Power management system and method for server, and device, medium and program product

Abstract

The present application relates to the technical field of power management. Provided are a power management system and method for a server, and a device, a medium and a program product. The system comprises a power supply unit, a backup battery unit, and a power control device. A baseboard management controller in a server is used for configuring an abnormal power-off sequence for the power supply unit in response to detecting that the server is a storage server, wherein the abnormal power-off sequence comprises an alarm value used for triggering the power supply unit to issue power anomaly alarm information, the alarm value being less than a fault value when a fault occurs in the power supply unit. The power control device is used for switching, when it is detected that the power supply unit issues a power anomaly alarm signal, the backup battery unit to supply power to a fan and the baseboard management controller in the server, and for performing data backup.

Description

Server power management system, method, device, medium and program product

[0001] Cross-reference to Related Applications

[0002] This application claims priority to the Chinese patent application No. 202411370072.5, filed on September 29, 2024, and entitled “Server power management system, method, device, medium and program product”, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present application relates to the technical field of power management, in particular to a server power management system, method, device, medium and program product. BACKGROUND

[0004] With the continuous development of digital technology, the amount of data is also increasing, and storage servers for data storage have been widely used. Correspondingly, the use requirements for storage servers are becoming higher and higher. Especially the power management scheme of the storage server is becoming more and more demanding. SUMMARY

[0005] The present application provides a server power management system, method, device, medium and program product.

[0006] The present application provides a server power management system, which comprises a power supply unit, a backup battery unit and a power control device.

[0007] The baseboard management controller in the server is configured to configure a power abnormality power-off time sequence for the power supply unit in response to detecting that the server is a storage server; the power abnormality power-off time sequence comprises an alarm value for triggering the power supply unit to send a power abnormality alarm information, and the alarm value is less than a fault value when the power supply unit fails; and

[0008] The power control device is configured to switch the backup battery unit to supply power to the fan and the baseboard management controller in the server and perform data backup in response to detecting that the power supply unit sends a power abnormality alarm signal.

[0009] According to the server power management system provided by the present application, the power supply unit is connected with the power control device and the hard disk, the expansion card, the fan and the baseboard management controller in the server respectively, and the backup battery unit is electrically connected with the power control device and the fan and the baseboard management controller in the server.

[0010] In response to determining that the backup battery unit supplies power to the fan and the baseboard management controller in the server, the hard disk and the expansion card are powered off.

[0011] According to the server power management system provided in the application, the power control device is further configured to: perform in-place signal determination on the power supply unit; and in response to determining that the in-place signal of the first power supply unit or the second power supply unit changes, re-perform server type detection.

[0012] According to the server power management system provided in the application, the power control device is further configured to: in response to determining that the in-place signal of the power supply unit does not change, detect time synchronization information between the power supply unit and the power control device; and in response to determining that a time deviation between the power supply unit and the power control device exceeds a preset time length according to the time synchronization information, the power control device sends the time synchronization information to the power supply unit to ensure that the time stamps of the power supply unit and the power control device match.

[0013] According to the server power management system provided in the application, the baseboard management controller is configured to: perform power redundancy supply mode setting according to a master-slave mode instruction input by a user; wherein the power redundancy supply mode includes: current-sharing redundancy supply mode, forced master-slave supply mode master, forced master-slave redundancy supply mode slave, and automatic master-slave redundancy supply mode master.

[0014] According to the server power management system provided in the application, the baseboard management controller is further configured to: in response to detecting a power abnormality alarm signal of the power supply unit, collect the power abnormality alarm signal and write the power abnormality alarm signal into an abnormality log.

[0015] According to the server power management system provided in the application, the server further includes: an evaluation control unit; wherein the evaluation control unit is configured to: perform state monitoring and backup power supply capability evaluation on the backup battery unit; and in response to determining that the backup power supply capability of the backup battery unit is abnormal, generate a backup power supply alarm signal.

[0016] According to the server power management system provided in the application, the evaluation control unit is further configured to: in response to determining that the server is a non-storage server, monitor the power supply unit; and in response to detecting a power abnormality alarm signal sent by the power supply unit, control the server to perform frequency reduction processing.

[0017] According to the server power management system provided in the application, the power supply unit each includes: a first pull-up resistor, a second pull-up resistor, a third zero-ohm resistor, a fourth pull-down resistor, a fifth pull-down resistor, a sixth pull-up resistor, a seventh pull-up resistor, an eighth pull-up resistor, a ninth pull-down resistor, and a power supply element.

[0018] The serial data line is connected to the power supply element through a first pull-up resistor; the serial clock line is connected to the power supply element through a second pull-up resistor; the first address line is connected to the power supply element through a sixth pull-up resistor; the second address line is connected to the power supply element through a seventh pull-up resistor; the power-on signal interface is grounded through a third zero-ohm resistor; the alarm signal interface is grounded through a fourth pull-down resistor; the power state signal interface is grounded through a fifth pull-down resistor; the input voltage normal signal interface is grounded through a ninth pull-down resistor; and the presence signal interface is connected to the power supply element through an eighth pull-up resistor.

[0019] According to the server power management system provided in the application, the power supply unit is configured to: generate a presence signal in response to determining that the power supply unit is in place and the presence signal interface is in a high level state; and stop generating the presence signal in response to determining that the power supply unit is not in place and the presence signal interface is in a low level state.

[0020] The application further provides a server power management method based on any one of the above server power management systems, comprising:

[0021] The baseboard management controller is configured to configure a power supply abnormal power-off timing for the power supply unit in response to detecting that the server is a storage server; wherein the power supply abnormal power-off timing comprises: an alarm value for triggering the power supply unit to send a power supply abnormal alarm information, the alarm value being less than a fault value when the power supply unit fails; and

[0022] The power control device is configured to switch the backup battery unit to supply power to the fan and the baseboard management controller in the server and perform data backup in response to detecting that the power supply unit sends a power supply abnormal alarm signal.

