Control method and device for heat dissipation equipment on server and electronic equipment

Abstract

The embodiment of the invention provides a control method and device for heat dissipation equipment on a server and electronic equipment, the server comprises a server component, a first controller and the heat dissipation equipment, a first operating system and a second operating system are deployed on the first controller, and the method comprises the steps that the first controller starts to be started when the server is powered on; the first operation system starts to control the heat dissipation equipment to operate from the first time after the starting time of the first controller; the first operation system stops controlling the heat dissipation equipment to operate at a second time after the first time; and the second operation system starts to control the operation of the heat dissipation equipment from the second time. According to the method and the device, the problem that the timeliness of heat dissipation of the server in the powered-on state by the heat dissipation equipment is poor is solved, and the effect of the timeliness of heat dissipation of the server in the powered-on state by the heat dissipation equipment is further achieved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computers, and in particular, to a control method, device and electronic device for a heat dissipation device on a server. Background Art

[0002] The heat dissipation on the server has a crucial impact on the life of the server components and business operations. During use, the server may be in a state where it is powered on but not operating normally. However, in the current related technologies, no effective control strategy for the heat dissipation device has been proposed in this state, resulting in the heat generated by the server in this state cannot be processed in time, which may affect the normal operation of the server.

[0003] In the related art, there is no effective solution to the problem that the heat dissipation device is not timely enough to dissipate heat for the server in the powered-on state. Summary of the invention

[0004] The embodiments of the present application provide a control method, device and electronic device for a heat dissipation device on a server, so as to at least solve the problem in the related art that the heat dissipation device is not timely in dissipating heat for a server in a powered-on state.

[0005] According to an embodiment of the present application, a method for controlling a heat dissipation device on a server is provided, wherein the server comprises: a server component, a first controller and a heat dissipation device, a first operating system and a second operating system are deployed on the first controller, and the method comprises: the first controller starts to start when the server is powered on; the first operating system controls the operation of the heat dissipation device from a first time after the start time of the first controller, wherein the first time is the time when the first operating system completes the startup; the first operating system stops controlling the operation of the heat dissipation device at a second time after the first time, wherein the second time is the time when the second operating system completes the startup; and the second operating system controls the operation of the heat dissipation device from the second time.

[0006] In an exemplary embodiment, the controlling the heat dissipation device to run starting from a first time after the startup time of the first controller by the first operating system includes:

[0007] When the first operating system has been started and the server has not been started, the first operating system controls the operation of the heat dissipation device according to the server status of the server, the component status of the server component, the component temperature of the server component and the ambient temperature of the server;

[0008] The first operating system detects the system status of the second operating system.

[0009] In an exemplary embodiment, the first operating system stops controlling the operation of the heat dissipation device at a second time after the first time, including:

[0010] When it is detected that the system status is a status of having completed startup, and the server has not completed startup, the first operating system determines that the second time has arrived;

[0011] The first operating system stops controlling the operation of the heat dissipation device.

[0012] In an exemplary embodiment, the controlling the heat dissipation device to run starting from the second time by the second operating system includes:

[0013] After the second operating system is started, it starts to control the operation of the heat dissipation device according to the server status of the server, the component status of the server component, the component temperature of the server component and the ambient temperature of the server.

[0014] In an exemplary embodiment, controlling the operation of the heat dissipation device according to the server state of the server, the component state of the server component, the component temperature of the server component and the ambient temperature of the server includes:

[0015] detecting a server status of the server;

[0016] In a case where the server status is used to indicate that the server has been powered on but not turned on, controlling the operation of the heat dissipation device according to the component status of the server component belonging to the first type among the server components, the component temperature of the server component belonging to the first type, and the ambient temperature of the server, wherein the server component belonging to the first type is a server component that generates heat after the server is powered on;

[0017] In a case where the server status is used to indicate that the server is in the process of booting up, the operation of the cooling device is controlled according to the component status of the server component belonging to the first type among the server components, the component temperature of the server component belonging to the second type, and the ambient temperature of the server, wherein the server component belonging to the second type is a server component that allows the operating system controlling the cooling device to obtain the component temperature during the server booting up process.

[0018] In an exemplary embodiment, the first controller is further configured with a first heat dissipation curve and a first heat dissipation configuration, wherein the first heat dissipation curve is used to indicate a first conversion relationship between an ambient temperature of the server and an operating parameter of the heat dissipation device, and the first heat dissipation configuration is used to indicate a parameter configuration in an operating parameter algorithm corresponding to a server component belonging to a first type, and the operating parameter algorithm is used to calculate the operating parameter of the heat dissipation device according to the component temperature of the server component;

[0019] The controlling the operation of the heat dissipation device according to the component status of the server component belonging to the first type among the server components, the component temperature of the server component belonging to the first type and the ambient temperature of the server comprises:

[0020] detecting, on the server, a component status of a server component belonging to a first type;

[0021] In a case where it is detected that the component state of the server component belonging to the first type indicates that the server component belonging to the first type is configured on the server, calling the first heat dissipation curve to convert the ambient temperature of the server into a first operating parameter, and calling the first heat dissipation configuration to calculate a second operating parameter according to the component temperature of the server component belonging to the first type;

[0022] determining a target operating parameter according to the first operating parameter and the second operating parameter;

[0023] The operation of the heat dissipation device is controlled according to the target operating parameters.

[0024] In an exemplary embodiment, the server component belonging to the first type includes: a plurality of candidate server components, the first heat dissipation curve includes a plurality of heat dissipation curves corresponding to the plurality of candidate server components one by one, and the candidate server component with higher operating power consumption has higher heat dissipation performance of the heat dissipation device corresponding to the operating parameters on the corresponding heat dissipation curve under the same ambient temperature of the server;

[0025] The calling the first heat dissipation curve to convert the ambient temperature of the server into a first operating parameter includes:

[0026] Determining a target server component configured on the server from the plurality of candidate server components;

[0027] The target heat dissipation curve corresponding to the target server component is called from the multiple heat dissipation curves to convert the ambient temperature of the server into the first operating parameter.

[0028] In an exemplary embodiment, the plurality of candidate server components include: an open computing project network card and a smart network card, the plurality of heat dissipation curves include: a first curve corresponding to the open computing project network card and a second curve corresponding to the smart network card, and the heat dissipation performance of the heat dissipation device corresponding to the operating parameters on the first curve under the same ambient temperature of the server is lower than the heat dissipation performance of the heat dissipation device corresponding to the operating parameters on the second curve;

[0029] The step of calling the target heat dissipation curve corresponding to the target server component from the plurality of heat dissipation curves to convert the ambient temperature of the server into the first operating parameter includes:

[0030] In a case where the Open Compute Project network card is configured on the server, calling the first curve from the plurality of heat dissipation curves to convert the ambient temperature of the server into a first parameter, wherein the first operating parameter includes the first parameter;

[0031] When the smart network card is configured on the server, the second curve is called from the multiple heat dissipation curves to convert the ambient temperature of the server into a second parameter, wherein the first operating parameter includes the second parameter.

[0032] In an exemplary embodiment, the first type of server component includes: a plurality of candidate server components, and the first heat dissipation configuration includes a plurality of heat dissipation configurations corresponding one-to-one to the plurality of candidate server components;

[0033] The calling of the first heat dissipation configuration to calculate a second operating parameter according to a component temperature of a server component belonging to the first type includes:

[0034] Determining a target server component configured on the server from the plurality of candidate server components;

[0035] The target heat dissipation configuration corresponding to the target server component is called from the multiple heat dissipation configurations to calculate the second operating parameter according to the component temperature of the target server component.

[0036] In an exemplary embodiment, the plurality of candidate server components include: an open computing project network card and a smart network card, and the plurality of heat dissipation configurations include: a first configuration corresponding to the open computing project network card and a second configuration corresponding to the smart network card;

[0037] The step of calling the target heat dissipation configuration corresponding to the target server component from the multiple heat dissipation configurations and calculating the second operating parameter according to the component temperature of the target server component includes:

[0038] In a case where the open computing project network card is configured on the server, calling the first configuration from the plurality of cooling configurations to calculate a third parameter based on a component temperature of the open computing project network card, wherein the second operating parameter includes the third parameter;

[0039] When the smart network card is configured on the server, the second configuration is called from the multiple heat dissipation configurations to calculate a fourth parameter according to the component temperature of the smart network card, wherein the second operating parameter includes the fourth parameter.

[0040] In an exemplary embodiment, the operating parameter algorithm is used to calculate the operating parameters of the heat dissipation device based on the component temperature of the server component at the sampling time, the component temperature at the historical time, and the operating parameters corresponding to the historical sampling time;

[0041] The calling of the first heat dissipation configuration to calculate a second operating parameter according to a component temperature of a server component belonging to the first type includes:

[0042] Calling the first heat dissipation configuration and substituting it into the operating parameter algorithm to obtain a target operating parameter algorithm;

[0043] Obtaining a first component temperature of a server component belonging to the first type at a sampling moment, a second component temperature at a historical moment, and a historical operating parameter corresponding to the historical sampling moment, wherein the historical operating parameter is an operating parameter corresponding to the server component belonging to the first type calculated by the operating parameter algorithm at the historical sampling moment;

[0044] Substituting the first component temperature, the second component temperature and the historical operating parameters into the target operating parameter algorithm to obtain the second operating parameter.

[0045] In an exemplary embodiment, after detecting the component status of the server component belonging to the first type on the server, the method further comprises:

[0046] In a case where it is detected that the component status of the server component belonging to the first type indicates that the server component belonging to the first type is not configured on the server, the heat dissipation device does not operate.

[0047] In an exemplary embodiment, a second heat dissipation curve is further configured on the first controller, and the second heat dissipation curve is used to indicate a second conversion relationship between the ambient temperature of the server and the operating parameters of the heat dissipation device, and the heat dissipation performance of the heat dissipation device corresponding to the operating parameters under the first conversion relationship for the same ambient temperature of the server is higher than the heat dissipation performance of the heat dissipation device corresponding to the operating parameters under the second conversion relationship;

[0048] After detecting the component status of the server component belonging to the first type on the server, the method further comprises:

[0049] In a case where it is detected that the component state of the server component belonging to the first type indicates that the server component belonging to the first type is not configured on the server, calling the second heat dissipation curve to convert the ambient temperature of the server into a third operating parameter;

[0050] The heat dissipation device is controlled to operate according to the third operating parameter.

[0051] In an exemplary embodiment, when the operating system controlling the heat dissipation device is the first operating system, calling the first heat dissipation curve to convert the ambient temperature of the server into a first operating parameter, and calling the first heat dissipation configuration to calculate a second operating parameter according to the component temperature of the server component belonging to the first type, includes:

[0052] During the process of the second operating system being started, the second operating system collects the ambient temperature of the server and the temperature of the component of the first type of server component;

[0053] The second operating system sends the collected ambient temperature of the server and the temperature of the component of the server component belonging to the first type to the first operating system;

[0054] The first operating system calls the first heat dissipation curve to convert the ambient temperature of the server into a first operating parameter, and the first operating system calls the first heat dissipation configuration to calculate a second operating parameter according to the component temperature of the server component belonging to the first type.

[0055] In an exemplary embodiment, a target storage space is further deployed on the server, the target storage space allows the first operating system and the second operating system to access, and the second operating system sends the collected ambient temperature of the server and the component temperature of the server component belonging to the first type to the first operating system, including:

[0056] The second operating system writes the collected ambient temperature of the server and the component temperature of the server component belonging to the first type into the target storage space;

[0057] The second operating system sends an interrupt request to the first operating system;

[0058] The first operating system responds to the interrupt request and reads the ambient temperature of the server and the component temperature of the server component belonging to the first type from the target storage space.

[0059] In an exemplary embodiment, a third heat dissipation curve, a fourth heat dissipation curve and a second heat dissipation configuration are further configured on the first controller, the third heat dissipation curve is used to indicate a third conversion relationship between the ambient temperature of the server and the operating parameters of the heat dissipation device, the fourth heat dissipation curve is used to indicate a fourth conversion relationship between the ambient temperature of the server and the operating parameters of the heat dissipation device, the heat dissipation performance of the heat dissipation device corresponding to the operating parameters under the third conversion relationship for the same ambient temperature of the server is higher than the heat dissipation performance of the heat dissipation device corresponding to the operating parameters under the fourth conversion relationship, and the second heat dissipation configuration is used to indicate a parameter configuration in an operating parameter algorithm corresponding to a server component belonging to the second type;

[0060] The controlling the operation of the heat dissipation device according to the component status of the server component belonging to the first type among the server components, the component temperature of the server component belonging to the second type and the ambient temperature of the server comprises:

[0061] detecting, on the server, a component status of a server component belonging to a first type;

[0062] In the case where it is detected that the component state indicates that the server component of the first type is configured on the server, converting the ambient temperature of the server into a fourth operating parameter, and calling the second heat dissipation configuration to calculate a fifth operating parameter according to the component temperature of the server component belonging to the second type; determining a reference operating parameter according to the fourth operating parameter and the fifth operating parameter; and controlling the operation of the heat dissipation device according to the reference operating parameter;

[0063] In a case where it is detected that the component status indicates that the first type of server component is not configured on the server, the fourth heat dissipation curve is called to convert the ambient temperature of the server into a sixth operating parameter, and the second heat dissipation configuration is called to calculate a seventh operating parameter based on the component temperature of the second type of server component; device operating parameters are determined based on the sixth operating parameters and the seventh operating parameters; and the operation of the heat dissipation device is controlled according to the device operating parameters.

