Risk disposal system and method, storage medium and electronic equipment

Abstract

The embodiment of the invention provides a risk disposal system and method, a storage medium and electronic equipment, the risk disposal system comprises a substrate management controller, a liquid cooling control card connected with the substrate management controller, and a liquid cooling sensor connected with the liquid cooling control card, the monitoring module is used for monitoring operation data of a target component; the liquid cooling control card is used for acquiring the operation data monitored by the liquid cooling sensor under the condition of receiving a monitoring signal sent by the substrate management controller, and sending the operation data to the substrate management controller; the baseboard management controller calculates the operation state of the target component according to the operation data; and performing risk pre-judgment on the target component according to the running state, and performing risk disposal on the target component according to a pre-judgment result of the risk pre-judgment.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computers, and more specifically, to a risk management system and method, a storage medium, and an electronic device. Background Art

[0002] At present, in order to solve the leakage problem of cold plate liquid cooling, negative pressure cold plate liquid cooling technology has been proposed. The internal pressure of the circulation pipeline is lower than the external atmospheric pressure. When the pipeline is damaged, the liquid will not flow out of the pipeline. Instead, the external gas will enter the pipeline. Although the negative pressure cold plate liquid cooling technology will not have leakage problems, the gas entering the cooling cycle through the damaged part of the pipeline will destroy the continuity of the liquid flow, resulting in a decrease in the liquid cooling heat dissipation effect, and may even form air blockage or damage the cooling equipment at the far end. The reduction in pressure in the system will reduce the boiling point of the coolant. When the pressure is too low, cavitation may occur, impacting the circulation pipeline or cooling equipment. In addition, for negative pressure liquid cooling, the air intake caused by pipeline damage cannot be known. Therefore, there is a lack of effective pipeline damage detection means. That is, the relevant technology lacks a system that effectively monitors the operating data of the liquid cooling server and performs risk prediction and risk disposal based on the operating data. Risk prediction and risk disposal, for example: risk prediction and risk disposal of air intake problems caused by pipeline damage.

[0003] Therefore, the problem in related technologies of lack of a system for effectively monitoring the operating data of liquid-cooled servers and predicting and handling risks based on the operating data has not yet been effectively solved. Summary of the invention

[0004] The embodiments of the present application provide a risk management system and method, a storage medium and an electronic device to at least solve the problem in the related art that there is a lack of a system that effectively monitors the operating data of a liquid-cooled server and performs risk prediction and risk management based on the operating data.

[0005] According to one embodiment of the present application, a risk management system is provided, the system comprising: a baseboard management controller, a liquid cooling control card connected to the baseboard management controller, and a liquid cooling sensor connected to the liquid cooling control card, wherein: the liquid cooling sensor is used to monitor the operating data of a target component; the liquid cooling control card is used to obtain the operating data monitored by the liquid cooling sensor upon receiving a monitoring signal sent by the baseboard management controller, and send the operating data to the baseboard management controller; the baseboard management controller calculates the operating status of the target component according to the operating data; and performs risk prediction on the target component according to the operating status, and performs risk management on the target component according to the prediction result of the risk prediction.

[0006] In an exemplary embodiment, the baseboard management controller includes: a built-in algorithm module, wherein: the built-in algorithm module is used to determine the temperature change data, pressure difference data and flow control data of the target component within a first time period according to the operating data sent by the liquid cooling controller when the operating data is received, wherein the operating data includes: the temperature data, pressure data and flow data of the target component within the first time period; determine the solenoid valve opening control data corresponding to the target component according to the flow control data, wherein the target component includes: a solenoid valve, and the solenoid valve is used to adjust the flow corresponding to the target component; determine the operating status of the target component according to the temperature change data, the pressure difference data, the flow control data and the solenoid valve opening control data.

[0007] In an exemplary embodiment, the baseboard management controller is further used to: determine that the target component is in a risk-free state when it is determined according to the solenoid valve opening control data that the opening of the solenoid valve corresponding to the target component remains constant within a first time period, and the temperature data and pressure data of the target component within the first time period remain constant; determine that the target component is at risk of overload when the operating state of the target component indicates that the first temperature data of the target component at a first time point is greater than the second temperature data of the target component at a second time point, and the difference between the first temperature data and the second temperature data is greater than a preset temperature difference, wherein the first time period includes: the first time point and the second time point, the first time point being a time point after the second time point; when the operating status of the target component indicates that the pressure difference change value of the target component in the second time period is greater than the preset pressure difference change value, and the flow change difference value of the target component in the second time period is greater than the preset flow change difference value, it is determined that the target component has a leakage risk, wherein the first time period includes: the second time period; when the operating status of the target component indicates that the pressure data and / or flow data of the target component cannot be obtained within a third time period, it is determined that the target component has a component damage risk, wherein the first time period includes: the third time period.

[0008] In an exemplary embodiment, the baseboard management controller is further used to: determine the overload risk level of the target component when it is determined that the target component has an overload risk, and send an opening control signal to the liquid cooling control card according to the overload risk level, so that the liquid cooling control card sends the opening control signal to the solenoid valve in the target component, and adjusts the opening of the solenoid valve of the target component according to the overload risk level, wherein the solenoid valve is used to adjust the flow corresponding to the target component, and the solenoid valve opening of the target component corresponding to different overload risk levels is different, and the flow corresponding to the target component is proportional to the temperature of the target component; when it is determined that the target component has a leakage risk, send a closing signal to the liquid cooling control card, so that the liquid cooling control card sends the closing signal to the solenoid valve to close the solenoid valve of the target component; when it is determined that the target component has a component damage risk, send an alarm signal to the liquid cooling control card, so that the liquid cooling control card sends the alarm signal to the target component and controls the target component to stop working.