[0023] According to the server power management method provided in the embodiments of the application,

[0024] The baseboard management controller is configured to configure a power supply abnormal power-off timing for the power supply unit in response to detecting that the server is a storage server, comprising:

[0025] In response to determining that the server power management system comprises a first power supply unit and a second power supply unit, a first early warning value is configured for the first power supply unit, and a second early warning value is configured for the second power supply unit;

[0026] The first early warning value is less than a first fault value of the first power supply unit, the first early warning value is used to trigger the first power supply unit to generate a power supply abnormal alarm signal, and the first fault value is a threshold value when the first power supply unit triggers a fault; and

[0027] The second early warning value is less than a second failure value of the second power supply unit, the second early warning value is used to trigger the second power supply unit to generate a power abnormality alarm signal, and the second failure value is a threshold value when the second power supply unit triggers a failure.

[0028] The server power management method provided by the embodiment of the present application further comprises, before the step of configuring the power abnormality power-off sequence for the power supply unit by the baseboard management controller in response to detecting that the server is a storage server:

[0029] The power supply unit is subjected to in-place signal determination; and

[0030] The server type of the server is detected by the power supply control device in response to determining that the in-place signal of the first power supply unit or the second power supply unit changes.

[0031] The server power management method provided by the embodiment of the present application further comprises, after the step of determining the in-place signal of the power supply unit:

[0032] The time synchronization information between the power supply unit and the power supply control device is detected in response to determining that the in-place signal of the power supply unit does not change, and the power supply control device sends the time synchronization information to the power supply unit to ensure that the time stamps of the power supply unit and the power supply control device match in response to determining that the time deviation between the power supply unit and the power supply control device exceeds a preset time length according to the time synchronization information.

[0033] The server power management method provided by the embodiment of the present application further comprises:

[0034] The power supply redundant power supply mode is set according to the master-slave mode instruction input by the user, and the power supply redundant power supply mode includes: a current-sharing redundant power supply mode, a forced master-slave power supply mode master, a forced master-slave redundant power supply mode slave, and an automatic master-slave redundant power supply mode master.

[0035] The server power management method provided by the embodiment of the present application further comprises: in response to detecting a power abnormality alarm signal of the power supply unit, collecting the power abnormality alarm signal and writing the power abnormality alarm signal into an exception log.

[0036] The server power management method provided by the embodiment of the present application further comprises: in response to determining that the server is a non-storage server, an evaluation control unit in the server monitors the power supply unit; and in response to detecting a power abnormality alarm signal sent by the power supply unit, the server is controlled to perform frequency reduction processing.

[0037] The application further provides an electronic device, comprising one or more processors; and a memory associated with the one or more processors, the memory being configured to store computer readable instructions which, when executed by the one or more processors, implement any of the server power management methods described above.

[0038] The application further provides a non-transitory computer readable storage medium, the storage medium storing computer readable instructions which, when executed by one or more processors, implement any of the server power management methods described above.

[0039] The application further provides a computer program product, comprising computer readable instructions which, when executed by one or more processors, implement any of the server power management methods described above. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the application or related art, the drawings needed to be used in the embodiments or related art description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0041] Fig. 1 is a structural schematic diagram of a server power management system according to an embodiment of the application.

[0042] Fig. 2 is a structural schematic diagram of a power supply unit according to an embodiment of the application.

[0043] Fig. 3 is a server power management method according to an embodiment of the application.

[0044] Fig. 4 is a schematic diagram of an intelligent control algorithm of a power module according to an embodiment of the application.

[0045] Fig. 5 is a schematic diagram of an intelligent control flow according to an embodiment of the application.

[0046] Fig. 6 is a structural schematic diagram of an electronic device according to an embodiment of the application.

[0047] Fig. 7 is a structural schematic diagram of a computer program product according to an embodiment of the application.

[0048] Fig. 8 is a structural schematic diagram of a non-transitory computer readable storage medium according to an embodiment of the application. DETAILED DESCRIPTION

[0049] In order to make the purposes, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below in combination with the drawings in the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0050] FIG. 1 is a structural schematic diagram of a server power management system provided by an embodiment of the present application, as shown in FIG. 1, which includes a power supply unit (PSU) 11, a backup battery unit (BBU) 12 and a power control device 13.

[0051] The power supply unit 11 is connected with the power control device 13 and the hard disk, expansion card, fan and baseboard management controller in the server respectively, and the backup battery unit 12 is electrically connected with the power control device 13 and the fan and baseboard management controller (BMC) in the server.

[0052] The baseboard management controller in the server is configured to configure a power abnormality power-off time sequence for the power supply unit in response to detecting that the server is a storage server. The power abnormality power-off time sequence includes an alarm value for triggering the power supply unit to send power abnormality alarm information, and the alarm value is less than a fault value when the power supply unit fails.

[0053] The power abnormality power-off time sequence includes an alarm value for triggering the power supply unit to send power abnormality alarm information, and the alarm value is less than a fault value when the power supply unit fails. The power control device 13 is configured to switch the backup battery unit 12 to supply power to the fan and baseboard management controller in the server and perform data backup in response to detecting that the power supply unit 11 sends a power abnormality alarm signal.

[0054] In the embodiment of the present application, the power supply unit 11 is a main power supply unit of the server, which can include a first power supply unit PUS1 and a second power supply unit PUS2, and they provide power for the hard disk, expansion card, fan and baseboard management controller inside the server.

[0055] The BMC is responsible for monitoring and managing the hardware state of the server. In response to the server being identified as a storage server, the BMC will specially configure a power abnormality power-off time sequence for the PSU1 and PSU2, so that in the case of sending a power alarm, the power abnormality power-off time sequence is processed, thereby ensuring the safety of data storage.

[0056] In the embodiments of the present application, PSU1 and PSU2 can be connected with the fan and the baseboard management controller through an electronic fuse (EFUSE) and an anti-inrush circuit ORING for current protection.

