Control System for Server Power Supply
By deploying processors and transmitters between power supply and controllers, and using attenuation information and calibration information for signal compensation and calibration, the problem of low signal transmission quality between controllers and power supply is solved, and the control efficiency of server power supply is improved.
Patent Information
- Application Number
- CN202411941774.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-26
- Publication Date
- 2025-07-08
- Estimated Expiration
- 2044-12-26
AI Technical Summary
In the prior art, the signal transmission quality between the controller and the power supply power supply is low, resulting in low server power control efficiency, and the transmitter has problems with communication timing mismatch and version compatibility.
A processor and a transmitter are deployed between the power supply and the controller. The transmitter compensates the initial signal based on the attenuation information. The processor generates verification information. The controller calibrates the candidate signals based on the verification information to ensure the accuracy of the signal.
It improves the control efficiency of the server power supply, avoids the control of the operating status of the power supply by inaccurate signals, and ensures the precise control of the operating status of the power supply by the controller.
Smart Images

Figure CN119376512B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of computers, and more particularly, to a control system for a server power supply. Background Art
[0002] With the increasing complexity of server architectures, the communication distance between the controller and the power supply is getting longer, and the interference and impedance attenuation on the communication link are also increasing, resulting in a low signal transmission quality between the controller and the power supply. In the prior art, in order to avoid the influence of the impedance of the signal transmission link between the controller and the power supply on the power signal, a transmitter is added to the signal transmission link between the controller and the power supply to compensate for the signal attenuation caused by the link impedance, thereby improving the signal transmission quality. However, due to the communication timing mismatch and version compatibility problems of the transmitter, the compensated power signal may still be inaccurately output, resulting in a low control efficiency of the server power supply. Summary of the Invention
[0003] The embodiments of the present application provide a control system for a server power supply to at least solve the problem of low control efficiency of the server power supply in the related art.
[0004] According to an embodiment of the present application, a control system for a server power supply is provided, including:
[0005] A transmitter, a processor, and a controller, where the controller is respectively connected to the output end of the transmitter and the output end of the processor, and the input end of the transmitter and the input end of the processor are used to connect to the power supply of the server;
[0006] The transmitter is configured to perform signal compensation on the initial signal output by the power supply according to the attenuation information, and transmit the obtained candidate signal to the controller, where the attenuation information is used to indicate the influence of the signal transmission link between the power supply and the controller on signal transmission, and the initial signal is used to indicate the power supply state of the power supply to the server;
[0007] The processor is configured to generate verification information of the initial signal according to the initial signal, where the verification information is used to indicate the signal value of the initial signal;
[0008] The controller is configured to calibrate the candidate signal according to the verification information to obtain a target signal; and use the target signal to control the operating state of the power supply.
[0009] Optionally, the processor is further configured to: obtain a target parameter type of the power supply parameter indicated by the initial signal; convert a target parameter value of the power supply parameter according to the target parameter type and the initial signal, where the verification information includes the target parameter value of the power supply parameter.
[0010] Optionally, the processor is further configured to: obtain a target conversion relationship corresponding to the target parameter type, where the target conversion relationship is a conversion relationship between the signal value of a signal and the parameter value of the power supply parameter of the target parameter type;
[0011] Convert the initial signal value of the initial signal into the target parameter value by using the target conversion relationship.
[0012] Optionally, the processor is further configured to: when the initial signal is a level signal, detect a target level value of the initial signal; determine the target level value as the verification information.
[0013] Optionally, the controller is further configured to: match the initial signal value of the initial signal indicated by the verification information with the candidate signal value of the candidate signal; when the initial signal value does not match the candidate signal value, calibrate the candidate signal by using the initial signal value to obtain the target signal.
[0014] Optionally, the controller is further configured to: when the candidate signal is a candidate level signal, perform signal compensation on the candidate level signal according to a difference value between the candidate signal value and the initial signal value to obtain a target level signal, where the target signal includes the target level signal.
[0015] Optionally, the controller is further configured to: when the initial signal value does not match the candidate signal value, determine that the transmitter is faulty, and generate fault indication information for indicating that the transmitter is faulty; send the fault indication information to a target account, where the target account is an account for maintaining the running state of the server.
[0016] Optionally, the controller is further configured to: when determining that the transmitter is faulty, send a signal acquisition request to the processor, where the signal acquisition request is used to request to acquire the initial signal output by the power supply through the processor;
[0017] The processor is further configured to: when receiving the signal acquisition request, acquire the initial signal currently output by the power supply; compensate the initial signal according to the target attenuation information to obtain a compensated signal, where the target attenuation information is used to indicate the influence of the signal transmission link between the processor and the controller on the signal transmission quality; and send the compensated signal to the controller.
[0018] Optionally, the control system of the server power supply further includes a switch. The first port of the switch is connected to the output end of the transmitter, the second port of the switch is connected to the output end of the processor, and the third port of the transmitter is connected to the controller.
[0019] The controller is further configured to: when determining that the transmitter fails, send a link switching request to the switch, where the link switching request is used to request switching the connection status between the controller, the processor, and the transmitter.
[0020] The switch is configured to: in response to the link switching request, disconnect the connection link between the first port and the third port, and conduct the connection link between the second port and the third port.
[0021] Optionally, the controller is further configured to: when the initial signal value matches the candidate signal value, determine the candidate signal as the target signal.
[0022] Optionally, the controller is further configured to: when detecting that the operation load of the controller is greater than or equal to the target load, send a service migration request to the processor, where the service migration request is used to request migrating the services to be processed by the controller to the processor.
[0023] The processor is further configured to: when receiving the service migration request, acquire the candidate signal output by the transmitter; calibrate the candidate signal according to the verification information to obtain the target signal; generate a target control instruction for the power supply according to the target signal, where the target control instruction is used to indicate the operating state of the power supply; and send the target control instruction to the controller.
[0024] The controller is further configured to: when receiving the target control instruction, control the operating state of the power supply using the target control instruction.
