Server fan speed control method and electronic device

Abstract

The application discloses a server fan rotating speed control method and electronic equipment, and relates to the technical field of servers, and comprises the following steps: obtaining power consumption information of firmware of a server in a target task scene and a temperature difference between an air inlet and an air outlet of a case of the server in the target task scene, constructing a fan rotating speed calculation model, calculating required air volume for heat dissipation in the target task scene according to the power consumption information of the firmware of the server, the temperature difference between the air inlet and the air outlet of the case and a heat dissipation efficiency coefficient, and then determining a fan rotating speed according to the required air volume for heat dissipation to perform server heat dissipation control, so that a reasonable fan rotating speed can be accurately determined, the problem of insufficient heat dissipation or increased power consumption caused by unreasonable manual setting of the fan rotating speed is solved, and the server heat dissipation effect is ensured while fan power consumption is saved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of servers, and in particular to a server fan rotating speed control method and electronic equipment. BACKGROUND

[0002] A server is a core computing unit for data processing, and heat dissipation management is crucial for ensuring server reliability. As one of the server heat dissipation methods, air cooling heat dissipation achieves server heat dissipation management by controlling the rotating speed of the fan.

[0003] Currently, an operation and maintenance personnel sets the rotating speed of the fan according to different temperatures, and controls the rotating speed of the fan according to the temperature during heat dissipation management. However, the setting of the rotating speed of the fan mainly depends on the experience of the operation and maintenance personnel. If the rotating speed is set too low, the server hardware may be damaged due to insufficient heat dissipation. If the rotating speed is set too high, it will increase the power consumption and noise of the fan, and also accelerate the wear of the fan, reducing the service life of the fan.

[0004] Therefore, how to accurately calculate a reasonable rotating speed of the fan is a technical problem to be solved. SUMMARY

[0005] The present application provides a server fan rotating speed control method and electronic equipment to at least solve the problem of insufficient heat dissipation or increased power consumption caused by unreasonable fan rotating speed setting in the related art.

[0006] The present application provides a server fan rotating speed control method, comprising:

[0007] In response to the server running in a target task scenario, obtaining power consumption information of firmware of the server in the target task scenario, and a temperature difference between an inlet and an outlet of a case of the server in the target task scenario;

[0008] According to the power consumption information, the temperature difference between the inlet and the outlet of the case, and a heat dissipation efficiency coefficient of the server, determining a required air volume for heat dissipation of the server in the target task scenario; wherein the power consumption information is positively correlated with the required air volume for heat dissipation, and the temperature difference between the inlet and the outlet of the case is negatively correlated with the required air volume for heat dissipation;

[0009] According to the required air volume for heat dissipation, determining a rotating speed parameter of the fan of the server;

[0010] According to the rotating speed parameter of the fan, controlling the rotating speed of the fan in the target task scenario.

[0011] The present application also provides a server fan rotating speed control device, comprising:

[0012] An obtaining module, configured to, in response to the server running in a target task scenario, obtain power consumption information of firmware of the server in the target task scenario, and a temperature difference between an inlet and an outlet of a case of the server in the target task scenario;

[0013] The first determining module is configured to determine the required air volume for heat dissipation of the server in the target task scenario according to the power consumption information, the temperature difference between the air inlet and the air outlet of the case, and the heat dissipation efficiency coefficient of the server, wherein the power consumption information is positively correlated with the required air volume for heat dissipation, and the temperature difference between the air inlet and the air outlet of the case is negatively correlated with the required air volume for heat dissipation.

[0014] The second determining module is configured to determine the rotation speed parameter of the fan of the server according to the required air volume for heat dissipation.

[0015] The control module is configured to control the rotation speed of the fan in the target task scenario according to the rotation speed parameter of the fan.

[0016] 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 any of the server fan rotation speed control methods.

[0017] The application further provides a computer readable storage medium, and the computer readable storage medium stores a computer program, wherein the computer program is executed by a processor to implement the steps of any of the server fan rotation speed control methods.

[0018] The application further provides a computer program product, including a computer program, and the computer program is executed by a processor to implement the steps of any of the server fan rotation speed control methods.

[0019] According to the application, in response to the server running in a target task scenario, the power consumption information of the firmware of the server in the target task scenario and the temperature difference between the air inlet and the air outlet of the case of the server in the target task scenario are obtained, the required air volume for heat dissipation in the target task scenario is calculated according to the power consumption information of the firmware of the server, the temperature difference between the air inlet and the air outlet of the case, and the heat dissipation efficiency coefficient, and then the rotation speed of the fan is determined according to the required air volume for heat dissipation. Thus, a quantitative calculation method of the rotation speed of the fan is provided. Compared with the method in the related art in which the rotation speed of the fan depends on the experience of an operation and maintenance personnel, the reasonable rotation speed parameter of the fan can be accurately determined, so that the rotation speed control of the fan is performed through the rotation speed parameter in the corresponding target task scenario. The problem of insufficient heat dissipation or increased power consumption caused by unreasonable setting of the rotation speed of the fan is solved, the heat dissipation effect of the server is ensured, and the power consumption of the fan is saved. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the application, the drawings needed in the embodiments will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0021] Figure 1 A flowchart of a server fan speed control method provided for Embodiment One of the present application is shown in FIG. 1.

[0022] Figure 2 A flowchart of a server fan speed control method provided for Embodiment Two of the present application is shown in FIG. 2.

[0023] Figure 3 A flowchart of information extraction provided for the embodiments of the present application is shown in FIG. 3.

[0024] Figure 4 A flowchart of fan speed determination in a basic power consumption scenario provided for the embodiments of the present application is shown in FIG. 4.

