Method for testing anti-reverse rotation capability of power supply fan and server

Abstract

The application discloses a test method for anti-reversing capability of a power fan and a server, and relates to the technical field of servers. The method comprises the following steps: receiving a test instruction sent by a client, wherein the test instruction is used for indicating the anti-reversing capability of the power fan to a system fan; running a plurality of target test tasks corresponding to a test scene in the test scene according to a test rule corresponding to each test scene; collecting actual index values of each target test index in a plurality of target test indexes according to a data collection rule in the process of running each target test task; extracting reference index values corresponding to each target test index from a pre-constructed mapping table; and determining whether the anti-reversing capability of the power fan is abnormal according to the actual index values and the reference index values. The application solves the problem that the anti-reversing capability of the power fan cannot be directly tested, which leads to the problems of difficulty in accurately distinguishing the root cause of the heat dissipation problem, increased difficulty in maintenance and troubleshooting, and insufficient test coverage.

Description

Technical Field

[0001] This application relates to the field of server technology, and in particular to a test method for the anti-reverse capability of power supply fans and a server. Background Technology

[0002] In a server's internal cooling system, fan modules (also known as system fans) and power supply unit (PSU) fans perform different cooling functions. System fans provide forced cooling to high-heat components such as processors, memory, hard drives, network cards, and expansion cards through directional airflow; PSU fans dissipate heat from core components within the PSU, such as power devices and capacitors. In a server, the strong airflow generated by the system fans directly impacts the PSU fans, causing obstruction to their forward rotation and even reverse rotation. If the PSU fan's anti-reverse rotation capability is insufficient, it will lead to a significant risk of cooling failure. Therefore, testing the PSU fan's anti-reverse rotation capability is crucial.

[0003] In related technologies, the system fan speed is typically adjusted manually to simulate different airflow impact intensities. During this process, if the PSU fan experiences speed fluctuations or reverse rotation under high-speed airflow interference, the risk can be identified through power consumption monitoring or abnormal temperature sensor data, thus indirectly testing the PSU fan's anti-reverse rotation capability. However, this indirect testing method cannot determine whether the abnormal temperature or power consumption is caused by the system fan or the PSU fan, making it difficult to accurately distinguish the root cause of the heat dissipation problem, increasing the difficulty of troubleshooting, and the test coverage is insufficient. Summary of the Invention

[0004] This application provides a test method and server for the anti-reverse capability of a power supply fan, so as to at least solve the problems in the related technology that the anti-reverse capability of a power supply fan cannot be directly tested, which makes it difficult to accurately distinguish the root cause of heat dissipation problems, increases the difficulty of maintenance and troubleshooting, and has insufficient test coverage.

[0005] This application provides a method for testing the anti-reversal capability of a power supply fan, applied to a server, the server including a power supply fan and a system fan; the method includes: receiving a test instruction sent by a client, the test instruction indicating the test of the power supply fan's anti-reversal capability against the system fan, wherein the test instruction carries test rules and data acquisition rules corresponding to each of multiple test scenarios; running multiple target test tasks corresponding to each test scenario in the test scenario according to the test rules corresponding to each test scenario; collecting the actual index value of each target test index among multiple target test indices according to the data acquisition rules during the running of each target test task; extracting the benchmark index value corresponding to each target test index from a pre-built mapping table; and determining whether the anti-reversal capability of the power supply fan is abnormal based on the actual index value and the benchmark index value.

[0006] This application also provides a server, comprising: a transceiver module for receiving test instructions sent by a client, the test instructions indicating the anti-reversal capability of the power supply fan against the system fan, wherein the test instructions carry test rules and data acquisition rules corresponding to each of the multiple test scenarios; a processing module for running multiple target test tasks corresponding to each test scenario in the test scenario according to the test rules corresponding to each test scenario; an acquisition module for acquiring the actual index value of each target test index among the multiple target test indices according to the data acquisition rules during the execution of each target test task; and the processing module further for extracting the benchmark index value corresponding to each target test index from a pre-built mapping table; and determining whether the anti-reversal capability of the power supply fan is abnormal based on the actual index value and the benchmark index value.

[0007] This application also provides a server, including: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of the test method for the anti-reversal capability of any of the above power supply fans.

[0008] This application also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the steps of the test method for the anti-reverse capability of any of the above-described power supply fans.

[0009] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of a test method for the anti-reverse capability of any of the above-described power supply fans.

[0010] This application allows for the testing of the power supply fan's anti-reversal capability under multiple test scenarios. These scenarios cover the entire load cycle of the server, encompassing all variations in fan speed or airflow. This enables targeted testing of the power supply fan's anti-reversal capability across the entire load cycle, improving test coverage and ensuring server quality upon delivery. Furthermore, because the testing directly targets the power supply fan, it allows for precise identification of whether a server's heat dissipation issues are caused by poor anti-reversal capability of the power supply fan. In addition, the automated testing process and methods avoid potential misjudgments from manual observation and assessment, saving labor costs and increasing the level of automation in factory testing. Attached Figure Description

[0011] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 A topology diagram of a test system for the anti-reverse capability of a power supply fan provided in an embodiment of this application;

[0013] Figure 2 A flowchart illustrating a method for testing the anti-reverse capability of a power supply fan, provided in an embodiment of this application;

[0014] Figure 3 A flowchart illustrating the testing method under a dynamic stress testing scenario provided in this application embodiment;

[0015] Figure 4 A flowchart illustrating the testing method for a dynamically adjusted rotational speed testing scenario provided in this application embodiment;

[0016] Figure 5 A flowchart illustrating the test method for dynamic power redundancy testing scenarios provided in this application embodiment;

[0017] Figure 6 A flowchart illustrating the test method under the power-on / off cycle test scenario provided in the embodiments of this application;

[0018] Figure 7 A flowchart illustrating the test method for a power-on / off cycle test scenario provided in this application embodiment;

[0019] Figure 8 A flowchart illustrating the testing method under the first combined testing scenario provided in the embodiments of this application;

[0020] Figure 9 A flowchart illustrating the testing method under the second combined testing scenario provided in the embodiments of this application;

[0021] Figure 10 A device structure block diagram of a server provided in an embodiment of this application;

[0022] Figure 11 This is a schematic diagram of the hardware structure of a server provided in an embodiment of this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0024] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. The terms "first," "second," etc., in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0025] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] This application applies to a scenario where the reverse rotation resistance of a server power supply fan is being tested. Poor reverse rotation resistance in a server power supply fan can obstruct forward rotation or even cause it to rotate in reverse. This not only prevents timely heat dissipation from the PSU, leading to a sudden increase in the temperature of core components, but can also cause hardware failures such as capacitor aging and component burnout, seriously threatening the lifespan and power supply stability of the PSU, and consequently affecting the reliable operation of the entire server. Therefore, the PSU fan needs to have stronger reverse rotation resistance to ensure stable operation of the power supply in complex airflow environments.