[0057] The backup battery unit is an emergency power supply for the system, which intervenes when the main power supply unit fails, ensuring that the server can continue to run for a period of time to perform necessary operations such as data backup. The power control device is responsible for monitoring the status of PSU1 and PSU2, and automatically switching to BBU power supply when both power supply units issue abnormal alarm signals within a preset time period. This process ensures that critical components of the server, such as the fan and the BMC, do not stop working due to power problems, thereby avoiding the risk of overheating or data loss.

[0058] In addition, the power control device is also responsible for managing the redundant power supply mode of the power module, automatically switching between current-sharing redundant power supply mode and master-slave redundant power supply mode according to the size of the load current. This intelligent management strategy helps to improve the energy efficiency of the server and reduce unnecessary energy consumption.

[0059] In the embodiments of the present application, the storage server and the non-storage server are distinguished by identifying the type of the server. The server type identification method can be to read the server model of the server, or to identify the type of the server according to the hardware architecture, storage capacity of the server, or the different communication protocols supported by the server.

[0060] In the case of identifying the server as a storage server, it means that when a power failure occurs, the server also needs to consider the problem of data backup. Therefore, the related information of the power-off timing of the power abnormality of at least one power supply unit can be further configured, so that the first power supply unit and the second power supply unit generate a power abnormality alarm signal in advance and switch the backup battery unit to supply power to the fan and the baseboard management controller in the server when they both meet the warning value but do not reach the failure value. Provide power for critical components, prevent data loss and service interruption, and perform data backup, thereby effectively protecting the data stored by the server from being damaged.

[0061] In some embodiments, at least one power supply unit is connected with the power control device and the hard disk, expansion card, fan, and baseboard management controller in the server, and the backup battery unit is electrically connected with the power control device and the fan and baseboard management controller in the server. In response to determining that the backup battery unit supplies power to the fan and the baseboard management controller in the server, the hard disk and the expansion card are powered off. This can effectively reduce the load pressure of the backup battery unit.

[0062] In some embodiments, the baseboard management controller is configured to configure a first pre-warning value for the first power supply unit and a second pre-warning value for the second power supply unit in response to determining that the server is a storage server.

[0063] wherein the first pre-warning value is less than a first failure value of the first power supply unit, and the first pre-warning value is configured to trigger the first power supply unit to generate a power abnormality alarm signal, and the first failure value is a threshold value at which the first power supply unit triggers a failure.

[0064] wherein the second pre-warning value is less than a second failure value of the second power supply unit, and the second pre-warning value is configured to trigger the second power supply unit to generate a power abnormality alarm signal, and the second failure value is a threshold value at which the second power supply unit triggers a failure.

[0065] In the embodiments of the present application, when the server is identified as a storage server, the BMC configures at least one power supply unit with a first pre-warning value and a second pre-warning value respectively. These pre-warning values are pre-set threshold values that are used to monitor the power status of the power supply unit.

[0066] The first pre-warning value is set to be lower than the first failure value of the first power supply unit. This means that when the power status of the first power supply unit reaches the first pre-warning value but has not yet reached the first failure value, a power abnormality alarm signal will be triggered.

[0067] Similarly, the second pre-warning value is also set to be lower than the second failure value of the second power supply unit. When the power status of the second power supply unit reaches the second pre-warning value but has not yet reached the second failure value, a power abnormality alarm signal will also be triggered.

[0068] In some embodiments, the first pre-warning value and the second pre-warning value are set so that the power supply unit can issue an alarm signal in advance before reaching the failure value, thereby providing sufficient time for the power control device to take measures such as switching to a backup battery unit or performing other protection measures.

[0069] Through this pre-warning mechanism, the BMC can more effectively manage the power supply because it can take action before the power supply unit fails.

[0070] This method improves the response speed of the system and reduces the risk of data loss or service interruption due to power problems.

[0071] At the same time, by providing a pre-warning before failure occurs, the system can plan data backup and power switching, further protecting the data stored by the server and the stability of the system.

[0072] In some embodiments, the power supply control device is further configured to perform in-place signal determination on the power supply unit. In response to determining that the in-place signal of the first power supply unit or the second power supply unit changes, the power supply control device re-performs server type detection.

[0073] In embodiments of the present application, the power supply control device is responsible for monitoring the in-place signal (usually a logic signal such as the PRESENT signal) of at least one power supply unit. The in-place signal is used to indicate whether the power supply unit is properly installed and connected to the server. In response to determining that the power supply unit is in place, the signal is usually set to high level. In response to determining that it is not in place, it is set to low level.

[0074] In embodiments of the present application, when the power supply control device detects a change in the in-place signal of the power supply unit, it triggers a response mechanism. The change in the in-place signal can mean that the power supply unit is replaced, removed, or has a connection problem.

[0075] In embodiments of the present application, after detecting a change in the in-place signal, the power supply control device re-performs server type detection. This is to ensure that the power management strategy matches the current actual configuration and needs of the server.

[0076] Server type detection can involve identifying whether the server is a storage type, a computing type, or other types, as different types of servers can require different power management strategies.

[0077] In embodiments of the present application, the power supply control device monitors the in-place signal of the power supply unit and re-detects the server type when the signal changes, achieving intelligent adaptation and optimization of the power management system, further improving the efficiency and reliability of server power management.

[0078] In some embodiments, the power supply control device is further configured to, in response to determining that the in-place signal of the power supply unit does not change, detect time synchronization information between the power supply unit and the power supply control device. In response to determining that the time deviation between the power supply unit and the power supply control device exceeds a preset time length according to the time synchronization information, the power supply control device sends time synchronization information to the power supply unit to ensure that the time stamps of the power supply unit and the power supply control device match.

[0079] In embodiments of the present application, when the in-place signal of at least one power supply unit does not change, the power supply control device detects the time synchronization information between the two power supply units and itself. The time synchronization information ensures that the power supply unit and the power supply control device are consistent in time.

[0080] In response to detecting that the time deviation between the power supply unit and the power supply controller according to the time synchronization information exceeds the preset time length, the power supply controller sends new time synchronization information to at least one power supply unit. This is to ensure that the timestamp of at least one power supply unit matches the timestamp of the power supply controller.