[0025] Figure 5 A flowchart of a server fan speed control method provided for Embodiment Three of the present application is shown in FIG. 5.

[0026] Figure 6 A flowchart of fan speed determination in a preset task scenario provided for the embodiments of the present application is shown in FIG. 6.

[0027] Figure 7 A structural diagram of a server fan speed control device provided for the embodiments of the present application is shown in FIG. 7. DETAILED DESCRIPTION

[0028] 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, but not all the embodiments of the present application. Based on the embodiments in the present application, any other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.

[0029] It should be noted that, in the description of the present application, the terms “comprise”, “contain” or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not explicitly listed or 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.

[0030] In order for 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 drawings and specific embodiments.

[0031] The embodiments of the present application provide a server fan speed control method. The method is described in detail in combination with the execution flow of the server fan speed control method.

[0032] Figure 1 A flowchart of a server fan speed control method is provided for an embodiment of the present application. The method can be executed by a server fan speed control device provided by an embodiment of the present application. The device can be implemented in software and / or hardware, and can be integrated in an electronic device.

[0033] As shown in Figure 1 The server fan speed control method includes the following steps:

[0034] In step 101, in response to the server running in a target task scenario, the power consumption information of the firmware of the server in the target task scenario is obtained, and the temperature difference between the air outlet and the air inlet of the server in the target task scenario is obtained.

[0035] In this embodiment, a plurality of task scenarios are pre-divided, and the target task scenario is any one of the plurality of task scenarios. The plurality of task scenarios include but are not limited to an upgrade task scenario, a computing task scenario, and a basic power consumption scenario. The firmware of the server includes hardware that generates power consumption when running, such as a processor, a memory, a power supply, etc. The processor includes a central processing unit (CPU).

[0036] In this embodiment, the power consumption information of each firmware in the target task scenario is obtained, and the temperature sensor is used to collect data of the server to obtain the outlet temperature and the inlet temperature of the server in the target task scenario, and then the temperature difference between the outlet temperature and the inlet temperature is used to determine the temperature difference between the air inlet and the air outlet of the cabinet.

[0037] In an embodiment of the present application, for different target task scenarios, the power consumption information of the firmware in the target task scenario can be obtained in a corresponding manner. The power consumption information of the firmware of the server in the target task scenario is obtained, including: in the case that the target task scenario is a preset task scenario, the power consumption information of the firmware is collected by a detector, and in the case that the target task scenario is a basic power consumption scenario, the power consumption information of the firmware is obtained by a hardware management protocol. The preset task can be determined according to the total power consumption of the server, for example, a task with a total power consumption greater than a preset power threshold when executing the task is determined as a preset task. Optionally, the preset task includes an upgrade task, a computing task, etc., and the preset task scenario includes an upgrade task scenario and a computing task scenario. In the case that the server runs in the preset task scenario, the real-time power consumption information of the firmware is collected by the detector. The basic power consumption scenario includes a scenario such as initial management of the server. The firmware information is obtained by the hardware management protocol, the power consumption information of the firmware is obtained from the firmware information by a text processing method, and then the power consumption information is used as the power consumption information of the firmware in the basic power consumption scenario.

[0038] At step 102, the required air volume for heat dissipation of the server in the target task scenario is determined according to the power consumption information, the temperature difference between the inlet and outlet of the case, and the heat dissipation efficiency coefficient of the server.

[0039] In this embodiment, the calculation formula of the required air volume for heat dissipation is constructed based on a thermodynamic model, and the required air volume for heat dissipation of the server in the target task scenario is calculated according to the power consumption information, the temperature difference between the inlet and outlet of the case, the heat dissipation efficiency coefficient of the server, and the calculation formula. The power consumption information is positively correlated with the required air volume for heat dissipation, the temperature difference between the inlet and outlet of the case is negatively correlated with the required air volume for heat dissipation, and the heat dissipation efficiency coefficient of the server is a parameter related to the server and used to represent the heat dissipation efficiency of the server.

[0040] As an example, the calculation formula of the required air volume for heat dissipation is as follows:

[0041] ;

[0042] Wherein, FR1 is the required air volume for heat dissipation, Ptotal is the total power consumption information of the server, the total power consumption information can be determined according to the power consumption information of each firmware, C is the heat dissipation efficiency coefficient, the heat dissipation efficiency coefficients of different servers may be different, for example, the C value of the server is 0.7, which means that the heat dissipation efficiency is 70%, p is the air density (fixed value is 1.2), C' is the air constant pressure heat fusion ratio (fixed value is 1005), is the temperature difference between the inlet and outlet of the case, the temperature difference between the inlet and outlet of the case is derived from the data collected by the temperature sensor, which is obtained by subtracting the inlet temperature from the outlet temperature. Optionally, the temperature difference between the inlet and outlet of the case is usually set to 20 when the server is initially put into the case.

[0043] At step 103, the rotation speed parameter of the fan of the server is determined according to the required air volume for heat dissipation.

[0044] In this embodiment, the rotation speed parameter of each fan is determined according to the required air volume for heat dissipation and the number of fans of the server. Optionally, the to-be-provided air volume of at least one fan is determined according to the required air volume for heat dissipation and the number of fans, and then the rotation speed parameter of at least one fan is determined according to the to-be-provided air volume of at least one fan, the maximum air volume coefficient, and the fan air volume information.

[0045] As an example, the calculation formula of the to-be-provided air volume is as follows:

[0046] ;

[0047] Wherein, FR1 is the required air volume for heat dissipation, FR2 is the to-be-provided air volume of each fan. N is the number of available fans, which can be determined according to the state information in the fan firmware information, for example, the fan with the health information field content of "normal" in the state information as the available fan.