[0025] Optionally, the control system of the server power supply further includes a switch. The first port of the switch is connected to the output end of the transmitter, the second port of the switch is connected to the output end of the processor, and the third port of the transmitter is connected to the controller;
[0026] The controller is further configured to: when it is necessary to send the service migration request to the processor, send a target switching request to the switch, where the target switching request is used to request to switch the connection status between the controller, the processor, and the transmitter;
[0027] The switch is further configured to: in response to the target switching request, disconnect the connection link between the first port and the third port, and conduct the connection link between the second port and the third port;
[0028] The controller is further configured to: when it is determined that the switch conducts the connection link between the second port and the third port, send the service migration request to the processor.
[0029] Optionally, the control system of the server power supply further includes a switch. The first port of the switch is connected to the output end of the transmitter, the second port of the switch is connected to the output end of the processor, and the third port of the transmitter is connected to the controller;
[0030] The switch is further configured to: when receiving the service migration request, transmit the service migration request to the processor, and conduct the connection link between the first port and the second port;
[0031] The processor is further configured to: call the connection link between the first port and the second port to obtain the candidate signal output by the transmitter.
[0032] Optionally, the processor is further configured to: when determining the target control instruction to be transmitted to the controller, send a reference switching request to the switch, where the reference switching request is used to request to switch the connection status between the processor, the controller, and the transmitter;
[0033] The switch is further configured to: in response to the reference switching request, disconnect the connection link between the first port and the second port, and conduct the connection link between the second port and the third port;
[0034] The processor is further configured to: call the connection link between the second port and the third port to send the target control instruction to the controller.
[0035] Optionally, the processor is further configured to: when receiving a fault signal sent by the power supply, obtain power operation information of the power supply stored in the cache space of the processor, where the fault signal is used to indicate that the power supply is currently in a fault state, and the power operation information is used to indicate the power supply situation of the server by the power supply within a reference time period before the current moment; predict target fault information of the server power supply according to the power operation information; and send the target fault information to the controller.
[0036] The controller is further configured to: perform fault maintenance on the power supply according to the target fault information.
[0037] Through the present application, by deploying a processor connected between the power supply and the controller, and a transmitter connected between the power supply and the controller, the transmitter can compensate an initial signal output by the power supply for indicating the power supply situation of the server to the server according to attenuation information indicating the influence of the signal transmission link between the power supply and the controller on signal transmission, and transmit the obtained candidate signal to the controller. At the same time, the processor can generate verification information indicating the signal value situation of the initial signal according to the initial signal output by the power supply and transmit it to the controller. Furthermore, the controller can calibrate the candidate signal transmitted by the transmitter according to the verification information generated by the processor, thereby avoiding the controller using inaccurate signals output by the transmitter to control the operation state of the power supply, so that the controller can more accurately control the operation state of the power supply. Therefore, the problem of low control efficiency of the server power supply in the related art can be solved, and the effect of improving the control efficiency of the server power supply can be achieved. Description of the Drawings
[0038] Figure 1 is a hardware connection diagram of a control system for a server power supply according to an embodiment of the present application;
[0039] Figure 2 is a schematic diagram of the hardware connection of a control system for a server power supply according to an embodiment of the present application;
[0040] Figure 3 is the hardware interaction for business migration of a control system for a server power supply according to an embodiment of the present application Figure 1 ;
[0041] Figure 4 is the hardware interaction for business migration of a control system for a server power supply according to an embodiment of the present application Figure 2 ;
[0042] Figure 5It is the hardware interaction for business migration according to a control system of a server power supply in an embodiment of the present application Figure 3 ;
[0043] Figure 6 It is a hardware connection diagram of a reliable redundant server power supply communication monitoring design according to an embodiment of the present application;
[0044] Figure 7 It is a method flowchart of a reliable redundant server power supply communication monitoring design according to an embodiment of the present application;
[0045] Figure 8 It is a method flowchart of EEPROM chip partition management of a reliable redundant server power supply communication monitoring design according to an embodiment of the present application;
[0046] Figure 9 It is a business migration flowchart of a reliable redundant server power supply communication monitoring design according to an embodiment of the present application. Specific embodiments
[0047] In the following, embodiments of the present application will be described in detail with reference to the accompanying drawings and in conjunction with the embodiments.
[0048] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence.
[0049] In this embodiment, a control system of a server power supply is provided. Figure 1 It is a hardware connection diagram of a control system of a server power supply according to an embodiment of the present application. As Figure 1 shown, the system includes:
[0050] A transmitter, a processor, and a controller. The controller is respectively connected to the output end of the transmitter and the output end of the processor. The input end of the transmitter and the input end of the processor are used to connect to the power supply of the server;
[0051] The transmitter is used to perform signal compensation on the initial signal output by the power supply according to the attenuation information, and transmit the obtained candidate signal to the controller, where the attenuation information is used to indicate the influence of the signal transmission link between the power supply and the controller on signal transmission, and the initial signal is used to indicate the power supply state of the power supply to the server;
[0052] The processor is used to generate verification information of the initial signal according to the initial signal, where the verification information is used to indicate the signal value situation of the initial signal;
[0053] The controller is configured to calibrate the candidate signal according to the verification information to obtain a target signal, and use the target signal to control the operating state of the power supply.
[0054] Through the above content, by deploying a processor connected between the power supply and the controller, and a transmitter connected between the power supply and the controller, the transmitter can compensate the initial signal output by the power supply for indicating the power supply state of the server to the server according to the attenuation information indicating the influence of the signal transmission link between the power supply and the controller on the signal transmission, and transmit the obtained candidate signal to the controller. At the same time, the processor can generate verification information for indicating the signal value of the initial signal according to the initial signal output by the power supply and transmit it to the controller. Furthermore, the controller can calibrate the candidate signal transmitted by the transmitter according to the verification information generated by the processor, thereby avoiding the controller using the inaccurate signal output by the transmitter to control the operating state of the power supply, so that the controller can more accurately control the operating state of the power supply. Therefore, the problem of low control efficiency of the server power supply in the related art can be solved, and the effect of improving the control efficiency of the server power supply can be achieved.
