Component testing method, device, equipment, medium and product of server

Abstract

The application discloses a kind of server component test method, device, equipment, medium and product, in the case where it is detected that the stress test of component to be tested in server is in starting state, load is applied to server to increase the temperature of component in server, and the temperature of component to be tested and other components of server is collected in real time;When detecting the difference between the temperature of other components and the current set temperature is less than the preset threshold, the current set temperature is increased to the target set temperature according to the preset step, and the speed regulating temperature of other components is set according to the temperature of other components and the temperature safety threshold;When detecting the temperature of component to be tested reaches the target test temperature, start stress test on component to be tested. By increasing the set temperature of other components, the influence of the temperature of other components on the heat dissipation system of the server can be delayed, and precise temperature control of each component in the server is achieved, ensuring that the temperature of the component to be tested reaches the required temperature for testing.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of server testing, and in particular to a component testing method and device for a server, equipment, a medium and a product. BACKGROUND

[0002] In a computing device such as a server, in order to perform reliability verification and fault detection, the components therein need to be subjected to high-temperature pressure testing. Specifically, an external temperature control device can be used to raise the ambient temperature, so that the server is subjected to overall temperature rise, or the rotation speed of the fan in the server is reduced to reduce heat dissipation and raise the internal temperature. However, the above methods are based on temperature control of the entire server, and cannot accurately control the temperature of specific components. In addition, due to the different performances of the components in the server, some components may be locally overheated, which poses a risk of overtemperature and causes damage to the components. Therefore, how to accurately raise the temperature of the test component to the required temperature while ensuring that the temperature of other components is within a safe range has become a problem to be solved. SUMMARY

[0003] The present application provides a component testing method and device for a server, equipment, a medium and a product, to at least solve the problem in the related art of how to accurately raise the temperature of the test component to the required temperature while ensuring that the temperature of other components is within a safe range.

[0004] The present application provides a component testing method for a server, comprising: in a case where it is detected that pressure testing of a to-be-tested component in the server is in a starting state, applying a load to the server to increase the temperature of the components in the server, and collecting the temperature of the to-be-tested component and other components of the server in real time;

[0005] For any other component of the server, when it is detected that the difference between the temperature of the other component and the current set temperature is less than a preset threshold, the current set temperature is increased to a target set temperature according to a preset step size, and the speed regulation temperature of the other component is set according to the temperature of the other component and a temperature safety threshold; the target set temperature is less than or equal to the speed regulation temperature; and the speed regulation temperature is a temperature used to indicate adjustment of the heat dissipation power of the server;

[0006] When it is detected that the temperature of the to-be-tested component reaches a target test temperature, pressure testing of the to-be-tested component is started.

[0007] The present application also provides a component testing device for a server, comprising: a processing module configured to, in a case where it is detected that pressure testing of a to-be-tested component in the server is in a starting state, apply a load to the server to increase the temperature of the components in the server;

[0008] a collection module configured to collect the temperature of the to-be-tested component and other components of the server in real time;

[0009] the processing module is further configured to, for any other component of the server, when detecting that a difference between the temperature of the other component and a current set temperature is less than a preset threshold, increase the current set temperature to a target set temperature according to a preset step size, and set a speed regulation temperature of the other component according to the temperature of the other component and a temperature safety threshold; the target set temperature is less than or equal to the speed regulation temperature; and the speed regulation temperature is a temperature used to indicate adjustment of a heat dissipation power of the server.

[0010] The processing module is further configured to, when detecting that the temperature of the to-be-tested component reaches a target test temperature, start the stress test on the to-be-tested component.

[0011] The application further provides an electronic device, including a memory configured to store a computer program, and a processor configured to execute the computer program to implement the steps of the component test method of the server.

[0012] The application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the component test method of the server.

[0013] The application further provides a computer program product, which includes a computer program, and the computer program is executed by a processor to implement the steps of the component test method of the server.

[0014] In the application, when it is detected that a stress test of a to-be-tested component in a server is in a starting state, a load is applied to the server to increase the temperature of the component, and the temperatures of the to-be-tested component and other components of the server are collected in real time; for any other component of the server, when it is detected that a difference between the temperature of the other component and a current set temperature is less than a preset threshold, the current set temperature is increased to a target set temperature according to a preset step size, and a speed regulation temperature of the other component is set according to the temperature of the other component and a temperature safety threshold; the target set temperature is less than or equal to the speed regulation temperature; and the speed regulation temperature is a temperature used to indicate adjustment of a heat dissipation power of the server; and when it is detected that the temperature of the to-be-tested component reaches a target test temperature, the stress test on the to-be-tested component is started. In the scheme, by adjusting the speed regulation temperature of the other component except the to-be-tested component and increasing the set temperature, the influence of the temperature of the other component on the heat dissipation system of the server can be postponed, external equipment is not relied on, the cost is reduced, and accurate temperature control is implemented on each component in the server, which not only ensures that the temperature of the to-be-tested component can reach a required temperature for testing, but also controls the temperature of the other component to be in an ideal range. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. Obviously, the drawings described below are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort based on these drawings.

[0016] Figure 1 A system architecture diagram of a component testing method of a server provided by an embodiment of the present application is shown in FIG. 1.

[0017] Figure 2 A flowchart of a component testing method of a server provided by an embodiment of the present application is shown in FIG. 2. Figure 1

[0018] Figure 3 A flowchart of a component testing method of a server provided by an embodiment of the present application is shown in FIG. 2. Figure 2

[0019] Figure 4 A structural diagram of a component testing device of a server provided by an embodiment of the present application is shown in FIG. 3.