[0009] In an exemplary embodiment, the baseboard management controller is also used to: when the first component temperature of the target component is greater than or equal to the first temperature threshold, determine that the overload risk level of the target component is a first-level overload risk level, and adjust the heat dissipation level corresponding to the target component to the first heat dissipation level, wherein the first heat dissipation level includes: determining whether the second component temperature of other components is greater than the first temperature threshold, the number of components and the server temperature corresponding to the server, wherein the server includes: the target component and the other components; when it is determined that the number of components is greater than or equal to the first preset number of components, or when it is determined that the server temperature is greater than or equal to the second temperature threshold, regulating the server to a liquid cooling and air cooling mixed state to dissipate heat for the target component; when it is determined that the number of components is less than When the first preset component quantity is greater than the second preset component quantity, and when it is determined that the server temperature is less than the second temperature threshold, the server is adjusted to a liquid cooling state to dissipate heat for the target component; when the first component temperature of the target component is less than the first temperature threshold, the overload risk level of the target component is set to a second overload risk level, and the heat dissipation level corresponding to the target component is adjusted to a second heat dissipation level, wherein the first overload risk level is greater than the second overload risk level, the heat dissipation intensity corresponding to the first heat dissipation level is greater than the heat dissipation intensity corresponding to the second heat dissipation level, and the second heat dissipation level includes: when it is determined that the first component temperature of the target component is less than the first temperature threshold, the server is adjusted to an air cooling state to dissipate heat for the target component.

[0010] In an exemplary embodiment, the baseboard management controller is further used to: determine whether the target component still faces the overload risk when the target component is cooled according to the first heat dissipation level; and if it is determined that the target component still faces the overload risk, reduce the coolant temperature of the coolant corresponding to the target component to dissipate heat for the target component.

[0011] In an exemplary embodiment, the baseboard management controller is further used to: when it is determined that multiple components are at risk of overload, determine the maximum temperature and the minimum temperature of each of the multiple components; evaluate the heat dissipation load state of each component according to the maximum temperature and the minimum temperature; sort the heat dissipation requirements of each component according to the heat dissipation load state of each component; and perform heat dissipation processing on each component according to the arrangement order of the multiple components.

[0012] According to another embodiment of the present application, a risk management method is provided, including: monitoring operating data of a target component; acquiring the monitored operating data when a monitoring signal is received; calculating an operating state of the target component based on the operating data, and performing risk prediction on the target component based on the operating state, and performing risk management on the target component based on a prediction result of the risk prediction.

[0013] 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 in the above method embodiment when running.

[0014] 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 the above method embodiment.

[0015] 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 the above method embodiment are implemented.

[0016] The risk disposal system of the present application includes a baseboard management controller, a liquid cooling control card connected to the baseboard management controller, and a liquid cooling sensor connected to the liquid cooling control card, wherein: the liquid cooling sensor is used to monitor the operating state of the target component, and the liquid cooling control card is used to obtain the operating data of the target component monitored by the liquid cooling sensor when receiving the monitoring signal sent by the baseboard management controller, and send the obtained operating data to the baseboard management controller. Then the baseboard management controller can calculate the operating state of the target component according to the received operating data, and can prejudge the risk of the target component according to the operating state of the target component, and then treat the risk of the target component according to the result of the risk prejudgment. That is to say, the risk disposal system of the present application can not only monitor and obtain the operating data of the target component, but also determine the operating state of the target component according to the operating data, and then prejudge and treat the risk of the target component according to the operating state. Through the embodiments of the present application, the problem of the lack of a system for effectively monitoring the operating data of the liquid cooling server and prejudging and treating the risk according to the operating data in the related art can be solved. The risk management system of the present application integrates monitoring and obtaining the operating data of the target components, determining the operating status of the target components, and performing risk prediction and risk management on the target components based on the operating status. It can realize effective monitoring and risk prediction of the target components, and timely perform risk management on the target components. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a structural block diagram of a risk management system according to an embodiment of the present application;

[0018] Figure 2 It is a system block diagram of a cooling monitoring and flow control system for a liquid-cooled server according to an optional embodiment of the present application;

[0019] Figure 3 It is a flow chart of a cooling monitoring and flow control method of a liquid-cooled server in an optional embodiment of the present application;

[0020] Figure 4 It is a hardware structure block diagram of a computer terminal of a risk handling method in an embodiment of the present application;

[0021] Figure 5 It is a flow chart of a risk management method according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0023] 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.

[0024] In this embodiment, a risk management system is provided. Figure 1 is a structural block diagram of a risk management system according to an embodiment of the present application, such as Figure 1 As shown: The system includes: a baseboard management controller 12, a liquid cooling control card 14 connected to the baseboard management controller, and a liquid cooling sensor 16 connected to the liquid cooling control card, wherein:

[0025] The liquid cooling sensor 16 is used to monitor the operating data of the target component;

[0026] The liquid cooling sensor is used to monitor the data of the target component, and the target component may be each component in the liquid cooling server.

[0027] The liquid cooling control card 14 is used to obtain the operation data monitored by the liquid cooling sensor and send the operation data to the baseboard management controller when receiving the monitoring signal sent by the baseboard management controller;

[0028] Among them, the liquid cooling control card is used to acquire data from the target component.

[0029] The baseboard management controller 12 calculates the operating status of the target component according to the operating data; and performs risk prejudgment on the target component according to the operating status, and performs risk disposal on the target component according to the prediction result of the risk prejudgment.