[0027] In related technologies, the anti-reversal capability of PSU fans is typically tested indirectly using the following three methods: Method 1: The system fan speed is manually adjusted to simulate different airflow impact intensities. During this process, if the PSU fan exhibits speed fluctuations or reverse rotation under high-speed airflow interference, the risk can be identified through power consumption monitoring or abnormal temperature sensor data, thus indirectly testing the PSU fan's anti-reversal capability. Method 2: The server's power-on / off cycle is simulated, and the PSU fan's rotation response at startup is manually observed. When the system fan and PSU fan rotate in conflict, the PSU fan may experience startup delays or abnormal noise, indirectly testing its anti-reversal capability. Method 3: During single / dual PSU redundancy testing of the server, the main power supply is disconnected to observe the backup power supply's takeover status. Simultaneously, the operational stability of the PSU fan under sudden load changes is monitored, indirectly testing its anti-reversal capability.

[0028] Of the three methods mentioned above, only certain anti-reversal scenarios can be triggered under specific operating conditions (such as startup and sudden load changes), which cannot fully simulate the airflow interference to the PSU fan under the full load cycle of the server, resulting in insufficient test coverage. When the PSU fails due to insufficient fan anti-reversal capability, indirect testing makes it difficult to accurately distinguish the root cause of the problem, increasing the difficulty of maintenance and troubleshooting.

[0029] To address the aforementioned technical issues, this application provides a method for testing the anti-reversal capability of a power supply fan. This method uses the entire server load cycle as the testing dimension, randomly generating test tasks under various scenarios to comprehensively simulate airflow interference to the PSU fan under the entire server load cycle (idle, full load, and mixed load), thereby improving the test coverage of the power supply fan's anti-reversal capability. Simultaneously, by combining real-time data acquisition with comparison to a preset mapping table, the root cause of heat dissipation failures can be accurately located, reducing the difficulty of troubleshooting and repair.

[0030] The following is based on Figure 1 Taking the test system for the anti-reverse capability of the power supply fan shown as an example, the method provided in the embodiments of this application will be described. Figure 1 This is merely an illustrative diagram and does not constitute a limitation on the applicable scenarios of the technical solutions provided in this application.

[0031] like Figure 1 As shown, Figure 1 This is a topology diagram of a test system for the anti-reverse capability of a power supply fan, provided in an embodiment of this application. Figure 1 In the test system 100 for the reverse resistance capability of the power supply fan, there may be a server 101 and a client 102.

[0032] Server 101 can be any type of server. For example, it can be a tower server, rack server, blade server, file server, etc. Server 101 includes a power supply fan and a system fan. In addition, the server also includes multiple components such as a processor, memory, and graphics card, as well as a main power supply and a backup power supply.

[0033] Client 102 can be any device with display and communication capabilities. For example, the client can be a mobile device, an IoT device, etc.

[0034] Figure 1 The power supply fan anti-reversal capability test system 100 shown is for illustrative purposes only and is not intended to limit the technical solutions of this application. Those skilled in the art should understand that in specific implementations, the power supply fan anti-reversal capability test system 100 may also include other devices, without limitation.

[0035] This application provides a method for testing the anti-reverse capability of a power supply fan, applied to server 101, such as... Figure 2 As shown, Figure 2 This is a flowchart illustrating a method for testing the anti-reverse capability of a power supply fan according to an embodiment of this application. The method includes the following steps:

[0036] S201 receives test commands sent by the client.

[0037] The test command is used to instruct the power supply fan to resist the reverse rotation of the system fan. The test command carries the test rules and data acquisition rules corresponding to each of the multiple test scenarios.

[0038] The test scenarios include dynamic stress testing, dynamic fan speed adjustment testing, power redundancy dynamic testing, power-on / off cycle testing, power-on / off cycle testing, a first combination of dynamic stress testing and power redundancy dynamic testing, and a second combination of dynamic fan speed adjustment and power redundancy dynamic testing. These multiple test scenarios cover the entire load cycle of the server, meaning they correspond to all scenarios of system fan speed changes.

[0039] The test rules for each test scenario can be the number of test tasks and the test duration for each test task.

[0040] The data collection rules for each test scenario can be the collection frequency of the actual indicator values ​​of the test indicators and the type of test indicators during the execution of each test task.

[0041] For example, in response to the number of test tasks and the test duration of each test task set by the tester on the client, the client generates a test instruction and sends it to the server; the server receives the test instruction and parses it to obtain the number of test tasks and the test duration of each test task.

[0042] S202, based on the test rules corresponding to each test scenario, runs multiple target test tasks corresponding to the test scenario in the test scenario.

[0043] In one example, the server determines multiple target test tasks in the task pool corresponding to each test scenario based on the number of test tasks and the test duration of each test task; and runs multiple target test tasks corresponding to that test scenario.

[0044] S203: During the execution of each target test task, the actual indicator value of each target test indicator among multiple target test indicators is collected according to the data collection rules.

[0045] Several target test indicators include power supply fan speed, power supply temperature, power supply power consumption, and ambient temperature.

[0046] For example, taking a data acquisition rule with a acquisition frequency of three times per second and test indicators of power fan speed and power temperature as an example, the server acquires power fan speed, power temperature, power consumption and ambient temperature three times per second during the execution of each target test task, and obtains multiple actual indicator values ​​corresponding to power fan speed, power temperature, power consumption and ambient temperature respectively.