[0020] Figure 5 A structural diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 4. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort fall within the protection scope of the present application.

[0022] It should be noted that, in the description of the present application, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or device. The terms "first", "second" and the like in the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence.

[0023] ​​It should be noted that in the embodiments of the present application, the words such as "exemplary" or "for example" are used to mean serving as an example, instance, or illustration. Any embodiment or design presented as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or advantageous than other embodiments or design solutions. In fact, a word such as "exemplary" or "for example" is used to present concepts in a concrete manner.

[0024] In server and computing device reliability verification, memory high temperature test (such as: target temperature ≥ 70℃) is the key to verify its stability and detect faults. In the related art, in order to realize the temperature rise of components, a temperature chamber experiment method can be used, that is, the environmental temperature is raised by an external temperature control device (such as: a high temperature test chamber), the whole machine is heated to passively heat the memory. This scheme mainly relies on additional external equipment, which has high cost and large equipment size, is inconvenient to move, and is limited in test environment. When testing a large-scale server cluster, it is limited by the number of temperature chambers and the cost increases sharply. In addition, the temperature chamber can only control the environmental temperature and cannot accurately control the temperature of specific components such as memory. In order to maintain a high temperature environment, continuous refrigeration and heating are needed, which has high energy consumption. In addition, different components have different heat dissipation characteristics, and the whole machine temperature rise has the risk of overtemperature of individual components, which may cause damage to the components for a long time.

[0025] In addition, in order to realize heat dissipation and ensure that the temperature of each component in the server is maintained within a suitable temperature range, a fan can be arranged in the server. Therefore, when performing high temperature stress test on the server, in order to heat the components in the server, the fan can also be fixed at a low speed to reduce heat dissipation and increase the internal temperature. However, reducing the heat dissipation capacity by reducing the fan speed cannot distinguish the priority between components, which may cause local overheating and damage the components. In addition, the high temperature of the components may trigger the protection mechanism of the baseboard management controller (BMC) to cause test interruption.

[0026] Therefore, when performing high temperature stress test on the server, it is necessary to accurately increase the temperature of the test components in the server to reach the target test temperature while ensuring the safety of other components, such as not overheating the network card, and not relying on external equipment to reduce cost and test environment.

[0027] In order to solve all or part of the above technical problems, the embodiments of the present application provide a server component test method, device, equipment, medium and product. In order for those skilled in the art to better understand the present application, the present application will be further described in detail below in conjunction with the drawings and specific embodiments.

[0028] Figure 1A system architecture diagram of a component testing method of a server is provided for an embodiment of the present application, and the system includes a hardware layer and a software layer.

[0029] As shown in Figure 1 , the hardware layer can include server hardware, a temperature sensor, and a heat dissipation system. The server hardware, i.e., the server to be tested, includes components such as memory, a network card, a CPU, a hard disk, and a power supply. The temperature sensor can be an internal sensor of the server, which is used to monitor the temperature of each component. The heat dissipation system mainly includes a fan array, which is used to dissipate heat from each component in the server. Of course, it can also be a liquid cooling device or other devices that can be used for heat dissipation.

[0030] As shown in Figure 1 , the software layer can include a stress testing unit, a temperature monitoring and regulation control unit, and a control unit. The stress testing unit can perform continuous high-intensity stress testing on the component to be tested by running a stress testing tool in the server. On the one hand, this causes the temperature of the component to rise rapidly. On the other hand, it is easier to expose component failures under high-intensity stress. The stress testing tool can include memtester or stressapp, etc. The temperature monitoring and regulation control unit can read the real-time temperature of each component in the server through BMC, make a judgment according to a preset algorithm, and dynamically adjust the heat dissipation regulation strategy, including how to adjust the set point and speed regulation point of each component, how to adjust the fan speed, etc. The control unit can execute commands to achieve regulation and control through the Intelligent Platform Management Interface (IPMI) or Redfish interface of BMC according to the adjustment strategy given by the temperature monitoring and regulation control unit.

[0031] As shown in Figure 2 , Figure 2 A flowchart of a component testing method of a server is provided for an embodiment of the present application. The method can be implemented through mutual cooperation between the hardware layer and the software layer described above. The method can include the following steps:

[0032] 201. In a case where it is detected that stress testing of a component to be tested in a server is in a starting state, a load is applied to the server to increase the temperature of the component in the server, and the temperature of the component to be tested and other components of the server is collected in real time.

[0033] In the embodiments of the present application, the to-be-tested component can be any component in the server that needs to be stress tested, which can generally refer to the memory, and of course can also be other components. The other components can refer to components in the server other than the to-be-tested component. When the to-be-tested component needs to be stress tested, the temperature of the to-be-tested component needs to be raised so that the temperature of the to-be-tested component reaches the target test temperature required for testing. Therefore, a load can be applied to the server to increase the temperature of the components in the server.

[0034] It should be noted that a stress testing tool can be used to apply a high load to the server to cause the components in the server to start heating. The stress testing tool can be memtester or stressapp, etc. The following instruction can be used: / memtester -t $time -m $ (free -g | awk ' / Mem / {print $7-10}'), where -t is run by time; $time is the test time, which is selected according to the test requirements; -m is the size of the component for stress testing.