[0030] Among them, the baseboard management controller is used to calculate the operating status of the target component, and to predict and deal with the risks of the target component.

[0031] The risk disposal system of the present application includes a baseboard management controller, a liquid cooling control card connected to the baseboard management controller, and a liquid cooling sensor connected to the liquid cooling control card, wherein: the liquid cooling sensor is used to monitor the operating state of the target component, and the liquid cooling control card is used to obtain the operating data of the target component monitored by the liquid cooling sensor when receiving the monitoring signal sent by the baseboard management controller, and send the obtained operating data to the baseboard management controller. Then the baseboard management controller can calculate the operating state of the target component according to the received operating data, and can prejudge the risk of the target component according to the operating state of the target component, and then treat the risk of the target component according to the result of the risk prejudgment. That is to say, the risk disposal system of the present application can not only monitor and obtain the operating data of the target component, but also determine the operating state of the target component according to the operating data, and then prejudge and treat the risk of the target component according to the operating state. Through the embodiments of the present application, the problem of the lack of a system for effectively monitoring the operating data of the liquid cooling server and prejudging and treating the risk according to the operating data in the related art can be solved. The risk management system of the present application integrates monitoring and obtaining the operating data of the target components, determining the operating status of the target components, and performing risk prediction and risk management on the target components based on the operating status. It can realize effective monitoring and risk prediction of the target components, and timely perform risk management on the target components.

[0032] Optionally, the above-mentioned baseboard management controller includes: a built-in algorithm module, wherein: the built-in algorithm module is used to determine the temperature change data, pressure difference data and flow control data of the target component within a first time period according to the operating data when receiving the operating data sent by the liquid cooling controller, wherein the operating data includes: the temperature data, pressure data and flow data of the target component within the first time period; determine the solenoid valve opening control data corresponding to the target component according to the flow control data, wherein the target component includes: a solenoid valve, and the solenoid valve is used to adjust the flow corresponding to the target component; determine the operating status of the target component according to the temperature change data, the pressure difference data, the flow control data and the solenoid valve opening control data.

[0033] It can be understood that the baseboard management controller in the embodiment of the present application further includes: a built-in algorithm module, wherein the built-in algorithm module can calculate the operating state of the target component according to the received operating data of the target component, specifically:

[0034] When the temperature data, pressure data, and flow data of the target component in the first time period are obtained, the stability change data, pressure difference data, and flow control data of the target component can be determined based on the temperature data, pressure data, and flow data, and then the solenoid valve opening control data of the target component can be determined based on the flow control data. Among them, there may be a temperature sensor at the entrance of the target component, that is, the temperature data of the target component can also be directly obtained through the temperature sensor of the target component. Furthermore, the operating state of the target component can be determined based on the temperature change data, pressure difference data, flow control data, and solenoid valve opening control data of the target component.

[0035] The solenoid valve opening control data is control data sent by the baseboard management controller when the solenoid valve opening needs to be controlled.

[0036] According to the embodiment of the present application, based on the built-in algorithm module, the operating status of the target component is determined according to the operating data of the target component, so that the built-in algorithm module can monitor the temperature, flow and pressure data of the target component in real time to ensure that the operating status of the server is always within a controllable range, and then it can be determined in time whether the operating status of the target component is normal to ensure the stability of the liquid-cooled server.

[0037] Optionally, the baseboard management controller is further used to: determine that the target component is in a risk-free state when it is determined according to the solenoid valve opening control data that the opening of the solenoid valve corresponding to the target component remains constant within a first time period, and the temperature data and pressure data of the target component within the first time period remain constant; determine that the target component is at risk of overload when the operating state of the target component indicates that the first temperature data of the target component at a first time point is greater than the second temperature data of the target component at a second time point, and the difference between the first temperature data and the second temperature data is greater than a preset temperature difference, wherein the first time period includes: the first time point and the second time point, the first time point being a time point after the second time point; when the operating status of the target component indicates that the pressure difference change value of the target component in the second time period is greater than the preset pressure difference change value, and the flow change difference value of the target component in the second time period is greater than the preset flow change difference value, it is determined that the target component has a leakage risk, wherein the first time period includes: the second time period; when the operating status of the target component indicates that the pressure data and / or flow data of the target component cannot be obtained within a third time period, it is determined that the target component has a component damage risk, wherein the first time period includes: the third time period.

[0038] It is understandable that the baseboard management controller can also be used to pre-judge the risk of the target component according to the operating status of the target component, and the target component can be divided into several situations: no risk, overload risk, leakage risk and component damage risk. Specifically:

[0039] When the opening of the solenoid valve remains unchanged and the temperature data and pressure data remain constant within the first time period (that is, the changes in the temperature data and pressure data within the first time period are less than the preset temperature change range and the preset pressure change range), it can be determined that the target component is in a risk-free state.

[0040] When it is determined that the first temperature data of the target component at the first time point is greater than the second temperature data at the second time point, and the difference between the first temperature data and the second temperature data is greater than the preset temperature difference (i.e., the temperature of the target component increases dramatically in a short period of time), it can be determined that the target component is in an overload risk state.

[0041] When it is determined that the pressure difference change value of the target component in the second time period is greater than the preset pressure difference change value, and the flow change difference value is greater than the preset flow change difference value, it can be determined that the target component has a leakage risk.

[0042] The pressure difference refers to the difference between the pressure values ​​measured by the two solenoid valves. In general, it is assumed that the pressure in the pipeline is equal everywhere, so the pressure difference is 0. After adjusting the opening of the solenoid valve, the pressure may be affected, and the pressure values ​​obtained by the two solenoid valves are different. At this time, if there is no leakage or air intake in the pipeline, there may be a stable pressure difference. If there is a leak or air intake, the pressure difference value changes. If the liquid in the pipeline leaks to the outside, the downstream pressure is less than the upstream pressure, and the downstream flow rate decreases. If the gas enters the negative pressure pipeline, the downstream pressure is greater than the upstream pressure, and the flow rate increases.