[0081] In the embodiments of the present application, by periodically checking and updating the time synchronization information, the power supply controller ensures the consistency of the entire power management system in time, which is crucial for system logging, fault analysis and event correlation.

[0082] In some embodiments, the baseboard management controller is configured to: set the power supply redundancy mode according to the user inputted master-slave mode instruction.

[0083] The power supply redundancy mode includes: current-sharing redundancy power supply mode, forced master-slave power supply mode master, forced master-slave redundancy power supply mode slave, and automatic master-slave redundancy power supply mode master.

[0084] In the embodiments of the present application, the user can send instructions to the BMC through a specific interface (such as a command line interface, a graphical interface or a remote management interface) to configure the operation mode of the power supply system. The BMC sets the power supply redundancy mode according to the user inputted master-slave mode instruction.

[0085] In the embodiments of the present application, the redundancy power supply mode control algorithm is as follows:

[0086] In some embodiments, the current-sharing redundancy power supply mode: in this mode, multiple power supply units (such as the first power supply unit and the second power supply unit) share the power supply demand of the server, and each power supply unit outputs the same or proportionally allocated current.

[0087] Forced master-slave power supply mode master: in this mode, one power supply unit (master) is responsible for providing all or most of the power, and the other power supply unit (slave) takes over the power supply when the master fails.

[0088] Forced master-slave redundancy power supply mode slave: in contrast to the forced master-slave power supply mode master, in this mode, the slave power supply unit is in standby state and is activated only when the master power supply unit has a problem.

[0089] Automatic master-slave redundancy power supply mode master: in this mode, the system automatically selects one power supply unit as the master and the other as the slave, and automatically switches according to the state and load of the power supply unit.

[0090] In some embodiments, the baseboard management controller is further configured to, in response to detecting the power abnormality alarm signal of the power supply unit, collect the power abnormality alarm signal and write the power abnormality alarm signal into an exception log.

[0091] In the embodiments of the present application, the BMC continuously monitors the status of at least one power supply unit. When any power supply unit detects a power abnormality (such as overvoltage, undervoltage, overtemperature, etc.), it will send an alarm signal.

[0092] Once the BMC detects the power abnormality alarm signal, it will immediately collect these signals. The collected information can include the type of alarm signal, the time of occurrence, the duration, and related power parameters. The BMC records the collected power abnormality alarm signal information in the exception log of the server. The exception log is a file that records abnormal events that occur during system operation, and it is crucial for fault diagnosis and system maintenance. In the embodiments of the present application, through the recording of the exception log, the problem can be accurately analyzed and located using the log record, effectively improving the processing efficiency.

[0093] In some embodiments, the server further comprises an evaluation control unit. The evaluation control unit is configured to monitor the state of the backup battery unit and evaluate the backup power capability. In response to determining that the backup battery unit has an abnormal backup power capability, a backup power alarm signal is generated.

[0094] In the embodiments of the present application, the evaluation control unit continuously monitors the state of the backup battery unit, including key parameters such as the state of charge, the state of discharge, the voltage level, the temperature, the degree of aging, etc. This monitoring helps to ensure that the backup battery unit is always in good working condition, so that it can take over power supply in case of problems with the power supply unit.

[0095] The evaluation control unit periodically evaluates the backup power capability of the backup battery unit, i.e., evaluates the length of time that the battery can support the operation of the server in the case of power failure. When the evaluation control unit detects an abnormal backup power capability of the backup battery unit, such as the battery capacity being below a predetermined threshold, the battery being unable to charge or discharge normally, the battery temperature being abnormal, etc., it will generate a backup power alarm signal. This alarm signal will be synchronized to the baseboard management controller (BMC) so that appropriate measures can be taken, such as replacing the battery, performing battery maintenance, or adjusting the power management strategy.

[0096] In the embodiments of the present application, through continuous monitoring and evaluation of the backup battery unit, the system can timely discover potential problems, thereby avoiding server downtime due to battery failure in emergency situations.

[0097] In some embodiments, the evaluation control unit is further configured to monitor the at least one power supply unit in response to determining that the server is a non-storage server. In response to detecting an abnormal power alarm signal emitted by the power supply unit, the server is controlled to perform frequency reduction processing. In the embodiments of the present application, when the server is a non-storage server, the evaluation control unit is responsible for real-time monitoring of the at least one power supply unit. The monitoring content includes but is not limited to parameters such as power output voltage, current, power, temperature, and the working state and any abnormal conditions of the power supply unit. The evaluation control unit continuously detects whether the at least one power supply unit emits an abnormal power alarm signal. These alarm signals can be caused by power failure, overload, overheating or other power-related problems. Once an abnormal power alarm signal is detected, the evaluation control unit will take measures to protect the server hardware and maintain the stable operation of the system.

[0098] The frequency reduction processing refers to reducing the running frequency of the CPU (central processing unit) or other processors of the server to reduce power consumption and heat generation. By frequency reduction, the server can continue to run critical tasks when the power supply is insufficient or there is a potential power problem, while reducing the demand for power supply and avoiding system crash.

[0099] In the embodiments of the present application, the evaluation control unit enhances the self-protection capability of the server in abnormal power supply conditions by monitoring the power supply state and implementing frequency reduction processing when necessary, ensuring the high availability and data security of the server.

[0100] In some embodiments, FIG. 2 is a structural diagram of a power supply unit provided by the embodiments of the present application, as shown in FIG. 2, the power supply unit comprises: a first pull-up resistor R1, a second pull-up resistor R2, a third zero-ohm resistor R3, a fourth pull-down resistor R4, a fifth pull-down resistor R5, a sixth pull-up resistor R6, a seventh pull-up resistor R7, an eighth pull-up resistor R8, a ninth pull-down resistor R9, and a power supply.