[0064] In an exemplary embodiment, the controlling the heat dissipation device to run starting from a first time after the startup time of the first controller by the first operating system includes:

[0065] Determining, by the first operating system, heat dissipation operating parameters starting from the first time;

[0066] The first operating system controls the operating parameters of the heat dissipation device to rise to the heat dissipation operating parameters at a third time, wherein there is a time interval between the third time and the first time.

[0067] In an exemplary embodiment, the controlling, by the first operating system, the operating parameter of the heat dissipation device to rise to the heat dissipation operating parameter at a third time includes:

[0068] The first operating system uses the operating parameter as a starting value as the initial current operating parameter and repeatedly performs the following steps until the operating parameter of the heat dissipation device is the heat dissipation operating parameter:

[0069] Calculating the difference between the heat dissipation operating parameter and the current operating parameter;

[0070] When the difference is greater than or equal to the step length operating parameter, sending a next current operating parameter to the heat dissipation device after a target time period, wherein the next current operating parameter is the sum of the current operating parameter and the step length operating parameter;

[0071] In a case where the difference is smaller than the step length operating parameter, the heat dissipation operating parameter is sent to the heat dissipation device after the target time period.

[0072] In an exemplary embodiment, a second controller is further deployed on the server, and the method further includes:

[0073] When the server is powered on, the second controller is started;

[0074] The second controller monitors the startup result of the first controller;

[0075] In a case where the startup result indicates that the first controller fails to start, the second controller identifies a server status of the server;

[0076] In the case of identifying that the server state is powered on but not turned on, the second controller detects the component state of a server component belonging to a first type on the server, wherein the server component belonging to the first type is a server component that generates heat after the server is powered on;

[0077] When it is detected that the component state indicates that the server component of the first type is configured on the server, the second controller controls the operation of the heat dissipation device according to an eighth operation parameter;

[0078] When it is detected that the component status indicates that the first type of server component is not configured on the server, the second controller controls the operation of the cooling device according to a ninth operating parameter, wherein the cooling performance of the cooling device corresponding to the eighth operating parameter for the same ambient temperature of the server is higher than the cooling performance of the cooling device corresponding to the ninth operating parameter.

[0079] In an exemplary embodiment, after the second controller identifies the operating status of the server, the method further includes:

[0080] In the case of identifying that the operating state is a state in the booting stage, the second controller detects the component state of the server component belonging to the first type on the server;

[0081] When it is detected that the component state indicates that the server component of the first type is configured on the server, the second controller controls the operation of the heat dissipation device according to a tenth operation parameter;

[0082] When it is detected that the component status is used to indicate that the first type of server component is not configured on the server, the second controller controls the operation of the cooling device according to the eleventh operating parameter, wherein the cooling performance of the cooling device corresponding to the tenth operating parameter for the same ambient temperature of the server is higher than the cooling performance of the cooling device corresponding to the eleventh operating parameter.

[0083] In an exemplary embodiment, the first controller is connected to the heat dissipation device via the second controller;

[0084] The monitoring of the startup result of the first controller by the second controller includes: the second controller checking whether the heartbeat of the first operating system is normal; if the heartbeat of the first operating system is abnormal, checking whether the heartbeat of the second operating system is normal; if the heartbeat of the second operating system is abnormal, determining that the startup of the first controller fails; if the heartbeat of the first operating system is normal, determining that the startup of the first controller is successful;

[0085] In the case where the startup result indicates that the first controller fails to start, the second controller identifies the running state of the server, including: in the case where the startup result indicates that the first controller fails to start, the second controller discards the received running parameters sent by the first controller and identifies the running state of the server;

[0086] After the second controller monitors the startup result of the first controller, the method further includes: when the startup result is used to indicate that the first controller is successfully started, the second controller sends the operating parameters received from the first controller to the heat dissipation device.

[0087] According to another embodiment of the present application, a control device for a heat dissipation device on a server is provided, the server comprising: a server component, a first controller and a heat dissipation device, a first operating system and a second operating system are deployed on the first controller, and the device comprises: a startup module, for starting the first controller when the server is powered on; a first control module, for controlling the operation of the heat dissipation device by the first operating system from a first time after the startup time of the first controller, wherein the first time is the time when the first operating system completes the startup; the first operating system stops controlling the operation of the heat dissipation device at a second time after the first time, wherein the second time is the time when the second operating system completes the startup; and a second control module, for controlling the operation of the heat dissipation device by the second operating system from the second time.

[0088] According to another embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when run.

[0089] According to another embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0090] According to another embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0091] Through this application, dual operating systems (i.e., the first operating system and the second operating system) are deployed on the first controller in the server. The first controller starts to start when the server is powered on. The first operating system completes startup at the first time after the startup time of the first controller, and the first operating system starts to control the operation of the heat dissipation device, so that the heat dissipation device can be operated as soon as possible after the server is powered on to dissipate the heat generated on the server at this time. The second operating system completes startup at the second time after the first time, and the control right of the heat dissipation device is transferred from the first operating system to the second operating system, and the second operating system controls the heat dissipation device more comprehensively. Therefore, the technical problem of the poor timeliness of the heat dissipation device for the server in the powered-on state can be solved, and the technical effect of improving the timeliness of the heat dissipation device for the server in the powered-on state can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0092] Figure 1It is a hardware structure block diagram of a server device of a method for controlling a heat dissipation device on a server according to an embodiment of the present application;

[0093] Figure 2 is a flow chart of a method for controlling a heat dissipation device on a server according to an embodiment of the present application;

[0094] Figure 3 is a flow chart of a method for operating a heat dissipation device on a server according to an embodiment of the present application;

[0095] Figure 4 is a schematic diagram of an RTOS system controlling a server cooling system according to an embodiment of the present application;

[0096] Figure 5 is a schematic diagram of the architecture of a BMC according to an embodiment of the present application;

[0097] Figure 6 is a schematic diagram of control and operation of a heat dissipation device according to an embodiment of the present application;

[0098] Figure 7 is a schematic diagram of RTOS control and operation of a heat dissipation device according to an embodiment of the present application;

[0099] Figure 8 is a schematic diagram of BMC control and operation of a heat dissipation device according to an embodiment of the present application;

[0100] Fig. 9 It is a schematic diagram of CPLD control and operation of a heat dissipation device according to an embodiment of the present application;

[0101] Fig.10 It is a structural block diagram of a control device for a heat dissipation device on a server according to an embodiment of the present application. DETAILED DESCRIPTION

[0102] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0103] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0104] The method embodiments provided in the embodiments of the present application can be executed in a server device or a similar computing device. Taking running on a server device as an example, Figure 1 1 is a hardware structure block diagram of a server device of a method for controlling a heat dissipation device on a server according to an embodiment of the present application. Figure 1 As shown, the server device may include one or more ( Figure 1Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the above-mentioned server device may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above server device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0105] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the control method of the heat dissipation device on the server in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the server device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0106] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the server device. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0107] In this embodiment, a method for controlling a heat dissipation device on a server is provided. The server includes: a server component, a first controller, and a heat dissipation device. A first operating system and a second operating system are deployed on the first controller. Figure 2 is a flow chart of a method for controlling a heat dissipation device on a server according to an embodiment of the present application. Figure 2 As shown, the process includes the following steps:

[0108] Step S202, the first controller starts to start when the server is powered on;

[0109] Step S204, the first operating system starts controlling the operation of the heat dissipation device from a first time after the startup time of the first controller, wherein the first time is the time when the first operating system completes startup;

[0110] Step S206, the first operating system stops controlling the operation of the heat dissipation device at a second time after the first time, wherein the second time is the time when the second operating system completes startup;

[0111] Step S208: The second operating system controls the operation of the heat dissipation device starting from the second time.

[0112] Through the above steps, dual operating systems (i.e., the first operating system and the second operating system) are deployed on the first controller in the server. The first controller starts to start when the server is powered on. The first operating system completes startup at the first time after the startup time of the first controller, and the first operating system starts to control the operation of the heat dissipation device, so that the heat dissipation device can be operated as soon as possible after the server is powered on to dissipate the heat generated on the server at this time. The second operating system completes startup at the second time after the first time, and the control right of the heat dissipation device is transferred from the first operating system to the second operating system, and the second operating system controls the heat dissipation device more comprehensively. Therefore, the technical problem of the poor timeliness of the heat dissipation device for the server in the powered-on state can be solved, and the technical effect of improving the timeliness of the heat dissipation device for the server in the powered-on state can be achieved.

[0113] Optionally, in this embodiment, the first operating system and the second operating system may be, but are not limited to, two heterogeneous or homogeneous operating systems, that is, the first operating system and the second operating system may be of the same type or different types.

[0114] Taking the first operating system and the second operating system as heterogeneous operating systems as an example, the first operating system and the second operating system may be operating systems with different sensitivities to response time, for example, the first operating system is more sensitive to response time than the second operating system. Alternatively, the first operating system and the second operating system may be operating systems with different resource occupancy, for example, the first operating system occupies less resources for services than the second operating system. The first operating system is an operating system that starts faster than the second operating system.

[0115] The above-mentioned first operating system and second operating system can be but are not limited to two heterogeneous operating systems deployed on the controller of the embedded system, that is, embedded operating systems. Embedded operating systems can be divided into real-time operating systems (RTOS) and non-real-time operating systems according to the sensitivity to response time. Real-time operating systems can include but are not limited to Free RTOS (Free Real-Time Operating System) and RT Linux (RealTime Linux). Non-real-time operating systems can include but are not limited to contiki (Contiki Operating System), HeliOS (Helix Operating System) and Linux (Linux Operating System), etc.

[0116] The first controller may include, but is not limited to, a baseboard management controller (BMC) of the server, the second operating system is the main operating system of the BMC, and the first operating system is the auxiliary operating system of the BMC. The heat dissipation device may include, but is not limited to, a fan, a heat sink, a heat pipe, etc. The operation control of the heat dissipation device by the first controller may include, but is not limited to, the control of the operation parameters of the heat dissipation device by the first controller. For example, if the heat dissipation device is a fan, the first controller may control the duty cycle of the fan speed. If the heat dissipation device is a heat sink, a heat pipe, etc., the first controller may control the operation parameters such as the flow rate or flow velocity of the condensed material.

[0117] The first time is the time when the first operating system completes startup, and the second time is the time when the second operating system completes startup. The first operating system starts faster than the second operating system, so that the heat dissipation device can start running as soon as possible after the server is powered on. From the second time when the second operating system completes startup, the control right of the heat dissipation device is transferred from the first operating system to the second operating system. The second operating system, as the main operating system of the first controller, can perform more comprehensive control over the heat dissipation device.

[0118] In an optional example, in the above step S204, the first operating system can control the operation of the cooling device from the first time after the startup time of the first controller in the following manner but is not limited to: when the first operating system has completed startup and the server has not completed startup, the first operating system controls the operation of the cooling device according to the server status of the server, the component status of the server components, the component temperature of the server components and the ambient temperature of the server; and the first operating system detects the system status of the second operating system.

[0119] When the first operating system completes startup, if the server has not completed startup, the first operating system can, but is not limited to, control the operation of the cooling device according to the server status of the server, the component status of the server component, the component temperature of the server component and the ambient temperature of the server.

[0120] In this embodiment, the server status may refer to, but is not limited to, the server power-on and boot-up status, which may include, but is not limited to: the server is powered on but not booted, the server is powered on and booted but the booting is not completed, the server is powered on and the booting is completed, the server is restarted, etc. The component status of the server component may be, but is not limited to, used to indicate the configuration status of the server component, etc. For example: whether the configured server component will generate heat in the current server state. The component temperature of the server component may be, but is not limited to, collected by a temperature sensor deployed for the server component, and the ambient temperature of the server may be, but is not limited to, collected by a temperature sensor deployed for the environment where the server is located.

[0121] The system status of the second operating system may be, but is not limited to, used to indicate the startup status of the second operating system, such as whether the second operating system has completed startup.

[0122] After the server is powered on, before normal operation, the server will remain in S5 state for a period of time (i.e., the server is powered on but the power-on operation is not performed (for example, the power-on button is not triggered)) and the state during the power-on process (i.e., the server is powered on and the power-on operation is performed (for example, the power-on button is triggered)); it takes a certain amount of time for the first controller to start and control the cooling device (i.e., the time it takes for the second operating system to start). Before the first controller is started, the first operating system controls the operation of the cooling device according to the server status of the server, the status of the server components, the component temperature of the server components, the ambient temperature of the server, etc., thereby realizing refined control of the server cooling.