[0055] Optionally, in the embodiments of the present application, Figure 1 is a hardware connection diagram of a control system for a server power supply according to an embodiment of the present application. As Figure 1 shown, the server power supply control system includes a transmitter, a processor, and a controller. The controller is respectively connected to the output end of the transmitter and the output end of the processor. The input end of the transmitter and the input end of the processor are used to connect to the power supply of the server. Since the initial signal output by the power supply will undergo signal attenuation on the transmission link, the transmitter compensates the initial signal output by the power supply to obtain a candidate signal and transmits the candidate signal to the controller. At the same time, the processor generates verification information for indicating the signal value of the initial signal according to the initial signal output by the power supply and transmits the verification information to the controller. Furthermore, the controller can use the verification information to calibrate the candidate information sent by the transmitter to obtain a target signal, and then the controller uses the target signal to control the operating state of the power supply, thereby avoiding the controller using an abnormal power signal to control the operating state of the power supply and improving the control efficiency of the server power supply.
[0056] Optionally, in the embodiments of the present application, the initial signal is used to reflect the current power supply state of the power supply. The initial signal may include, but is not limited to, a power supply state signal (such as power load, temperature, etc.), a power supply parameter signal (such as output voltage, current, power, etc. of the power supply), a level signal, etc. The present solution does not limit this.
[0057] Optionally, in the embodiments of the present application, the attenuation information is data or parameters used to characterize the loss degree of a signal on the signal transmission link between the power supply and the controller. The attenuation information may include, but is not limited to, signal amplitude attenuation, phase shift, link impedance, signal delay, etc. This solution does not make any limitations in this regard.
[0058] Optionally, in the embodiments of the present application, the transmitter is used to compensate for the signal attenuation that occurs during the transmission of a signal on the communication link. The transmitter can analyze the loss degree of the initial signal on the signal transmission link according to the attenuation information, and then preprocess the initial signal. For example, amplify the initial signal or adjust the phase and frequency of the initial signal. In the embodiments of the present application, the transmitter may include, but is not limited to, expansion chips (Buffer ICs), digital signal processors (DSPs), signal conditioners (Signal Conditioner ICs), etc. This solution does not make any limitations in this regard.
[0059] Optionally, in the embodiments of the present application, the processor is used to convert the initial signal transmitted by the power supply into verification information indicating the signal value corresponding to the initial signal and transmit it to the controller. For example, when the initial signal is a signal representing power supply parameters, the processor is used to convert various power supply parameters indicated by the initial signal (such as the output voltage, current, power, etc. of the power supply) into corresponding power supply parameter values. The verification information may be an array composed of each power supply parameter value, or a mapping relationship between each power supply parameter and the power supply parameter value, or a string generated by performing a mathematical operation on each power supply parameter value according to a certain rule using a specific algorithm as the verification information; when the initial signal is a level signal, the processor is used to convert the initial signal into the level value corresponding to the level signal, and the verification information may be the level value corresponding to the level signal. This solution does not make any limitations in this regard.
[0060] Optionally, in the embodiments of the present application, the processor is an arithmetic device integrated with the function of converting the initial signal transmitted by the power supply into verification information indicating the signal value corresponding to the initial signal. It may include, but is not limited to, EEPROM (Electrically Erasable Programmable Read-Only Memory) chips, FPGAs (Field-Programmable Gate Arrays), CPUs (Central Processing Units), etc. This solution does not make any limitations in this regard.
[0061] Optionally, in the embodiments of the present application, the controller is used to calibrate the candidate signal according to the verification information. After receiving the verification information sent by the processor, the controller restores the verification information to the signal value of the initial signal to verify the accuracy of the candidate signal. Furthermore, in the case where the signal value of the candidate signal does not match the signal value of the initial signal, the signal value of the initial signal is used to calibrate the candidate signal to obtain the target signal, and then the target signal is used to control the operating state of the power supply, thereby avoiding controlling the operating state of the power supply with an incorrect candidate signal and improving the control efficiency of the server power supply.
[0062] Optionally, in the embodiments of the present application, the controller can be, but is not limited to, BMC (Baseboard Management Controller), IPMI (Intelligent Platform Management Interface), CPLD (Complex Programmable Logic Device), etc. This solution does not make any limitations in this regard.
[0063] Optionally, in the embodiments of the present application, the power supply is used to provide electrical energy for the server. The power supply can be, but is not limited to, PSU (Power Supply Unit), IPM (Intelligent Power Module), etc. This solution does not make any limitations in this regard.
[0064] As an optional embodiment, the processor is further configured to: obtain the target parameter type of the power supply parameter indicated by the initial signal; convert the target parameter value of the power supply parameter according to the target parameter type and the initial signal, where the verification information includes the target parameter value of the power supply parameter.
[0065] Optionally, in the embodiments of the present application, after the processor obtains the initial signal transmitted by the power supply, it immediately converts the power supply parameters of each type indicated by the initial signal into corresponding parameter values and saves them as verification information, ensuring the accuracy and integrity of the initial signal, enabling the subsequent controller to use accurate verification information to calibrate the candidate signal, and improving the accuracy of calibrating the candidate signal.
[0066] Optionally, in the embodiments of the present application, the target parameter type of the power supply parameter refers to the specific parameter type encoded in the initial signal, such as the output voltage, current, power, etc. of the power supply, so that the processor can convert the parameter value of the power supply parameter according to the target parameter type. The conversion method may be: decoding the initial signal transmitted by the power supply to obtain a reference signal, where the reference signal contains a target type identifier for indicating the target parameter type of the power supply parameter; screening out a target conversion algorithm corresponding to the target type identifier from the type identifiers and conversion algorithms with corresponding relationships; using the target conversion algorithm to convert the power supply parameter corresponding to the target type identifier into a target parameter value.
[0067] Through the above method, the processor converts the power supply parameters of each type indicated by the initial signal into corresponding parameter values and saves them as verification information, which can ensure that the initial signal obtained by the processor is quickly converted into stable data, guarantee the accuracy and integrity of the calibration information, and further improve the calibration accuracy of the controller for the candidate signal.
[0068] As an optional embodiment, the processor is further configured to: obtain a target conversion relationship corresponding to the target parameter type, where the target conversion relationship is a conversion relationship between the signal value of the signal and the parameter value of the power supply parameter of the target parameter type;
[0069] Use the target conversion relationship to convert the initial signal value of the initial signal into the target parameter value.
[0070] Optionally, in the embodiments of the present application, the target conversion relationship is a conversion formula or mapping between the signal value and the actual power supply parameter value, which takes into account the distortion during signal transmission, the characteristic curve of the sensor, and the signal format, etc. For example, after the processor receives a signal value with a power supply parameter type of voltage, it will obtain the voltage conversion formula corresponding to the voltage from the power supply parameter type and conversion formula with a corresponding relationship, and then convert the signal value into a specific voltage value according to the voltage conversion formula.