[0101] The serial data line is connected to the power supply through the first pull-up resistor, and the serial clock line is connected to the power supply through the second pull-up resistor. The first address line is connected to the power supply through the sixth pull-up resistor, and the second address line is connected to the power supply through the seventh pull-up resistor. The power-on signal interface is grounded through the third zero-ohm resistor, the alarm signal interface is grounded through the fourth pull-down resistor, the power supply state signal interface is grounded through the fifth pull-down resistor, the input voltage normal signal interface is grounded through the ninth pull-down resistor, and the presence signal interface is connected to the power supply through the eighth pull-up resistor. The serial data line (Serial Data, SDA) is connected to the power supply through the first pull-up resistor. This means that when the SDA line is at a high level, it will be pulled to the power supply voltage level through the first pull-up resistor. The serial clock line (Serial Clock Line, SCL) is connected to the power supply through the second pull-up resistor. Similarly, when the SCL line is at a high level, it will be pulled to the power supply voltage level through the second pull-up resistor.

[0102] In the embodiments of the present application, the first address line (AD0) is connected to the power supply through the sixth pull-up resistor. This is used to set or read the address of the PMBus (Power Management Bus, power management bus) device. The second address line (AD1) is connected to the power supply through the seventh pull-up resistor. Similarly, this is also part of the address configuration.

[0103] The power-on signal interface is grounded through the third zero-ohm resistor. Zero-ohm resistors are often used in circuit design to provide configurable connection points, and the third zero-ohm resistor is grounded to disconnect or connect the power-on signal when needed.

[0104] The PSU state signals Alert, Pwok, and Vin-good are grounded through pull-down resistors, and the Present signal is connected to 3.3V through a pull-up resistor, ensuring accurate identification of abnormal power supply states when the power supply is not in place. The PSU LS bus is connected to a block, and the printed board is designed away from interference sources to ensure that the current sharing accuracy is within 5%.

[0105] The PRESENT signal is connected through a pull-up resistor to ensure that the PRESENT signal is invalid when the PSU is not in place. The baseboard management controller (BMC) identifies the PRESENT signal and intelligently configures the power-down timing sequence when the server system is powered on or the PRESENT signal changes from invalid to valid in the event of PSU failure.

[0106] In the embodiments of the present application, these connection relationships ensure that each signal line can provide the correct level state at the appropriate time, thereby ensuring the stability and reliability of PMBus communication, and also providing necessary control and monitoring signals for the power management system.

[0107] In some embodiments, the power supply unit is configured to generate the presence signal in response to determining that the power supply unit is present and the presence signal interface is in a high state. The power supply unit is configured to stop generating the presence signal in response to determining that the power supply unit is not present and the presence signal interface is in a low state.

[0108] In embodiments of the application, when the power supply units are properly installed in the server and functioning correctly, they will drive the presence signal interface (often labeled as PRESENT or similar) to a high state through internal circuitry. This signal interface is usually connected to the power supply through a pull-up resistor to ensure that the presence signal interface can remain high when the power supply unit is present.

[0109] The high presence signal indicates that the power supply unit is ready and can provide power. This signal is detected by the server's baseboard management controller (BMC) or other management circuitry to confirm the presence and status of the power supply unit.

[0110] In response to determining that the power supply unit is removed or cannot function properly due to a fault, the internal circuitry will no longer be able to drive the presence signal interface to a high state, so the interface will be in a low state due to the action of the pull-down resistor.

[0111] The low presence signal indicates that the power supply unit is not present or cannot function. After detecting this signal, the server management system can take a series of measures, such as attempting to start a backup power supply unit, recording an event, sending an alarm to notify the administrator, or taking other fault handling procedures.

[0112] Figure 3 is a server power management method provided by embodiments of the application, as shown in Figure 3, comprising:

[0113] Step 310, the baseboard management controller configures a power supply abnormal power-off timing for the power supply unit in response to detecting that the server is a storage server. The power supply abnormal power-off timing includes an alarm value for triggering the power supply unit to send power supply abnormal alarm information, and the alarm value is less than a fault value when the power supply unit fails.

[0114] The baseboard management controller (BMC) first detects the type of server. In response to determining that the server is identified as a storage server, the BMC will configure a power supply abnormal power-off timing for at least one power supply unit.

[0115] In embodiments of the application, the power supply abnormal power-off timing can be a first warning value configured for a first power supply unit and a second warning value configured for a second power supply unit. This is used to safely shut down the power supply unit when the power supply is abnormal. This prevents data loss or hardware damage.

[0116] At step 320, the power control device is configured to switch to the backup battery unit to power the fans and the baseboard management controller (BMC) in the server and initiate a data backup process in response to detecting that both power supply units are issuing power anomaly alarm signals.

[0117] In embodiments of the present application, the power control device monitors whether at least one power supply unit is issuing a power anomaly alarm signal within a first predetermined time period.

[0118] If the power control device detects that both power supply units are issuing a power anomaly alarm signal within the first predetermined time period, it indicates that the server may be facing a serious power issue.

[0119] In response, the power control device switches to the backup battery unit to ensure that critical components such as the fans and the BMC are still powered in the event of a main power failure.

[0120] The backup battery unit will power the fans and the BMC to maintain necessary cooling and system management functions. At the same time, the power control device will also trigger a data backup process to protect data in the server from being lost due to power issues.

[0121] In some embodiments, the baseboard management controller is configured to configure a power anomaly power-off timing for the power supply units in response to detecting that the server is a storage server, comprising:

[0122] In response to determining that the server power management system includes a first power supply unit and a second power supply unit, a first warning value is configured for the first power supply unit and a second warning value is configured for the second power supply unit.

[0123] The first warning value is less than a first failure value of the first power supply unit, and the first warning value is used to trigger the first power supply unit to generate a power anomaly alarm signal, and the first failure value is a threshold value when the first power supply unit triggers a failure.

[0124] The second warning value is less than a second failure value of the second power supply unit, and the second warning value is used to trigger the second power supply unit to generate a power anomaly alarm signal, and the second failure value is a threshold value when the second power supply unit triggers a failure.