[0043] In the case where it is determined that the pressure data and / or flow data of the target component cannot be obtained, it can be determined that there is a risk of component damage to the target component.

[0044] By predicting the risks of target components based on their operating status, the reliability and stability of liquid-cooled servers can be improved, the risk of failure can be reduced, and the performance and efficiency of the system can be improved.

[0045] Optionally, the baseboard management controller is further used to: when it is determined that the target component has an overload risk, determine the overload risk level of the target component, and send an opening control signal to the liquid cooling control card according to the overload risk level, so that the liquid cooling control card sends the opening control signal to the solenoid valve in the target component, and adjusts the opening of the solenoid valve of the target component according to the overload risk level, wherein the solenoid valve is used to adjust the flow corresponding to the target component, and the opening of the solenoid valve of the target component corresponding to different overload risk levels is different, and the flow corresponding to the target component is proportional to the temperature of the target component; when it is determined that the target component has a leakage risk, send a closing signal to the liquid cooling control card, so that the liquid cooling control card sends the closing signal to the solenoid valve to close the solenoid valve of the target component; when it is determined that the target component has a component damage risk, send an alarm signal to the liquid cooling control card, so that the liquid cooling control card sends the alarm signal to the target component and controls the target component to stop working.

[0046] It can be understood that the flow rate corresponding to the target component is proportional to the temperature of the target component, which means that the higher the temperature of the target component, the larger the flow rate corresponding to the target component is when the opening of the solenoid valve is adjusted. Similarly, when the flow rate is large, the temperature corresponding to the target component will be lower after the opening of the solenoid valve is adjusted to reduce the flow rate.

[0047] Optionally, the baseboard management controller is further used to: when the first component temperature of the target component is greater than or equal to a first temperature threshold, determine that the overload risk level of the target component is a first-level overload risk level, and adjust the heat dissipation level corresponding to the target component to a first heat dissipation level, wherein the first heat dissipation level includes: determining whether the second component temperature of other components is greater than the first temperature threshold, the number of components and the server temperature corresponding to the server, wherein the server includes: the target component and the other components; when it is determined that the number of components is greater than or equal to the first preset number of components, or when it is determined that the server temperature is greater than or equal to the second temperature threshold, regulating the server to a liquid cooling and air cooling mixed state to dissipate heat for the target component; when it is determined that the number of components is less than the first When the number of preset components is greater than the second preset number of components, and when it is determined that the temperature of the server is less than the second temperature threshold, the server is adjusted to a liquid cooling state to dissipate heat for the target component; when the temperature of the first component of the target component is less than the first temperature threshold, the overload risk level of the target component is set to a second overload risk level, and the heat dissipation level corresponding to the target component is adjusted to a second heat dissipation level, wherein the first overload risk level is greater than the second overload risk level, the heat dissipation intensity corresponding to the first heat dissipation level is greater than the heat dissipation intensity corresponding to the second heat dissipation level, and the second heat dissipation level includes: when it is determined that the temperature of the first component of the target component is less than the first temperature threshold, the server is adjusted to an air cooling state to dissipate heat for the target component.

[0048] It is understandable that the baseboard management controller can also be used to perform a series of risk disposal based on the risk prediction of the target component, that is, through the risk prediction of the target component, it can be determined that the target component may have overload risk, leakage risk and component damage risk, etc. Different risk disposal measures can be taken for different risks, specifically:

[0049] For overload risk, the target component needs to be heat-dissipated. For example, the overload risk level of the target component can be determined, and different heat dissipation treatments can be performed on the target component according to different overload risk levels.

[0050] The cooling state of the server can be adjusted to achieve the effect of cooling the server. The cooling state of the server can be divided into air cooling, liquid cooling, and mixed cooling. The cooling state can be determined based on the real-time temperature and power consumption distribution of the server, or specified by the user corresponding to the server. Set relevant thresholds to distinguish between low temperature and high temperature states, and low power consumption and high power consumption states. Specifically:

[0051] Determining an operating status of a target server and operating statuses of multiple components in the target server;

[0052] When it is determined that the operating state of the target server is a low-temperature and low-power consumption state, determining the cooling state of the target server to be an air-cooling state;

[0053] In the case where it is determined that the operating state of the server is a low temperature state and a first number of components in the target server are in a high power consumption state, determining the cooling state of the target server as a liquid cooling state, wherein the first number is less than a preset number;

[0054] When it is determined that the operating state of the server is a high temperature state, and / or a second number of components in the target server are in a high power consumption state, the cooling state of the target server is determined to be a mixed cooling state, wherein the second number is greater than or equal to the preset number.

[0055] For leakage risks, a closing signal can be sent to the solenoid valve to close the solenoid valve. The power supply to the target component is also cut off, and relevant alarm information is issued. In serious cases, the server containing the target component can be shut down.

[0056] For the risk of component damage, relevant warning information can be issued and the power supply to the target component can be cut off if necessary.

[0057] According to the embodiments of the present application, performing different risk treatments for different risks can improve the stability and durability of the server.

[0058] Optionally, the above-mentioned baseboard management controller is also used to: determine whether the target component still has the overload risk when the target component is cooled according to the first heat dissipation level; when it is determined that the target component still has the overload risk, reduce the coolant temperature of the coolant corresponding to the target component to dissipate heat for the target component.