[0071] Through the above method, the processor can convert various power supply parameters into corresponding parameter values according to the conversion relationships corresponding to different power supply parameter types, improve the efficiency of signal processing and the accuracy of the signal, and avoid misjudgment or system failure caused by signal parsing errors.
[0072] As an optional embodiment, the processor is further configured to: when the initial signal is a level signal, detect the target level value of the initial signal; determine the target level value as the verification information.
[0073] Optionally, in the embodiments of the present application, when the initial signal is a level signal, the processor calculates the target level value of the initial signal, and then determines the target level value as the verification information.
[0074] As an optional embodiment, the controller is further configured to: match the initial signal value indicated by the verification information of the initial signal with the candidate signal value of the candidate signal; in the case where the initial signal value does not match the candidate signal value, use the initial signal value to calibrate the candidate signal to obtain the target signal.
[0075] Optionally, in the embodiments of the present application, after receiving the verification information, the controller first parses the initial signal value corresponding to the initial signal from the verification information, and then the controller compares the initial signal value with the candidate signal value of the currently received candidate signal. In the case where the initial signal value does not match the candidate signal value, the initial signal value is used to calibrate the candidate signal. The calibration method may be: obtaining the difference information between the initial signal value and the candidate signal value, where the difference information is used to indicate the signal parameter difference between the candidate signal and the initial signal; generating a signal processing parameter for the candidate signal according to the difference information, where the signal processing parameter is used to indicate the adjustment of the signal parameters of the candidate signal, and using the signal processing parameter to process the candidate signal so that the candidate signal value matches the initial signal value.
[0076] By the above method, by calibrating the candidate signal with the initial signal value in the case where the initial signal value does not match the candidate signal value, it can be ensured that the controller controls the operating state of the power supply with the correct signal, improving the control efficiency of the server power supply.
[0077] As an optional embodiment, the controller is further configured to: in the case where the candidate signal is a candidate level signal, perform signal compensation on the candidate level signal according to the difference value between the candidate signal value and the initial signal value to obtain a target level signal, where the target signal includes the target level signal.
[0078] Optionally, in the embodiments of the present application, when the candidate signal is a level signal, the candidate signal value is the level value of the candidate signal. Then the controller calculates the difference value between the level value of the candidate signal and the level value of the initial signal. The difference value is used to characterize the attenuation degree or gain degree of the signal during transmission. Then the controller performs signal compensation on the candidate level signal according to the difference value. The compensation method may be to adjust the gain and offset of the candidate level signal, or apply a specific signal processing algorithm to process the candidate level signal so that the level value of the compensated candidate signal matches the level value of the initial signal.
[0079] In the above manner, by compensating the candidate level signal according to the difference value between the candidate signal value and the initial signal value, it can be ensured that the controller uses the correct level signal to control the operating state of the power supply, improving the control efficiency of the server power supply.
[0080] As an optional embodiment, the controller is further configured to: in the case where the initial signal value does not match the candidate signal value, determine that the transmitter is faulty, and generate a fault indication information for indicating that the transmitter is faulty; send the fault indication information to a target account, where the target account is an account for maintaining the operating state of the server.
[0081] Optionally, in the embodiment of the present application, when the initial signal value does not match the candidate signal value, the controller will further detect whether the difference value between the initial signal value and the candidate signal value exceeds a difference threshold. In the case where the difference value exceeds the difference threshold, it is determined that the transmitter connected to the controller fails. After determining the transmitter failure, the controller will generate a fault indication information for indicating that the transmitter is faulty. The fault indication information may include the fault type, the time of fault occurrence, the fault location, and the recommended fault handling measures, etc., and send the fault indication information to a preset target account through a secure communication protocol. The target account is usually a professional account for maintaining the operating state of the server, such as the account of the operation and maintenance personnel or the system administrator in the data center. The notification method may be an email, a text message, a system warning message, or a message sent through a dedicated maintenance platform.
[0082] In the above manner, the controller can automatically identify and report the hardware faults occurring in the communication link, and timely notify the maintenance personnel to handle them, thereby reducing the downtime of the server and improving the running stability of the server system.
[0083] As an optional embodiment, the controller is further configured to: in the case of determining the transmitter failure, send a signal acquisition request to the processor, where the signal acquisition request is used to request the processor to acquire the initial signal output by the power supply.
[0084] The processor is further configured to: in the case of receiving the signal acquisition request, acquire the initial signal currently output by the power supply; compensate the initial signal according to the target attenuation information, where the target attenuation information is used to indicate the influence of the signal transmission link between the processor and the controller on the signal transmission quality; send the compensated signal to the controller.
[0085] Optionally, in the embodiments of the present application, when it is determined that the transmitter fails, the controller sends a signal acquisition request to the processor to request to obtain the initial signal output by the power supply through the processor, thereby avoiding the control interruption of the power supply caused by the failure of the transmitter.
[0086] Optionally, in the embodiments of the present application, after receiving the signal acquisition request sent by the controller, the processor obtains the initial signal output by the power supply, analyzes the loss degree of the initial signal on the signal transmission link between the processor and the controller according to the target attenuation information, and then performs signal compensation on the initial signal to obtain a compensation signal, such as amplifying the initial signal or adjusting the phase and frequency of the initial signal, and sends the compensation signal to the controller. That is, the functions of the transmitter are also integrated on the processor. When the transmitter fails, the controller can obtain the initial signal transmitted by the power supply through the processor, and then control the operating state of the power supply.
[0087] In the above manner, even if the transmitter fails, the controller can still obtain an accurate power signal through the processor, ensuring the normal operation of the server and efficient power management.
[0088] As an optional embodiment, the control system of the server power supply further includes a switch. The first port of the switch is connected to the output end of the transmitter, the second port of the switch is connected to the output end of the processor, and the third port of the transmitter is connected to the controller;
[0089] The controller is further configured to: when it is determined that the transmitter fails, send a link switching request to the switch, where the link switching request is used to request to switch the connection status between the controller, the processor, and the transmitter;
[0090] The switch is configured to: in response to the link switching request, disconnect the connection link between the first port and the third port, and conduct the connection link between the second port and the third port.