[0125] In embodiments of the present application, for the first power supply unit, the BMC configures a first warning value for it. This warning value is a specific power parameter threshold, such as a voltage or current level, which is less than the first failure value of the first power supply unit.

[0126] For the second power supply unit, the BMC configures a second pre-alarm value for it. Again, this pre-alarm value is less than the second failure value of the second power supply unit.

[0127] The first pre-alarm value is less than the first failure value of the first power supply unit. This means that when the parameter of the power supply unit reaches the first pre-alarm value, it has not yet reached the failure state, but is close enough to warrant an alarm signal.

[0128] The second pre-alarm value is less than the second failure value of the second power supply unit. Again, this means that when the parameter of the power supply unit reaches the second pre-alarm value, an alarm signal needs to be generated.

[0129] When the parameter of the first power supply unit reaches the first pre-alarm value, it triggers the generation of a power anomaly alarm signal, informing the BMC that there might be a problem with the power supply unit. When the parameter of the second power supply unit reaches the second pre-alarm value, it also triggers the generation of a power anomaly alarm signal.

[0130] The first failure value is the threshold at which the first power supply unit triggers a failure, i.e. when the parameter of the power supply unit reaches or exceeds this value, the power supply unit is considered to have failed. The second failure value is the threshold at which the second power supply unit triggers a failure, and serves the same purpose as the first failure value.

[0131] In some embodiments, the baseboard management controller, in response to detecting that the server is a storage server, before the step of configuring the power anomaly power down timing for the at least one power supply unit, further comprises performing a presence signal determination for the power supply unit. In response to determining that the presence signal of the first power supply unit or the second power supply unit has changed, the power control device performs a server type detection for the server.

[0132] In embodiments of the application, the BMC performs a presence signal determination for the at least one power supply unit. If the presence signals indicate that the power supply units are correctly installed and ready for operation (typically a high level state), the BMC considers these units to be present and available.

[0133] The BMC continuously monitors these presence signals to detect any changes. If the BMC detects a change in the presence signal of a power supply unit, this can be due to the power supply unit being unplugged, plugged in, or failing.

[0134] Once a change in the presence signal is detected, the power control device (which can be the BMC or other control logic) performs a server type detection. The purpose of the server type detection is to determine the model and configuration of the server, so that the correct power management strategy can be applied.

[0135] In some embodiments, the method further comprises: in response to determining that the in-place signal of the power supply unit does not change, detecting time synchronization information between the power supply unit and the power supply control device. In response to determining that the time synchronization information exceeds the first preset time length compared with the current time, the power supply control device sends the time synchronization information to the power supply unit to ensure that the time stamp of the power supply unit matches that of the power supply control device.

[0136] In the embodiments of the present application, the BMC or the power supply control device detects time synchronization information between at least one power supply unit and the power supply control device. The time synchronization information is used to ensure that the power supply unit and the power supply control device operate according to the same time reference, which is crucial for coordinating operations and event recording.

[0137] According to the detected time synchronization information, it is determined whether re-synchronization is needed. If the time deviation between the power supply unit and the power supply control device exceeds the preset time length according to the time synchronization information, it indicates that re-synchronization is needed. The power supply control device sends the time synchronization information to at least one power supply unit.

[0138] The purpose of this is to correct the time deviation and ensure that the time stamp of at least one power supply unit matches that of the power supply control device.

[0139] In some embodiments, the method further comprises: setting a power supply redundancy mode according to a user inputted master-slave mode instruction. The power supply redundancy mode includes: a current-sharing redundancy power supply mode, a forced master-slave power supply mode master, a forced master-slave redundancy power supply mode slave, and an automatic master-slave redundancy power supply mode master.

[0140] In the embodiments of the present application, the current-sharing redundancy power supply mode means that two power supply units (such as at least one power supply unit) work simultaneously and share the total power demand of the server equally. This mode can improve the efficiency and reliability of the power supply, because each power supply unit bears a part of the load, reducing the burden of a single power supply unit.

[0141] The forced master-slave power supply mode master means that one power supply unit (master) is responsible for providing all power demand of the server, while the other power supply unit (slave) is in standby state. In response to determining that the master power supply fails, the slave power supply will automatically take over the power supply to ensure the continuous operation of the server.

[0142] The forced master-slave redundancy power supply mode slave means that it is similar to the forced master-slave power supply mode master, but the roles are reversed. One power supply unit acts as a slave, while the other acts as a master. This mode is usually used in specific fault recovery scenarios or maintenance operations.

[0143] The automatic master-standby redundant power supply mode host refers to that the system automatically selects one power supply unit as the master and the other as the standby. The master is responsible for power supply, while the standby is in standby state. In response to determining that the master fails, the system automatically switches to the standby for power supply. The user can select any of the above power supply redundant power supply modes by inputting a master-standby mode instruction.

[0144] In some embodiments, the method further comprises: in response to determining that the server is a non-storage server, an evaluation control unit in the server monitors at least one power supply unit. In response to detecting a power supply abnormal alarm signal issued by the power supply unit, the control server performs frequency reduction processing.

[0145] In the embodiments of the present application, in response to determining that the server is a non-storage server, an evaluation control unit (possibly referring to BMC or other management control unit of the server) in the server monitors at least one power supply unit. The monitoring generally includes continuous detection of the output voltage, current, temperature and other key parameters of the power supply unit.

[0146] If the evaluation control unit detects a power supply abnormal alarm signal issued by at least one power supply unit, it indicates that the power supply may have problems such as overload, overheating, unstable output voltage, etc. After detecting the power supply abnormal alarm signal, the evaluation control unit will take measures to protect the server hardware and ensure the stability of the system. One of the measures is to control the server to perform frequency reduction processing.

[0147] Frequency reduction processing means reducing the running frequency of the CPU or other processors of the server, thereby reducing the overall power consumption and heat generation. This measure helps to prevent the power supply unit from further deteriorating due to overload, while allowing the server to continue running critical tasks under limited power supply.