[0123] In an optional example, the first operating system can stop controlling the operation of the heat dissipation device at a second time after the first time in the following manner but is not limited to: when it is detected that the system status is a completed startup state and the server has not completed startup, the first operating system determines that the second time has arrived; and the first operating system stops controlling the operation of the heat dissipation device.

[0124] If the first operating system detects that the system state of the second operating system is in the state of having completed startup and the server has not completed startup, it is determined that the second time has been reached, and the first operating system stops controlling the operation of the heat dissipation device, and the control right of controlling heat dissipation is handed over to the second operating system.

[0125] In an optional example, the second operating system may, but is not limited to, control the operation of the cooling device from the second time in the following manner: after the second operating system is started, it starts to control the operation of the cooling device according to the server status of the server, the component status of the server components, the component temperature of the server components and the ambient temperature of the server.

[0126] The second operating system can obtain more temperatures of server components than the first operating system, and the second operating system can perform heat dissipation more accurately than the first operating system when controlling the heat dissipation device.

[0127] In this embodiment, a method for operating a heat dissipation device on a server is also provided. Figure 3 is a flow chart of a method for operating a heat dissipation device on a server according to an embodiment of the present application. Figure 3 As shown, the process includes the following steps:

[0128] Step S302, the heat dissipation device starts to run at a target time after the server is powered on, wherein the target time is a startup time of the first operating system, and the startup time of the first operating system is less than a startup time of the second operating system;

[0129] Step S304: The heat dissipation device operates according to the operating parameters output by the first controller, wherein the operating parameters output by the first controller are determined according to the server status of the server, the component status of the server component, and the temperature of the server.

[0130] Through the above steps, dual operating systems (i.e., the first operating system and the second operating system) are deployed on the first controller in the server, and the heat dissipation device starts to run at the target time after the server is powered on. The target time is the startup time of the first operating system. On the first controller, the startup time of the first operating system is less than the startup time of the second operating system, so that the heat dissipation device runs as soon as possible after the server is powered on to dissipate the heat generated on the server at this time. The heat dissipation device runs according to the operating parameters output by the first controller. The operating parameters are determined according to the server status of the server, the component status of the server components, and the temperature of the server, so that the heat dissipation device can run more finely and accurately to dissipate heat for the server. Therefore, the technical problem of the poor timeliness of the heat dissipation device for the server in the powered-on state can be solved, and the technical effect of improving the timeliness of the heat dissipation device for the server in the powered-on state can be achieved.

[0131] In this embodiment, the server status may refer to, but is not limited to, the server power-on and boot-up status, which may include, but is not limited to: the server is powered on but not booted, the server is powered on and booted but the booting is not completed, the server is powered on and the booting is completed, the server is restarted, etc. The component status of the server component may be, but is not limited to, used to indicate the configuration status of the server component, etc. For example: whether the configured server component will generate heat in the current server state. The component temperature of the server component may be, but is not limited to, collected by a temperature sensor deployed for the server component, and the ambient temperature of the server may be, but is not limited to, collected by a temperature sensor deployed for the environment where the server is located.

[0132] In this embodiment, the target duration may refer to, but is not limited to, the duration between the power-on time of the server and the first time, that is, the heat dissipation device can dissipate heat for the server in time when the first operating system is started after the server is powered on.

[0133] In an optional example, the operation of the cooling device can be controlled according to the server status of the server, the component status of the server components, the component temperature of the server components and the ambient temperature of the server in the following manners, but not limited to: detecting the server status of the server; when the server status is used to indicate that the server is powered on but not turned on, controlling the operation of the cooling device according to the component status of the server components belonging to a first type in the server components, the component temperature of the server components belonging to the first type and the ambient temperature of the server, wherein the server components belonging to the first type are server components that generate heat after the server is powered on; when the server status is used to indicate that the server is in the process of being turned on, controlling the operation of the cooling device according to the component status of the server components belonging to the first type in the server components, the component temperature of the server components belonging to the second type and the ambient temperature of the server, wherein the server components belonging to the second type are server components that allow the operating system that controls the cooling device to obtain the component temperature during the server startup process.

[0134] Among the server components that are allowed to be deployed on the server, some server components will generate heat when the server is powered on but not turned on. In this embodiment, such server components may be, but are not limited to, server components belonging to the first type. For example, server components that support the Network Controller – Sideband Interface (NCSI) function include Open Compute Project (OCP) network cards, smart network cards, etc.

[0135] Different server components have different presence signals. The operating system can detect the presence signals of different components to determine the configuration status of the server components on the server.

[0136] Different server states of the server can, but are not limited to, use different cooling strategies to control the cooling device. If the server is powered on but not turned on, the cooling device can be controlled based on the configuration of the server components that generate heat in the server state, the component temperature, and the ambient temperature. If the server is in the process of starting up, the cooling device can be controlled based on the configuration of the server components that generate heat in the powered-on state and the component temperature of the server components that can be obtained by the operating system currently controlling the cooling device in this state, and the ambient temperature.

[0137] In an optional example, the operating system on the first controller responsible for controlling the heat dissipation device obtains the operating parameters of the heat dissipation device according to factors of various dimensions, and outputs them to the heat dissipation device, and the heat dissipation device operates according to the operating parameters output by the first controller to dissipate heat for the server. For example: in the case where the server status is used to indicate that the server has been powered on but not turned on, the operating parameters output by the first controller are determined based on the component status of the server components belonging to the first type in the server components, the component temperature of the server components belonging to the first type, and the ambient temperature of the server, wherein the server components belonging to the first type are server components that generate heat after the server is powered on; in the case where the server status is used to indicate that the server is in the process of being turned on, the operating parameters output by the first controller are determined based on the component status of the server components belonging to the first type in the server components, the component temperature of the server components belonging to the second type, and the ambient temperature of the server, wherein the server components belonging to the second type are server components that allow the operating system controlling the heat dissipation device to obtain the component temperature during the server startup process.

[0138] Through the above steps, the cooling device of the server can start operating in time after the server is powered on, and the first controller can control the operating parameters of the cooling device according to different status conditions of the server in combination with different reference factors, so that the resources consumed by the operation of the cooling device can match the status of the server, thereby reducing the waste of resources, ensuring the timeliness of the operation of the cooling device and improving the flexibility of the control of the cooling device.

[0139] In an optional example, the first controller is also configured with a first heat dissipation curve and a first heat dissipation configuration, the first heat dissipation curve is used to indicate a first conversion relationship between the ambient temperature of the server and the operating parameters of the heat dissipation device, the first heat dissipation configuration is used to indicate the parameter configuration in the operating parameter algorithm corresponding to the server component belonging to the first type, and the operating parameter algorithm is used to calculate the operating parameters of the heat dissipation device according to the component temperature of the server component; the operation of the heat dissipation device can be controlled according to the component status of the server component belonging to the first type in the server component, the component temperature of the server component belonging to the first type, and the ambient temperature of the server in the following manners, but not limited to: detecting the component status of the server component belonging to the first type on the server; when it is detected that the component status of the server component belonging to the first type is used to indicate that the server component belonging to the first type is configured on the server, calling the first heat dissipation curve to convert the ambient temperature of the server into the first operating parameter, and calling the first heat dissipation configuration to calculate the second operating parameter according to the component temperature of the server component belonging to the first type; determining the target operating parameter according to the first operating parameter and the second operating parameter; and controlling the operation of the heat dissipation device according to the target operating parameter.

[0140] Optionally, in this embodiment, the first heat dissipation curve may be, but is not limited to, any curve form that conforms to the heat dissipation law of the server, for example: the first conversion relationship may be, but is not limited to, a linear relationship, then the first heat dissipation curve may be, but is not limited to, a straight line, or a segmented straight line. The first conversion relationship may be, but is not limited to, an exponential relationship, then the first heat dissipation curve may be, but is not limited to, an exponential curve. The operating parameter algorithm may be, but is not limited to, any function algorithm that conforms to the heat dissipation law of the server, for example: a proportional integral differential (PID) control speed regulation algorithm.

[0141] In an optional example, from the perspective of the operation of the heat dissipation device, the operating parameters output by the first controller are determined based on the component status of the server components belonging to the first type in the server components, the component temperature of the server components belonging to the first type, and the ambient temperature of the server, including: when the component status of the server components belonging to the first type is used to indicate that the server components belonging to the first type are configured on the server, the operating parameters output by the first controller are the first operating parameters or the second operating parameters, wherein the ambient temperature of the server and the first operating parameters conform to the first heat dissipation curve, the first heat dissipation curve is used to indicate a first conversion relationship between the ambient temperature of the server and the operating parameters of the heat dissipation device, and the second operating parameters are calculated based on the component temperature of the server components belonging to the first type.

[0142] In this embodiment, the conversion relationship indicated by each heat dissipation curve can be, but is not limited to, designed according to the server configuration, the model of the heat dissipation device used, and the operating performance of the heat dissipation device. For example: if the heat dissipation device is a fan, then the conversion relationship indicated by each heat dissipation curve can be, but is not limited to, designed according to the server configuration, the model of the fan, and the PQ characteristic curve. The PQ characteristic curve is one of the key curves that describe the performance of the cooling fan. Here P represents the static pressure (Pressure) generated by the fan, and Q represents the air volume (Airflow) of the fan. The PQ characteristic curve shows the static pressure value that the fan can provide at different air volumes. Specifically, when the air volume increases, the static pressure of the fan usually decreases; conversely, when the air volume decreases, the static pressure of the fan increases. This relationship is expressed as a downward sloping curve on the PQ curve.

[0143] For example, as shown in Table 1, the conversion relationship between the ambient temperature and the fan speed duty cycle parameter is shown. The conversion relationship can be, but is not limited to, the curve PWM=k*Inlet+b, where PWM is the speed duty cycle and Inlet is the ambient temperature. In a corresponding relationship, multiple straight lines can be spliced ​​at the same time. In different states and configurations, the air volume requirements of the heat dissipation components are different, and different logics can be achieved by adjusting the size of k and b; for example, in the S5 state (that is, the state where the server is powered on but not started), the air volume requirement when there is a smart network card in the configuration is greater than the air volume requirement when there is an OCP network card, and the value of b can be increased accordingly; when there is a smart network card in the configuration, the various components are gradually powered on during the boot process, and the air volume requirement is greater than the air volume requirement in the S5 state, and the values ​​of k and b can be adjusted at the same time. When the temperature is lower than the minimum temperature value defined by the Inlet curve, the corresponding PWM takes the PWM corresponding to the defined minimum temperature; when the temperature is higher than the minimum value defined by the Inlet curve, the corresponding PMW takes the PWM corresponding to the defined maximum temperature. When multiple curves or algorithms are called simultaneously in a certain state and a certain configuration, the maximum fan speed value obtained by combining the multiple curves or algorithms in parallel can be output to the fan.

[0144] Table 1

[0145]

[0146] In an optional example, different server components belonging to the first type correspond to different heat dissipation curves. Under the same ambient temperature of the server, the higher the operating power consumption of the server components belonging to the first type, the higher the corresponding heat generated, and the higher the heat dissipation performance of the heat dissipation device corresponding to the operating parameters on the corresponding heat dissipation curve, thereby ensuring a better heat dissipation effect. For example: the server components belonging to the first type include: multiple candidate server components, the first heat dissipation curve includes multiple heat dissipation curves corresponding to the multiple candidate server components one by one, the candidate server components with higher operating power consumption have higher heat dissipation performance of the heat dissipation device corresponding to the operating parameters on the corresponding heat dissipation curve under the same ambient temperature of the server; the first heat dissipation curve can be called to convert the ambient temperature of the server into the first operating parameter in the following manner, but is not limited to: determine the target server component configured on the server from the multiple candidate server components; call the target heat dissipation curve corresponding to the target server component from the multiple heat dissipation curves to convert the ambient temperature of the server into the first operating parameter.

[0147] Optionally, in this embodiment, the plurality of candidate server components may include, but are not limited to: components supporting NCSI functions (including OCP network cards, smart network cards, etc.), 54V power supply modules in AI models (a model of a graphics processor GPU), etc. Compared with smart network cards, OCP network cards have slightly lower power consumption and relatively smaller heat dissipation performance requirements, while smart network cards have higher power consumption and greater heat dissipation performance requirements.

[0148] In an optional example, from the perspective of the operation of the heat dissipation device, the server components belonging to the first type include: multiple candidate server components, the first heat dissipation curve includes multiple heat dissipation curves corresponding to the multiple candidate server components one by one, the candidate server components with higher operating power consumption have higher heat dissipation performance of the heat dissipation device corresponding to the operating parameters on the corresponding heat dissipation curve at the same server ambient temperature; the first operating parameters are the operating parameters of the target server components configured on the server among the multiple candidate server components on the corresponding heat dissipation curve.