[0035] In some embodiments, it is assumed that the to-be-tested component is the memory, that is, when the memory needs to be stress tested, the size of the component for stress testing can be determined by subtracting a certain memory, for example, 10G, from the size of the available memory. The 10G can be used as reserved memory for normal operation overhead of the server to avoid the case that the remaining memory is too small to cause memory overflow and affect the normal operation of the server.

[0036] In the embodiments of the present application, when the components in the server are caused to be heated, the temperatures of the to-be-tested component and other components of the server can be collected in real time. The temperatures of the components of the server can be monitored in real time through the IPMI or Redfish interface of the BMC, for example, the temperature values of the components can be read by executing ipmitool sensor list under linux. Here, not only the temperature of the to-be-tested component needs to be read, but also the temperatures of other components other than the to-be-tested component need to be read.

[0037] 202、for any other component of the server, when it is detected that the difference between the temperature of the other component and the current set temperature is less than the preset threshold, the current set temperature is increased to the target set temperature according to the preset step size, and the speed regulating temperature of the other component is set according to the temperature of the other component and the temperature safety threshold.

[0038] It should be noted that each component in the server is provided with its corresponding speed regulation temperature and set temperature, wherein the speed regulation temperature can be used to indicate the temperature for adjusting the heat dissipation power of the server, that is, when the component temperature reaches the speed regulation temperature, the heat dissipation power of the server needs to be increased to reduce the component temperature, for example: when the speed regulation temperature of the network card is 100°C, the fan can be controlled to speed up when the network card temperature is greater than 100°C; the set temperature can indicate the optimal temperature that the server expects the component to maintain. For each component, the set temperature is less than the speed regulation temperature.

[0039] In the embodiment of the present application, subsequent operations are performed for any other component of the server, and if the difference between the temperature of any other component and the current set temperature corresponding to the component is less than the preset threshold value, it can be indicated that the component is easy to trigger the adjustment of the heat dissipation power, and therefore the set temperature and the speed regulation temperature of the component need to be adjusted, so that the temperature change of the component will not trigger the adjustment of the heat dissipation power. Specifically, the speed regulation temperature of the other component can be set according to the current temperature of the other component and the temperature safety threshold value, and the current set temperature is increased to the target set temperature according to the preset step length. The preset step length can be a small temperature change value defined by the user, such as 1°C, that is, the current set temperature of the component is increased by 1°C each time.

[0040] In addition, the temperature safety threshold value can be referred to when setting the speed regulation temperature. The temperature safety threshold value can be considered as the safe upper limit temperature of the component. The temperature safety threshold value of each component can be the same or different, and is not specifically limited. If the component temperature exceeds the temperature safety threshold value, the component can be damaged by overheating. Therefore, the component temperature cannot exceed the temperature safety threshold value. In addition, since the speed regulation temperature can trigger the increase of the heat dissipation power, and if the heat dissipation power increases, the temperature of the tested component will inevitably decrease, which cannot be tested under pressure. Therefore, in order to ensure that the tested component can be heated smoothly, it is also necessary to ensure that the temperature of the other component does not exceed the speed regulation temperature. Since the set temperature of the other component will be increased cyclically, there is a correlation between the current set temperature and the real-time temperature of the component. Therefore, in order to ensure that the temperature of the other component does not exceed the speed regulation temperature, it is necessary to ensure that the target set temperature of the other component after each adjustment is less than or equal to the speed regulation temperature.

[0041] In some embodiments, since the temperature of each component in the entire server is increased, that is, the temperature of multiple other components can reach the set temperature, or the difference between the temperature and the current set temperature is less than the preset threshold value. Therefore, the current set temperature of each of the multiple other components can be increased to the target set temperature according to the preset step length, and the speed regulation temperature of the other component can be set according to the temperature of the other component and the temperature safety threshold value.

[0042] 203. When the temperature of the component under test is detected to have reached the target test temperature, the pressure test on the component under test is started.

[0043] In this embodiment of the application, the component under test will continue to heat up under the influence of server load, and by dynamically adjusting the speed trigger threshold (i.e., set temperature and speed adjustment temperature) of other components, the occupation of its heat dissipation system is delayed, ensuring that the heat dissipation system will not affect the temperature rise of the component under test. Therefore, if the temperature of the component under test is detected to reach the target test temperature, it means that the current temperature environment can be used for stress testing, so stress testing of the component under test can begin.

[0044] In this embodiment of the application, by adjusting the speed control temperature of components other than the component under test and increasing the set temperature, the impact of the temperature of other components on the server's heat dissipation system can be delayed. This reduces costs by not relying on external equipment and achieves precise temperature control of each component in the server. It not only ensures that the temperature of the component under test can reach the required test temperature, but also controls the temperature of other components to be within the ideal range.

[0045] like Figure 3 As shown, Figure 3 Another flowchart of a server component testing method provided for embodiments of this application, the method may include the following steps:

[0046] 301. When the stress test of the component under test in the server is detected to be in the start state, apply a load to the server to increase the temperature of the components in the server, and collect the temperature of the component under test and other components of the server in real time.

[0047] In this embodiment, the description of step 301 is the same as the detailed description of step 201 in the above embodiments, and will not be repeated in this embodiment.

[0048] 302. For any other component of the server, when the difference between the temperature of the other component and the current set temperature is less than a preset threshold, determine the speed regulation temperature adjustment value of the other component based on the temperature of the other component, the temperature safety threshold, and the safety factor.