[0059] It is understandable that, when the first component temperature of the target component is greater than or equal to the first temperature threshold, the target component can be cooled by the heat dissipation measures corresponding to the first heat dissipation level, and if necessary, the initial temperature of the coolant corresponding to the target component can also be cooled. When the first component temperature of the target component is less than the first temperature threshold, the target component can be cooled by the heat dissipation measures corresponding to the second heat dissipation level.

[0060] Through the above technical solution, it can be ensured that the target component can effectively dissipate heat when running under high load.

[0061] Optionally, the above-mentioned baseboard management controller is also used to: when it is determined that multiple components are at risk of overload, determine the maximum temperature and the minimum temperature of each of the multiple components; evaluate the heat dissipation load state of each component according to the maximum temperature and the minimum temperature; sort the heat dissipation requirements of each component according to the heat dissipation load state of each component; and perform heat dissipation processing on each component in turn according to the arrangement order of the multiple components.

[0062] It is understandable that the built-in algorithm module of the baseboard management controller can determine the maximum temperature and the minimum temperature of each component in the multiple components, and then evaluate the heat dissipation load state of each component. The heat dissipation requirements of each component are sorted, and each component is heat-dissipated in the order of arrangement.

[0063] In order to better understand the above-mentioned risk management system, the above-mentioned risk management system is described below in combination with optional embodiments, but it is not used to limit the technical solution of the embodiments of the present application.

[0064] With the development of information technology, the demand for computing power in all walks of life is getting higher and higher. In order to provide higher computing power, the power density of server equipment is getting higher and higher, so the heat dissipation demand per unit volume has soared. In the face of such high heat dissipation demand, traditional air cooling has encountered bottlenecks, and more efficient liquid cooling technology has attracted widespread attention. At present, liquid cooling technology has been widely used in data centers.

[0065] The current liquid cooling heat dissipation is dominated by cold plate liquid cooling. In the server chassis, the heat generated by the chips and electronic devices is taken away by the cooling liquid in the circulating pipe through the efficient heat conduction components, so that the heat is transferred from the hot zone to the remote end, and the coolant is cooled at the remote end. In the cold plate liquid cooling technology, the coolant does not directly contact the chips and components on the motherboard, the installation is easy, the technology is mature, energy-saving and environmentally friendly, and the noise is low. However, the cold plate liquid cooling technology has the problem of coolant leakage. Once the coolant in the circulating pipe enters the electronic components on the motherboard such as the CPU, chipset, etc., the circuit short circuit will damage the electronic components or even the entire server, causing the server to shut down, and in severe cases, the related service functions will be paralyzed. Therefore, in order to prevent the occurrence of the above accidents, a leakage detection circuit can be added to the cold plate liquid cooling server. By regularly detecting the working status of the liquid cooling pipe, the leakage risk can be discovered in time, and the server can be powered off to minimize the adverse effects. However, this method requires winding a detection coil on the outside of the liquid cooling pipe, and the coil is long, which affects the space allocation of the chassis. In addition, the circulation loop is connected in series between the heat-generating components on the motherboard, the line is single, and the heat dissipation effect of the rear components is affected by the heat dissipation of the front components. It is even more impossible to adaptively match the liquid cooling flow according to the power and heat of different components. The liquid cooling has low adjustability and the heat dissipation effect is restricted.

[0066] In view of the problem that the leakage detection coil in the above-mentioned positive pressure cold plate heat dissipation is long and occupies chassis space, and the problem that pipe damage and air intake cannot be effectively detected in negative pressure liquid cooling. The optional embodiment of the present application provides a cooling monitoring and flow control system and device for a liquid-cooled server. It aims to solve the problem that the coolant circulation pipeline in the cold plate heat dissipation in the related technology has a single line, low configurability, and cannot adaptively match the heat distribution. At the same time, the optional embodiment of the present application proposes a risk management plan to deal with the related risks caused by the damage of positive and negative pressure liquid cooling pipelines.

[0067] Figure 2 is a system block diagram of a cooling monitoring and flow control system for a liquid cooling server according to an optional embodiment of the present application, such as Figure 2 As shown:

[0068] The cooling monitoring and flow control system includes: a server baseboard controller (Baseboard Management Controller, referred to as BMC) module (i.e., the baseboard management controller of this application), a liquid cooling control card, a liquid cooling sensor, a server motherboard programmable logic device (Complex Programmable Logic Device, referred to as CPLD) and necessary logic circuits.

[0069] The server BMC module includes: a cooling monitoring or flow control module, which includes: a built-in algorithm and data processing module (i.e., the built-in algorithm module of the present application), a data transfer module, and a signal operation module. The cooling monitoring or flow control module is connected to the liquid cooling control card on the mainboard, sends out a monitoring signal, processes the collected data, and determines the liquid cooling operation status according to the built-in algorithm and data processing module.

[0070] 1) The built-in algorithm and data processing module can calculate the cooling hydraulic pressure and flow rate. At the same time, artificial intelligence (AI) algorithms are used to analyze data and predict risks. AI algorithms can be implemented by hardware or software.

[0071] 2) The data transfer module is used to temporarily store transfer data and is connected to the internal storage device of the BMC module.

[0072] 3) The signal operation module is used to generate monitoring signals, data collection signals, risk disposal signals, etc., or receive corresponding response signals.

[0073] The built-in algorithm and data processing module calculates the stability of the liquid cooling pipeline pressure over time and compares the upstream and downstream flow rates of the pipeline to assess whether the pipeline is leaking or damaged.

[0074] The liquid cooling control card is connected to the liquid cooling sensor, executes the signal of the cooling monitoring module, monitors the sensor status, and collects the pressure and flow data measured by the sensor in the liquid cooling circulation pipeline.