[0149] In an optional example, the multiple candidate server components may include, but are not limited to: an open computing project network card and a smart network card, the multiple heat dissipation curves include: a first curve corresponding to the open computing project network card and a second curve corresponding to the smart network card, and under the same server ambient temperature, the heat dissipation performance of the heat dissipation device corresponding to the operating parameters on the first curve is lower than the heat dissipation performance of the heat dissipation device corresponding to the operating parameters on the second curve; the target heat dissipation curve corresponding to the target server component may be called from the multiple heat dissipation curves to convert the server ambient temperature into the first operating parameter in the following manner, but is not limited to: when the open computing project network card is configured on the server, the first curve is called from the multiple heat dissipation curves to convert the server ambient temperature into the first parameter, wherein the first operating parameter includes the first parameter; when the smart network card is configured on the server, the second curve is called from the multiple heat dissipation curves to convert the server ambient temperature into the second parameter, wherein the first operating parameter includes the second parameter.

[0150] Optionally, in this embodiment, the conversion relationship can be obtained by but is not limited to splicing multiple straight lines. When the temperature is between the minimum temperature and the maximum temperature, the heat dissipation curve based on the ambient temperature Inlet can adopt a linear relationship; when the temperature is lower than the minimum temperature value defined by the Inlet curve, the corresponding PWM takes the PWM corresponding to the defined minimum temperature; when the temperature is higher than the minimum value defined by the Inlet curve, the corresponding PMW takes the PWM corresponding to the defined maximum temperature.

[0151] In an optional example, from the operation of the heat dissipation device, the server components belonging to the first type include: an open computing project network card and / or an intelligent network card, the heat dissipation device includes: a fan, the operation parameters of the heat dissipation device include: a speed duty cycle of the fan, and the first heat dissipation curve includes: a first curve corresponding to the open computing project network card and a second curve corresponding to the intelligent network card; when the open computing project network card is configured on the server, the first curve includes: when the ambient temperature of the server is less than or equal to the first temperature, the speed duty cycle is the first duty cycle, when the ambient temperature of the server is greater than or equal to the second temperature, the speed duty cycle is the second duty cycle, and when the ambient temperature of the server is greater than the first temperature, the speed duty cycle is the second duty cycle. When the ambient temperature of the server is lower than the first temperature and lower than the second temperature, the speed duty cycle is linearly related to the ambient temperature of the server between the first duty cycle and the second duty cycle; when a smart network card is configured on the server, the second curve includes: when the ambient temperature of the server is lower than or equal to the first temperature, the speed duty cycle is the third duty cycle, when the ambient temperature of the server is greater than or equal to the second temperature, the speed duty cycle is the fourth duty cycle, when the ambient temperature of the server is greater than the first temperature and lower than the second temperature, the speed duty cycle is linearly related to the ambient temperature of the server between the third duty cycle and the fourth duty cycle; wherein, the third duty cycle is greater than the first duty cycle, and the fourth duty cycle is greater than the second duty cycle.

[0152] For example, taking the cooling device including a fan, the operating parameters of the cooling device including a fan speed duty cycle PWM, and the ambient temperature of the server as Inlet as an example, the first cooling curve includes a first curve corresponding to the open computing project network card and a second curve corresponding to the smart network card;

[0153] When an open computing project network card is configured on the server, the first curve may be, but is not limited to, ;

[0154] When a smart network card is configured on the server, the second curve can be, but is not limited to, .

[0155] Optionally, in this embodiment, when an Open Compute Project network card and a Smart Network Card are configured on the server at the same time, the first operating parameter is an operating parameter corresponding to the ambient temperature of the server on the second curve.

[0156] Take a 2U server as an example. When the server is in S5 state and there is an OCP network card in the configuration, it is evaluated that appropriate air volume is needed for heat dissipation. In the corresponding Inlet-2 curve (i.e. the first curve mentioned above), PWM=k2*Inlet+b2, k2=3, b2=-30, and the corresponding Inlet-2 correspondence (Inlet_Temp, PWM) is (20,30), (25,45), (30,60), (35,75); when Inlet≤20C, PWM=30, when Inlet≥ When the temperature is 35°C, PWM=75; when there is a smart network card in the configuration, it is evaluated that a higher air volume is required for heat dissipation. The corresponding Inlet-3 curve (that is, the second curve mentioned above) PWM=k3*Inlet+b3, k3=3, b3=-20, and the corresponding Inlet-3 correspondence (Inlet_Temp, PWM) is (20,40), (25,55), (30,70), (35,85); when Inlet≤20°C, PWM=40, and when Inlet≥35°C, PWM=85.

[0157] In an optional example, the first type of server component may include but is not limited to: multiple candidate server components, the first heat dissipation configuration may include but is not limited to multiple heat dissipation configurations corresponding to the multiple candidate server components; the first heat dissipation configuration may be called but is not limited to calculate the second operating parameter according to the component temperature of the server component belonging to the first type in the following manner: determining the target server component configured on the server from the multiple candidate server components; calling the target heat dissipation configuration corresponding to the target server component from the multiple heat dissipation configurations to calculate the second operating parameter according to the component temperature of the target server component.

[0158] In an optional example, the multiple candidate server components may include, but are not limited to: an open computing project network card and a smart network card, and the multiple cooling configurations include: a first configuration corresponding to the open computing project network card and a second configuration corresponding to the smart network card; the target cooling configuration corresponding to the target server component may be called from the multiple cooling configurations to calculate the second operating parameter according to the component temperature of the target server component in the following manner, but is not limited to: when the open computing project network card is configured on the server, the first configuration is called from the multiple cooling configurations to calculate the third parameter according to the component temperature of the open computing project network card, wherein the second operating parameter includes the third parameter; when the smart network card is configured on the server, the second configuration is called from the multiple cooling configurations to calculate the fourth parameter according to the component temperature of the smart network card, wherein the second operating parameter includes the fourth parameter.

[0159] In an optional example, an operating parameter algorithm is used to calculate the operating parameters of a cooling device based on the component temperature of the server component at a sampling moment, the component temperature at a historical moment, and the operating parameters corresponding to the historical sampling moment; the first cooling configuration may be called to calculate the second operating parameter based on the component temperature of the server component belonging to the first type in the following manner, but is not limited to: calling the first cooling configuration and substituting it into the operating parameter algorithm to obtain a target operating parameter algorithm; obtaining the first component temperature of the server component belonging to the first type at the sampling moment, the second component temperature at a historical moment, and the historical operating parameters corresponding to the historical sampling moment, wherein the historical operating parameters are the operating parameters corresponding to the server component belonging to the first type calculated by the operating parameter algorithm at the historical sampling moment; substituting the first component temperature, the second component temperature, and the historical operating parameters into the target operating parameter algorithm to obtain the second operating parameters.

[0160] For the component temperature of the server components in the server, PID speed regulation can be used but is not limited to it. In the PID calculation, the formula is PWM(k)=PWM(k-1)+▽PWM; ▽PWM=Kp*[T(k)-T(k-1)]+Ki(T(k)-Tsp)+Kd*[[T(k)-T(k-1)]-[T(k-1)-T(k-2)]], PWM(k) is the PWM at time k, PWM(k-1) is the virtual PWM calculated by this temperature sensor at time (k-1) (that is, the historical operating parameters corresponding to the above historical sampling time), Tsp is the set control point, that is, during the operation, the highest temperature value that the component temperature is expected to reach, T(k), T(k-1), and T(k-2) are the temperature values ​​of the temperature sensor at times k, k-1, and k-2, respectively.

[0161] Among them, Kp*[T(k)-T(k-1)] is the temperature difference term, which represents the difference between the temperature at time k and the temperature at time k-1. When the temperature of a component changes, this term can be used to respond quickly: when the temperature of a component rises, this term is positive, which increases the corresponding fan speed; when the temperature of a component drops, this term is negative, which decreases the corresponding fan speed. For components such as CPU and GPU, when the power consumption changes significantly, the temperature will also change significantly. Generally, a larger value (usually 6~12) is set for Kp in this term to increase the fan speed change brought about by this term and avoid temperature overshoot.

[0162] Ki(T(k)-Tsp) is an integral term, which represents the difference between the temperature at time k and the temperature at the control point. When the component temperature is higher than the control point, this term is positive, which can increase the corresponding fan speed. When the component temperature is lower than the control point, this term is negative, which can reduce the corresponding fan speed. The control point in this term determines the stable value of the temperature during the control process.

[0163] Kd*[[T(k)-T(k-1)]-[T(k-1)-T(k-2)]] is a differential term, which represents the difference between the temperature difference at time k and the temperature difference at time k-1.

[0164] When an OCP network card is involved, the control point Tsp of the temperature of the OCP network card component is set to 85C, Kp=6.0, Ki=0.3, Kd=0.1 (that is, the first configuration mentioned above), and the corresponding optical module temperature Tsp is 62C, Kp=5.5, Ki=0.2, Kd=0.1; when an intelligent network card is involved, the control point Tsp of the temperature of the intelligent network card component is set to 90C, Kp=7.0, Ki=0.3, Kd=0.2 (that is, the second configuration mentioned above), and the corresponding optical module temperature Tsp is 62C, Kp=5.0, Ki=0.3, Kd=0.1.

[0165] In an optional example, if the server component of the first type is not configured on the server, the heat dissipation device may not operate or may operate with a smaller air volume when the server is powered on but not turned on (i.e., S5 state). For example: after detecting the component state of the server component of the first type on the server, when it is detected that the component state of the server component of the first type is used to indicate that the server component of the first type is not configured on the server, the heat dissipation device does not operate. Alternatively, the first controller is also configured with a second heat dissipation curve, the second heat dissipation curve is used to indicate a second conversion relationship between the ambient temperature of the server and the operating parameters of the heat dissipation device, and the heat dissipation performance of the heat dissipation device corresponding to the operating parameters of the ambient temperature of the same server under the first conversion relationship is higher than the heat dissipation performance of the heat dissipation device corresponding to the operating parameters under the second conversion relationship; after detecting the component state of the server component of the first type on the server, when it is detected that the component state of the server component of the first type is used to indicate that the server component of the first type is not configured on the server, the second heat dissipation curve is called to convert the ambient temperature of the server into a third operating parameter; and the operation of the heat dissipation device is controlled according to the third operating parameter.

[0166] In an optional example, from the operation of the heat dissipation device, when the component state of the server component belonging to the first type is used to indicate that the server component belonging to the first type is not configured on the server, the operating parameter output by the first controller is a target parameter value; or, when the component state of the server component belonging to the first type is used to indicate that the server component belonging to the first type is not configured on the server, the operating parameter output by the first controller is a third operating parameter, wherein the ambient temperature of the server and the third operating parameter conform to a second heat dissipation curve, and the second heat dissipation curve is used to indicate a second conversion relationship between the ambient temperature of the server and the operating parameters of the heat dissipation device, and the heat dissipation performance of the heat dissipation device corresponding to the operating parameters under the first conversion relationship for the same server ambient temperature is higher than the heat dissipation performance of the heat dissipation device corresponding to the operating parameters under the second conversion relationship.

[0167] Taking a 2U server as an example, when the server is in S5 state and there are no components such as OCP network cards and smart network cards that require heat dissipation in the configuration, it is evaluated that there is no air volume demand and the fan does not need to run. In the Inlet-1 curve (i.e., the second heat dissipation curve mentioned above) PWM=k1*Inlet+b1, k1=0, b1=0, the corresponding Inlet-1 corresponding relationship (Inlet_Temp, PWM) is (20, 0), (25, 0), (30, 0), (35, 0). Alternatively, k1=0, b1=5, the corresponding Inlet-1 corresponding relationship (Inlet_Temp, PWM) is (20, 5), (25, 5), (30, 5), (35, 5). Alternatively, k1=1, b1=-20, the corresponding Inlet-1 corresponding relationship (Inlet_Temp, PWM) is (20, 0), (25, 5), (30, 10), (35, 15).

[0168] Take the case where the first controller is BMC, the first operating system is RTOS, and the second operating system is Linux. In order to make full use of the computing power resources of BMC, the RTOS real-time operating system is deployed. According to the BMC Linux / RTOS heterogeneous dual-system parallel technology, data exchange between multi-core and multi-system is realized. The ambient temperature and component temperature are collected through the PECI bus, which can realize millisecond-level signal acquisition control. Then, the temperature and heat dissipation are dynamically controlled through closed-loop feedback, so as to accurately control the heat dissipation resources, minimize the resources to meet the heat dissipation requirements, and reduce ineffective power consumption. For example: Figure 4 is a schematic diagram of an RTOS system controlling a server cooling system according to an embodiment of the present application, such as Figure 4As shown in the figure, the RTOS system collects component temperatures from temperature sensors deployed on various hardware components such as the CPU deployed on the server, collects ambient temperature from temperature sensors deployed in the server's cooling system, and adjusts the fan speed of the fan deployed in the cooling system according to the component temperature and ambient temperature. At the same time, the RTOS system also has the function of regulating the performance of various hardware components.

