 to 9 is implemented.

Images