[0048] The calculation formula of the rotation speed parameter is as follows:

[0049]

[0050] wherein S is the rotation speed parameter, for example, in the form of rotation speed percentage, K is the maximum air volume coefficient, representing the maximum air volume coefficient provided by a single fan when the rotation speed percentage is 100%, the maximum air volume coefficient is related to the fan model, for example, the maximum air volume coefficient is 0.00033 according to the fan model in the fan firmware information and obtained from the corresponding firmware document, n is the fan air volume information, the fan air volume information is determined according to the fan manufacturer document, and the value range is [2, 3], for example, the fan air volume information is 2.8.

[0051] In an embodiment of the present application, the rotation speed parameter of the at least one fan is determined according to the air volume to be provided by the at least one fan, the maximum air volume coefficient and the fan air volume information, comprising: for any fan, determining the candidate rotation speed parameter of the fan according to the air volume to be provided, the maximum air volume coefficient and the fan air volume information, correcting the candidate rotation speed parameter according to the safety margin coefficient to obtain the corrected rotation speed parameter, and determining the rotation speed parameter of the fan according to the corrected rotation speed parameter and the rotation speed configuration constraint condition.

[0052] wherein the candidate rotation speed parameter can be determined according to the calculation formula of the rotation speed parameter in the above example, the safety margin coefficient is used to provide additional rotation speed redundancy, and the rotation speed configuration constraint condition is used to constrain the specific value, parameter form, etc. of the rotation speed parameter.

[0053] As an example, the calculation formula for determining the rotation speed parameter of the fan according to the candidate rotation speed parameter is as follows: S1= min(100, max(S0×(1+α), 10)). Wherein α is the safety margin coefficient, for example, the safety margin coefficient is 0.08, S0 is the candidate rotation speed parameter, and S1 is the rotation speed parameter of the fan. According to the rotation speed configuration constraint condition, the rotation speed parameter is in the form of rotation speed percentage, the rotation speed parameter set by the server BMC (Baseboard Management Controller, baseboard management controller) is between 10% and 100% and is an integer multiple of 10%, and the output value calculated by the above formula is the minimum value between 10 and 100 and meets the corrected rotation speed parameter and the rotation speed configuration constraint condition. In this example, the candidate rotation speed parameter is corrected by setting the safety margin coefficient, which can provide a certain safety margin and reduce the risk of equipment damage caused by insufficient heat dissipation, further improving the accuracy of fan rotation speed control.

[0054] Step 104, controlling the rotation speed of the fan under the target task scene according to the rotation speed parameter of the fan.

[0055] ​In the embodiment, after determining the rotation speed parameter of each fan of the server, the rotation speed of each fan is controlled according to the rotation speed parameter, so as to realize the heat dissipation control of the server in the target task scenario.

[0056] As an example, in response to the server running in the target task scenario, the power consumption information and the temperature difference between the inlet and outlet of the case are obtained at each time in a plurality of times, and the rotation speed parameter at each time is determined by calculation, and then the fan is controlled according to the rotation speed parameter of the fan at each time. Wherein, the plurality of times are determined according to a preset time interval, that is, the rotation speed parameter is determined once every preset time interval, and the rotation speed of the fan is controlled based on the rotation speed parameter.

[0057] The server fan rotation speed control method of the embodiment of the application, in response to the server running in the target task scenario, obtains the power consumption information of the firmware of the server in the target task scenario, and the temperature difference between the inlet and outlet of the case of the server in the target task scenario, calculates the required air volume for heat dissipation in the target task scenario according to the power consumption information of the firmware of the server, the temperature difference between the inlet and outlet of the case and the heat dissipation efficiency coefficient, and then determines the rotation speed of the fan according to the required air volume for heat dissipation, thereby providing a way to quantitatively calculate the rotation speed of the fan. Compared with the way of setting the rotation speed of the fan depending on the experience of the operation and maintenance personnel in the related art, the reasonable rotation speed parameter of the fan can be accurately determined, so as to control the rotation speed of the fan through the rotation speed parameter in the corresponding target task scenario, solve the problem of insufficient heat dissipation or increased power consumption caused by unreasonable setting of the rotation speed of the fan by human, and ensure the heat dissipation effect of the server while saving the power consumption of the fan.

[0058] In an optional embodiment of the application, as shown in Figure 2 The server fan rotation speed control method can include the following steps:

[0059] Step 201, in response to the server running in the basic power consumption scenario, obtaining the power consumption information of the firmware through the hardware management protocol, and obtaining the temperature difference between the inlet and outlet of the case of the server.

[0060] In this embodiment, the basic power consumption scenario includes a scenario in which the server does not perform a preset task, and the preset task includes an upgrade task, a computing task, etc. For example, the basic power consumption scenario includes a scenario in which the server is initially managed, etc. The hardware management protocol is, for example, a Redfish protocol. Core data information such as server corresponding firmware information and server information is obtained through the Redfish protocol and according to corresponding interface analysis. Information extraction is performed on the firmware information and the server information according to a rule engine, and power consumption information of each firmware, firmware features, device features of the server, etc. are obtained. The firmware features include, but are not limited to, model, manufacturer, and other specification information. The device features of the server include, but are not limited to, model, manufacturer, and other specification information, as well as BMC version and other basic information. In the process of management software operation and maintenance, real-time sensor collection information is obtained through the Redfish protocol by using the corresponding sensors of the server, so as to filter out the information required for fan speed calculation.

[0061] The power consumption information of the firmware is described below.