[0075] The voltage required by the liquid cooling control card and the liquid cooling sensor can be provided by the server mainboard CPLD.

[0076] The server mainboard CPLD is connected to the liquid cooling control card and supplies power, and the liquid cooling control card supplies power to each liquid cooling sensor.

[0077] The liquid cooling sensor is installed at the inlet and outlet of the cooling circulation pipe of the radiator of the main heat-generating component of the motherboard to monitor the cooling hydraulic pressure and flow rate of each component area.

[0078] The heat generating components include: CPU, Graphics Processing Unit (GPU for short), smart network card and the like.

[0079] The server's liquid cooling circuit has one main inlet and one main outlet. The flow is divided inside the chassis by a diverter. The diversion method is determined by the motherboard architecture. A temperature sensor can be added at the inlet.

[0080] The main heat-generating components of the motherboard can be grouped, and the radiators in each group are connected by the same branch pipe, and non-main heat-generating components are cooled by a branch pipe or by air cooling.

[0081] The flow control system of the optional embodiment of the present application can obtain the temperature of each first component of the server from the BMC module. The server temperature monitoring system can obtain the power information of each component of the server in real time. The flow control system is based on the cooling monitoring system, and a solenoid valve is added at the inlet and outlet of the radiator pipe of each heating component.

[0082] According to the temperature information of each first component, the power information of each component, the cooling liquid intensity and flow information at each component, the built-in algorithm and data processing module calculates the cooling liquid flow control data to obtain the opening control data of the upstream and downstream solenoid valves of each component. The signal operation module sends the solenoid valve opening control signal to the liquid cooling control card.

[0083] The BMC module obtains the temperature of each first component of the server and transmits it to the built-in algorithm and data processing module through the data transfer module. The built-in algorithm and data processing module calculates the maximum, minimum, and average values ​​of the temperature to evaluate the heat dissipation load status. The heat dissipation requirements of each component are ranked, and the heat dissipation problems of the components with the highest ranking are dealt with first. Compared with the preset temperature threshold, when the temperature of the first component exceeds the threshold, it indicates that the heat dissipation needs to be strengthened. When the temperature of the first component is lower than the threshold, it indicates that the heat dissipation intensity can be reduced.

[0084] The temperature sensor at the total inlet of the cooling circulation pipeline provides the coolant temperature, which determines the upper limit of the liquid cooling heat dissipation capacity. If necessary, the heat dissipation can be enhanced by lowering the initial coolant temperature.

[0085] Optionally, the built-in algorithm and data processing module adopts AI algorithm to predict future temperature and heat dissipation requirements based on the power consumption information of each component, and adjust the liquid cooling flow of each component.

[0086] The liquid cooling control card is connected to the electromagnetic valve, and adjusts the opening of the electromagnetic valve according to the electromagnetic valve opening control signal to change the flow rate of the cooling liquid.

[0087] Optionally, the solenoid valve has a built-in liquid cooling sensor to realize the cooling hydraulic pressure and flow monitoring functions. In this case, the independent liquid cooling sensors in the inlet and outlet pipes of the heating component can be eliminated.

[0088] It is understandable that the pressure monitoring and flow control system has the function of coordinated control of liquid cooling and air cooling. The cooling status of the server is divided into air cooling, liquid cooling, and mixed cooling. The cooling status is determined by the built-in algorithm and data processing module according to the real-time temperature and power consumption distribution of the server, or specified by the server user. Relevant thresholds are set to distinguish between low temperature and high temperature states, and low power consumption and high power consumption states.

[0089] (1) If the server is in low temperature and low power consumption operation, the built-in algorithm and data processing module determine that the server enters the air cooling state;

[0090] (2) If the server is at a low temperature, but the power of local components is high and the heat is obvious, the server is judged to be in liquid cooling state, and the coolant flow rate can be adaptively controlled;

[0091] (3) If the server is at a high temperature or has many components with high power and high heat generation, the server is judged to enter a mixed cooling state and the cooling of the entire machine is strengthened.

[0092] In the mixed cooling state, the built-in algorithm and data processing module gives the status data of the liquid cooling and air cooling system operation based on the temperature and power consumption information, and the signal operation module sends out liquid cooling and air cooling adjustment signals based on this.

[0093] The flow control module is connected to a fan control module such as a pulse width modulation (PWM) module of the BMC module to perform air cooling control. The PWM module can be used as a submodule of the flow control module.

[0094] Figure 3 This is a flow chart of a cooling monitoring and flow control method for a liquid cooling server in an optional embodiment of the present application, which is applied to Figure 2 In the system, such as Figure 3 As shown:

[0095] Step S301: The BMC module periodically sends a monitoring signal and a data collection signal to the liquid cooling control card, and the liquid cooling control card forwards the monitoring signal and the data collection signal to the sensor.

[0096] Step S302, the liquid cooling sensor collects data and feeds it back to the liquid cooling control card. The liquid cooling control card sends the data collected by the liquid cooling sensor (i.e., the operating data of this application) to the data transfer module in the BMC module. The data transfer module sends the data to the built-in algorithm and data processing module in the BMC module, and can also transfer the data to the BMC storage in the BMC module through the interface.

[0097] The optional embodiment of the present application also has a risk handling function. The execution process of the risk handling function is divided into three steps: risk prejudgment, information warning, and risk handling.