[0169] In an optional example, when the first operating system controls the operation of the heat dissipation device, if the second operating system is starting up and has the ability to collect temperature parameters during its startup process, then the ambient temperature, component temperature and other parameters required by the first operating system can be, but are not limited to, collected by the second operating system and transmitted to the first operating system through inter-core communication. For example, in the case where the operating system controlling the heat dissipation device is the first operating system, the following methods can be used to call the first heat dissipation curve to convert the ambient temperature of the server into the first operating parameter, and call the first heat dissipation configuration to calculate the second operating parameter according to the component temperature of the server component belonging to the first type: when the second operating system is starting up, the second operating system collects the ambient temperature of the server and the component temperature of the server component belonging to the first type; the second operating system sends the collected ambient temperature of the server and the component temperature of the server component belonging to the first type to the first operating system; the first operating system calls the first heat dissipation curve to convert the ambient temperature of the server into the first operating parameter, and the first operating system calls the first heat dissipation configuration to calculate the second operating parameter according to the component temperature of the server component belonging to the first type.

[0170] In an optional example, the method of inter-core communication may be, but is not limited to, a method of combining shared memory with interrupt requests. For example, a target storage space is also deployed on the server, and the target storage space allows the first operating system and the second operating system to access it. The second operating system may, but is not limited to, send the collected server ambient temperature and the component temperature of the server component belonging to the first type to the first operating system in the following manner: the second operating system writes the collected server ambient temperature and the component temperature of the server component belonging to the first type to the target storage space; the second operating system sends an interrupt request to the first operating system; the first operating system responds to the interrupt request and reads the server ambient temperature and the component temperature of the server component belonging to the first type from the target storage space.

[0171] For example, the first controller is BMC, the first operating system is RTOS real-time operating system, and the second operating system is Linux. Figure 5 is a schematic diagram of the architecture of a BMC according to an embodiment of the present application, such as Figure 5As shown in the figure, RTOS and Linux are deployed in BMC, and the two communicate through shared memory combined with inter-core communication. BMC is connected to the flash memory (NOR Flash), interface controller (SD / EMMC), hard disk (DDR), out-of-band interface (MAC), central processing unit (CPU), fan (FAN), sensor (Sensor) and integrated south bridge (PCH) on the server.

[0172] Based on the real-time acquisition of sensor temperature data through the RTOS system, before the BMC Linux system is started, the RTOS collects and controls the system temperature; during the BMC Linux system startup phase, Linux collects sensor temperature information, and then passes it to the RTOS through shared memory, and the RTOS performs fan control; when the BMC Linux system is fully started, the Linux system collects sensor temperature and implements temperature control itself. At the same time, when the BMC Linux system fails or restarts, the RTOS can quickly take over the cooling system and accurately control the fan speed.

[0173] Among the three control firmwares of RTOS, BMC Linux and CPLD, BMC has the advantages of high control accuracy and high logic complexity, but BMC takes a long time to start up. When BMC has not started up, fan control cannot be achieved. Both RTOS and CPLD have the characteristics of fast startup, and can start up and control the fan in 3-5S. In addition, RTOS can also obtain the ambient temperature and the temperature of some important components. After obtaining the temperature, RTOS can perform refined control calculations and fan speed output according to these temperatures.

[0174] When the server is in the process of starting up, the heat dissipation device can also be controlled by combining the heat dissipation curve with the operating parameter algorithm. For example: the first controller is also configured with a third heat dissipation curve, a fourth heat dissipation curve and a second heat dissipation configuration. The third heat dissipation curve is used to indicate the third conversion relationship between the ambient temperature of the server and the operating parameters of the heat dissipation device. The fourth heat dissipation curve is used to indicate the fourth conversion relationship between the ambient temperature of the server and the operating parameters of the heat dissipation device. The heat dissipation performance of the heat dissipation device corresponding to the operating parameters of the same server ambient temperature under the third conversion relationship is higher than the heat dissipation performance of the heat dissipation device corresponding to the operating parameters under the fourth conversion relationship. The second heat dissipation configuration is used to indicate the parameter configuration in the operating parameter algorithm corresponding to the server component belonging to the second type. The operation of the heat dissipation device can be controlled according to the component status of the server component belonging to the first type in the server component, the component temperature of the server component belonging to the second type and the ambient temperature of the server in the following manners, but is not limited to: in the server The method comprises the steps of: detecting a component status of a server component of the first type on the server; converting an ambient temperature of the server into a fourth operating parameter when detecting that the component status indicates that the server component of the first type is configured on the server, and calling the second heat dissipation configuration to calculate a fifth operating parameter according to the component temperature of the server component of the second type; determining a reference operating parameter according to the fourth operating parameter and the fifth operating parameter; and controlling the operation of the heat dissipation device according to the reference operating parameter; calling the fourth heat dissipation curve to convert the ambient temperature of the server into a sixth operating parameter when detecting that the component status indicates that the server component of the first type is not configured on the server, and calling the second heat dissipation configuration to calculate a seventh operating parameter according to the component temperature of the server component of the second type; determining the device operating parameter according to the sixth operating parameter and the seventh operating parameter; and controlling the operation of the heat dissipation device according to the device operating parameter.

[0175] In an optional example, from the operation of the heat dissipation device, when the component status of the server component belonging to the first type is used to indicate that the server component belonging to the first type is configured on the server, the operating parameter output by the first controller is a fourth operating parameter or a fifth operating parameter, wherein the ambient temperature of the server and the fourth operating parameter conform to the third heat dissipation curve, the third heat dissipation curve is used to indicate the third conversion relationship between the ambient temperature of the server and the operating parameter of the heat dissipation device, and the fifth operating parameter is calculated based on the component temperature of the server component belonging to the second type; when the component status of the server component belonging to the first type is used to indicate that the server component belonging to the first type is not configured on the server, the operating parameter output by the first controller is a sixth operating parameter or a seventh operating parameter, wherein the ambient temperature of the server and the sixth operating parameter conform to the fourth heat dissipation curve, the fourth heat dissipation curve is used to indicate the fourth conversion relationship between the ambient temperature of the server and the operating parameter of the heat dissipation device, and the seventh operating parameter is calculated based on the component temperature of the server component belonging to the second type, and the heat dissipation performance of the heat dissipation device corresponding to the operating parameter under the third conversion relationship for the same server ambient temperature is higher than the heat dissipation performance of the heat dissipation device corresponding to the operating parameter under the fourth conversion relationship.

[0176] In an optional example, from the operation of the heat dissipation device, the server components belonging to the first type include: an open computing project network card and / or an intelligent network card, the heat dissipation device includes: a fan, the operation parameters of the heat dissipation device include: a speed duty cycle of the fan, and the third heat dissipation curve includes: a first curve corresponding to the open computing project network card and a second curve corresponding to the intelligent network card; the third heat dissipation curve includes: when the ambient temperature of the server is less than or equal to the first temperature, the speed duty cycle is a fifth duty cycle, when the ambient temperature of the server is greater than or equal to the second temperature, the speed duty cycle is a sixth duty cycle, and when the ambient temperature of the server is greater than the first temperature, the speed duty cycle is a sixth duty cycle. When the ambient temperature of the server is lower than the first temperature and lower than the second temperature, the speed duty cycle is between the fifth duty cycle and the sixth duty cycle, which is linearly related to the ambient temperature of the server; the fourth heat dissipation curve includes: when the ambient temperature of the server is lower than or equal to the first temperature, the speed duty cycle is the seventh duty cycle, when the ambient temperature of the server is greater than or equal to the second temperature, the speed duty cycle is the eighth duty cycle, when the ambient temperature of the server is greater than the first temperature and lower than the second temperature, the speed duty cycle is between the seventh duty cycle and the eighth duty cycle, which is linearly related to the ambient temperature of the server; wherein, the fifth duty cycle is greater than the seventh duty cycle, and the sixth duty cycle is greater than the eighth duty cycle.

[0177] For example, the server components belonging to the first type include: an open computing project network card and / or an intelligent network card, the heat dissipation device includes: a fan, the operating parameters of the heat dissipation device include: a fan speed duty cycle PWM, the ambient temperature of the server is Inlet, and the third heat dissipation curve includes: a first curve corresponding to the open computing project network card and a second curve corresponding to the intelligent network card;

[0178] The third heat dissipation curve may be, but is not limited to, ;

[0179] The fourth heat dissipation curve may be, but is not limited to, .

[0180] Take a 2U server as an example. When the server is in the boot process and there is no smart network card or OCP network card in the configuration, it is estimated that a slightly lower air volume is needed for heat dissipation. In the corresponding Inlet-4 curve (that is, the fourth heat dissipation curve mentioned above), PWM=k4*Inlet+b4, k4=3, b4=-25, and the corresponding Inlet-4 corresponding relationship (Inlet_Temp, PWM) is (20,35), (25,50), (30,65), (35,80); when Inlet≤20C, PWM=35, when Inlet When let≥35C, PWM=80; when there is a smart network card in the configuration, it is evaluated that a higher air volume is required for heat dissipation. Corresponding to the Inlet-5 curve (that is, the third heat dissipation curve mentioned above), PWM=k5*Inlet+b5, k5=3, b5=-15, the corresponding Inlet-5 correspondence (Inlet_Temp, PWM) is (20,45), (25,60), (30,75), (35,90); when Inlet≤20C, PWM=45, when Inlet≥35C, PWM=90.

[0181] Taking the first type of server components as OCP network cards and smart network cards as an example, the startup time of the first operating system is about 3-5S. When the server configuration does not install components such as OCP network cards and smart network cards that need heat dissipation in the S5 state, the server is powered on and enters the S5 state. The fan does not run. When the ambient temperature of the server is increased or decreased, the fan speed does not change and always maintains at 0 speed. When the ambient temperature remains at 25C, after pressing the power button, the fan speed duty cycle is increased to 50% duty. When the ambient temperature of the server is increased, the fan speed increases accordingly. It can be found that the corresponding relationship between the ambient temperature and the fan speed is generally linear, and under the same ambient temperature, the fan speed duty cycle during the startup process is higher than the fan speed duty cycle in the S5 state; when the ambient temperature rises to 35C and then increases, the fan speed no longer increases, and when the ambient temperature drops to 20C and then decreases, the fan speed duty cycle no longer decreases. About 1.5 to 3 minutes after pressing the power button, the BIOS Post is completed, and the temperatures of components such as the CPU can be read in the web BMC. The speed during the boot process fails and the fan speed decreases.

[0182] When the OCP network card is installed in the server configuration but the smart network card is not installed, the server is powered on and enters the S5 state. The fan starts to run about 3-5 seconds after power-on. When the ambient temperature is maintained at 25°C, the fan speed duty cycle is 45% duty. When the ambient temperature of the server is increased, the fan speed increases accordingly. It can be found that the corresponding relationship between the ambient temperature and the fan speed is generally linear. When the ambient temperature rises to 35°C and then increases, the fan speed no longer increases. When the ambient temperature drops to 20°C and then decreases, the fan speed duty cycle no longer decreases. When the ambient temperature is maintained at 25°C, after the power button is pressed (the subsequent status description is consistent with the power-on process phenomenon without an OCP network card), the fan speed duty cycle is increased to 50% duty. When the ambient temperature of the server is increased, the fan speed increases accordingly. It can be found that the corresponding relationship between the ambient temperature and the fan speed is generally linear, and at the same ambient temperature, the fan speed duty cycle during the power-on process is higher than the fan speed duty cycle in the S5 state; when the ambient temperature rises to 35°C and then increases, the fan speed no longer increases, and when the ambient temperature drops to 20°C and then decreases, the fan speed duty cycle no longer decreases. About 1.5 to 3 minutes after pressing the power button, BIOSPost is completed, and the temperatures of components such as the CPU can be read in the web BMC one after another. The speed during the power-on process fails, and the fan speed decreases.

[0183] When the OCP network card is not installed in the server and the smart network card is installed, the server is powered on and enters the S5 state. The fan starts to run about 3-5 seconds after power-on. When the ambient temperature is maintained at 25°C, the fan speed duty cycle is 55% duty. When the ambient temperature of the server is increased, the fan speed increases accordingly. It can be found that the corresponding relationship between the ambient temperature and the fan speed is generally linear. Under the same ambient temperature, the fan speed duty cycle when the smart network card is in the S5 state is higher than the fan speed duty cycle when the OCP network card is in the S5 state. When the ambient temperature rises to 35°C and then increases, the fan speed no longer increases. When the ambient temperature drops to 20°C and then decreases, the fan speed duty cycle no longer decreases. When the ambient temperature is maintained at 25°C, after the power button is pressed, the fan speed duty cycle is increased to 60% duty. When the ambient temperature of the server is increased, the fan speed increases accordingly. It can be found that the corresponding relationship between ambient temperature and fan speed is generally linear, and at the same ambient temperature, the fan speed duty cycle during the boot process is higher than the fan speed duty cycle in the S5 state; when the ambient temperature rises to 35°C and then increases, the fan speed no longer increases, and when the ambient temperature drops to 20°C and then decreases, the fan speed duty cycle no longer decreases. About 1.5 to 3 minutes after pressing the power button, the BIOS Post is completed, and the temperatures of components such as the CPU can be read in the web BMC one after another. The speed during the boot process fails, and the fan speed decreases.