[0091] Optionally, in the embodiments of the present application, Figure 2 is a schematic diagram of the hardware connection of a control system of a server power supply according to an embodiment of the present application. As Figure 2 shown, the control system of the server power supply further includes a switch. The first port of the switch is connected to the output end of the transmitter, the second port of the switch is connected to the output end of the processor, and the third port of the transmitter is connected to the controller.
[0092] Optionally, in the embodiments of the present application, when it is determined that the transmitter fails, the controller sends a link switching request to the switch, requesting to disconnect the connection between the controller and the transmitter and switch to the connection link between the controller and the processor. Subsequently, the controller can obtain the initial signal output by the power supply through the connection link between the controller and the processor.
[0093] Optionally, in the embodiments of the present application, after receiving the link switching request sent by the controller, the switch disconnects the connection link between the first port and the third port, that is, disconnects the connection between the controller and the transmitter, and conducts the connection link between the second port and the third port, that is, conducts the connection between the controller and the processor.
[0094] In the above manner, by introducing a switch and a link switching mechanism, the server power control system can better adapt to hardware failures. Even when the transmitter fails, the switch can quickly switch the communication link of the controller, avoiding the interruption of the control of the server power caused by the transmitter failure.
[0095] As an alternative embodiment, the controller is further configured to: when the initial signal value matches the candidate signal value, determine the candidate signal as the target signal.
[0096] Optionally, in the embodiments of the present application, when the initial signal value matches the candidate signal value, it indicates that the accuracy and integrity of the candidate signal obtained by compensating the initial signal by the transmitter are relatively high, and it can be accepted and processed by the controller as a valid signal without further signal compensation. Therefore, the candidate signal can be directly determined as the target signal.
[0097] In the above manner, by determining the candidate signal as the target signal when the initial signal value matches the candidate signal value, unnecessary signal processing steps and system resource consumption are reduced, improving the efficiency and stability of server power management.
[0098] As an alternative embodiment, the controller is further configured to: when it is detected that the operation load of the controller is greater than or equal to the target load, send a service migration request to the processor, where the service migration request is used to request to migrate the service to be processed by the controller to the processor;
[0099] The processor is further configured to: when receiving the service migration request, obtain the candidate signal output by the transmitter; calibrate the candidate signal according to the calibration information to obtain the target signal; generate a target control instruction for the power supply according to the target signal, where the target control instruction is used to indicate the operating state of the power supply; and send the target control instruction to the controller.
[0100] The controller is further configured to: when receiving the target control instruction, control the operating state of the power supply using the target control instruction.
[0101] Optionally, in the embodiments of the present application, when the controller detects that its operation load exceeds a preset target load, it may actively send a service migration request to the processor, requesting to migrate the services to be processed by the controller to the processor, thereby reducing the load of the controller and improving the overall performance of the system. Selecting to migrate the services to be processed by the controller to the processor may be: screening out a target migration amount corresponding to the operation load of the controller from the corresponding relationship between the load amount and the service migration amount; and selecting the services to be migrated corresponding to the target migration amount from the service priority list of the controller in the order of priority from high to low, where the service priority list sorts the services to be migrated in descending order of priority.
[0102] Optionally, in the embodiments of the present application, after receiving the service migration request sent by the controller, the processor directly obtains the candidate signal from the transmitter, calibrates the candidate signal using the calibration information to obtain the target signal, and then the processor generates a target control instruction for the power supply according to the calibrated target signal. The target control instruction is used to regulate the operating state of the power supply, such as voltage regulation, power distribution, or power-off protection. Then, after receiving the target control instruction generated by the processor, the controller can directly apply it to the power supply to adjust the operating state of the power supply, reducing the operation pressure of the controller.
[0103] By the above method, when the operation load of the controller is too large, the services to be processed by the controller are shared by the processor for processing. Then, the controller can directly apply the control instruction generated by the processor to the power supply, reducing the time for the controller to process signals internally, improving the resource utilization efficiency of the server and the control efficiency of the server power supply.
[0104] As an optional embodiment, the control system of the server power supply further includes a switch. The first port of the switch is connected to the output end of the transmitter, the second port of the switch is connected to the output end of the processor, and the third port of the transmitter is connected to the controller.
[0105] The controller is further configured to: in case that the service migration request needs to be sent to the processor, send a target switching request to the switch, where the target switching request is used to request to switch the connection status between the controller, the processor, and the transmitter;
[0106] The switch is further configured to: in response to the target switching request, disconnect the connection link between the first port and the third port, and conduct the connection link between the second port and the third port;
[0107] The controller is further configured to: in case that the switch conducts the connection link between the second port and the third port, send the service migration request to the processor.
[0108] Optionally, in the embodiments of the present application, Figure 3 is the hardware interaction for service migration of a control system of a server power supply according to the embodiments of the present application Figure 1 , as Figure 3 shown, the control system of the server power supply further includes a switch. The first port of the switch is connected to the output end of the transmitter, the second port of the switch is connected to the output end of the processor, and the third port of the transmitter is connected to the controller. When the controller needs to migrate the service to be processed to the processor for processing, it will first send a target switching request to the switch to request to disconnect the communication link between the controller and the transmitter and conduct the communication link between the controller and the processor. Then, the controller can send a service migration request to the processor.
[0109] Optionally, in the embodiments of the present application, when the switch receives the target switching request sent by the controller, it will disconnect the connection link between the first port and the third port, that is, disconnect the connection between the controller and the transmitter, and conduct the connection link between the second port and the third port, that is, conduct the connection between the controller and the processor. Then, when the controller determines that the connection link between the second port and the third port is conducted, it can send a service migration request to the processor through the connection link between the second port and the third port.
[0110] Optionally, in the embodiments of the present application, the service migration between the controller and the processor is dynamically adjusted. When the computing load of the controller drops below the safe level, the controller can send a recovery request to the switch, requesting the switch to re - establish the connection link between the first port and the third port and disconnect the connection between the second port and the third port at the same time. This dynamic switching and recovery mechanism allows the controller to dynamically adjust the service processing mode according to the real - time load situation to ensure the efficient utilization of resources.