[0049] In this embodiment of the application, when setting the speed regulation temperature of other components, the speed regulation temperature adjustment value of other components can be determined first based on the current temperature of other components, the temperature safety threshold of the other components, and the safety factor.

[0050] In some embodiments, the current temperature of other components and the corresponding temperature safety threshold of those components can be obtained using the ipmitool sensor list command.

[0051] In some embodiments, the speed regulation temperature adjustment value can be calculated by the following formula:

[0052]

[0053] wherein, represents the speed regulation temperature adjustment value, represents the temperature safety threshold corresponding to the other component, represents the current temperature of the other component, represents the safety coefficient, the default value of which is 0.8, and ensures that .

[0054] 303. Determine the first speed regulation temperature according to the speed regulation temperature adjustment value and the temperature of the other component.

[0055] In the embodiments of the present application, after the speed regulation temperature adjustment value is calculated, the speed regulation temperature adjustment value and the current temperature of the other component can be added to obtain the first speed regulation temperature.

[0056] In some embodiments, in combination with the above formula, the first speed regulation temperature can be represented as , and the first speed regulation temperature is less than the temperature safety threshold.

[0057] 304. Determine the speed regulation temperature of the other component according to the initial speed regulation temperature corresponding to the other component and the first speed regulation temperature.

[0058] In the embodiments of the present application, each component is provided with an original set temperature and a speed regulation temperature, and under the server BMC system, the temperature regulation strategy can be queried by the monitor_app --show-fan-param command, which contains the original speed regulation temperature and the set temperature corresponding to the other component. Since the speed regulation temperature directly affects the heat dissipation power, the greater the speed regulation temperature, the smaller the influence of the other component on the heat dissipation system. Since the original speed regulation temperature is not considered when calculating the speed regulation temperature adjustment value, the first speed regulation temperature determined according to the temperature of the other component, the temperature safety threshold and the safety coefficient cannot guarantee the size relationship between the original speed regulation temperature, and therefore the final speed regulation temperature corresponding to the other component can be determined according to the initial speed regulation temperature corresponding to the other component and the first speed regulation temperature.

[0059] In some embodiments, determining the speed regulation temperature of the other component according to the initial speed regulation temperature corresponding to the other component and the first speed regulation temperature can specifically include: performing numerical comparison on the initial speed regulation temperature and the first speed regulation temperature to obtain a comparison result; and determining the speed regulation temperature of the other component according to the maximum value between the initial speed regulation temperature and the first speed regulation temperature indicated by the comparison result.

[0060] It should be noted that the initial speed regulation temperature and the first speed regulation temperature can be compared, the maximum value between the initial speed regulation temperature and the first speed regulation temperature is determined, and the maximum value is determined as the speed regulation temperature of the other component, and the speed regulation temperature of the other component is updated.

[0061] In some embodiments, assuming that the temperature safety threshold of the network card is 105°C, the initial speed regulation temperature of the network card is 100°C, and the first speed regulation temperature obtained after calculation is 101°C, after comparison: 101°C>100°C, 101°C can be determined as the latest speed regulation temperature of the network card, and the speed regulation temperature of the network card is updated to 101°C according to the monitor_app --set-fan-param bjpid11_threshold80:101 command.

[0062] In some embodiments, the speed regulation temperature affects the triggering of the adjustment of the heat dissipation power, and then when the speed regulation temperature of the other component is adjusted, in order to delay the influence of the temperature of the other component on the heat dissipation power as much as possible, it is necessary to increase the speed regulation temperature as much as possible, and therefore, on the basis of the temperature safety threshold and the real-time temperature, the initial speed regulation temperature can be further combined to take the maximum value, so that the temperature rise of the to-be-tested component cannot be affected by the heat dissipation system, and the temperature of the to-be-tested component can be accurately controlled.

[0063] 305、When it is detected that the difference between the speed regulation temperature of the other component and the current set temperature is greater than or equal to a preset step length, the current set temperature corresponding to the other component is increased to the target set temperature according to the preset step length.

[0064] In the embodiments of the present application, since the adjustment of the heat dissipation power will be caused when the temperature of the other component exceeds the speed regulation temperature, the set temperature needs to be ensured not to exceed the speed regulation temperature when the set temperature is adjusted. Since the set temperature is adjusted according to the preset step length each time, that is, the target set temperature after adjustment is equal to the sum of the current set temperature and the preset step length, in order to ensure that the target set temperature after adjustment does not exceed the preset step length, before adjustment, the difference between the current set temperature and the speed regulation temperature can be calculated first. If the difference is greater than or equal to the preset step length, the target set temperature after adjustment is still less than or equal to the speed regulation temperature and will not exceed the speed regulation temperature, but if the difference is less than the preset step length, the target set temperature after adjustment will be greater than the speed regulation temperature, which will cause the change of the heat dissipation power of the server and cannot realize the continuous temperature rise of the to-be-tested component. Therefore, only when it is detected that the difference between the speed regulation temperature of the other component and the current set temperature is greater than or equal to the preset step length, the current set temperature corresponding to the other component can be increased to the target set temperature according to the preset step length.

[0065] In some embodiments, assuming that the current set temperature of the network card is 85°C and the preset step is 1°C, that is, the current set temperature is increased from 85°C to 86°C by adding 1°C to the current set temperature each time, as the target set temperature, the command monitor_app --set-fan-param bjpid11_sp86 can be used to achieve the target set temperature.