[0047] S204 extracts the benchmark metric value corresponding to each target test metric from the pre-built mapping table.

[0048] The mapping table includes multiple correspondences, each corresponding to the power supply fan speed, power supply temperature, power supply power consumption, and ambient temperature.

[0049] The benchmark value corresponding to the first target test indicator is the benchmark value for each target test indicator, based on the actual value of each of the other target test indicators (excluding the first target test indicator). The first target test indicator can be any one of the multiple target test indicators.

[0050] For example, taking the power supply fan speed as the first target test index and other target test indexes including power supply temperature, power supply power consumption, ambient temperature, the actual index value of power supply temperature as the first index value, the actual index value of power supply power consumption as the second index value, and the actual index value of ambient temperature as the third index value as an example, the server extracts the benchmark index value corresponding to the power supply fan speed when the ambient temperature is the third index value, the power supply temperature is the first index value, and the power supply power consumption is the second index value from the pre-built mapping table.

[0051] S205, based on the actual index value and the benchmark index value, determine whether the anti-reverse capability of the power supply fan is abnormal.

[0052] In one example, the server compares the actual indicator value with the benchmark indicator value. If the difference between the actual indicator value and the benchmark indicator value is greater than the target value, it is determined that the power supply fan's anti-reverse capability is abnormal; if the difference between the actual indicator value and the benchmark indicator value is less than or equal to the target value, it is determined that the power supply fan's anti-reverse capability is normal.

[0053] The target value can be set according to actual needs and is not limited. For example, the target value can be the product of a benchmark value and a preset coefficient. The preset coefficient can be any coefficient within a preset coefficient range, specifically between 0.95 and 1.05.

[0054] Optionally, based on the actual and benchmark index values, determine whether the power supply fan's anti-reverse capability is abnormal, including:

[0055] In one example, in each of the multiple test scenarios, the difference between the actual and benchmark values ​​of the power supply fan speed, power supply temperature, and power consumption for each target test task in each test scenario is calculated; the ratio between each difference and the corresponding benchmark value is calculated to obtain the deviation of the power supply fan speed, power supply temperature, and power consumption for each target test task.

[0056] In one example, if the deviation of the power supply temperature in each target test task is greater than a first threshold, it is determined that the power supply fan has an abnormal anti-reversal capability.

[0057] In another example, if the deviation of power consumption in each target test task exceeds a second threshold, or if the deviation of power fan speed in each target test task exceeds a third threshold, then the first weight value corresponding to power fan speed, the second weight value corresponding to power temperature, and the third weight value corresponding to power consumption are obtained. Based on the deviations of power fan speed, power temperature, and power consumption for each target test task, as well as the first, second, and third weight values, an anomaly score for each target test task is obtained. When an anomaly score for a target test task exceeds a preset comprehensive threshold, the anti-reversal capability of the power fan is determined to be abnormal.

[0058] Among them, the first weight value is greater than the second weight value; the second weight value is greater than the third weight value.

[0059] Specifically, the expression corresponding to the anomaly score for each target test task can be as follows:

[0060]

[0061] in, These are abnormal scores; It is the first weight; This represents the deviation corresponding to the power supply fan speed. As the second weight; This represents the deviation corresponding to the power supply temperature. It is the third weight; This represents the deviation corresponding to the power consumption.

[0062] Understandably, power supply temperature directly affects the safety of the server and power supply fan; high temperatures can directly lead to power supply burnout or server crashes. Therefore, when the power supply temperature deviation exceeds a first threshold, the power supply fan's anti-reversal capability is deemed abnormal. To avoid misjudgment based on a single non-fatal indicator anomaly, the deviations in power supply fan speed and power consumption are weighted to reflect the importance of each test indicator. A weighted calculation is used to comprehensively evaluate whether the power supply fan is abnormal, which better reflects the characteristics of multiple indicators working together in real-world scenarios and improves test accuracy.

[0063] based on Figure 2 The method shown allows the server to run multiple target test tasks corresponding to each test scenario in a test scenario, based on the test rules corresponding to each test scenario. During the execution of each target test task, the server collects the actual index value of each target test index among the multiple target test indices according to the data collection rules. The server extracts the benchmark index value corresponding to each target test index from the pre-built mapping table. Based on the actual index value and the benchmark index value, the server determines whether the anti-reverse capability of the power supply fan is abnormal.

[0064] Because the server's power supply fan resilience can be tested under multiple test scenarios, covering the entire load cycle of the server—that is, encompassing all variations in system fan speed or airflow—targeted testing of the power supply fan resilience across the entire load cycle is possible. This improves test coverage and ensures server quality upon delivery. Furthermore, since the testing is directly focused on the power supply fan, it allows for precise identification of whether a server's overheating issues are caused by poor power supply fan resilience. In addition, the automated testing process and methods avoid potential misjudgments from manual observation and assessment, saving labor costs and increasing the level of automation in factory testing.

[0065] In an optional example, based on the aforementioned embodiments and as described above, when the test scenario is a dynamic stress test scenario, multiple target test tasks corresponding to each test scenario are run within the test scenario according to the test rules corresponding to each test scenario, as follows: (See details in the original text.) Figure 3 As shown, Figure 3 A flowchart illustrating the testing method for a dynamic stress testing scenario provided in this application embodiment includes:

[0066] S301, according to the test rules corresponding to the dynamic stress test scenario, randomly select a first number of subtasks from at least one type of test task as target test tasks in the task pool corresponding to the dynamic stress test scenario.

[0067] The test rules for dynamic stress test scenarios include the number of first-order test tasks among multiple target test tasks, and the test duration of each target test task in the first-order test task.

[0068] The task pool corresponding to the dynamic stress test scenario includes multiple types of test tasks. Each type of test task includes a different number of server components to be stress tested. The number of components included in each type of test task and the total number of components determine the number of subtasks included in each type of test task.

[0069] The test tasks can be categorized into four types: Type 1, Type 2, Type 3, and Type 4. Table 1 below shows the different types of test tasks.