[0184] When both the OCP NIC and the smart NIC are installed in the configuration (the subsequent status description is consistent with the phenomenon of installing the smart NIC in the server), the server is powered on and enters the S5 state. The fan starts to run about 3-5 seconds after power-on. When the ambient temperature is maintained at 25°C, the fan speed duty cycle is 55% duty. When the ambient temperature of the server is increased, the fan speed increases accordingly. It can be found that the corresponding relationship between the ambient temperature and the fan speed is generally linear. Under the same ambient temperature, the fan speed duty cycle of the smart NIC in the S5 state is higher than that of the OCP NIC in the S5 state. When the ambient temperature rises to 35°C and then increases, the fan speed no longer increases. When the ambient temperature drops to 20°C and then decreases, the fan speed duty cycle no longer decreases. When the ambient temperature is maintained at 25°C, after the power button is pressed, the fan speed duty cycle is increased to 60% duty. When the ambient temperature of the server is increased, the fan speed increases accordingly. It can be found that the corresponding relationship between ambient temperature and fan speed is generally linear, and at the same ambient temperature, the fan speed duty cycle during the boot process is higher than the fan speed duty cycle in the S5 state; when the ambient temperature rises to 35°C and then increases, the fan speed no longer increases, and when the ambient temperature drops to 20°C and then decreases, the fan speed duty cycle no longer decreases. About 1.5 to 3 minutes after pressing the power button, the BIOS Post is completed, and the temperatures of components such as the CPU can be read in the web BMC one after another. The speed during the boot process fails, and the fan speed decreases.

[0185] It can be seen that RTOS can quickly control the fan and the control is more precise, which greatly reduces the time required for startup and reduces the heat dissipation risk, system power consumption and fan noise during the startup process.

[0186] In an optional example, when the first operating system controls the heat dissipation device, the operating parameters of the scattering device may be, but are not limited to, gradually rising to the operating parameters corresponding to the current temperature parameters, thereby reducing the noise generated by the heat dissipation device after the server is powered on. For example, the first operating system may, but are not limited to, control the operation of the heat dissipation device from the first time after the startup time of the first controller in the following manner: the first operating system determines the heat dissipation operating parameters from the first time; the first operating system controls the operating parameters of the heat dissipation device to rise to the heat dissipation operating parameters at a third time, wherein there is a time interval between the third time and the first time.

[0187] The way in which the operating parameter rises to the heat dissipation operating parameter at the third time may be, but is not limited to, a smooth linear rise, or may be, but is not limited to, a smooth step-wise rise.

[0188] In an optional example, the first operating system can be used but is not limited to control the operating parameters of the heat dissipation device to rise to the heat dissipation operating parameters at the third time in the following manner: the first operating system uses the operating parameters as the starting value as the initial current operating parameters, and repeats the following steps until the operating parameters of the heat dissipation device are the heat dissipation operating parameters: calculate the difference between the heat dissipation operating parameters and the current operating parameters; when the difference is greater than or equal to the step operating parameters, send the next current operating parameters to the heat dissipation device after the target time period, wherein the next current operating parameters are the sum of the current operating parameters and the step operating parameters; when the difference is less than the step operating parameters, send the heat dissipation operating parameters to the heat dissipation device after the target time period.

[0189] Optionally, in this embodiment, the above starting value may be, but not limited to, 0, or may be a smaller value, such as a value less than 5, a value less than 10, etc. The step length operation parameter may be, but not limited to, determined according to specific circumstances, such as, but not limited to, the step length operation parameter may be, but not limited to, 5.

[0190] In an optional example, from the operation of the heat dissipation device, the heat dissipation device can, but is not limited to, operate in accordance with the operating parameters output by the first controller in the following manner: the heat dissipation device operates in accordance with the operating parameters output by the first operating system in the first stage, wherein the first stage is the stage from when the first operating system has completed startup to when the second operating system has completed startup; the heat dissipation device operates in accordance with the operating parameters output by the second operating system in the second stage, wherein the second stage is the stage from when the second operating system has completed startup to when the server has completed startup.

[0191] In an optional example, from the perspective of the operation of the heat dissipation device, the heat dissipation device can, but is not limited to, operate in the first stage according to the operating parameters output by the first operating system in the following manner: the operating parameters of the heat dissipation device rise to the heat dissipation operating parameters determined by the first operating system at a reference time after the start of operation, wherein there is a time interval between the reference time and the first time.

[0192] In an optional example, from the operation of the heat dissipation device, after the first time, the operating parameter of the heat dissipation device starts from the starting value and increases from the current operating parameter to the next current operating parameter every target time period until it increases to the heat dissipation operating parameter; wherein, when the difference between the heat dissipation operating parameter and the current operating parameter is greater than or equal to the step operating parameter, the increase in the operating parameter is the step operating parameter; when the difference between the heat dissipation operating parameter and the current operating parameter is less than the step operating parameter, the increase in the operating parameter is the difference between the heat dissipation operating parameter and the current operating parameter.

[0193] For example, if the first operating system is RTOS and the heat dissipation device is a fan, after AC is powered on, the fan speed starts from 0 duty and increases by 5% duty every 10 seconds. This speed is called "smoothed speed". The "target speed" controlled by RTOS refers to the speed value calculated using the corresponding Inlet curve in the current scenario. When the target speed - smoothed speed ≥ 5%, the smoothed speed is output. When the target speed - smoothed speed < 5%, the smoothed speed at this time is continued for another 10 seconds, and then the fan speed corresponding to the inlet is directly adjusted and output. If the BMC takes over the fan control right to control the fan during the RTOS smoothing process, the BMC will no longer perform the smoothing mechanism and directly output the current target speed.

[0194] In an optional example, a second controller is also deployed on the server, and the second controller can monitor the startup status of the first controller, so as to take over the control of the heat dissipation device in time, and ensure that the heat dissipation device can dissipate heat for the server even if the first controller fails to start successfully. For example: when the server is powered on, the second controller is started; the second controller monitors the startup result of the first controller; when the startup result indicates that the startup of the first controller fails, the second controller identifies the server status of the server; when the server status is identified as a powered-on but not turned-on state, the second controller detects the component status of the server component belonging to the first type on the server, wherein the server component belonging to the first type is a server component that generates heat after the server is powered on; when the component status is detected to indicate that the server component of the first type is configured on the server, the second controller controls the operation of the heat dissipation device according to the eighth operating parameter; when the component status is detected to indicate that the server component of the first type is not configured on the server, the second controller controls the operation of the heat dissipation device according to the ninth operating parameter, wherein the heat dissipation performance of the heat dissipation device corresponding to the ambient temperature of the same server under the eighth operating parameter is higher than the heat dissipation performance of the heat dissipation device corresponding to the ninth operating parameter.

[0195] In this embodiment, the second controller may include, but is not limited to, a complex programmable logic device (CPLD for short).

[0196] In an optional example, from the operation of the heat dissipation device, if a second controller is also deployed on the server, when the server is powered on but not started, and the first controller fails to start, the heat dissipation device starts to run after the second controller is started; when server components belonging to the first type are configured on the server, the heat dissipation device runs according to first preset parameters, wherein the server components belonging to the first type are server components that generate heat after the server is powered on; when server components of the first type are not configured on the server, the heat dissipation device runs according to second preset parameters, wherein the heat dissipation performance of the heat dissipation device corresponding to the first preset parameters is higher than the heat dissipation performance of the heat dissipation device corresponding to the second preset parameters.

[0197] In an optional example, the second controller may also control the heat dissipation device differently according to whether the first type of server components are configured on the server. For example: after the second controller identifies the operating status of the server, when it is identified that the operating status is in the boot-up stage, the second controller detects the component status of the first type of server components on the server; when it is detected that the component status indicates that the first type of server components are configured on the server, the second controller controls the operation of the heat dissipation device according to the tenth operating parameter; when it is detected that the component status indicates that the first type of server components are not configured on the server, the second controller controls the operation of the heat dissipation device according to the eleventh operating parameter, wherein the heat dissipation performance of the heat dissipation device corresponding to the ambient temperature of the same server under the tenth operating parameter is higher than the heat dissipation performance of the heat dissipation device corresponding to the eleventh operating parameter.

[0198] In an optional example, from the perspective of the operation of the heat dissipation device, when the first controller fails to start, the server is in the boot-up stage, and server components belonging to the first type are configured on the server, the heat dissipation device operates according to third preset parameters; when the first controller fails to start, the server is in the boot-up stage, and server components belonging to the first type are not configured on the server, the heat dissipation device operates according to fourth preset parameters, wherein the heat dissipation performance of the heat dissipation device corresponding to the third preset parameters is higher than the heat dissipation performance of the heat dissipation device corresponding to the fourth preset parameters.

[0199] In an optional example, the first controller is connected to the heat dissipation device through the second controller, and the second controller can be used to control the transmission of operating parameters. For example: the second controller checks whether the heartbeat of the first operating system is normal; if the heartbeat of the first operating system is abnormal, check whether the heartbeat of the second operating system is normal; if the heartbeat of the second operating system is abnormal, determine that the first controller fails to start; if the heartbeat of the first operating system is normal, determine that the first controller is successfully started; if the startup result indicates that the first controller fails to start, the second controller discards the operating parameters received from the first controller and identifies the operating status of the server; after the second controller monitors the startup result of the first controller, if the startup result indicates that the first controller is successfully started, the second controller sends the operating parameters received from the first controller to the heat dissipation device.

[0200] Taking the OCP network card and smart network card as the first type of server components, the startup time of the second controller is about 3-5S. When the BMC chip is removed, there is no BMC in the server to control the fan; when the OCP network card, smart network card and other components that need heat dissipation in the S5 state are not installed in the server configuration, the server is powered on and enters the S5 state. The fan does not run. When the ambient temperature of the server is increased or decreased, the fan speed does not change and always maintains at 0 speed. When the ambient temperature remains at 25C, when the power button is pressed, the fan speed duty cycle is increased to 50% duty. When the ambient temperature of the server is increased or decreased, the fan speed does not change. The fan speed duty cycle during the startup process is higher than the fan speed duty cycle in the S5 state. About 5 minutes after pressing the power button, the fan speed is increased to about 80% duty.

[0201] When the BMC chip is removed, there is no BMC in the server for fan control; when the OCP network card is installed in the server configuration, but the smart network card is not installed, the server is powered on and enters the S5 state. The fan starts running about 3-5 seconds after power-on. When the ambient temperature remains at 25°C, the fan speed duty cycle is 45% duty. When the ambient temperature of the server is increased or decreased, the fan speed does not change and always maintains 45% duty. When the ambient temperature remains at 25°C, after pressing the power button (the subsequent state description is consistent with the power-on process phenomenon without the OCP network card in point 5), the fan speed duty cycle is increased to 50% duty. When the ambient temperature of the server is increased or decreased, the fan speed does not change. The fan speed duty cycle during the power-on process is higher than the fan speed duty cycle in the S5 state. About 5 minutes after pressing the power button, the fan speed is increased to about 80% duty.

[0202] When the BMC chip is removed, there is no BMC in the server for fan control; when the OCP network card is not installed in the server configuration, the smart network card is installed, and the server is powered on, the server enters the S5 state, and the fan starts to run about 3-5 seconds after power-on. When the ambient temperature remains at 25C, the fan speed duty cycle is 55% duty. When the ambient temperature of the server is increased or decreased, the fan speed does not change and always maintains 55% duty. When the ambient temperature remains at 25C, when the power button is pressed, the fan speed duty cycle is increased to 60% duty. When the ambient temperature of the server is increased or decreased, the fan speed does not change. The fan speed duty cycle during the power-on process is higher than the fan speed duty cycle in the S5 state. About 5 minutes after pressing the power button, the fan speed is increased to about 80% duty.

[0203] When the BMC chip is removed, there is no BMC in the server for fan control; when both the OCP network card and the smart network card are installed in the server configuration (the subsequent status description is consistent with the boot process phenomenon of the smart network card installed without the OCP network card installed in point 7), the server is powered on and enters the S5 state. The fan starts running about 3-5 seconds after power-on. When the ambient temperature remains at 25°C, the fan speed duty cycle is 55% duty. When the ambient temperature of the server is increased or decreased, the fan speed does not change and always maintains a speed of 55% duty. When the ambient temperature remains at 25°C, when the power button is pressed, the fan speed duty cycle is increased to 60% duty. When the ambient temperature of the server is increased or decreased, the fan speed does not change. The fan speed duty cycle during the boot process is higher than the fan speed duty cycle in the S5 state. About 5 minutes after the power button is pressed, the fan speed is increased to about 80% duty.