[0098] First, the built-in algorithm and data processing module processes information such as temperature and pressure, and predicts risks based on the operating status of the liquid cooling circulation pipeline. Then, when the system determines that a risk has occurred, the signal operation module executes the information alarm process, issues a risk disposal signal, and records it in the BMC log. Finally, the liquid cooling control card, solenoid valve, fan, CPLD and other components receive the risk disposal signal and perform risk disposal operations.

[0099] In step S303, the built-in algorithm and data processing module acquires data, obtains the liquid cooling operation status information (i.e., the operation status of the present application) of the component (i.e., the target component of the present application), and executes the risk prediction process of the risk disposal process, and sends the result of the risk prediction to the signal operation module.

[0100] Risk prejudgment classifies response risks into categories, including no risk, overload risk, leakage risk, component damage risk, etc. No risk means normal operation; overload risk means cooling and heating are mismatched, efficiency is insufficient, and server temperature surges; leakage risk refers to positive pressure coolant leakage or negative pressure coolant intake caused by pipeline damage; component damage risk means that the response information of the solenoid valve or sensor cannot be obtained, indicating that it has failed. That is:

[0101] 1) No risk: When the opening of the upstream and downstream solenoid valves of the radiator pipe of the heating component remains unchanged, the cooling hydraulic pressure difference and flow rate remain constant during the monitoring time, and the built-in algorithm and data processing module can determine that the pipe is risk-free.

[0102] 2) Overload risk: Server temperature surges.

[0103] 3) Leakage risk: Rapid heating of components may cause changes in the physical state of the coolant, resulting in slight changes in the pressure difference and flow rate. Therefore, a pressure difference and flow rate change threshold is set, and changes exceeding the threshold are judged as leakage risks.

[0104] 4) Risk of component damage: Unable to obtain response information from the solenoid valve or sensor.

[0105] Step S304: If the result of risk prediction is no risk, the relevant information is saved to the BMC storage through the data transfer module. If the target component has a risk, the information alarm and risk disposal process are executed according to the risk type and risk level.

[0106] Risk management operations can be divided into:

[0107] 1) General overload risk, including but not limited to increasing the opening of the solenoid valve; for severe overload risk, the CPLD can cut off the power supply to the component.

[0108] 2) Leakage risk: CPLD cuts off the power supply to the components, and the BMC module issues relevant alarm information. In serious cases, the server can be shut down.

[0109] 3) Risk of component damage: The BMC module will issue relevant alarm information and cut off the power supply to the component if necessary.

[0110] The optional embodiment of the present application proposes a pressure monitoring and flow control system and device for a liquid-cooled server, which monitors the liquid pressure in the liquid cooling pipes at the important components of the server in real time through the baseboard controller, and can be used for both positive pressure liquid cooling and negative pressure liquid cooling; in conjunction with the temperature or power information of the electronic components of the motherboard. The optional embodiment of the present application can intelligently control the coolant flow at each component to achieve balanced heat dissipation and reduce energy consumption; further, the fan can be coordinated to reduce or increase the air cooling intensity, and the coordinated scheduling of liquid cooling and air cooling can be achieved to ensure the stable operation of the server heat dissipation system and the efficient heat dissipation of the entire server. By monitoring the liquid cooling operation status, the risks of overload, leakage, and component failure can be prevented. When related risks occur, relevant processing operations are performed as soon as possible to ensure server safety.

[0111] 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.

[0112] The present application also provides a risk management method. The method provided in the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. For example, running on a computer terminal, Figure 4 1 is a hardware structure block diagram of a computer terminal of a risk management method according to an embodiment of the present application. Figure 4 As shown, the computer terminal may include one or more ( Figure 4 Only 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 computer terminal 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 4 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. Figure 4 More or fewer components as shown, or with Figure 4 Different configurations are shown.

[0113] 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 method for determining the interactive state 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 examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the computer terminal 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.

[0114] 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 a computer terminal. 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.

[0115] A risk management method is provided in an embodiment of the present application. Figure 5 is a flow chart of a risk management method according to an embodiment of the present application, such as Figure 5 As shown, the process includes the following steps:

[0116] Step S502, monitoring the operating data of the target component;

[0117] Step S504, when the monitoring signal is received, obtaining the monitored operation data;

[0118] Step S506, calculating the operating state of the target component according to the operating data, performing risk prejudgment on the target component according to the operating state, and performing risk disposal on the target component according to the prediction result of the risk prejudgment.

[0119] The risk management method of the present application includes: not only can the operating data of the target component be monitored and obtained, but also the operating status of the target component can be determined based on the operating data, and then the risk prediction and risk management of the target component can be performed based on the operating status. Through the embodiments of the present application, the problem of the lack of a system that effectively monitors the operating data of the liquid-cooled server and performs risk prediction and risk management based on the operating data in the related technology can be solved. The risk management method of the present application integrates monitoring and obtaining the operating data of the target component, determining the operating status of the target component, and performing risk prediction and risk management of the target component based on the operating status. It can achieve effective monitoring and risk prediction of the target component, and timely risk management of the target component.

[0120] 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 in the above method embodiment when running.

[0121] 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.

[0122] 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 the above method embodiment.

[0123] 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.

[0124] An embodiment of the present application further provides a computer program product, including a computer program, which is implemented to perform the steps in the above method embodiment when executed by a processor.

[0125] 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.

[0126] 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.

[0127] 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 risk management system, characterized in that: include: A baseboard management controller, a liquid cooling control card connected to the baseboard management controller, and a liquid cooling sensor connected to the liquid cooling control card, wherein: The liquid-cooled sensor is used to monitor the operating data of the target component; The liquid cooling control card is used to obtain the operation data monitored by the liquid cooling sensor and send the operation data to the baseboard management controller when receiving the monitoring signal sent by the baseboard management controller; The baseboard management controller calculates the operating status of the target component according to the operating data; and performs risk prejudgment on the target component according to the operating status, and performs risk disposal on the target component according to the prediction result of the risk prejudgment.