[0062] In an embodiment of the present application, the power consumption information of the firmware is obtained through the hardware management protocol, including: performing accurate matching in the firmware information of the server according to a preset firmware power consumption field, to determine the power consumption information matched with the preset firmware power consumption field, and then, if the power consumption information matched with the preset firmware power consumption field is not matched, performing regular matching in the firmware information through a regular matching keyword rule, to determine the power consumption information of the firmware.

[0063] In this embodiment, due to the difference in the information fields returned by the Redfish protocol of different manufacturers, the rule engine is required to improve the completeness of information analysis. The rule engine includes an accurate analysis engine and a regular matching analysis engine. The accurate analysis engine is used to perform accurate matching through a preset firmware power consumption field. When a field consistent with the preset firmware power consumption field is matched, the power consumption information matched with the preset firmware power consumption field is determined. The regular matching analysis engine is provided with a regular matching keyword rule. The regular matching keyword rule is used to perform regular matching on diversified information. The regular matching keyword rule can be set for power consumption information, firmware features, device features of the server, etc.

[0064] As an example, the firmware includes a CPU. For the firmware information of the CPU, the preset firmware power consumption field includes TdpWatts (thermal design power consumption watts). The TdpWatts field is accurately matched in the firmware information of the CPU through the accurate analysis engine. The content of the TdpWatts field is used as the basic power consumption of the CPU, so as to determine the power consumption information of the CPU.

[0065] Optionally, the rule engine further comprises a data formatting engine, which is configured to parse the numerical information in the core data information such as the firmware information, and perform standardized processing on the numerical information according to a preset data format. For example, after the power consumption information of the firmware is determined by the accurate parsing engine and the regular matching parsing engine, the numerical information in the power consumption information is parsed, and the numerical information is standardized processed according to the preset data format.

[0066] As an example, for the CPU basic power consumption in the firmware information, the content returned by different manufacturers' BMCs is different, for example, the A manufacturer returns "300W", and the B manufacturer returns "300". The engine removes the calculation symbol and processes it uniformly as "300".

[0067] Therefore, by comprehensively performing information extraction by the accurate parsing engine, the regular matching parsing engine and the data formatting engine, the power consumption information of the firmware can be accurately obtained, the extracted information can be filled into the firmware information template and stored in the firmware information library, data support is provided for subsequent fan speed calculation, and then used for fan speed parameter calculation in the basic power consumption scene, thereby improving the accuracy of fan speed control.

[0068] The case inlet and outlet air temperature difference of the server is described below.

[0069] In an embodiment of the present application, the case inlet and outlet air temperature difference of the server in the target task scene is obtained by the following steps: data of the server is collected by a sensor to obtain sensor collection information, then, regular matching is performed on the sensor collection information by a regular matching keyword rule to determine the inlet air temperature and the outlet air temperature of the server, and the case inlet and outlet air temperature difference is determined according to the inlet air temperature and the outlet air temperature of the server.

[0070] In this embodiment, the rule engine comprises a regular matching parsing engine. The regular matching parsing engine is provided with a regular matching keyword rule, which is used to perform regular matching on diversified information, and the regular matching keyword rule can be set for sensor collection information and the like.

[0071] As an example, the sensor comprises a temperature sensor, the real-time inlet air temperature and outlet air temperature of the server are collected by the temperature sensor to obtain sensor collection information, then, after the sensor collection information is obtained by the Redfish protocol, the sensor names in different situations are diversified, for example, the standard return of the temperature index is Inlet_Temp (temperature collection), and the content returned by different models of BMCs is different, therefore, the inlet air temperature and the outlet air temperature can be determined from the sensor collection information by the regular matching keyword rule, and the case inlet and outlet air temperature difference is determined by the difference between the outlet air temperature and the inlet air temperature.

[0072] Optionally, the rule engine further comprises a data formatting engine, which is configured to parse the numerical information in the core data information such as the sensor collection information, and perform standardization processing on the numerical information according to a preset data format. For example, the numerical information in the Reading information in the sensor collection information returned by the sensor interface can be standardized processed by the data formatting engine.

[0073] It should be noted that the implementation manner of processing by the accurate parsing engine, the regular matching parsing engine and the data formatting engine in the rule engine is an example. For different application scenarios, after obtaining the core data information through the Redfish protocol, the above rule combination processing can be performed, which is not limited specifically herein.

[0074] The information extraction process will be described below in combination with actual application scenarios.

[0075] In an embodiment of the present application, the information extraction involves CPU, memory, power supply, fan, server and sensor, and the information is obtained according to the Redfish request for the interface of CPU, memory, power supply, fan and sensor, and the server information can be obtained according to the mainboard information after the management software covers the corresponding server. For example, the information returned is the corresponding json format information, and the return content for CPU includes CPU model, CPU manufacturer, basic power consumption, total core number, basic frequency and maximum frequency, the content of CPU model is "model": "CPU model one", the content of CPU manufacturer is "manufacturer": "CPU manufacturer two", the content of basic power consumption is "heat dissipation design power watt": "300", the content of total core number is "total core number": 8, the content of basic frequency is "frequency": 2200 | 2.2GHz, and the content of maximum frequency is "maximum frequency megahertz": 3400. The return content for memory includes memory model, memory manufacturer, memory type, basic frequency and memory capacity, the content of memory model is "model": "memory model three", the content of memory manufacturer is "manufacturer": "memory manufacturer four", the content of memory type is "storage device type": "memory type five", the content of basic frequency is "frequency megahertz": 3200, and the content of memory capacity is "capacity": 32768MB | 64G. The return content for power supply includes power supply model, power supply manufacturer, temperature, maximum power and power supply state, the content of power supply model is "model": "power supply model six", the content of power supply manufacturer is "manufacturer": "power supply manufacturer seven", the content of temperature is "temperature": 35 | 35°C, the content of maximum power is "power capacity watt": 2000, and the content of power supply state is "health information": normal | warning | abnormal. The return content for fan includes fan model, fan manufacturer, maximum speed and fan state, the content of fan model is "model": "fan model eight", the content of fan manufacturer is "manufacturer": "fan manufacturer nine", and the content of fan state is "health information": normal | warning | abnormal. The return content for sensor includes sensor name, sensor unit (temperature | power consumption), sensor value and sensor state, the content of sensor name is "name": "temperature collection" | "power consumption collection", the content of sensor unit (temperature | power consumption) is "reading unit": "deg_c" | "watts", the content of sensor value is "reading value": 35 | 2000W, and the content of sensor state is "health information": normal | warning | abnormal. The information extraction process is shown in, for example, Figure 3