[0070] Table 1

[0071]

[0072] In the first type of test task, each test task involves stress testing a component of the server.

[0073] In the second type of test task, each test task involves simultaneously stress testing two components of the server.

[0074] In the third type of test task, each test task involves simultaneously stress testing three components.

[0075] In the fourth type of test task, each test task performs stress tests on all components of the server simultaneously.

[0076] S302, In a dynamic stress test scenario, run the i-th target test task according to the test duration of the i-th target test task, and end the operation after all the target test tasks of the first number of tasks have been run.

[0077] Where i is a positive integer.

[0078] In one example, the test command also carries system fan speed control mode information. In a dynamic stress test scenario, the server sets the system fan speed control mode to automatic speed control mode based on the system fan speed control mode information, runs the i-th target test task according to the test duration of the i-th target test task, and terminates the operation after all the target test tasks of the first number of tasks have been completed.

[0079] Understandably, the pressure faced by a real server during operation is often dynamically changing, causing the airflow required by the system fans to also change dynamically. Therefore, in stress testing scenarios, the "mixed load" that a server experiences in actual operation can be simulated by "randomly selecting target test tasks from multiple types of test tasks." This avoids the problem of the "single load mode" in static testing being out of touch with real-world scenarios, ensuring that the airflow generated by the system fans matches the actual operating conditions and improving the accuracy of testing the power supply fan's resilience.

[0080] In an optional example, based on the aforementioned embodiments and as described above, when the test scenario is a dynamic speed adjustment test scenario, multiple target test tasks corresponding to each test scenario are run in the test scenario according to the test rules corresponding to each test scenario, as follows: (See details in the original text.) Figure 4 As shown, Figure 4 A flowchart illustrating the testing method for a dynamically adjusted rotational speed testing scenario provided in this application embodiment includes:

[0081] S401, Based on the test rules corresponding to the dynamic speed adjustment test scenario, select the target test task of the second number of tasks from the task pool corresponding to the dynamic speed adjustment test scenario.

[0082] The test rules for the dynamic speed adjustment test scenario include the number of second tasks in multiple target test tasks, and the test duration of each target test task in the target test tasks of the second number of target test tasks.

[0083] The task pool corresponding to the dynamic speed adjustment test scenario includes multiple test tasks, and the speed of the system fan is different for every two test tasks.

[0084] For example, in multiple test tasks, the system fan speed starts at 10% of the system fan's maximum speed, and each 5% increase in speed corresponds to one test task, until the system fan reaches its maximum speed.

[0085] In the second target test task, the difference in system fan speed between any two target test tasks must be greater than a first threshold. This first threshold can be set based on the maximum system fan speed. For example, the first threshold could be 10% of the maximum system fan speed.

[0086] Understandably, in dynamic speed adjustment testing scenarios, selecting a second number of tasks from the task pool according to the testing rules, and stipulating that the speed difference between adjacent selected tasks must be greater than a first threshold, avoids selecting tasks with similar speed conditions. This helps to focus on detecting the impact of system fans on power supply fans under significantly different speed conditions, preventing testing resources from being wasted on similar scenarios, thereby improving the rationality and relevance of the test.

[0087] S402, in the dynamic speed adjustment test scenario, run the j-th target test task according to the test duration of the j-th target test task, and end the operation after all the target test tasks of the second number of tasks have been completed.

[0088] Where j is a positive integer.

[0089] In one example, the test command also carries system fan speed control mode information. In a dynamic speed adjustment test scenario, the server sets the system fan speed control mode to manual speed control mode based on the system fan speed control mode information, runs the j-th target test task according to the test duration of the j-th target test task, and terminates the operation after all the target test tasks of the second number of tasks have been completed.

[0090] Understandably, changes in system fan speed can alter system cooling and internal load. By testing under various significantly different fan speeds for specified durations, it becomes easier to capture the impact of speed adjustments on the power supply fan, improving the accuracy of power supply fan anti-reversal capability testing, increasing the likelihood of discovering hidden problems, and ultimately contributing to improved server reliability.

[0091] In an optional example, based on the aforementioned embodiments and as described above, when the test scenario is a power redundancy dynamic test scenario, multiple target test tasks corresponding to each test scenario are run within the test scenario according to the test rules corresponding to each test scenario, as follows: (See details in the original text.) Figure 5 As shown, Figure 5 A flowchart illustrating the test method for dynamic power redundancy testing scenarios provided in this application embodiment includes:

[0092] S501, according to the test rules corresponding to the power redundancy dynamic test scenario, in the task pool corresponding to the power redundancy dynamic test scenario, select test tasks equal to the number of the third task in turn from single power supply test tasks and dual power supply test tasks as target test tasks.

[0093] Among them, the test rules corresponding to the power redundancy dynamic test scenario include the number of third tasks in multiple target test tasks, and the test duration of each target test task in the target test tasks with the number of third tasks.

[0094] The task pool corresponding to the power redundancy dynamic test scenario includes single-power supply test tasks and dual-power supply test tasks. Single-power supply test tasks are for testing when either of the server's two power supplies is running at a single power source. Dual-power supply test tasks are for testing when the server is running at a dual power source.

[0095] Understandably, the target number of test tasks for the third task includes dual power supply test tasks, single power supply test tasks, dual power supply test tasks, single power supply test tasks, dual power supply test tasks, single power supply test tasks, etc.

[0096] S502, in the power redundancy dynamic test scenario, runs the kth target test task according to the test duration of the kth target test task, and ends the operation after all the target test tasks of the third number of tasks have been completed.

[0097] Where k is a positive integer.

[0098] Understandably, in dynamic power redundancy testing scenarios, alternating between single-power-supply and dual-power-supply modes allows for comprehensive testing of the server's power supply and fan resilience under different power supply conditions, avoiding blind spots caused by testing with a single power supply mode. Furthermore, alternating between dual-power-supply and single-power-supply tests more closely resembles real-world server application scenarios, specifically the actual operating conditions of the system fans, making the test results more valuable for practical use.