[0066] In some embodiments, before adjusting the set temperature of the other components, the difference between the set temperature and the speed-limit temperature and the preset step are compared to ensure that the set temperature is not increased beyond the speed-limit temperature after the preset step is added, so as to avoid increasing the heat dissipation power of the server and ensuring that the component under test can continue to increase in temperature.

[0067] 306、When it is detected that the temperature of the component under test is less than the target test temperature, the current set temperature of the other components is increased by the preset step or the heat dissipation power of the server is reduced according to the difference between the current set temperature and the speed-limit temperature of the other components.

[0068] In the embodiments of the present application, after the current set temperature of the other components is increased to the target set temperature, the current temperature of the component under test can be detected. If the temperature of the component under test is less than the target test temperature, it indicates that the component under test has not yet reached the requirements of the stress test, and then the temperature needs to be continued to be increased. At this time, the current set temperature of the other components can be increased by the preset step in a loop, or the heat dissipation power of the server can also be reduced. The specific measures to be taken can be determined in combination with the difference between the current set temperature and the speed-limit temperature of the other components.

[0069] In some embodiments, when it is detected that the temperature of the component under test is less than the target test temperature, the current set temperature of the other components is increased by the preset step or the heat dissipation power of the server is reduced according to the difference between the current set temperature and the speed-limit temperature of the other components. Specifically, the following two optional implementation manners can be included:

[0070] Implementation manner one: when it is detected that the temperature of the component under test is less than the target test temperature and the difference between the current set temperature and the speed-limit temperature of the other components is greater than or equal to the preset step, the current set temperature of the other components is increased by the preset step.

[0071] It should be noted that, on the basis that the temperature of the component under test is less than the target test temperature, if it is further detected that the difference between the current set temperature and the speed-limit temperature of the other components is greater than or equal to the preset step, it indicates that the current set temperature can be increased by the preset step on the basis of the current set temperature, and the target set temperature after the increase will not exceed the speed-limit temperature. Therefore, the current set temperature of the other components can be continued to be increased by the preset step.

[0072] In a second implementation, when it is detected that the temperature of the component under test is less than the target test temperature, and the difference between the current set temperature and the speed regulation temperature of the other component is less than the preset step, the heat dissipation power of the server is reduced.

[0073] It should be noted that, on the basis that the temperature of the component under test is less than the target test temperature, if it is further detected that the difference between the current set temperature and the speed regulation temperature of the other component is less than the preset step, it indicates that on the basis of the current set temperature, if the current set temperature is increased by the preset step, the target set temperature after the increase will exceed the speed regulation temperature, causing the adjustment of the heat dissipation power and the failure to achieve the temperature rise of the component under test, and therefore the set temperature cannot be further increased. That is, if the set temperature of the other component cannot be further increased, but the temperature of the component under test has not reached the target test temperature, in order to ensure that the component under test can continue to rise in temperature, the heat dissipation power of the server can be reduced.

[0074] In some embodiments, the heat dissipation system of the server can be implemented at least by liquid cooling or air cooling. The liquid cooling is to achieve cooling by the flow of cooling liquid in the server, and the air cooling is to achieve cooling by the operation of the fan in the server. Therefore, reducing the heat dissipation power of the server can specifically include reducing the flow speed or flow area of the cooling liquid, and reducing the rotation speed of the fan to suppress heat dissipation. Of course, the heat dissipation of the server can also be implemented by other ways, which are not limited in the embodiments of the present application.

[0075] In some embodiments, when the set temperature of the other component is adjusted, the temperature of the component under test can not be raised to the test temperature at one time, and therefore the set temperature can need to be adjusted in cycles, and the set temperature needs to be ensured not to exceed the speed regulation temperature at each time of adjustment, so as to take different heat dissipation suppression tests to ensure that the component under test can continue to rise in temperature, and also to ensure that the temperature change of the other component will not increase the heat dissipation power.

[0076] 307、When the temperature of the component under test is greater than the target test temperature, the current set temperature of the other component is reduced by the preset step, and the heat dissipation power of the server is increased.

[0077] In the embodiments of the present application, if after the current set temperature is increased to the target set temperature, it is detected that the temperature of the component under test has exceeded the target test temperature, the component under test needs to be cooled down at this time, and therefore the current set temperature of the other component can be reduced, and the heat dissipation power of the server can be increased.

[0078] It should be noted that during the temperature rising process of the to-be-tested component, other components in the server will also rise in temperature, the speed regulation temperature corresponding to the component is greater than the set temperature, and once the temperature of the component exceeds the speed regulation temperature, the heat dissipation power will be triggered to increase greatly, for example, the fan speed is directly increased from the original 40% speed to 80% speed to achieve the purpose of rapid cooling, and if the temperature of the component exceeds the set temperature, the heat dissipation power will not be triggered to increase greatly, but will be fine-tuned according to the algorithm of the heat dissipation system, for example, the fan speed is fine-tuned from the original 40% speed to 42% speed, so as to make the temperature of the component be at the set temperature as much as possible. It can be understood that if the current set temperature of the other component is reduced, the other component will reach the current set temperature faster, that is, the fine-tuning of the heat dissipation power will be triggered faster, and the temperature of the to-be-tested component can be reduced. However, reducing the current set temperature cannot ensure that the heat dissipation power will be fine-tuned immediately, so if it is desired to quickly make the temperature of the to-be-tested component equal to the target test temperature, the heat dissipation power of the server can also be directly increased.