[0204] In an optional implementation, taking the case where the first controller is a BMC, the first operating system is an RTOS, the second operating system is Linux (representing the BMC), the second controller is a CPLD, and the heat dissipation device is a fan as an example, the control and operation of the heat dissipation device of the server in different states are as follows:

[0205] Figure 6 is a schematic diagram of the control and operation of a heat dissipation device according to an embodiment of the present application, such as Figure 6As shown in the figure, after the server is powered on, if the RTOS starts successfully, the RTOS controls the fans and monitors whether the BMC has completed the startup. If the RTOS fails to start successfully, the CPLD controls the fans and monitors whether the BMC has completed the startup. If the BMC has completed the startup, the BMC Linux controls the fans. During the process of the CPLD controlling the fans and monitoring whether the BMC has completed the startup, if the RTOS starts successfully, the CPLD hands over the control of the fans to the RTOS, and the RTOS controls the fans.

[0206] The specific fan control process includes: Figure 7 is a schematic diagram of RTOS control and operation of a heat dissipation device according to an embodiment of the present application, such as Figure 7 As shown in the figure, after the server is powered on, RTOS and CPLD are started first, and CPLD will check whether the heartbeat of RTOS is normal. RTOS takes precedence over CPLD in fan control. When RTOS is successfully started, its corresponding heartbeat signal is started. After CPLD receives the heartbeat signal transmitted by RTOS and it lasts for more than a period of time, it can be determined that RTOS is successfully started, and CPLD does not receive fan control rights. If RTOS is successfully started and successfully takes over the fan control rights, then RTOS will take the lead in fan control. RTOS will differentiate and adjust the speed according to the server status, configuration (i.e. component status), ambient temperature and component temperature of the current server. When RTOS recognizes that the server is in S5 according to the status, it will further distinguish the configuration. By judging whether there are components such as OCP network card and smart network card in the configuration, different ambient temperature curves are called according to the obtained ambient temperature. In addition, RTOS can obtain the component temperature of some components (such as OCP network card temperature) through I2C. After obtaining the temperature, it can perform refined fan control according to PID. When RTOS recognizes that the server is in the boot process based on the status, it further determines the configuration. By judging whether there are components such as smart network cards in the configuration, different ambient temperature curves are called according to the obtained ambient temperature. Compared with the S5 state, RTOS can obtain the core temperatures of more components (such as CPU temperature, memory temperature, PCH temperature, etc.) during the boot process. After obtaining the temperature, fine-grained fan control can be performed according to PID.

[0207] For example, when RTOS identifies that the server is in S5 state based on the status: when there is no OCP network card, smart network card or other components that need heat dissipation in S5 state in the configuration, RTOS calls the Inlet-1 curve to use the ambient temperature for linear speed regulation; when there is an OCP network card in the configuration, RTOS calls the Inlet-2 curve to use the ambient temperature for linear speed regulation, and performs PID speed regulation based on the OCP network card temperature obtained through I2C; when there is a smart network card in the configuration, RTOS calls the Inlet-3 curve to use the ambient temperature for linear speed regulation; when RTOS identifies that the server is in the boot process based on the status: when there is no smart network card in the configuration, RTOS calls the Inlet-4 curve to use the ambient temperature for linear speed regulation, and after the temperatures of components such as CPU and memory can be obtained, PID speed regulation is performed synchronously; when there is a smart network card in the configuration, RTOS calls the Inlet-5 curve to use the ambient temperature for linear speed regulation, and after the temperatures of components such as CPU and memory can be obtained, PID speed regulation is performed synchronously.

[0208] Figure 8 is a schematic diagram of BMC control and operation of a heat dissipation device according to an embodiment of the present application, such as Figure 8 As shown, RTOS performs fan control and checks the BMC status simultaneously. When BMC is started, the heartbeat signal corresponding to BMC starts and lasts for more than a period of time. When RTOS recognizes that the BMC heartbeat is normal, RTOS hands over the fan control to BMC, which performs differentiated speed regulation based on the server status and configuration (i.e., component status) of the current server, the ambient temperature that can be obtained, and the component temperature. When BMC recognizes that the server is in S5, it further distinguishes the configuration, and by judging whether there are components such as OCP network cards and smart network cards in the configuration, different ambient temperature curves are called respectively according to the obtained ambient temperature. Compared with RTOS, BMC supports obtaining the core temperature of more components (such as OCP network card temperature, smart network card temperature, etc.). After obtaining the temperature, fine fan control can be performed according to PID. When the BMC identifies that the server is in the boot process based on the status, it further determines the configuration. By judging whether there are components such as smart network cards in the configuration, different ambient temperature curves are called based on the obtained ambient temperature. Compared with the S5 state, the BMC can obtain the core temperatures of more components (such as CPU temperature, memory temperature, PCH temperature, PCIe card temperature, etc.) during the boot process. After obtaining the temperature, fine-grained fan control can be performed based on PID.

[0209] For example, when the BMC identifies that the server is in S5 state based on the status: when there is no OCP network card, smart network card or other components that need heat dissipation in S5 state in the configuration, the BMC calls the Inlet-1 curve to use the ambient temperature for linear speed regulation; when there is an OCP network card in the configuration, the BMC calls the Inlet-2 curve to use the ambient temperature for linear speed regulation, and performs PID speed regulation based on the OCP network card temperature obtained through I2C; when there is a smart network card in the configuration, the BMC calls the Inlet-3 curve to use the ambient temperature for linear speed regulation, and performs PID speed regulation based on the smart network card temperature obtained through I2C; When the BMC identifies that the server is in the startup process based on the status: when there is no smart network card in the configuration, the BMC calls the Inlet-4 curve to use the ambient temperature for linear speed regulation, and after the temperatures of components such as the CPU, memory, and PCIe network card can be obtained, the PID speed regulation is performed synchronously; when there is a smart network card in the configuration, the BMC calls the Inlet-5 curve to use the ambient temperature for linear speed regulation, and after the temperatures of components such as the CPU, memory, and PCIe network card can be obtained, the PID speed regulation is performed synchronously.

[0210] Fig. 9 is a schematic diagram of CPLD control and operation of a heat dissipation device according to an embodiment of the present application, such as Fig. 9 As shown, 2. After the server is powered on, RTOS and CPLD are started first, and CPLD will check whether the heartbeat of RTOS is normal. If CPLD still cannot detect the RTOS heartbeat within a certain period of time after power-on, CPLD determines that RTOS startup fails, then CPLD takes precedence over RTOS and BMC for fan control. CPLD performs differentiated speed regulation according to the current state and configuration of the server; when CPLD recognizes that the server is in S5 according to the state, it further distinguishes the configuration, and calls different fixed speed values ​​by judging whether there are components such as OCP network cards and smart network cards in the configuration. When CPLD recognizes that the server is in the boot process according to the state, it further distinguishes the configuration, and calls different fixed speed values ​​by judging whether there are components such as smart network cards in the configuration.

[0211] For example: When the CPLD identifies that the server is in S5 state based on the status: When there is no OCP network card, smart network card or other components that need heat dissipation in S5 state in the configuration, the CPLD controls not to power on the fan and the fan speed is 0; ② When there is an OCP network card in the configuration, the CPLD outputs at a fixed speed of 115PWM; when there is a smart network card in the configuration, the CPLD outputs at a fixed speed of 140PWM; When the BMC identifies that the server is in the boot process based on the status: When there is no smart network card in the configuration, the CPLD outputs at a fixed speed of 128PWM; when there is a smart network card in the configuration, the CPLD outputs at a fixed speed of 153PWM.

[0212] CPLD controls the fans and checks the BMC status simultaneously. When the BMC is started, the heartbeat signal of the BMC is started. When CPLD recognizes that the BMC heartbeat is normal and lasts for a period of time, CPLD hands over the fan control to BMC. BMC performs differentiated speed regulation based on the current server status and configuration, and the component temperature that can be obtained.

[0213] CPLD performs fan control. When it detects that the BMC still has no heartbeat, it further checks the heartbeat of the RTOS. If it detects that the RTOS heartbeat is normal and lasts for more than a period of time, the CPLD transfers the fan control to the RTOS. The RTOS performs differentiated speed regulation based on the current server status, configuration, and component temperature that can be obtained.

[0214] The CPLD performs fan control. If it detects that the BMC still has no heartbeat and the RTOS has no heartbeat, the CPLD continues to maintain fan control.

[0215] In summary, BMC can obtain more component temperatures for fan control, the control logic is more complex, and the fan control is more refined. However, the BMC startup time is long, and it cannot be started and fan control is performed in a short time; RTOS can be started and fan control is performed in a short time, and it can obtain the ambient temperature and the temperature of some core components, and can achieve some fine speed regulation; CPLD can be started and monitor the BMC startup results and take over the fan control in a short time. Through the synergy of RTOS, CPLD, and BMC, it can not only ensure the fast and stable startup of the server, but also ensure that the server can achieve the most refined fan control at different stages, ensure that each component does not overheat and runs at high performance, and ensure that the system noise and fan power consumption are reduced.

[0216] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0217] In this embodiment, a control device for a heat dissipation device on a server is also provided. The server includes: a server component, a first controller and a heat dissipation device. A first operating system and a second operating system are deployed on the first controller. The device is used to implement the above-mentioned embodiments and preferred implementation modes. The descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0218] Fig.10 is a structural block diagram of a control device for a heat dissipation device on a server according to an embodiment of the present application, such as Fig.10 As shown, the device comprises:

[0219] A startup module 1002, used for starting the first controller when the server is powered on;

[0220] The first control module 1004 is configured to control the operation of the heat dissipation device by the first operating system starting from a first time after the start time of the first controller, wherein the first time is the time when the first operating system completes the start-up; and stop controlling the operation of the heat dissipation device by the first operating system at a second time after the first time, wherein the second time is the time when the second operating system completes the start-up;

[0221] The second control module 1006 is used to control the operation of the heat dissipation device starting from a second time by a second operating system.

[0222] The control device of the heat dissipation device on the server is also used to execute the steps in any of the above method embodiments.

[0223] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0224] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0225] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0226] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0227] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0228] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.

[0229] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0230] An embodiment of the present application also provides a computer program, which includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in any one of the above method embodiments.

[0231] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0232] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0233] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for controlling a heat dissipation device on a server, characterized in that: The server includes: a server component, a first controller and a heat dissipation device, a first operating system and a second operating system are deployed on the first controller, and the method includes: The first controller starts to start when the server is powered on; The first operating system controls the operation of the heat dissipation device from a first time after the startup time of the first controller, wherein the first time is the time when the first operating system completes startup; The first operating system stops controlling the operation of the heat dissipation device at a second time after the first time, wherein the second time is the time when the second operating system completes startup; The second operating system controls the operation of the heat dissipation device starting from the second time.

2. The method according to claim 1, characterized in that The controlling, by the first operating system, of the operation of the heat dissipation device from a first time after the start time of the first controller includes: When the first operating system has been started and the server has not been started, the first operating system controls the operation of the heat dissipation device according to the server status of the server, the component status of the server component, the component temperature of the server component and the ambient temperature of the server; The first operating system detects the system status of the second operating system.

3. The method according to claim 2, characterized in that The first operating system stopping controlling the operation of the heat dissipation device at a second time after the first time includes: When it is detected that the system status is a status of having completed startup, and the server has not completed startup, the first operating system determines that the second time has arrived; The first operating system stops controlling the operation of the heat dissipation device.

4. The method according to claim 1, characterized in that: The controlling the heat dissipation device to run starting from the second time by the second operating system includes: After the second operating system is started, it starts to control the operation of the heat dissipation device according to the server status of the server, the component status of the server component, the component temperature of the server component and the ambient temperature of the server.

5. The method according to claim 2 or 4, characterized in that: The controlling the operation of the heat dissipation device according to the server state of the server, the component state of the server component, the component temperature of the server component and the ambient temperature of the server includes: detecting a server status of the server; In a case where the server status is used to indicate that the server has been powered on but not turned on, controlling the operation of the heat dissipation device according to the component status of the server component belonging to the first type among the server components, the component temperature of the server component belonging to the first type, and the ambient temperature of the server, wherein the server component belonging to the first type is a server component that generates heat after the server is powered on; In a case where the server status is used to indicate that the server is in the process of booting up, the operation of the cooling device is controlled according to the component status of the server component belonging to the first type among the server components, the component temperature of the server component belonging to the second type, and the ambient temperature of the server, wherein the server component belonging to the second type is a server component that allows the operating system controlling the cooling device to obtain the component temperature during the server booting up process.