[0099] In an optional example, based on the aforementioned embodiments and as described above, when the test scenario is a power-on / off cycle test scenario, multiple target test tasks corresponding to each test scenario are run within the test scenario according to the test rules corresponding to each test scenario, as follows: (See details in the original text.) Figure 6 As shown, Figure 6 A flowchart illustrating the test method under the power-on / off cycle test scenario provided in the embodiments of this application includes:

[0100] S601, according to the test rules corresponding to the power-on / off cycle test scenario, in the task pool corresponding to the power-on test scenario, select test tasks equal to the number of the fourth task in turn from the power-on test tasks and the power-off test tasks respectively as target test tasks.

[0101] Among them, the test rules corresponding to the power-on / off cycle test scenario include the number of fourth tasks in multiple target test tasks, and the test duration of each target test task in the target test tasks with the number of fourth tasks.

[0102] The task pool corresponding to the power-on / off cycle test scenario includes power-on test tasks and power-off test tasks.

[0103] S602, in the power-on / off cycle test scenario, run the nth target test task according to the test duration of the nth target test task, until the operation ends after all the target test tasks of the fourth number of tasks have been completed.

[0104] Where n is a positive integer.

[0105] Understandably, alternating between power-on and power-off states in power-on / power-off cycle testing scenarios allows for a comprehensive test of the power supply fan's resilience during repeated power switching, avoiding test vulnerabilities caused by testing in a single state. Furthermore, in real-world scenarios, servers may frequently experience power-on / power-off cycles due to routine maintenance, fault restarts, power grid fluctuations, etc. Alternating between power-on and power-off test tasks more closely reflects the actual application of system fans, further exposing potential issues with the power supply fan's resilience under long-term cycling.

[0106] In an optional example, based on the aforementioned embodiments and as described above, when the test scenario is a power-on / off cycle test scenario, multiple target test tasks corresponding to each test scenario are run within the test scenario according to the test rules corresponding to each test scenario, as follows: (See details in the original text.) Figure 7 As shown, Figure 7 A flowchart illustrating the test method for a power-on / off cycle test scenario provided in this application embodiment includes:

[0107] S701, according to the test rules corresponding to the power-on / off cycle test scenario, in the task pool corresponding to the power-on cycle test scenario, select test tasks equal to the number of the fifth task in turn from the power-on test tasks and power-off test tasks in turn as target test tasks.

[0108] The test rules for the power-on / off loop test scenario include the number of fifth tasks in multiple target test tasks, and the test duration of each target test task in the target test tasks with the number of fifth tasks.

[0109] The task pool corresponding to the power-on / off loop test scenario includes power-on test tasks and power-off test tasks.

[0110] S702, in the power-on / off cycle test scenario, runs the m-th target test task according to the test duration of the m-th target test task, until the operation ends after all the target test tasks of the fifth number of tasks have been completed.

[0111] Where m is a positive integer.

[0112] Understandably, alternating between power-on and power-off cycles in a test scenario allows for a systematic test of the power supply fan's resilience during repeated start-ups and shutdowns, avoiding incomplete testing due to single-operation testing. Furthermore, in real-world use, servers may frequently power on and off due to system updates, feature debugging, and troubleshooting. Alternating between power-on and power-off tests simulates this high-frequency cyclical scenario, effectively exposing potential resilience issues in the power supply fan that may arise during long-term use.

[0113] In an optional example, based on the aforementioned embodiments and as described above, when the test scenario is the first combined test scenario, multiple target test tasks corresponding to each test scenario are run in the test scenario according to the test rules corresponding to each test scenario, as follows: (See details in the original text.) Figure 8 As shown, Figure 8 A flowchart illustrating the testing method for the first combined testing scenario provided in this application embodiment includes:

[0114] S801, according to the test rules corresponding to the first combined test scenario, in the task pool corresponding to the dynamic stress test scenario, randomly select a sixth number of subtasks from at least one type of test task as the target test task.

[0115] S802, the sixth number of test tasks are alternately generated into the first number of dual-power supply test tasks and the second number of single-power supply test tasks.

[0116] The total number of the first and second quantities is the number of the sixth task, with the first quantity being one more than the second quantity.

[0117] S803, in the first combined test scenario, runs the h-th target test task according to the test duration of the h-th target test task, until the operation ends after all the target test tasks of the sixth number of tasks have been completed.

[0118] Where h is a positive integer.

[0119] In one example, in the first combined test scenario, the server sets the system fan speed control mode to automatic speed control mode based on the system fan speed control mode information, runs the h-th target test task according to the test duration of the h-th target test task, and ends the operation after all the target test tasks of the sixth number of tasks have been completed.

[0120] Understandably, in the first test scenario, the dynamic changes in server load are simulated and the power supply mode changes alternately. This makes the operating conditions of the system fan more similar to those of an actual server. The power supply mode may switch dynamically due to faults, load changes, etc. At the same time, the tasks handled also have complex scenarios with randomness. This allows for a thorough test of the power supply fan's resilience under complex scenarios such as power state switching and task load fluctuations.

[0121] In an optional example, based on the aforementioned embodiments and as described above, when the test scenario is the second combined test scenario, multiple target test tasks corresponding to each test scenario are run in the test scenario according to the test rules corresponding to each test scenario, as follows: (See details in the original text.) Figure 9 As shown, Figure 9 A flowchart illustrating the testing method under the second combined testing scenario provided in this application embodiment includes:

[0122] S901, according to the test rules corresponding to the second combined test scenario, select the seventh test task from the task pool corresponding to the dynamic speed adjustment test scenario.

[0123] Among them, in the seventh number of test tasks, the difference in system fan speed between every two test tasks is greater than the second threshold.

[0124] The test rules corresponding to the second combined test scenario include the number of seventh tasks in multiple target test tasks, and the test duration of each target test task in the target test tasks with the number of seventh tasks.

[0125] S902, the seventh number of test tasks will be alternately generated into the third number of dual power supply test tasks and the fourth number of single power supply test tasks.

[0126] The total number of the third and fourth quantities is the number of the seventh task, with the third quantity being one more than the fourth quantity.