[0111] In the above manner, the controller can intelligently adjust the service processing mode according to its own operation load status, migrate some processing tasks to the processor, thereby avoiding controller overload and ensuring the stable operation of the system under high load conditions. At the same time, through the flexible control of the switch, the system can flexibly switch between different operation modes, improving the efficiency and reliability of power management.
[0112] As an optional embodiment, the control system of the server power supply further includes a switch. The first port of the switch is connected to the output end of the transmitter, the second port of the switch is connected to the output end of the processor, and the third port of the transmitter is connected to the controller.
[0113] The switch is further configured to: when receiving the service migration request, transmit the service migration request to the processor and conduct the connection link between the first port and the second port.
[0114] The processor is further configured to: call the connection link between the first port and the second port to obtain the candidate signal output by the transmitter.
[0115] Optionally, in the embodiments of the present application, Figure 4 is the hardware interaction for service migration according to a control system of a server power supply in the embodiments of the present application Figure 2 , as Figure 4 shown, the control system of the server power supply further includes a switch. The first port of the switch is connected to the output end of the transmitter, the second port of the switch is connected to the output end of the processor, and the third port of the transmitter is connected to the controller.
[0116] Optionally, in the embodiments of the present application, as Figure 4 shown, when the switch receives the service migration request sent by the controller, it will conduct the connection link between the second port and the third port, transmit the service migration request to the processor through the connection link between the second port and the third port, then disconnect the connection link between the second port and the third port, and conduct the connection link between the first port and the second port, that is, control the connection between the transmitter and the processor. Furthermore, the processor can directly obtain the candidate signal output by the transmitter through the connection link between the first port and the second port, and then perform processing such as parsing and calibration on the candidate signal to generate a target control instruction, and send the target control instruction to the controller to adjust the operation state of the power supply.
[0117] In the above manner, the switch can dynamically adjust the communication link according to the load status of the controller, adjust any connection mode among the controller, the processor, and the transmitter, and improve the service migration efficiency between the controller and the processor.
[0118] As an optional embodiment, the processor is further configured to: when determining the target control instruction to be transmitted to the controller, send a reference switching request to the switcher, where the reference switching request is used to request to switch the connection state between the processor, the controller, and the transmitter;
[0119] The switcher is further configured to: in response to the reference switching request, disconnect the connection link between the first port and the second port, and conduct the connection link between the second port and the third port;
[0120] The processor is further configured to: call the connection link between the second port and the third port to send the target control instruction to the controller.
[0121] Optionally, in the embodiments of the present application, Figure 5 It is a hardware interaction for service migration according to a control system of a server power supply in the embodiments of the present application Figure 3 , such as Figure 5 shown, when the processor determines that it is necessary to transmit a target control instruction to the controller, it sends a reference switching request to the switcher to request to conduct the connection link between the processor and the controller. After receiving the reference switching request sent by the processor, the switcher will disconnect the connection link between the first port and the second port, that is, disconnect the connection between the transmitter and the processor, and conduct the connection link between the second port and the third port, that is, control the connection between the processor and the controller. Furthermore, the processor can send the target control instruction to the controller through the connection link between the second port and the third port.
[0122] In the above manner, the switcher can flexibly adjust the connection state between the processor and the controller according to the service handling situation of the processor, and timely transmit the target control instruction generated by the processor to the controller, avoiding the situation of delay in the control instruction for the power supply due to resource tension of the controller, thereby improving the control efficiency of the server power supply.
[0123] As an optional embodiment, the processor is further configured to: when receiving a fault signal sent by the power supply, obtain the power operation information of the power supply stored in the cache space of the processor, where the fault signal is used to indicate that the power supply is currently in a fault state, and the power operation information is used to indicate the power supply situation of the server by the power supply within a reference time period before the current moment; predict the target fault information of the server power supply according to the power operation information; send the target fault information to the controller;
[0124] The controller is further configured to perform fault maintenance on the power supply according to the target fault information.
[0125] Optionally, in an embodiment of the present application, when the processor receives a fault signal sent by the power supply, it can obtain the power operation information of the power supply from the cache space of the processor, that is, the historical operation information of the power supply during a reference time period before the current moment (such as historical data of the voltage, current, and power output of the power supply); extract target fault features from the historical operation information, where the target fault features are used to indicate features related to power supply faults (such as abnormal voltage fluctuations, current spikes, continuously rising temperature, unstable power output, etc.); extract reference fault features from the power operation data collected in real time, and perform similarity matching between the reference fault features and the target fault features to calculate a similarity score; determine that there is a fault risk for the power supply when the similarity score exceeds a similarity threshold; and then generate target fault information for the power supply according to the reference fault features, where the target fault information may include, but is not limited to, fault type, possible fault location, and fault urgency, etc.; and send the target fault information to the controller. Then, after receiving the target fault information, the controller can quickly initiate a fault maintenance process according to the type, location, and urgency of the fault.
[0126] Optionally, in the embodiments of the present application, the cache space of the processor is used to cache and update in real time the signal data sent by the power supply in the chronological order of the signal sending time of the power supply. That is, after the cache space reaches the preset capacity or time window, the earliest signal data will be automatically cleared to make room for storing the latest signal data, ensuring that the cache space always stores the latest power operation information within a certain time range. When the cache space of the processor stores the signal data transmitted by the power supply, it will detect the validity of the signal data, and then eliminate the abnormal signal data. It can be: detecting the signal change amplitude of the candidate signal, where the candidate signal is used to indicate the signal stored in the cache space by the processor at the current moment; in the case where the signal change amplitude of the candidate signal is greater than the abnormal threshold, determining that the candidate signal is an abnormal signal and eliminating the candidate signal from the cache space. It can also be: detecting the signal change amplitude of the candidate signal, where the candidate signal is used to indicate the signal stored in the cache space by the processor at the current moment; predicting the signal trend information in the candidate time period after the current moment according to the historical signal data stored in the cache space, where the signal trend information is used to indicate the signal change amplitude corresponding to each moment in the candidate time period; finding the reference change amplitude corresponding to the current moment information from the signal trend information according to the current moment information, matching the signal change amplitude of the candidate signal with the reference change amplitude, and in the case where the signal change amplitude of the candidate signal is greater than the reference change amplitude, determining that the candidate signal is an abnormal signal and eliminating the candidate signal from the cache space.