[0148] In some embodiments, Figure 4 is a schematic diagram of the intelligent control algorithm of the power supply module provided by the embodiments of the present application. As shown in Figure 4, through the PMBUS interface, the abnormal power-off timing trigger condition of the power supply module can be flexibly configured to meet different power management needs. At the same time, the power supply redundant power supply mode can also be set as needed, including the master-standby redundant power supply mode and the current-sharing redundant power supply mode. In the master-standby redundant power supply mode, forced master-standby redundant power supply or automatic master-standby redundant power supply can be selected. In addition, the system time can be timed synchronized to the power supply module, and the power supply module will accumulate and update the system time, and overwrite its own accumulated time when receiving a new system time.

[0149] The SMBUS (System Management BUS) subprogram is responsible for transmitting the electrical parameters, alarm information and abnormal log records of the power module to the system, while receiving the control instructions sent by the system. The instruction recognition subprogram will determine the frame format integrity of these instructions, and intelligently recognize and classify the control instructions, and then jump to the corresponding control processing flow. The abnormal power-off timing configuration subprogram is responsible for configuring the alarm Alert signal change trigger condition of the power module under various abnormal scenarios, such as whether the power overheat protection triggers the Alert signal change.

[0150] The timestamp timing synchronization subprogram ensures that the system time is synchronized to the power module, and updates the time of the power module in time. The control subprogram monitors the key parameters inside the power supply, and intelligently controls according to the key parameters. For example, when receiving the instruction of the current-sharing redundant power supply mode, the power module will enter the mode, taking the current-sharing bus voltage as the parameter of the control outer ring and inner ring. In the forced master-slave redundant power supply mode, the power module will be forced to enter the mode. In the automatic master-slave redundant power supply mode, the power module will automatically switch between the master-slave redundant power supply mode and the current-sharing redundant power supply mode according to the change of the load current.

[0151] The AD (Analog-to-Digital) sampling subprogram is responsible for sampling the input voltage, input current, output voltage, output current, system power bus voltage, key component temperature and power inlet temperature of the power module. The abnormal diagnosis subprogram is optimized based on the related basis, and can record the abnormal time when the abnormality occurs, and is synchronized with the system time. The subprogram can also repeatedly record the same abnormality, such as overcurrent protection, in order to facilitate fault analysis and processing.

[0152] Fig. 5 is a schematic diagram of the intelligent control flow provided by the embodiment of the application. As shown in Fig. 5, the server system determines the server model by intelligent recognition, so as to determine whether to configure the abnormal power-off timing of the power module. At the same time, the system configures the redundant power supply mode of the power module according to the control instruction of the core software, and synchronizes the system time in time, so as to ensure that the timestamp of the abnormal log record of the power module is consistent with the system time.

[0153] In order to facilitate the positioning of customer site problems, the system collects black box logs, so that accurate fault diagnosis can be performed without returning the power module when the power module has a problem. The server system continuously monitors the in-place signal of the power supply, and judges whether the power module has a plug-in action through the signal change. When the server device is just powered on or the power module has a plug-in action, the system will re-identify the server model, and intelligently configure the power-off timing of the power module.

[0154] For the storage server, the system is particularly configured with the Alert signal change trigger condition under the conditions of overheat alarm state, overcurrent alarm state, input alarm state, etc. to prevent the risk of data loss. The time synchronization control subroutine performs time synchronization on the power module every half hour to ensure that the timestamp of the power module matches the timestamp of the system log.

[0155] The power supply mode control subroutine sends redundant power supply mode control instructions according to the needs of the customer to adapt to different power management strategies. The abnormal log collection subroutine actively collects the abnormal logs of the current page and the history page when the power module has a power supply abnormality, so that the problem on the customer's site can be accurately located without returning the power module.

[0156] FIG. 6 is a structural schematic diagram of an electronic device provided by the present application. As shown in FIG. 6, the electronic device can include one or more processors 610, a communications interface 620, a memory 630, and a communications bus 640, wherein the processor 610, the communications interface 620, and the memory 630 complete mutual communication through the communications bus 640. The processor 610 can invoke computer readable instructions in the memory 630 to execute a server power management method, which includes:

[0157] The baseboard management controller configures a power supply abnormality power-off timing for the power supply unit in response to detecting that the server is a storage server. The power supply abnormality power-off timing includes an alarm value for triggering the power supply unit to send power supply abnormality alarm information, and the alarm value is less than a fault value when the power supply unit fails. The power supply controller device switches the backup battery unit to supply power to the fan and the baseboard management controller in the server and performs data backup in response to detecting that the power supply unit sends a power supply abnormality alarm signal.

[0158] Further, the computer readable instructions in the memory 630 described above can be implemented in the form of software functional units and sold or used as independent products, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the parts that essentially contribute to the related art or the parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0159] In another aspect, as shown in FIG. 7, the present application also provides a computer program product, which includes computer readable instructions that can be stored on a non-transitory computer readable storage medium. When the computer program is executed by one or more processors, the computer can execute the server power management method provided by the above-mentioned methods, which includes:

[0160] The baseboard management controller configures a power abnormality power-off sequence for the power supply unit in response to detecting that the server is a storage server. The power abnormality power-off sequence includes an alarm value for triggering the power supply unit to issue power abnormality alarm information, and the alarm value is less than a fault value when the power supply unit fails. The power control device switches the backup battery unit to supply power to the fan and the baseboard management controller in the server and performs data backup in the case of detecting that the power supply unit issues a power abnormality alarm signal.

[0161] In another aspect, as shown in FIG. 8, the present application also provides a non-transitory computer readable storage medium having computer readable instructions stored thereon. When the computer readable instructions are executed by one or more processors, the server power management method provided by the above-mentioned methods is implemented, which includes:

[0162] The baseboard management controller configures a power abnormality power-off sequence for the power supply unit in response to detecting that the server is a storage server. The power abnormality power-off sequence includes an alarm value for triggering the power supply unit to issue power abnormality alarm information, and the alarm value is less than a fault value when the power supply unit fails. The power control device switches the backup battery unit to supply power to the fan and the baseboard management controller in the server and performs data backup in the case of detecting that the power supply unit issues a power abnormality alarm signal.