[0127] S903, in the second combined test scenario, run the p-th target test task according to the test duration of the p-th target test task, until the operation ends after all the target test tasks of the seventh number of tasks have been completed.

[0128] Where p is a positive integer.

[0129] In one example, in the second combined test scenario, the server sets the system fan speed control mode to manual speed control mode based on the system fan speed control mode information, runs the p-th target test task according to the test duration of the p-th target test task, and ends the operation after all the target test tasks of the seventh number of tasks have been completed.

[0130] Understandably, in the second test scenario, the dynamic changes in system fan speed are simulated, and the power supply mode alternates. This makes the operating conditions of the system fans more closely resemble actual use, where server fan speed dynamically adjusts with load and ambient temperature, and the power supply mode may change due to faults or maintenance—a complex scenario. This allows for a thorough test of the power supply fan's resilience under complex scenarios such as power state switching and changes in system fan speed.

[0131] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0132] Embodiments of this application also provide a server, which includes a power supply fan and a system fan; such as Figure 10 As shown, Figure 10 A device structure block diagram of a server provided in this application embodiment; the server includes:

[0133] The transceiver module 1001 is used to receive test instructions sent by the client. The test instructions are used to indicate the anti-reverse capability of the test power supply fan against the system fan. The test instructions carry test rules and data acquisition rules corresponding to each test scenario in multiple test scenarios.

[0134] The processing module 1002 is used to run multiple target test tasks corresponding to each test scenario in the test scenario according to the test rules corresponding to each test scenario.

[0135] The data acquisition module 1003 is used to collect the actual index value of each target test index among multiple target test indicators according to the data acquisition rules during the execution of each target test task.

[0136] The processing module 1002 is also used to extract the benchmark index value corresponding to each target test index from the pre-built mapping table; and to determine whether the anti-reverse capability of the power supply fan is abnormal based on the actual index value and the benchmark index value.

[0137] In some optional implementations, when the test scenario is a dynamic stress test scenario, the test rules corresponding to the dynamic stress test scenario include the first number of multiple target test tasks and the test duration of each target test task in the first number of target test tasks; the task pool corresponding to the dynamic stress test scenario includes multiple types of test tasks, each type of test task includes a different number of server components to be stress tested, and the number of components included in each type of test task and the total number of components determine the number of subtasks included in each type of test task; the processing module 1002 is specifically used to randomly select the first number of subtasks as target test tasks from at least one type of test task in the task pool corresponding to the dynamic stress test scenario according to the test rules corresponding to the dynamic stress test scenario; in the dynamic stress test scenario, the i-th target test task is run according to the test duration of the i-th target test task until the first number of target test tasks have all been run and the operation ends, where i is a positive integer.

[0138] In some optional implementations, when the test scenario is a dynamic speed adjustment test scenario, the test rules corresponding to the dynamic speed adjustment test scenario include the second number of multiple target test tasks and the test duration of each target test task in the second number of target test tasks; the task pool corresponding to the dynamic speed adjustment test scenario includes multiple test tasks, and the speed of the system fan corresponding to every two test tasks is different; the processing module 1002 is specifically used to select the second number of target test tasks in the task pool corresponding to the dynamic speed adjustment test scenario according to the test rules corresponding to the dynamic speed adjustment test scenario, wherein the speed difference of the system fan corresponding to every two target test tasks in the second number of target test tasks is greater than a first threshold; in the dynamic speed adjustment test scenario, the j-th target test task is run according to the test duration of the j-th target test task until all the second number of target test tasks have been run and the operation ends, where j is a positive integer.

[0139] In some optional implementations, when the test scenario is a power redundancy dynamic test scenario, the test rules corresponding to the power redundancy dynamic test scenario include the number of third tasks among multiple target test tasks, and the test duration of each target test task among the target test tasks of the third number of target test tasks; the task pool corresponding to the power redundancy dynamic test scenario includes single power supply test tasks and dual power supply test tasks; the processing module 1002 is specifically used to, according to the test rules corresponding to the power redundancy dynamic test scenario, sequentially and alternately select test tasks equal to the number of third tasks from the single power supply test tasks and dual power supply test tasks in the task pool corresponding to the power redundancy dynamic test scenario as target test tasks; in the power redundancy dynamic test scenario, the kth target test task is run according to the test duration of the kth target test task, until all the target test tasks of the third number of target test tasks are completed and the operation ends, where k is a positive integer.

[0140] In some optional implementations, when the test scenario is a power-on / off loop test scenario, the test rules corresponding to the power-on / off loop test scenario include the fourth number of multiple target test tasks and the test duration of each target test task in the fourth number of target test tasks; the task pool corresponding to the power-on / off loop test scenario includes power-on test tasks and power-off test tasks; the processing module 1002 is specifically used to, according to the test rules corresponding to the power-on / off loop test scenario, sequentially and alternately select test tasks equal to the fourth number of target test tasks from the power-on test tasks and power-off test tasks in the task pool corresponding to the power-on / off loop test scenario as target test tasks; in the power-on / off loop test scenario, the nth target test task is run according to the test duration of the nth target test task until all the target test tasks of the fourth number of target test tasks have been run and the operation ends, where n is a positive integer.

[0141] In some optional implementations, when the test scenario is a power-on / off loop test scenario, the test rules corresponding to the power-on / off loop test scenario include the number of fifth tasks among multiple target test tasks, and the test duration of each target test task among the target test tasks of the number of fifth tasks; the task pool corresponding to the power-on / off loop test scenario includes power-on test tasks and power-off test tasks; the processing module 1002 is specifically used to, according to the test rules corresponding to the power-on / off loop test scenario, sequentially and alternately select test tasks equal to the number of fifth tasks from the power-on test tasks and power-off test tasks in the task pool corresponding to the power-on / off loop test scenario as target test tasks; in the power-on / off loop test scenario, the m-th target test task is run according to the test duration of the m-th target test task, until all the target test tasks of the number of fifth tasks have been run and the operation ends, where m is a positive integer.