[0076] ​In step 202, the server cooling required air volume in the basic power consumption scenario is determined according to the power consumption information, the temperature difference between the inlet and outlet of the case, and the server cooling efficiency coefficient.

[0077] In step 203, the rotation speed parameter of the server fan is determined according to the server cooling required air volume.

[0078] In this embodiment, the firmware includes CPU, memory, and power supply. In the basic power consumption scenario, the power consumption information of the firmware is obtained through information extraction. Then, the total power consumption information of the server is determined according to the power consumption information of the CPU, the power consumption information of the memory, and the power consumption information of the power supply. The server cooling required air volume in the basic power consumption scenario is determined according to the total power consumption information, the temperature difference between the inlet and outlet of the case, and the server cooling efficiency coefficient.

[0079] In one embodiment of the present application, the server cooling required air volume in the target task scenario is determined according to the power consumption information, the temperature difference between the inlet and outlet of the case, and the server cooling efficiency coefficient, including: summing the power consumption information of the CPU, the power consumption information of the memory, the power consumption information of the power supply, and the preset power consumption offset to obtain the total power consumption information. Then, the server cooling required air volume in the target task scenario is determined according to the total power consumption information, the temperature difference between the inlet and outlet of the case, and the server cooling efficiency coefficient.

[0080] In this embodiment, the preset power consumption offset is used to represent the power consumption information of other firmware except the CPU, the memory, and the power supply, such as the graphics processing unit (GPU), the hard disk, and the PCIE (Peripheral Component Interconnect Express) device. Optionally, the preset power consumption offset is set to 30W.

[0081] The power consumption information of the firmware is determined according to the basic power consumption and / or information related to power consumption calculation.

[0082] As an example, for the basic power consumption scenario, the power consumption information of the CPU is determined according to the basic power consumption, the basic frequency, the maximum frequency, and the core number. The power consumption information of the memory is determined according to the memory capacity and the memory working frequency of the memory. The power consumption information of the power supply is determined according to the basic power consumption of the power supply. In this example, the power consumption information of the power supply is the basic power consumption of the power supply. The calculation formula of the power consumption information of the CPU and the memory is as follows:

[0083] ;

[0084] Wherein, is the power consumption information of the CPU, is the basic power consumption of the CPU, is a base frequency, such as 3Ghz, is a maximum frequency, such as 4Ghz, is a CPU core number.

[0085] ;

[0086] wherein, is power consumption information of the memory, is a memory capacity, such as 16GB, is a memory working frequency, such as 3200Mhz.

[0087] As an example, when the management software initially manages the server, the specific firmware information is calculated as follows:

[0088] ;

[0089] ;

[0090] .

[0091] In this example, the air volume required for heat dissipation is calculated according to the total power consumption information 970W:

[0092] ;

[0093] The air volume to be provided by the fan is calculated according to the air volume required for heat dissipation:

[0094] ;

[0095] The candidate rotation speed parameter of the fan is calculated according to the air volume to be provided by the fan:

[0096] ;

[0097] The rotation speed parameter of the fan is determined according to the candidate rotation speed parameter:

[0098] ;

[0099] wherein, the corrected rotation speed parameter is 7.452%, and according to the rotation speed configuration constraint condition, the rotation speed parameter of the fan is finally obtained as 10%. Optionally, the device features of the server, the firmware features of the firmware, the base power consumption scene, and the rotation speed parameter of the fan are template processed to be stored in a fan rotation speed template library. The fan rotation speed determination process of the above base power consumption scene is shown in, for example, Figure 4 .

[0100] Step 204, according to the rotation speed parameter of the fan, control the rotation speed of the fan under the base power consumption scene.

[0101] The server fan rotating speed control method of the embodiment of the application obtains firmware information through protocol analysis, accurately obtains power consumption information from the firmware information through a plurality of matching rules, so that the reasonable fan rotating speed can be accurately determined in the basic power consumption scene such as the initial management of the server, the application scene is expanded, and the universality is improved.

[0102] In an optional embodiment of the application, as shown in Figure 5 The server fan rotating speed control method can include the following steps on the basis of the foregoing embodiment.

[0103] In step 501, the power consumption information of the firmware is collected by a detector in response to the server running in a preset task scene, and the temperature difference between the inlet and outlet of the case of the server is obtained.

[0104] In the embodiment, the server usually performs different types of tasks in the server management software operation process, wherein the preset tasks include upgrade tasks, computing tasks, and the like, and the computing task is, for example, a task with a scale greater than a preset scale threshold. In the preset task scene, the real-time power consumption information of the firmware is collected by a detector, and the detector can be, for example, a device capable of detecting power consumption.