[0079] In some embodiments, the temperature of the to-be-tested component can also be greater than the test temperature, and corresponding measures need to be taken to reduce the temperature of the to-be-tested component, so that the temperature of the to-be-tested component can meet the test temperature.

[0080] 308、After the server is static for a preset time length, when it is detected that the temperature of the to-be-tested component reaches the target test temperature, the stress test on the to-be-tested component is started.

[0081] In the embodiments of the application, after the set temperature of each of the other components is increased each time, a period of time can be first static to ensure that the temperatures of all components in the entire server and the heat dissipation system tend to be stable before detecting the temperature of the to-be-tested component. The preset time length can be a self-set time length, for example, 50s, 1min, etc. After the adjustment of the set temperature of the other components or the adjustment of the heat dissipation power of the server, if it is detected that the temperature of the to-be-tested component reaches the target test temperature, it indicates that the to-be-tested component has met the test temperature environment, and therefore the stress test on the to-be-tested component can be started.

[0082] In some embodiments, after the set temperature of each of the other components is increased each time, because the temperature of the component can not change in time, there can be a certain response time between the adjustment of the set temperature and the increase of the real-time temperature, and the temperature of the component can also suddenly increase and become unstable due to other influences. Therefore, a period of time can be static before detecting the real-time temperature, so as to improve the accuracy of temperature detection and achieve accurate temperature control of each component.

[0083] 309、Compare the temperatures of the components with the temperature safety threshold to obtain a temperature detection result.

[0084] In the embodiments of the present application, the server can also be configured with a security fusing mechanism, that is, each component is correspondingly provided with a temperature safety threshold, and if the temperature safety threshold is exceeded, the component can be overheated and damaged, therefore, on the basis of collecting the temperatures of the to-be-tested component and other components of the server in real time, the temperature of each component can be compared with the temperature safety threshold to obtain a temperature detection result, which can indicate the size relationship between the temperature of each component and the corresponding temperature safety threshold.

[0085] 310. According to the temperature detection result, a corresponding safety measure is taken for the component in the server.

[0086] In the embodiments of the present application, the safety measures corresponding to various temperature detection results can be pre-set, and after determining the temperature detection result of a certain component, the safety measure corresponding to the temperature detection result can be taken for the component.

[0087] In some embodiments, the safety measures for temperature can include multiple levels of protection such as pre-warning, recovery, emergency cooling, etc.

[0088] In some embodiments, when the component temperature reaches 98% of the temperature safety threshold, a pre-warning information is sent; when the component temperature reaches the temperature safety threshold, the speed regulating temperature and the set temperature of all components are immediately recovered to ensure that the adjustment of the heat dissipation power of the server can be triggered in time; when the component temperature reaches 102% of the temperature safety threshold, the heat dissipation power of the server is immediately adjusted to the maximum value to achieve rapid cooling and prevent hardware damage caused by over-temperature. The values of 98% and 102% of the temperature safety threshold can be set by the user and are not limited.

[0089] In some embodiments, through the security fusing mechanism, the temperatures of various components are monitored in real time, and corresponding measures are taken to ensure that the component temperature does not exceed the safety threshold and to ensure the normal operation of the server and the normal testing of the to-be-tested component.

[0090] 311. When it is detected that the temperature of the to-be-tested component reaches the target test temperature, a set temperature up value of the other component is determined.

[0091] In the embodiments of the present application, when it is detected that the temperature of the to-be-tested component reaches the target test temperature, it indicates that the to-be-tested component meets the test temperature environment and can start testing, and it also indicates that the adjustment of the set temperature of the other component is appropriate, and therefore the set temperature up value of the other component can be determined, which can be the difference between the initial set temperature of the other component and the set temperature when the temperature of the to-be-tested component reaches the target test temperature.

[0092] 312. generating a temperature change model of the server according to the temperature change value of the component to be tested, the set temperature up-regulation value, the load power of the component to be tested, and the heat dissipation power of the server.

[0093] In the embodiments of the present application, the temperature change value of the component to be tested can refer to the difference between the temperature value when the server is just subjected to load so that each component starts to heat up and the temperature value when the temperature of the component to be tested reaches the target test temperature (i.e. the target test temperature); the load power of the component to be tested can refer to the load power of the server subjected to load, and if the load changes, the load power can take the maximum value; the heat dissipation power of the server can refer to the initial heat dissipation power of the server, and it needs to be noted that, in an ideal case, the temperature of the component to be tested can reach the target test temperature only by adjusting the speed regulation temperature and the set temperature of other components, and the adjustment of the heat dissipation power of the server in the present application is only an operation in some scenarios.

[0094] In some embodiments, the temperature change model of the server can be represented by the following formula:

[0095]

[0096] wherein, the temperature change value of the component to be tested, the set temperature up-regulation value, the load power of the component to be tested, the heat dissipation power of the server, the heat dissipation coupling coefficient, which is related to the design of the heat dissipation system, and usually takes a value of 0.6-0.9; and are power influence coefficients, which can be obtained through a large amount of data experiments.

[0097] Through the formula, it can be seen that for the same server, multiple component heating tests can be performed, and different components to be tested can be selected each time, and different target test temperatures can also be set. Through multiple experiments and recording the temperature change value of the component to be tested, the set temperature up-regulation value, the load power of the component to be tested, the heat dissipation power of the server and other data of each experiment, the temperature change model can be generated.