[0142] In some optional implementations, when the test scenario is a first combined test scenario corresponding to a dynamic stress test scenario and a power redundancy dynamic test scenario, the test rules corresponding to the first combined test scenario include the sixth number of multiple target test tasks and the test duration of each target test task in the sixth number of target test tasks; the processing module 1002 is specifically used to, according to the test rules corresponding to the first combined test scenario, randomly select the sixth number of sub-tasks as target test tasks from at least one type of test task in the task pool corresponding to the dynamic stress test scenario; sequentially and alternately generate the sixth number of test tasks into a first number of dual-power supply test tasks and a second number of single-power supply test tasks, the total number of the first number and the second number being the sixth number of tasks, the first number being one more than the second number; in the first combined test scenario, run the h-th target test task according to the test duration of the h-th target test task, until all the target test tasks of the sixth number of tasks have been run and the operation ends, where h is a positive integer.

[0143] In some optional implementations, when the test scenario is a second combined test scenario corresponding to a dynamic speed adjustment test scenario and a power redundancy dynamic test scenario, the test rules corresponding to the second combined test scenario include the seventh number of target test tasks and the test duration of each target test task in the seventh number of target test tasks; the processing module 1002 is specifically used to select the seventh number of test tasks from the task pool corresponding to the dynamic speed adjustment test scenario according to the test rules corresponding to the second combined test scenario, wherein the speed difference of the system fan corresponding to every two test tasks in the seventh number of test tasks is greater than a second threshold; the seventh number of test tasks are used to alternately generate a third number of dual power supply test tasks and a fourth number of single power supply test tasks, the total number of the third and fourth numbers being the seventh number of tasks, the third number being one more than the fourth number; in the second combined test scenario, the p-th target test task is run according to the test duration of the p-th target test task until all the target test tasks of the seventh number of tasks are completed and the operation ends, where p is a positive integer.

[0144] In some optional implementations, determining whether the power supply fan's anti-reverse capability is abnormal based on the actual index value and the benchmark index value includes: if the difference between the actual index value and the benchmark index value is greater than the target value, then the power supply fan's anti-reverse capability is determined to be abnormal.

[0145] For a description of the features of the embodiment corresponding to the test device for the anti-reverse capability of the power supply fan, please refer to the relevant description of the embodiment corresponding to the test method for the anti-reverse capability of the power supply fan, which will not be repeated here.

[0146] Embodiments of this application also provide a server, such as Figure 11 As shown, Figure 11 This is a schematic diagram of the hardware structure of a server provided in an embodiment of this application. The server includes a processor 10 and a memory 20, in which a computer program is stored. The processor 10 is configured to run the computer program to perform the steps in the embodiment of the test method for the anti-reversal capability of any of the power supply fans described above.

[0147] Embodiments of this application also provide a computer-readable storage medium storing a computer program configured to execute the steps in the embodiments of the test method for the anti-reversal capability of any of the above power supply fans when running.

[0148] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0149] The embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in the embodiments of the test method for the anti-reverse capability of any of the above-described power supply fans.

[0150] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in the embodiments of the test method for the anti-reversal capability of any of the above power supply fans.

[0151] Those skilled in the art will further 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 implementation should not be considered beyond the scope of this application.

[0152] The above provides a detailed description of the anti-reverse capability test and server of a power supply fan provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only intended to help understand the method and core ideas of this application. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A method for testing the anti-reverse capability of a power supply fan, characterized in that, The method is applied to a server, the server including a power supply fan and a system fan; the method includes: The system receives a test instruction sent by the client. The test instruction is used to instruct the power supply fan to test the anti-reverse capability of the system fan. The test instruction carries test rules and data acquisition rules corresponding to each of the multiple test scenarios. According to the test rules corresponding to each test scenario, multiple target test tasks corresponding to the test scenario are run in the test scenario. During the execution of each of the target test tasks, the actual index value of each of the multiple target test indicators is collected in accordance with the data collection rules. Extract the benchmark metric value corresponding to each of the target test metrics from the pre-built mapping table; Based on the actual index value and the benchmark index value, determine whether the anti-reverse capability of the power supply fan is abnormal; The step of determining whether the anti-reverse capability of the power supply fan is abnormal based on the actual index value and the benchmark index value includes: In each test scenario, the difference between the actual index value and the benchmark index value of the power supply fan speed, power supply temperature and power supply power consumption for each target test task in each test scenario is calculated. Calculate the ratio between each difference and the corresponding benchmark value to obtain the deviation of the power supply fan speed, power supply temperature and power consumption for each target test task; If the deviation of power consumption in each target test task is greater than the second threshold, or if the deviation of power fan speed in each target test task is greater than the third threshold, then the first weight value corresponding to the power fan speed, the second weight value corresponding to the power temperature, and the third weight value corresponding to the power consumption are obtained. Based on the deviation of the power supply fan speed, power supply temperature and power consumption corresponding to each target test task, as well as the first weight value, the second weight value and the third weight value, the abnormal score of each target test task is obtained. If the abnormal score of the target test task is greater than the preset comprehensive threshold, it is determined that the anti-reverse capability of the power supply fan is abnormal.

2. The method according to claim 1, characterized in that, When the test scenario is a dynamic stress test scenario, the test rules corresponding to the dynamic stress test scenario include the first number of multiple target test tasks and the test duration of each target test task in the first number of target test tasks; the task pool corresponding to the dynamic stress test scenario includes multiple types of test tasks, each type of test task includes a different number of server components to be stress tested, and the number of components included in each type of test task and the total number of components determine the number of subtasks included in each type of test task; The step of running multiple target test tasks corresponding to each test scenario in the test scenario according to the test rules corresponding to each test scenario includes: According to the test rules corresponding to the dynamic stress test scenario, in the task pool corresponding to the dynamic stress test scenario, the first number of sub-tasks are randomly selected from at least one type of test task as the target test task. In the dynamic stress test scenario, the i-th target test task is run according to the test duration of the i-th target test task, until the first number of target test tasks have been completed and the operation ends, where i is a positive integer.