[0127] Through the above method, the processor can perform fault prediction based on the historical operation information of the power supply when receiving a fault signal, so as to perform effective intervention and processing at the initial stage of the fault, provide accurate fault information for the controller, guide fast and effective fault maintenance operations, and significantly improve the efficiency of the server power supply fault response.
[0128] Optionally, in the embodiments of the present application, a reliable redundant server power supply communication monitoring design is also provided. This solution mainly adds an EEPROM chip (processor) between the PSU (power supply) and the BMC (controller). The real-time information of the PSU is stored in the EEPROM chip. When the information obtained by the system BMC is abnormal, the BMC grabs the PSU information in the EEPROM and compares it with the information obtained through the expansion chip (transmitter). If the information is consistent, it can be determined that the PSU is abnormal. If the information is inconsistent, it can be determined that the link is abnormal after the signal passes through the expansion chip. The BMC can temporarily switch to communicate with the EEPROM to ensure that the information can be normally parsed and obtained without affecting the normal business operation of the server.
[0129] Figure 6It is a hardware connection diagram designed for reliable redundant server power communication monitoring according to an embodiment of the present application. As Figure 6 shown, an EEPROM chip is added to the link between the server PSU and the BMC. A Switch is added near the BMC end. The expansion chip and the EEPROM chip communicate with the BMC through the Switch. It is mainly used to switch the communication channel between the PSU and the BMC. The I2C signals of the PSU are interconnected through connectors. The data of the PSU is connected to the Switch after being processed by the EEPROM chip and communicates with the system BMC. As the communication reliability and detection functions of the system are more and more numerous and complex, the space and processing timeliness of the BMC will be rather cumbersome. Therefore, the EEPROM can be partitioned according to the actual application situation, and the data originally processed in the BMC is moved to the EEPROM for processing, such as data format conversion, data calculation, status monitoring, etc. Taking the data processing of the PSU part as Figure 6 an example, it is divided into three areas: A, B, and C. Different areas are used to indicate different functional modules of the EEPROM (processor). For example, area A (i.e., functional module A) is used to record the real-time raw data of the PSU, area B (i.e., functional module B) monitors the status of the PSU and stores data. When the PSU fails, the data before the PSU failure can be obtained through an external interface, which is convenient for fault collection or processing. Area C (i.e., functional module C) is used to process the data of the PSU, including data format conversion, calculation of data such as power, current, and voltage, status monitoring and storing faults, etc. At the same time, the stored data can be made into a graphical interface. After the data is processed by area C, the BMC can directly obtain it without multiple conversion processes, saving the usage rate of the BMC. The EEPROM supports online upgrade and programming. According to different business requirements, different programs can be programmed to achieve personalized settings. The BMC can obtain information from the expansion chip and the EEPROM respectively by switching the Switch channel.
[0130] Figure 7 It is a method flowchart designed for reliable redundant server power communication monitoring according to an embodiment of the present application. As Figure 7 shown, due to the long communication link, when working normally, the BMC directly obtains the information of the PSU through the expansion chip and performs conversion processing within the BMC. Due to link interference or chip problems, the information of the PSU obtained by the BMC is abnormal. At this time, the BMC switches the communication channel through the Switch and continuously reads the information from the EEPROM three times and compares it with the directly obtained information. If the abnormal information is judged to be consistent, it can be determined that the information sent by the PSU is abnormal. After being parsed by the BMC, it is recognized. At this time, the BMC can issue an alarm to notify the maintenance personnel to record or process it.
[0131] For another link, after the system is powered on, the BMC writes the time to the EEPROM through the link to ensure that the time of the EEPROM is synchronized with the BMC time, which can ensure the consistency of the information obtained by the EEPROM and the BMC information. The EEPROM obtains the PSU information in real time and processes different data in different blocks respectively, which can greatly improve the working efficiency of the EEPROM. Figure 8 It is a flowchart of the EEPROM chip partition management designed for a reliable redundant server power communication monitoring according to an embodiment of the present application, as Figure 8 shown. The obtained raw PSU data is recorded and stored in area A in real time. Area B monitors and stores the real-time status of the PSU. Area C is used to process the PSU data, including data format conversion, calculation of data such as power, current, and voltage, status monitoring and storage of faults, etc. Synchronously, the stored data can be made into a graphical interface. When the PSU fails, the data in area A can be obtained at this time for secondary or multiple determinations. After determining that there is an abnormality, the BMC can be notified of the abnormality through the signal on the hardware link. The BMC can obtain the data when and before the PSU fails through an external interface, which is convenient for maintenance personnel to collect or handle faults. In addition, the data processed by the EEPROM can be directly obtained by the BMC without multiple conversion processes, saving the usage rate of the BMC.
[0132] Figure 9 It is a flowchart of service migration designed for a reliable redundant server power communication monitoring according to an embodiment of the present application, as Figure 9 shown. Under normal circumstances, the BMC directly obtains the information of the PSU through the expansion chip, so that the BMC and other component information or control are uniformly processed, which is beneficial to the overall planning and timeliness. However, as the information and components monitored and processed by the BMC increase, the usage rate of the BMC will continue to increase, which may cause delays or lags when obtaining information. At this time, the BMC can switch the communication link to the EEPROM by switching the SWITCH. The information of the PSU is processed in the EEPROM, and the BMC only needs to obtain the processed information, which can release the usage rate of the BMC and avoid delays or lags. At the same time, when an abnormal alarm appears in the EEPROM, the system BMC can be notified, which is convenient for maintenance personnel to collect or handle faults.
[0133] This solution adds an EEPROM chip between the PSU and the BMC. The real-time information of the PSU is stored in the EEPROM chip, and the information and data of the PSU can be independently processed, releasing the usage rate of the BMC and ensuring the stable and reliable operation of the system.
[0134] For the specific examples in this embodiment, reference can be made to the examples described in the above embodiments and exemplary embodiments, and details are not described herein again.
[0135] Obviously, those skilled in the art should understand that the various modules or steps of the present application described above can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed over a network composed of multiple computing devices. They can be implemented by program codes executable by the computing device. Thus, 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 here, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. In this way, the present application is not limited to any specific combination of hardware and software.
[0136] The above are only the preferred embodiments of the present application and are not used to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the principle of the present application shall be included within the protection scope of the present application.