[0105] As an example, the preset tasks include BMC upgrade tasks, large-scale computing tasks, and the like, and the power consumption information in the preset task scene is different from that in the basic power consumption scene. The management software obtains the sensor collection information at regular intervals, filters out the target sensor with a unit of Watts and a state of "normal", obtains the collection data corresponding to the target sensor, and obtains the total power consumption information of the server. The total power consumption information can be obtained by summing the power consumption information of each firmware, wherein the power consumption information of the firmware includes the power consumption information of the CPU, the memory, and the power supply, and the power consumption information of other firmware except the CPU, the memory, and the power supply.

[0106] In step 502, the required air volume for heat dissipation of the server in the preset task scene is determined according to the power consumption information, the temperature difference between the inlet and outlet of the case, and the heat dissipation efficiency coefficient of the server.

[0107] In step 503, the rotating speed parameter of the fan of the server is determined according to the required air volume for heat dissipation.

[0108] In step 504, the rotating speed of the fan in the preset task scene is controlled according to the rotating speed parameter of the fan.

[0109] In step 505, a fan rotating speed template library is established.

[0110] In an embodiment of the present application, after determining the rotation speed parameter of the fan of the server, the device feature of the server and the firmware feature of the firmware are acquired. Then, the target task scenario, the device feature of the server, the firmware feature of the firmware and the rotation speed parameter of the fan of the server are template processed and stored into the fan rotation speed template library. For example, refer to Figure 6

[0111] The device feature of the server includes but is not limited to model and manufacturer, and the firmware feature includes but is not limited to model and manufacturer.

[0112] As an example, taking the BMC upgrade task of a certain server as an example, the total power consumption information in the task process is 2000W, and the reasonable fan rotation speed is calculated to be 30%. The BMC upgrade task scenario, the device feature and the firmware feature of the server are template processed and stored into the fan rotation speed template library.

[0113] Optionally, in a preset task scenario, the server performs a preset task within a task duration, and based on the task duration, a plurality of time points within the task duration are determined, and the steps of acquiring the power consumption information of the firmware, acquiring the temperature difference between the inlet and outlet of the case of the server and determining the rotation speed parameter are performed at the plurality of time points to obtain a plurality of rotation speed parameters corresponding to the plurality of time points respectively. Then, the maximum rotation speed parameter is determined from the plurality of rotation speed parameters, and the target task scenario, the device feature of the server, the firmware feature of the firmware and the maximum rotation speed parameter are template processed to generate a target fan rotation speed template, and the target fan rotation speed template is stored into the fan rotation speed template library. Thus, for the case that part of the task scenarios are continuous scenarios, the fan rotation speed is also adjusted during the task duration, and the maximum fan rotation speed in this process is template processed and stored to further improve the accuracy of the fan rotation speed control.

[0114] As an example, the fan rotation speed template library is as follows:

[0115]

[0116] In an embodiment of the present application, in response to the server running in a target task scenario, the fan rotation speed template library can be queried first. Optionally, the fan rotation speed template library is queried according to the target task scenario, the device feature of the server and the firmware feature of the firmware to determine the corresponding target rotation speed parameter. Then, if the target rotation speed parameter suitable for the current server and the target task scenario exists in the fan rotation speed template library, the fan rotation speed in the target task scenario is controlled according to the target rotation speed parameter.

[0117] ​Therefore, for different task scenarios, templates can be established according to feature information and the calculated fan speed, and then in the case of facing the same feature information and task scenario, if the target speed parameter suitable for the current server and the target task scenario exists in the fan speed template library, the target speed parameter is directly used for fan speed control, without the need to perform the steps of obtaining power consumption information, temperature difference between the inlet and outlet of the case, and determining the required air volume for heat dissipation, thereby reducing the amount of calculation and improving processing efficiency. In addition, the fan speed template library can be reused, and after establishing multiple templates, it can be applied to multiple servers and multiple task scenarios, meeting the heat dissipation needs of different servers and task scenarios.

[0118] In an embodiment of the present application, before the server runs in the target task scenario, the method further comprises: setting a timing detection task to poll the task information to be executed by the server through the timing detection task, and determining the target task scenario according to the task information to be executed by the server.

[0119] In the embodiment, the early warning strategy is implemented through the timing detection task. The timing detection task is used to detect the task information to be executed by the server in a timing manner. The task information to be executed includes task name, task type, task state, and task estimated duration, etc. The interval of the timing detection task can be set according to actual application needs.

[0120] As an example, the server is obtained through the Redfish task service interface in a timing manner. The task information obtained includes task name "name": "BMC upgrade", task type "type": "BMC upgrade" | "stress test", task state "task state": "ready", and task estimated duration (minutes) "task duration": 30. In this example, the fan speed adjustment is triggered dynamically through the timing task. The target task scenario is determined according to the obtained task information. For example, no task information is detected by the last timing detection task, and the task information of the upgrade task is detected by the current timing detection task. Then, the fan speed template library is queried according to the upgrade task scenario, the device characteristics of the server, and the firmware characteristics of the firmware. If the corresponding target speed parameter is queried, the fan is controlled according to the target speed parameter. If the target speed parameter is not queried, the speed parameter of the fan is determined according to the flow of determining the fan speed based on the preset task scenario, and the fan is controlled according to the speed parameter and the template processing.

[0121] Therefore, the upcoming task is predicted through the timing detection task, the task type is accurately identified, and the steps of automatically performing fan speed determination and speed control are performed, the whole process does not need manual intervention, an automatic solution strategy is realized, and the server reliability is improved.