[0098] In some embodiments, after the temperature change model is generated, if the temperature of the server needs to be increased for stress testing of other components in the server, the corresponding test temperature can be directly input into the model. Ideally, the load power and the heat dissipation power of the same server are the same, so the corresponding set temperature adjustment value can be directly calculated through the temperature change model, so that the set temperature of other components can be directly increased, and fine tuning can be performed on this basis, without increasing the temperature step by step.

[0099] In some embodiments, a temperature change model is generated according to the corresponding temperature adjustment value, power, fan speed and other data during the stress test process, so that the specific temperature adjustment value can be directly obtained through the model during subsequent stress testing, without the need to increase the temperature step by step, to quickly increase the component temperature and improve the test efficiency.

[0100] From the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software and a necessary general hardware platform, and of course, it can also be implemented by hardware, but in many cases, the former is a better implementation.

[0101] As shown in Figure 4 The embodiments of the present application also provide a server component testing device, which can include:

[0102] The processing module 401 is configured to apply a load to the server to increase the temperature of the components in the server when it is detected that the stress test of the to-be-tested component in the server is in a starting state.

[0103] The acquisition module 402 is configured to collect the temperatures of the to-be-tested component and other components of the server in real time.

[0104] The processing module 401 is further configured to, for any other component of the server, when it is detected that the difference between the temperature of the other component and the current set temperature is less than a preset threshold, increase the current set temperature to a target set temperature according to a preset step, and set a speed-adjusted temperature of the other component according to the temperature of the other component and the temperature safety threshold; the target set temperature is less than or equal to the speed-adjusted temperature; and the speed-adjusted temperature is a temperature used to indicate adjustment of the heat dissipation power of the server.

[0105] The processing module 401 is further configured to start the stress test of the to-be-tested component when it is detected that the temperature of the to-be-tested component reaches the target test temperature.

[0106] In some embodiments, the processing module 401 is specifically configured to determine the speed-adjusted temperature adjustment value of the other component according to the temperature of the other component, the temperature safety threshold and a safety coefficient.

[0107] The processing module 401 is specifically configured to determine the first speed regulation temperature according to the speed regulation temperature adjustment value and the temperature of the other component.

[0108] The processing module 401 is specifically configured to determine the speed regulation temperature of the other component according to the initial speed regulation temperature and the first speed regulation temperature corresponding to the other component.

[0109] In some embodiments, the processing module 401 is specifically configured to compare the initial speed regulation temperature and the first speed regulation temperature to obtain a comparison result.

[0110] The processing module 401 is specifically configured to determine the speed regulation temperature of the other component according to the maximum value between the initial speed regulation temperature and the first speed regulation temperature indicated by the comparison result.

[0111] In some embodiments, the processing module 401 is specifically configured to increase the current set temperature of the other component to the target set temperature by the preset step size when it is detected that the difference between the speed regulation temperature of the other component and the current set temperature is greater than or equal to the preset step size.

[0112] In some embodiments, the processing module 401 is specifically configured to start the pressure test on the component to be tested when it is detected that the temperature of the component to be tested reaches the target test temperature after the server is static for the preset time length.

[0113] In some embodiments, the processing module 401 is further configured to increase the current set temperature of the other component by the preset step size or reduce the heat dissipation power of the server according to the difference between the current set temperature and the speed regulation temperature of the other component when it is detected that the temperature of the component to be tested is less than the target test temperature.

[0114] In some embodiments, the processing module 401 is specifically configured to increase the current set temperature of the other component by the preset step size when it is detected that the temperature of the component to be tested is less than the target test temperature and the difference between the current set temperature and the speed regulation temperature of the other component is greater than or equal to the preset step size.

[0115] In some embodiments, the processing module 401 is specifically configured to reduce the heat dissipation power of the server when it is detected that the temperature of the component to be tested is less than the target test temperature and the difference between the current set temperature and the speed regulation temperature of the other component is less than the preset step size.

[0116] In some embodiments, the processing module 401 is further configured to reduce the current set temperature of the other component by the preset step size and increase the heat dissipation power of the server when the temperature of the component to be tested is greater than the target test temperature.

[0117] In some embodiments, the processing module 401 is further configured to compare the temperature of each component with the temperature safety threshold to obtain a temperature detection result.

[0118] The processing module 401 is also used to take corresponding safety measures for the components in the server based on the temperature detection results.

[0119] In some embodiments, the processing module 401 is further configured to determine the set temperature adjustment value of other components when the temperature of the component under test is detected to have reached the target test temperature.

[0120] The processing module 401 is also used to generate a temperature change model of the server based on the temperature change value of the component under test, the set temperature adjustment value, the load power of the component under test, and the heat dissipation power of the server.

[0121] In the embodiments of this application, the description of the features corresponding to the component testing device of the server in the embodiments can be found in the relevant description of the component testing method of the server in the embodiments, and will not be repeated here.

[0122] like Figure 5 As shown, embodiments of this application also provide an electronic device, including a memory 501 and a processor 502. The memory 501 stores a computer program, and the processor 502 is configured to run the computer program to perform the steps in any of the above-described server component testing method embodiments.

[0123] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above-described embodiments of the server component testing method when it is run.

[0124] 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.

[0125] 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 component testing method for any of the above-described servers.

[0126] 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 any of the above-described server component testing methods.

[0127] Those skilled in the art will further realize that the mere concepts, teachings, and embodiments described herein are merely meant to provide an enabling description of the claimed application. Accordingly, modifications and / or additions, other than those explicitly described herein, can be obvious to those skilled in the art in the light of this disclosure. The claimed application is intended to embrace all such modifications and / or additions.