2. The system according to claim 1, characterized in that The baseboard management controller includes: a built-in algorithm module, wherein: The built-in algorithm module is used to determine the temperature change data, pressure difference data and flow control data of the target component in the first time period according to the operation data when receiving the operation data sent by the liquid cooling controller, wherein the operation data includes: the temperature data, pressure data and flow data of the target component in the first time period; Determining the electromagnetic valve opening control data corresponding to the target component according to the flow control data, wherein the target component includes: an electromagnetic valve, the electromagnetic valve is used to adjust the flow corresponding to the target component; The operating state of the target component is determined according to the temperature change data, the pressure difference data, the flow control data and the solenoid valve opening control data.

3. The system according to claim 2, characterized in that The baseboard management controller is further used for: When it is determined according to the solenoid valve opening control data that the opening of the solenoid valve corresponding to the target component remains constant within a first time period, and the temperature data and the pressure data of the target component within the first time period remain constant, it is determined that the target component is in a risk-free state; In the case where the operating state of the target component indicates that the first temperature data of the target component at the first time point is greater than the second temperature data of the target component at the second time point, and the difference between the first temperature data and the second temperature data is greater than a preset temperature difference, it is determined that the target component has an overload risk, wherein the first time period includes: the first time point and the second time point, and the first time point is a time point after the second time point; When the operating state of the target component indicates that the pressure difference change value of the target component in the second time period is greater than the preset pressure difference change value, and the flow change difference value of the target component in the second time period is greater than the preset flow change difference value, it is determined that the target component has a leakage risk, wherein the first time period includes: the second time period; When the operating status of the target component indicates that the pressure data and / or flow data of the target component cannot be obtained within a third time period, it is determined that there is a risk of component damage to the target component, wherein the first time period includes: the third time period.

4. The system according to claim 1, characterized in that The baseboard management controller is further used for: In the case where it is determined that the target component has an overload risk, the overload risk level of the target component is determined, and an opening control signal is sent to the liquid cooling control card according to the overload risk level, so that the liquid cooling control card sends the opening control signal to the solenoid valve in the target component, and adjusts the opening of the solenoid valve of the target component according to the overload risk level, wherein the solenoid valve is used to adjust the flow corresponding to the target component, and the opening of the solenoid valve of the target component corresponding to different overload risk levels is different, and the flow corresponding to the target component is proportional to the temperature of the target component; When it is determined that the target component has a leakage risk, sending a closing signal to the liquid cooling control card, so that the liquid cooling control card sends the closing signal to the solenoid valve to close the solenoid valve of the target component; When it is determined that there is a risk of component damage in the target component, an alarm signal is sent to the liquid cooling control card, so that the liquid cooling control card sends the alarm signal to the target component and controls the target component to stop working.

5. The system according to claim 4, characterized in that The baseboard management controller is further used for: In the case where the first component temperature of the target component is greater than or equal to the first temperature threshold, the overload risk level of the target component is determined to be the first overload risk level, and the heat dissipation level corresponding to the target component is adjusted to the first heat dissipation level, wherein the first heat dissipation level includes: determining whether the second component temperature of other components is greater than the first temperature threshold, the number of components and the server temperature corresponding to the server, wherein the server includes: the target component and the other components; in the case where it is determined that the number of components is greater than or equal to the first preset number of components, or the server temperature is greater than or equal to the second temperature threshold, the server is adjusted to a liquid cooling and air cooling mixed state to dissipate heat for the target component; in the case where it is determined that the number of components is less than the first preset number of components, and greater than the second preset number of components, and the server temperature is less than the second temperature threshold, the server is adjusted to a liquid cooling state to dissipate heat for the target component; When the first component temperature of the target component is lower than the first temperature threshold, the overload risk level of the target component is determined to be the second-level overload risk level, and the heat dissipation level corresponding to the target component is adjusted to the second heat dissipation level, wherein the first-level overload risk level is greater than the second-level overload risk level, and the heat dissipation intensity corresponding to the first heat dissipation level is greater than the heat dissipation intensity corresponding to the second heat dissipation level, and the second heat dissipation level includes: when it is determined that the first component temperature of the target component is lower than the first temperature threshold, the server is adjusted to an air-cooled state to dissipate heat for the target component.

6. The system according to claim 5, characterized in that The baseboard management controller is further used for: In a case where the target component is cooled according to the first heat dissipation level, determining whether the target component still has the overload risk; When it is determined that the target component still has the overload risk, the coolant temperature of the coolant corresponding to the target component is reduced to dissipate heat for the target component.

7. The system according to claim 1, characterized in that The baseboard management controller is further used for: In the case where it is determined that the multiple components all have an overload risk, determining a maximum temperature value and a minimum temperature value of each of the multiple components; evaluating the heat dissipation load state of each component according to the maximum temperature and the minimum temperature; sorting the heat dissipation requirements of each component according to the heat dissipation load state of each component; Heat dissipation is performed on each component according to the arrangement order of the multiple components.

8. A risk management method, characterized in that: include: Monitor the operating data of the target component; When receiving the monitoring signal, obtaining the monitored operation data; The operating state of the target component is calculated according to the operating data, and the risk of the target component is predicted according to the operating state, and the risk of the target component is handled according to the prediction result of the risk prediction.

9. A computer-readable storage medium, characterized in that: include: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of the method described in claim 8 when executed by a processor.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: include: When the processor executes the computer program, the steps of the method according to claim 8 are implemented.

Images