3. The method according to claim 2, characterized in that, When the test scenario is a dynamic speed adjustment test scenario, the test rules corresponding to the dynamic speed adjustment test scenario include the second number of multiple target test tasks and the test duration of each target test task in the second number of target test tasks; the task pool corresponding to the dynamic speed adjustment test scenario includes multiple test tasks, and the speed of the system fan corresponding to every two test tasks is different; The step of running multiple target test tasks corresponding to each test scenario in the test scenario according to the test rules corresponding to each test scenario includes: According to the test rules corresponding to the dynamic speed adjustment test scenario, a target test task of the second number of tasks is selected from the task pool corresponding to the dynamic speed adjustment test scenario, and the speed difference of the system fan corresponding to every two target test tasks in the second number of target test tasks is greater than a first threshold. In the dynamic speed adjustment test scenario, the j-th target test task is run according to the test duration of the j-th target test task, until all the target test tasks of the second number are completed and the operation ends, where j is a positive integer.

4. The method according to claim 3, characterized in that, When the test scenario is a power redundancy dynamic test scenario, the test rules corresponding to the power redundancy dynamic test scenario include the number of third tasks of multiple target test tasks, and the test duration of each target test task in the target test tasks of the third task number; the task pool corresponding to the power redundancy dynamic test scenario includes single power supply test tasks and dual power supply test tasks. The step of running multiple target test tasks corresponding to each test scenario in the test scenario according to the test rules corresponding to each test scenario includes: According to the test rules corresponding to the power redundancy dynamic test scenario, in the task pool corresponding to the power redundancy dynamic test scenario, test tasks of the same number as the third task are selected alternately from the single power supply test tasks and the dual power supply test tasks as the target test tasks. In the power redundancy dynamic test scenario, the kth target test task is run according to the test duration of the kth target test task, until the operation ends after all the target test tasks of the third number of tasks have been completed, where k is a positive integer.

5. The method according to any one of claims 1-4, characterized in that, When the test scenario is a power-on / off cycle test scenario, the test rules corresponding to the power-on / off cycle test scenario include the number of fourth tasks of multiple target test tasks, and the test duration of each target test task in the target test tasks of the number of fourth tasks. The task pool corresponding to the power-on / off cycle test scenario includes power-on test tasks and power-off test tasks. The step of running multiple target test tasks corresponding to each test scenario in the test scenario according to the test rules corresponding to each test scenario includes: According to the test rules corresponding to the power-on / off cycle test scenario, in the task pool corresponding to the power-on test scenario, test tasks equal to the number of the fourth task are selected alternately from the power-on test tasks and the power-off test tasks as target test tasks. In the power-on / off cycle test scenario, the nth target test task is run according to the test duration of the nth target test task, until the operation ends after all the target test tasks of the fourth number have been completed, where n is a positive integer.

6. The method according to any one of claims 1-4, characterized in that, When the test scenario is a power-on / off cycle test scenario, the test rules corresponding to the power-on / off cycle test scenario include the number of fifth tasks of multiple target test tasks, and the test duration of each target test task in the target test tasks of the number of fifth tasks; The task pool corresponding to the power-on / off cycle test scenario includes power-on test tasks and power-off test tasks; The step of running multiple target test tasks corresponding to each test scenario in the test scenario according to the test rules corresponding to each test scenario includes: According to the test rules corresponding to the power-on / off cycle test scenario, in the task pool corresponding to the power-on / off cycle test scenario, test tasks of the same number as the fifth task are selected alternately from the power-on test tasks and the power-off test tasks as target test tasks. In the power-on / off loop test scenario, the m-th target test task is run according to the test duration of the m-th target test task, until all the target test tasks of the fifth number are completed and the operation ends, where m is a positive integer.

7. The method according to claim 4, characterized in that, When the test scenario is the first combined test scenario corresponding to the dynamic stress test scenario and the power redundancy dynamic test scenario, the test rules corresponding to the first combined test scenario include the number of sixth tasks of multiple target test tasks, and the test duration of each target test task in the target test tasks of the number of sixth tasks. The step of running multiple target test tasks corresponding to each test scenario in the test scenario according to the test rules corresponding to each test scenario includes: According to the test rules corresponding to the first combined test scenario, in the task pool corresponding to the dynamic stress test scenario, the sixth number of sub-tasks are randomly selected from the at least one type of test task as the target test task. The sixth number of test tasks are alternately generated by generating a first number of dual-power supply test tasks and a second number of single-power supply test tasks. The total number of the first number and the second number is the sixth number of tasks, and the first number is one more than the second number. In the first combined test scenario, the h-th target test task is run according to the test duration of the h-th target test task, until the operation ends after all the target test tasks of the sixth number of tasks have been completed, where h is a positive integer.

8. The method according to claim 4, characterized in that, When the test scenario is the second combined test scenario corresponding to the dynamic speed adjustment test scenario and the power redundancy dynamic test scenario, the test rules corresponding to the second combined test scenario include the number of seventh tasks of multiple target test tasks, and the test duration of each target test task in the target test tasks of the number of seventh tasks. The step of running multiple target test tasks corresponding to each test scenario in the test scenario according to the test rules corresponding to each test scenario includes: According to the test rules corresponding to the second combined test scenario, the seventh number of test tasks are selected from the task pool corresponding to the dynamic speed adjustment test scenario, and the speed difference of the system fan corresponding to every two test tasks in the seventh number of test tasks is greater than the second threshold. The seventh number of test tasks are alternately generated into a third number of dual-power supply test tasks and a fourth number of single-power supply test tasks. The total number of the third and fourth tasks is the seventh number of tasks, and the third number is one more than the fourth number. In the second combined test scenario, the p-th target test task is run according to the test duration of the p-th target test task, until all the target test tasks of the seventh number are completed and the operation ends, where p is a positive integer.

9. The method according to claim 7 or 8, characterized in that, The step of determining whether the anti-reverse capability of the power supply fan is abnormal based on the actual index value and the benchmark index value includes: if the difference between the actual index value and the benchmark index value is greater than the target value, then the anti-reverse capability of the power supply fan is determined to be abnormal.

10. A server, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the test method for the anti-reverse capability of the power supply fan as described in any one of claims 1 to 9.

Images