[0128] The above provides a kind of server component test method, device, equipment, medium and product provided by the present application in detail.The principle and implementation of the present application are described in this paper by applying specific examples, the above example is only applicable to help understand the method and its core idea of the present application.It should be pointed out that, for those skilled in the art, without departing from the principle of the present application, some improvements and modifications can be made to the present application, and these improvements and modifications also fall within the protection scope of the claims of the present application.

Claims

1. A method of testing components of a server, the method comprising: The method comprises the following steps: When it is detected that a stress test of a to-be-tested component in the server is in a starting state, a load is applied to the server to increase the temperature of the components in the server, and the temperature of the to-be-tested component and other components of the server is collected in real time; For any other component of the server, when it is detected that the difference between the temperature of the other component and a current set temperature is less than a preset threshold value, and the difference between the speed regulation temperature of the other component and the current set temperature is greater than or equal to a preset step length, the current set temperature is increased to a target set temperature by the preset step length, and the speed regulation temperature of the other component is set according to the temperature of the other component and a temperature safety threshold value; the target set temperature is less than or equal to the speed regulation temperature; the speed regulation temperature is a temperature for indicating adjustment of the heat dissipation power of the server; When it is detected that the temperature of the to-be-tested component is less than a target test temperature, the current set temperature of the other component is increased by the preset step length according to the difference between the current set temperature of the other component and the speed regulation temperature, or the heat dissipation power of the server is reduced; When it is detected that the temperature of the to-be-tested component reaches the target test temperature, the stress test of the to-be-tested component is started.

2. The method of claim 1, wherein, The setting of the speed regulation temperature of the other component according to the temperature of the other component and a temperature safety threshold value comprises: determining a speed regulation temperature adjustment value of the other component according to the temperature of the other component, the temperature safety threshold value and a safety coefficient; determining a first speed regulation temperature according to the speed regulation temperature adjustment value and the temperature of the other component; determining the speed regulation temperature of the other component according to the initial speed regulation temperature corresponding to the other component and the first speed regulation temperature.

3. The method of claim 2, wherein, The determination of the speed regulation temperature of the other component according to the initial speed regulation temperature corresponding to the other component and the first speed regulation temperature comprises: performing numerical comparison on the initial speed regulation temperature and the first speed regulation temperature to obtain a comparison result; determining the speed regulation temperature of the other component according to the maximum value between the initial speed regulation temperature and the first speed regulation temperature indicated by the comparison result.

4. The method of claim 1, wherein, The starting of the stress test of the to-be-tested component when it is detected that the temperature of the to-be-tested component reaches the target test temperature comprises: after the server is rested for a preset time length, starting the stress test of the to-be-tested component when it is detected that the temperature of the to-be-tested component reaches the target test temperature.

5. The method of claim 1, wherein, The increasing of the current set temperature of the other component and / or the reducing of the heat dissipation power of the server when it is detected that the temperature of the to-be-tested component is less than the target test temperature according to the difference between the current set temperature of the other component and the speed regulation temperature by the preset step length comprises: when it is detected that the temperature of the to-be-tested component is less than the target test temperature, and the difference between the current set temperature of the other component and the speed regulation temperature is greater than or equal to the preset step length, increasing the current set temperature of the other component by the preset step length.

6. The method of claim 1, wherein, The method further comprises: When it is detected that the temperature of the to-be-tested component is less than the target test temperature, and the difference between the current set temperature of the other component and the speed regulation temperature is less than the preset step length, the heat dissipation power of the server is reduced.

7. The method of claim 1, wherein, The method further comprises: When it is detected that the temperature of the to-be-tested component reaches the target test temperature, a set temperature up-regulation value of the other component is determined.

8. The method of claim 1, wherein, According to the temperature change value of the to-be-tested component, the set temperature up-regulation value, the load power of the to-be-tested component, and the heat dissipation power of the server, a temperature change model of the server is generated. The method further comprises: When it is detected that the temperature of the to-be-tested component reaches the target test temperature, a set temperature up-regulation value of the other component is determined.

9. The method of claim 1, wherein, According to the temperature change value of the to-be-tested component, the set temperature up-regulation value, the load power of the to-be-tested component, and the heat dissipation power of the server, a temperature change model of the server is generated. The method further comprises: The processing module is further configured to, when it is detected that the temperature of the to-be-tested component is less than a target test temperature, increase the current set temperature of the other component by the preset step length according to the difference between the current set temperature of the other component and the speed regulation temperature, or reduce the heat dissipation power of the server.

10. A server component testing apparatus, characterized by, The method further comprises: The processing module is further configured to, when it is detected that the temperature of the to-be-tested component reaches the target test temperature, start the pressure test on the to-be-tested component. The method further comprises: The memory is configured to store a computer program. The memory is configured to store a computer program. ​ 11. An electronic device, comprising: ​ ​ A processor configured to implement the steps of the component testing method of the server of any one of claims 1 to 9 when executing the computer program.

12. A computer-readable storage medium, characterized in that, A computer program product comprising a computer program stored in a computer readable storage medium, wherein the computer program is configured to implement the steps of the component testing method of the server of any one of claims 1 to 9 when executed by a processor.

13. A computer program product, characterised in that, A computer program product comprising a computer program, wherein the computer program is configured to implement the steps of the component testing method of the server of any one of claims 1 to 9 when executed by a processor.

Images