[0122] In an embodiment of the present application, after obtaining the task information to be executed by the server through the timing detection task, when the fan speed template library is queried according to the target task scene, the device characteristics of the server, and the firmware characteristics of the firmware, the corresponding target speed parameter can also be determined through the similarity between the template. Optionally, the running characteristics of the server and / or the firmware are obtained, the similarity between the target task scene and each first task scene in the template is determined according to the running characteristics, the second task scene with a similarity greater than a preset similarity threshold is determined from the first task scene, and then, if the device characteristics of the server and the firmware characteristics of the firmware in the template of the second task scene match the current server, the speed parameter in the template of the second task scene is determined as the target speed parameter, and then the target speed parameter is controlled. The running characteristics include, for example, resource occupancy rate. Therefore, when the server faces a new task, the template suitable for the target task scene can be determined according to the similarity between the task scene in the existing template and the target task scene, which ensures the accuracy of the speed parameter and can accurately and quickly control the fan speed, reducing the risk caused by insufficient or lagging heat dissipation.

[0123] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software and the necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment.

[0124] Embodiments of the present application also provide a server fan speed control device. Figure 7 A structural schematic diagram of a server fan speed control device provided by an embodiment of the present application is shown in Figure 7 As shown in the figure, the server fan speed control device 70 includes an acquisition module 71, a first determination module 72, a second determination module 73, and a control module 74.

[0125] The acquisition module 71 is configured to, in response to the server running in a target task scene, acquire power consumption information of a firmware of the server in the target task scene and a temperature difference between an air inlet and an air outlet of a case of the server in the target task scene.

[0126] The first determining module 72 is configured to determine the required air volume for heat dissipation of the server in the target task scenario according to the power consumption information, the temperature difference between the air inlet and the air outlet of the case, and the heat dissipation efficiency coefficient of the server, wherein the power consumption information is positively correlated with the required air volume for heat dissipation, and the temperature difference between the air inlet and the air outlet of the case is negatively correlated with the required air volume for heat dissipation.

[0127] The second determining module 73 is configured to determine the rotation speed parameter of the fan of the server according to the required air volume for heat dissipation.

[0128] The control module 74 is configured to control the rotation speed of the fan in the target task scenario according to the rotation speed parameter of the fan.

[0129] Optionally, the acquisition module 71 is specifically configured to:

[0130] In a case where the target task scenario is a preset task scenario, the power consumption information of the firmware is acquired by the detector; the preset task scenario includes an upgrade task scenario and a computing task scenario.

[0131] In a case where the target task scenario is a basic power consumption scenario, the power consumption information of the firmware is acquired by the hardware management protocol.

[0132] Optionally, the acquisition module 71 is specifically configured to:

[0133] The power consumption information matched with the preset firmware power consumption field is determined by accurately matching the preset firmware power consumption field in the firmware information of the server;

[0134] If the power consumption information matched with the preset firmware power consumption field is not matched, the power consumption information of the firmware is determined by performing regular matching in the firmware information according to a regular matching keyword rule;

[0135] The numerical information in the power consumption information of the firmware is analyzed, and the numerical information is standardized according to a preset data format.

[0136] Optionally, the acquisition module 71 is specifically configured to:

[0137] The server is data-acquired by the sensor to acquire sensor-acquired information;

[0138] The air inlet temperature and the air outlet temperature of the server are determined by performing regular matching in the sensor-acquired information according to a regular matching keyword rule;

[0139] The temperature difference between the air inlet and the air outlet of the case is determined according to the air inlet temperature and the air outlet temperature of the server.

[0140] Optionally, the second determining module 73 is specifically configured to:

[0141] The required air volume of at least one fan is determined according to the required air volume for heat dissipation and the number of fans.

[0142] According to the to-be-provided air volume, the maximum air volume coefficient, and the fan air volume information of at least one fan, a rotation speed parameter of the at least one fan is determined.

[0143] Optionally, the second determination module 73 is specifically configured to:

[0144] For any fan, according to the to-be-provided air volume, the maximum air volume coefficient, and the fan air volume information, a candidate rotation speed parameter of the fan is determined;

[0145] The candidate rotation speed parameter is corrected according to the safety margin coefficient to obtain a corrected rotation speed parameter;

[0146] According to the corrected rotation speed parameter and a rotation speed configuration constraint condition of the fan, a rotation speed parameter of the fan is determined.

[0147] Optionally, the apparatus further includes:

[0148] The storage module is configured to acquire a device feature of the server and a firmware feature of the firmware, and perform template processing on a target task scenario, the device feature of the server, the firmware feature of the firmware, and a rotation speed parameter of a fan of the server, to store into a fan rotation speed template library;

[0149] The query module is configured to query the fan rotation speed template library according to the target task scenario, the device feature of the server, and the firmware feature of the firmware, to determine a corresponding target rotation speed parameter, and control the rotation speed of the fan in the target task scenario according to the target rotation speed parameter.

[0150] Optionally, the apparatus further includes:

[0151] The detection module is configured to set a timing detection task to acquire task information to be executed by the server through the timing detection task polling;

[0152] The target task scenario is determined according to the task information to be executed by the server.

[0153] Optionally, the firmware includes a processor, a memory, and a power supply, and the acquisition module 71 is specifically configured to:

[0154] The power consumption information of the processor is determined according to a basic power consumption of the processor, a basic frequency of the processor, a maximum frequency of the processor, and a core number of the processor;

[0155] The power consumption information of the memory is determined according to a memory capacity of the memory and a memory working frequency of the memory;

[0156] The power consumption information of the power supply is determined according to a basic power consumption of the power supply;

[0157] The first determination module 72 is specifically configured to:

[0158] Sum the power consumption information of the processor, the power consumption information of the memory, the power consumption information of the power supply and the preset power consumption offset to obtain total power consumption information;

[0159] Determine the required air volume for heat dissipation of the server in the target task scenario according to the total power consumption information, the temperature difference between the air inlet and the air outlet of the case and the heat dissipation efficiency coefficient of the server.