Claims
1. A control system for a server power supply, It is characterized in that it includes a transmitter, a processor and a controller. The controller is respectively connected to the output end of the transmitter and the output end of the processor. The input end of the transmitter and the input end of the processor are used to connect to the power supply of the server; the transmitter is used to perform signal compensation on the initial signal output by the power supply according to the attenuation information, and transmit the obtained candidate signal to the controller, where the attenuation information is used to indicate the influence of the signal transmission link between the power supply and the controller on signal transmission, and the initial signal is used to indicate the power supply state of the server by the power supply; the processor is used to generate verification information of the initial signal according to the initial signal, where the verification information is used to indicate the signal value situation of the initial signal; the controller is used to calibrate the candidate signal according to the verification information to obtain a target signal; and use the target signal to control the operating state of the power supply.
2. The system according to claim 1, characterized in that the processor is further used to: obtain the target parameter type of the power supply parameter indicated by the initial signal; convert the target parameter value of the power supply parameter according to the target parameter type and the initial signal, where the verification information includes the target parameter value of the power supply parameter.
3. The system according to claim 2, characterized in that the processor is further used to: obtain the target conversion relationship corresponding to the target parameter type, where the target conversion relationship is the conversion relationship between the signal value of the signal and the parameter value of the power supply parameter of the target parameter type; use the target conversion relationship to convert the initial signal value of the initial signal into the target parameter value.
4. The system according to claim 1, characterized in that the processor is further used to: when the initial signal is a level signal, detect the target level value of the initial signal; and determine the target level value as the verification information.
5. The system according to claim 1, characterized in that the controller is further used to: match the initial signal value of the initial signal indicated by the verification information with the candidate signal value of the candidate signal; when the initial signal value and the candidate signal value do not match, use the initial signal value to calibrate the candidate signal to obtain the target signal.
6. The system according to claim 5, characterized in that the controller is further used to: when the candidate signal is a candidate level signal, perform signal compensation on the candidate level signal according to the difference value between the candidate signal value and the initial signal value to obtain a target level signal, where the target signal includes the target level signal.
7. The system according to claim 5, characterized in that the controller is further used to: when the initial signal value and the candidate signal value do not match, determine that the transmitter is faulty, and generate fault indication information for indicating that the transmitter is faulty; Send the fault indication information to a target account, where the target account is an account for maintaining the operating status of the server.
8. The system according to claim 7, wherein The controller is further configured to: when determining that the transmitter fails, send a signal acquisition request to the processor, where the signal acquisition request is used to request to acquire the initial signal output by the power supply through the processor; The processor is further configured to: when receiving the signal acquisition request, acquire the initial signal currently output by the power supply; compensate the initial signal according to target attenuation information, where the target attenuation information is used to indicate the influence of the signal transmission link between the processor and the controller on the signal transmission quality; and send the compensated signal to the controller.
9. The system according to claim 8, wherein The control system of the server power supply further includes a switch. A first port of the switch is connected to an output end of the transmitter, a second port of the switch is connected to an output end of the processor, and a third port of the transmitter is connected to the controller; The controller is further configured to: when determining that the transmitter fails, send a link switching request to the switch, where the link switching request is used to request to switch the connection status between the controller, the processor, and the transmitter; The switch is configured to: in response to the link switching request, disconnect the connection link between the first port and the third port, and conduct the connection link between the second port and the third port.
10. The system according to claim 5, wherein The controller is further configured to: when the initial signal value matches the candidate signal value, determine the candidate signal as the target signal.
11. The system according to claim 1, wherein The controller is further configured to: when detecting that the operation load of the controller is greater than or equal to a target load, send a service migration request to the processor, where the service migration request is used to request to migrate the services to be processed by the controller to the processor; The processor is further configured to: when receiving the service migration request, acquire the candidate signal output by the transmitter; calibrate the candidate signal according to the verification information to obtain the target signal; generate a target control instruction for the power supply according to the target signal, where the target control instruction is used to indicate the operating status of the power supply; and send the target control instruction to the controller; The controller is further configured to: when receiving the target control instruction, control the operating status of the power supply using the target control instruction.
12. The system according to claim 11, wherein The control system of the server power supply further includes a switcher. The first port of the switcher is connected to the output end of the transmitter. The second port of the switcher is connected to the output end of the processor. The third port of the transmitter is connected to the controller; The controller is further configured to: when it is necessary to send the service migration request to the processor, send a target switching request to the switcher, where the target switching request is used to request to switch the connection status between the controller, the processor, and the transmitter; The switcher is further configured to: in response to the target switching request, disconnect the connection link between the first port and the third port, and conduct the connection link between the second port and the third port; The controller is further configured to: when it is determined that the switcher conducts the connection link between the second port and the third port, send the service migration request to the processor.
13. The system according to claim 11, wherein The control system of the server power supply further includes a switcher. The first port of the switcher is connected to the output end of the transmitter. The second port of the switcher is connected to the output end of the processor. The third port of the transmitter is connected to the controller; The switcher is further configured to: when receiving the service migration request, transmit the service migration request to the processor, and conduct the connection link between the first port and the second port; The processor is further configured to: call the connection link between the first port and the second port to obtain the candidate signal output by the transmitter.
14. The system according to claim 13, wherein The processor is further configured to: when determining the target control instruction to be transmitted to the controller, send a reference switching request to the switcher, where the reference switching request is used to request to switch the connection status between the processor, the controller, and the transmitter; The switcher is further configured to: in response to the reference switching request, disconnect the connection link between the first port and the second port, and conduct the connection link between the second port and the third port; The processor is further configured to: call the connection link between the second port and the third port to send the target control instruction to the controller.
15. The system according to claim 1, wherein The processor is further configured to: when receiving the fault signal sent by the power supply, obtain the power operation information of the power supply stored in the cache space of the processor, where the fault signal is used to indicate that the power supply is currently in a fault state, and the power operation information is used to indicate the power supply situation of the server by the power supply within a reference time period before the current moment; predict the target fault information of the server power supply according to the power operation information; send the target fault information to the controller; The controller is further configured to: perform fault maintenance on the power supply according to the target fault information.
Citation Information
Patent Citations
Direct current power supply system and communication system
CN115378120A
Firmware updating method, system and product
CN118708210A