6. The method according to claim 5, characterized in that The first controller is also configured with a first heat dissipation curve and a first heat dissipation configuration, wherein the first heat dissipation curve is used to indicate a first conversion relationship between an ambient temperature of the server and an operating parameter of the heat dissipation device, and the first heat dissipation configuration is used to indicate a parameter configuration in an operating parameter algorithm corresponding to a server component belonging to a first type, and the operating parameter algorithm is used to calculate the operating parameter of the heat dissipation device according to the component temperature of the server component; The controlling the operation of the heat dissipation device according to the component status of the server component belonging to the first type among the server components, the component temperature of the server component belonging to the first type and the ambient temperature of the server comprises: detecting, on the server, a component status of a server component belonging to a first type; In a case where it is detected that the component state of the server component belonging to the first type indicates that the server component belonging to the first type is configured on the server, calling the first heat dissipation curve to convert the ambient temperature of the server into a first operating parameter, and calling the first heat dissipation configuration to calculate a second operating parameter according to the component temperature of the server component belonging to the first type; determining a target operating parameter according to the first operating parameter and the second operating parameter; The operation of the heat dissipation device is controlled according to the target operating parameters.

7. The method according to claim 6, characterized in that The server components belonging to the first type include: a plurality of candidate server components, the first heat dissipation curve includes a plurality of heat dissipation curves corresponding to the plurality of candidate server components one by one, and the heat dissipation performance of the heat dissipation device corresponding to the operating parameters on the corresponding heat dissipation curve of the candidate server component with higher operating power consumption under the same ambient temperature of the server is higher; The calling the first heat dissipation curve to convert the ambient temperature of the server into a first operating parameter includes: Determining a target server component configured on the server from the plurality of candidate server components; The target heat dissipation curve corresponding to the target server component is called from the multiple heat dissipation curves to convert the ambient temperature of the server into the first operating parameter.

8. The method according to claim 7, characterized in that The plurality of candidate server components include: an open computing project network card and a smart network card, the plurality of heat dissipation curves include: a first curve corresponding to the open computing project network card and a second curve corresponding to the smart network card, and the heat dissipation performance of the heat dissipation device corresponding to the operating parameters on the first curve under the same ambient temperature of the server is lower than the heat dissipation performance of the heat dissipation device corresponding to the operating parameters on the second curve; The step of calling the target heat dissipation curve corresponding to the target server component from the plurality of heat dissipation curves to convert the ambient temperature of the server into the first operating parameter includes: In a case where the Open Compute Project network card is configured on the server, calling the first curve from the plurality of heat dissipation curves to convert the ambient temperature of the server into a first parameter, wherein the first operating parameter includes the first parameter; When the smart network card is configured on the server, the second curve is called from the multiple heat dissipation curves to convert the ambient temperature of the server into a second parameter, wherein the first operating parameter includes the second parameter.

9. The method according to claim 6, characterized in that The first type of server components includes: a plurality of candidate server components, and the first heat dissipation configuration includes a plurality of heat dissipation configurations corresponding one to one to the plurality of candidate server components; The calling of the first heat dissipation configuration to calculate a second operating parameter according to a component temperature of a server component belonging to the first type includes: Determining a target server component configured on the server from the plurality of candidate server components; The target heat dissipation configuration corresponding to the target server component is called from the multiple heat dissipation configurations to calculate the second operating parameter according to the component temperature of the target server component.

10. The method according to claim 9, characterized in that The plurality of candidate server components include: an open computing project network card and a smart network card, and the plurality of heat dissipation configurations include: a first configuration corresponding to the open computing project network card and a second configuration corresponding to the smart network card; The step of calling the target heat dissipation configuration corresponding to the target server component from the multiple heat dissipation configurations and calculating the second operating parameter according to the component temperature of the target server component includes: In a case where the open computing project network card is configured on the server, calling the first configuration from the plurality of cooling configurations to calculate a third parameter based on a component temperature of the open computing project network card, wherein the second operating parameter includes the third parameter; When the smart network card is configured on the server, the second configuration is called from the multiple heat dissipation configurations to calculate a fourth parameter according to the component temperature of the smart network card, wherein the second operating parameter includes the fourth parameter.

11. The method according to claim 6, characterized in that The operating parameter algorithm is used to calculate the operating parameters of the heat dissipation device according to the component temperature of the server component at the sampling time, the component temperature at the historical time and the operating parameters corresponding to the historical sampling time; The calling of the first heat dissipation configuration to calculate a second operating parameter according to a component temperature of a server component belonging to the first type includes: Calling the first heat dissipation configuration and substituting it into the operating parameter algorithm to obtain a target operating parameter algorithm; Obtaining a first component temperature of a server component belonging to the first type at a sampling moment, a second component temperature at a historical moment, and a historical operating parameter corresponding to the historical sampling moment, wherein the historical operating parameter is an operating parameter corresponding to the server component belonging to the first type calculated by the operating parameter algorithm at the historical sampling moment; Substituting the first component temperature, the second component temperature and the historical operating parameters into the target operating parameter algorithm to obtain the second operating parameter.

12. The method according to claim 6, characterized in that After detecting the component status of the server component belonging to the first type on the server, the method further comprises: In a case where it is detected that the component status of the server component belonging to the first type indicates that the server component belonging to the first type is not configured on the server, the heat dissipation device does not operate.

13. The method according to claim 6, characterized in that The first controller is also configured with a second heat dissipation curve, which is used to indicate a second conversion relationship between the ambient temperature of the server and the operating parameters of the heat dissipation device, and the heat dissipation performance of the heat dissipation device corresponding to the operating parameters under the first conversion relationship for the same ambient temperature of the server is higher than the heat dissipation performance of the heat dissipation device corresponding to the operating parameters under the second conversion relationship; After detecting the component status of the server component belonging to the first type on the server, the method further comprises: In a case where it is detected that the component state of the server component belonging to the first type indicates that the server component belonging to the first type is not configured on the server, calling the second heat dissipation curve to convert the ambient temperature of the server into a third operating parameter; The heat dissipation device is controlled to operate according to the third operating parameter.

14. The method according to claim 6, characterized in that In a case where the operating system controlling the heat dissipation device is the first operating system, calling the first heat dissipation curve to convert the ambient temperature of the server into a first operating parameter, and calling the first heat dissipation configuration to calculate a second operating parameter according to a component temperature of a server component belonging to the first type, includes: During the process of the second operating system being started, the second operating system collects the ambient temperature of the server and the temperature of the component of the first type of server component; The second operating system sends the collected ambient temperature of the server and the temperature of the component of the server component belonging to the first type to the first operating system; The first operating system calls the first heat dissipation curve to convert the ambient temperature of the server into a first operating parameter, and the first operating system calls the first heat dissipation configuration to calculate a second operating parameter according to the component temperature of the server component belonging to the first type.

15. The method according to claim 14, characterized in that The server is also deployed with a target storage space, the target storage space is accessible to the first operating system and the second operating system, and the second operating system sends the collected ambient temperature of the server and the temperature of the component of the server component belonging to the first type to the first operating system, including: The second operating system writes the collected ambient temperature of the server and the component temperature of the server component belonging to the first type into the target storage space; The second operating system sends an interrupt request to the first operating system; The first operating system responds to the interrupt request and reads the ambient temperature of the server and the component temperature of the server component belonging to the first type from the target storage space.

16. The method according to claim 5, characterized in that The first controller is also configured with a third heat dissipation curve, a fourth heat dissipation curve and a second heat dissipation configuration, wherein the third heat dissipation curve is used to indicate a third conversion relationship between the ambient temperature of the server and the operating parameters of the heat dissipation device, and the fourth heat dissipation curve is used to indicate a fourth conversion relationship between the ambient temperature of the server and the operating parameters of the heat dissipation device, and the heat dissipation performance of the heat dissipation device corresponding to the operating parameters under the third conversion relationship for the same ambient temperature of the server is higher than the heat dissipation performance of the heat dissipation device corresponding to the operating parameters under the fourth conversion relationship, and the second heat dissipation configuration is used to indicate a parameter configuration in an operating parameter algorithm corresponding to a server component belonging to the second type; The controlling the operation of the heat dissipation device according to the component status of the server component belonging to the first type among the server components, the component temperature of the server component belonging to the second type and the ambient temperature of the server comprises: detecting, on the server, a component status of a server component belonging to a first type; In the case where it is detected that the component state indicates that the server component of the first type is configured on the server, converting the ambient temperature of the server into a fourth operating parameter, and calling the second heat dissipation configuration to calculate a fifth operating parameter according to the component temperature of the server component belonging to the second type; determining a reference operating parameter according to the fourth operating parameter and the fifth operating parameter; and controlling the operation of the heat dissipation device according to the reference operating parameter; In a case where it is detected that the component status indicates that the first type of server component is not configured on the server, the fourth heat dissipation curve is called to convert the ambient temperature of the server into a sixth operating parameter, and the second heat dissipation configuration is called to calculate a seventh operating parameter based on the component temperature of the second type of server component; device operating parameters are determined based on the sixth operating parameters and the seventh operating parameters; and the operation of the heat dissipation device is controlled according to the device operating parameters.

17. The method according to claim 1, characterized in that The controlling, by the first operating system, of the operation of the heat dissipation device from a first time after the start time of the first controller includes: Determining, by the first operating system, heat dissipation operating parameters starting from the first time; The first operating system controls the operating parameters of the heat dissipation device to rise to the heat dissipation operating parameters at a third time, wherein there is a time interval between the third time and the first time.

18. The method according to claim 17, characterized in that The step of controlling the operating parameter of the heat dissipation device by the first operating system to rise to the heat dissipation operating parameter at a third time includes: The first operating system uses the operating parameter as a starting value as the initial current operating parameter and repeatedly performs the following steps until the operating parameter of the heat dissipation device is the heat dissipation operating parameter: Calculating the difference between the heat dissipation operating parameter and the current operating parameter; When the difference is greater than or equal to the step length operating parameter, sending a next current operating parameter to the heat dissipation device after a target time period, wherein the next current operating parameter is the sum of the current operating parameter and the step length operating parameter; In a case where the difference is smaller than the step length operating parameter, the heat dissipation operating parameter is sent to the heat dissipation device after the target time period.

19. The method according to claim 1, characterized in that A second controller is also deployed on the server, and the method further includes: When the server is powered on, the second controller is started; The second controller monitors the startup result of the first controller; In a case where the startup result indicates that the first controller fails to start, the second controller identifies a server status of the server; In the case of identifying that the server state is powered on but not turned on, the second controller detects the component state of a server component belonging to a first type on the server, wherein the server component belonging to the first type is a server component that generates heat after the server is powered on; When it is detected that the component state indicates that the server component of the first type is configured on the server, the second controller controls the operation of the heat dissipation device according to an eighth operation parameter; When it is detected that the component status indicates that the first type of server component is not configured on the server, the second controller controls the operation of the cooling device according to a ninth operating parameter, wherein the cooling performance of the cooling device corresponding to the eighth operating parameter for the same ambient temperature of the server is higher than the cooling performance of the cooling device corresponding to the ninth operating parameter.

20. The method according to claim 19, characterized in that After the second controller identifies the operating status of the server, the method further includes: In the case of identifying that the operating state is a state in the booting stage, the second controller detects the component state of the server component belonging to the first type on the server; When it is detected that the component state indicates that the server component of the first type is configured on the server, the second controller controls the operation of the heat dissipation device according to a tenth operation parameter; When it is detected that the component status is used to indicate that the first type of server component is not configured on the server, the second controller controls the operation of the cooling device according to the eleventh operating parameter, wherein the cooling performance of the cooling device corresponding to the tenth operating parameter for the same ambient temperature of the server is higher than the cooling performance of the cooling device corresponding to the eleventh operating parameter.

21. The method according to claim 19, characterized in that The first controller is connected to the heat dissipation device through the second controller; The monitoring of the startup result of the first controller by the second controller includes: the second controller checking whether the heartbeat of the first operating system is normal; if the heartbeat of the first operating system is abnormal, checking whether the heartbeat of the second operating system is normal; if the heartbeat of the second operating system is abnormal, determining that the startup of the first controller fails; if the heartbeat of the first operating system is normal, determining that the startup of the first controller is successful; In the case where the startup result indicates that the first controller fails to start, the second controller identifies the running state of the server, including: in the case where the startup result indicates that the first controller fails to start, the second controller discards the received running parameters sent by the first controller and identifies the running state of the server; After the second controller monitors the startup result of the first controller, the method further includes: when the startup result is used to indicate that the first controller is successfully started, the second controller sends the operating parameters received from the first controller to the heat dissipation device.

22. A control device for a heat dissipation device on a server, characterized in that: The server includes: a server component, a first controller and a heat dissipation device, a first operating system and a second operating system are deployed on the first controller, and the device includes: A startup module, used for the first controller to start starting when the server is powered on; a first control module, configured to control the operation of the heat dissipation device by the first operating system starting from a first time after the startup time of the first controller, wherein the first time is the time when the first operating system completes startup; and stop controlling the operation of the heat dissipation device by the first operating system at a second time after the first time, wherein the second time is the time when the second operating system completes startup; The second control module is used to control the operation of the heat dissipation device starting from the second time by the second operating system.

23. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of the method described in any one of claims 1 to 21 when executed by a processor.

24. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method described in any one of claims 1 to 21 are implemented.

25. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 21 are implemented.

Images