[0160] The description of the features in the embodiment of the server fan speed control device can be referred to the related description of the embodiment of the server fan speed control method, which will not be repeated here.

[0161] Embodiments of the present application also provide an electronic device, comprising a memory and a processor, the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any of the above server fan speed control method embodiments.

[0162] Embodiments of the present application also provide a computer readable storage medium, which stores a computer program, wherein the computer program is configured to perform the steps in any of the above server fan speed control method embodiments when running.

[0163] In an example embodiment, the above computer readable storage medium can include, but is not limited to, a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store computer programs.

[0164] Embodiments of the present application also provide a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps in any of the above server fan speed control method embodiments.

[0165] Embodiments of the present application also provide another computer program product, which comprises a non-volatile computer readable storage medium, and the non-volatile computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps in any of the above server fan speed control method embodiments.

[0166] 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.

[0167] The server fan speed control method, the electronic device, the storage medium and the program product provided by the application are described in detail above. The principles and implementation manners of the application are described by applying specific examples in the present disclosure. The above description of the embodiments is only applicable to help understand the method of the application and its core idea. It should be pointed out that, for those skilled in the art, without departing from the principles of the application, some improvements and modifications can be made to the application. These improvements and modifications also fall within the protection scope of the claims of the application.

Claims

1. A method for controlling the fan speed of a server, characterized in that, The method includes: In response to the server running in the target task scenario, the power consumption information of the server firmware under the target task scenario and the temperature difference between the server chassis inlet and outlet under the target task scenario are obtained. Based on the power consumption information, the temperature difference between the inlet and outlet of the chassis, and the heat dissipation efficiency coefficient of the server, the required airflow for heat dissipation of the server under the target task scenario is determined; wherein, the power consumption information is positively correlated with the required airflow for heat dissipation, and the temperature difference between the inlet and outlet of the chassis is negatively correlated with the required airflow for heat dissipation. Based on the required airflow for heat dissipation, determine the fan speed parameters of the server; Based on the fan's rotational speed parameters, control the fan's rotational speed in the target task scenario; The step of determining the fan speed parameters of the server based on the required airflow for heat dissipation includes: Based on the required airflow for heat dissipation and the number of fans, determine the airflow to be provided by at least one of the fans; For any of the aforementioned fans, candidate speed parameters of the fan are determined based on the air volume to be provided by the fan, the maximum air volume coefficient, and the fan air volume information. The candidate speed parameters are corrected based on the safety margin coefficient to obtain the corrected speed parameters; The fan speed parameters are determined based on the corrected speed parameters and the fan speed configuration constraints.

2. The method as described in claim 1, characterized in that, The step of obtaining the power consumption information of the server firmware under the target task scenario includes: When the target task scenario is a preset task scenario, the power consumption information of the firmware is collected by a detector; the preset task scenario includes upgrade task scenario and computing task scenario; In the case of the target task scenario as the basic power consumption scenario, the power consumption information of the firmware is obtained through the hardware management protocol.

3. The method as described in claim 2, characterized in that, The step of obtaining the power consumption information of the firmware through the hardware management protocol includes: The firmware information of the server is precisely matched according to the preset firmware power consumption field to determine the power consumption information that matches the preset firmware power consumption field. If no power consumption information matching the preset firmware power consumption field is found, regular expression matching is performed in the firmware information using regular expression matching keyword rules to determine the power consumption information of the firmware. The numerical information in the power consumption information of the firmware is parsed, and the numerical information is standardized according to a preset data format.

4. The method as described in claim 3, characterized in that, The following steps are used to obtain the temperature difference between the server's chassis inlet and outlet air vents under the target task scenario: Data is collected from the server using sensors to obtain sensor-collected information; The inlet and outlet temperatures of the server are determined by performing regular expression matching on the sensor-collected information using the regular expression keyword rules. The temperature difference between the air inlet and outlet of the chassis is determined based on the air inlet and outlet temperatures of the server.

5. The method as described in claim 1, characterized in that, After determining the fan speed parameters of the server, the method further includes: Obtain the device characteristics of the server and the firmware characteristics of the firmware; The target task scenario, the device characteristics of the server, the firmware characteristics of the firmware, and the fan speed parameters of the server are templated and stored in the fan speed template library. After responding to the server running in the target task scenario, the method further includes: Based on the target task scenario, the server's device characteristics, and the firmware characteristics, the fan speed template library is queried to determine the corresponding target speed parameters; The fan speed is controlled according to the target speed parameter in the target task scenario.

6. The method as described in claim 1, characterized in that, Before responding to the server running in the target task scenario, the method further includes: Set up a scheduled detection task to poll and obtain the task information to be executed on the server. The target task scenario is determined based on the task information to be executed by the server.

7. The method as described in claim 1, characterized in that, The firmware includes a processor, memory, and power supply. Obtaining the power consumption information of the server's firmware under the target task scenario includes: The power consumption information of the processor is determined based on the processor's base power consumption, base frequency, maximum frequency, and number of cores. The power consumption information of the memory is determined based on its memory capacity and operating frequency. Based on the power supply's base power consumption, determine the power consumption information of the power supply; The step of determining the required airflow for cooling the server under the target task scenario based on the power consumption information, the temperature difference between the chassis inlet and outlet, and the server's heat dissipation efficiency coefficient includes: The total power consumption information is obtained by summing the power consumption information of the processor, the power consumption information of the memory, the power supply, and a preset power consumption offset. Based on the total power consumption information, the temperature difference between the inlet and outlet of the chassis, and the heat dissipation efficiency coefficient of the server, the required airflow for heat dissipation of the server under the target task scenario is determined.

8. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the server fan speed control method as described in any one of claims 1 to 7 when executing the computer program.

Images