[0163] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0164] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and necessary universal hardware platforms, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of software products, and the computer software products can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and include a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0165] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features. These modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A server power management system, characterized by, The power supply unit, the backup battery unit and the power supply control device; wherein The baseboard management controller in the server is configured to configure a power abnormality power-off time sequence for the power supply unit in response to detecting that the server is a storage server; wherein the power abnormality power-off time sequence comprises an alarm value for triggering the power supply unit to issue a power abnormality alarm signal, and the alarm value is less than a fault value when the power supply unit fails; and The power supply control device is configured to switch the backup battery unit to supply power to the fan and the baseboard management controller in the server and perform data backup in response to detecting that the power supply unit issues the power abnormality alarm signal. The power supply unit is connected to the power supply control device and hard disks, expansion cards, the fan and the baseboard management controller in the server, and the backup battery unit is electrically connected to the power supply control device and the fan and the baseboard management controller in the server; 2. The server power management system of claim 1, wherein, In response to determining that the backup battery unit supplies power to the fan and the baseboard management controller in the server, the hard disks and the expansion cards are powered off. The power supply control device is further configured to:

3. The server power management system of claim 1, wherein, determine the on-site signal of the power supply unit; and in response to determining that the on-site signal of the power supply unit changes, the power supply control device re-performs server type detection. The power supply control device is further configured to:

4. The server power management system of claim 3, wherein, in response to determining that the on-site signal of the power supply unit does not change, detect time synchronization information between the power supply unit and the power supply control device; and in response to determining that the time deviation between the power supply unit and the power supply control device exceeds a preset time length according to the time synchronization information, the power supply control device sends the time synchronization information to the power supply unit to ensure that the time stamps of the power supply unit and the power supply control device match. The power supply unit comprises a first power supply unit and a second power supply unit; the baseboard management controller is configured to:

5. The server power management system of claim 1, wherein, perform power redundancy power supply mode setting according to a master-slave mode instruction input by a user; wherein the power redundancy power supply mode comprises a current-sharing redundancy power supply mode, a forced master-slave power supply mode master, a forced master-slave redundancy power supply mode slave and an automatic master-slave redundancy power supply mode master. The baseboard management controller is further configured to:

6. The server power management system of claim 1, wherein, in response to detecting the power abnormality alarm signal of the power supply unit, collect the power abnormality alarm signal and write the power abnormality alarm signal into an abnormality log. The server further comprises an evaluation control unit; wherein the evaluation control unit is configured to:

7. The server power management system of claim 1, wherein, monitor the state of the backup battery unit and evaluate the backup power capability; and in response to determining that the backup power capability of the backup battery unit is abnormal, generate a backup power alarm signal. The evaluation control unit is further configured to:

8. The server power management system of claim 7, wherein, in response to determining that the server is a non-storage server, monitor the power supply unit; and in response to detecting a power abnormality alarm signal issued by the power supply unit, control the server to perform frequency reduction processing. ​ 9. The server power management system of claim 1, wherein, The power supply unit comprises: a first pull-up resistor, a second pull-up resistor, a third zero-ohm resistor, a fourth pull-down resistor, a fifth pull-down resistor, a sixth pull-up resistor, a seventh pull-up resistor, an eighth pull-up resistor, a ninth pull-down resistor and a power supply element; wherein, The serial data line is connected to the power supply element through the first pull-up resistor; The serial clock line is connected to the power supply element through the second pull-up resistor; The first address line is connected to the power supply element through the sixth pull-up resistor; The second address line is connected to the power supply element through the seventh pull-up resistor; The power-on signal interface is grounded through the third zero-ohm resistor; The alarm signal interface is grounded through the fourth pull-down resistor; The power state signal interface is grounded through the fifth pull-down resistor; The input voltage normal signal interface is grounded through the ninth pull-down resistor; and The presence signal interface is connected to the power supply element through the eighth pull-up resistor.

10. The server power management system of claim 9, wherein, The power supply unit is used for: In response to determining that the power supply unit is in place, the presence signal interface is in a high level state, and a presence signal is generated; and In response to determining that the power supply unit is not in place, the presence signal interface is in a low level state, and the generation of the presence signal is stopped.

11. A method for managing power of a server based on the server power management system according to any one of claims 1-10, characterized in that, It comprises: The baseboard management controller configures a power abnormality power-off timing for the power supply unit in response to detecting that the server is a storage server; wherein the power abnormality power-off timing comprises: an alarm value for triggering the power supply unit to issue a power abnormality alarm signal, the alarm value being less than a fault value when the power supply unit fails; and The power control device switches the backup battery unit to supply power to the fan and the baseboard management controller in the server and performs data backup in response to detecting that the power supply unit issues the power abnormality alarm signal.

12. The server power management method of claim 11, wherein, The baseboard management controller configures a power abnormality power-off timing for the power supply unit in response to detecting that the server is a storage server, comprising: In response to determining that the server power management system comprises a first power supply unit and a second power supply unit, a first early warning value is configured for the first power supply unit, and a second early warning value is configured for the second power supply unit; Wherein, the first early warning value is less than a first fault value of the first power supply unit, the first early warning value is used to trigger the first power supply unit to generate the power abnormality alarm signal, and the first fault value is a threshold value when the first power supply unit triggers a fault; and The second early warning value is less than a second fault value of the second power supply unit, the second early warning value is used to trigger the second power supply unit to generate the power abnormality alarm signal, and the second fault value is a threshold value when the second power supply unit triggers a fault.

13. The server power management method of claim 11, wherein, Before the step of the baseboard management controller configuring a power abnormality power-off timing for the power supply unit in response to detecting that the server is a storage server, it further comprises: The power supply unit is subjected to in-place signal determination; and In response to determining that the in-place signal of the power supply unit changes, the power control device performs server type detection on the server.

14. The server power management method of claim 13, wherein, The on-site signal determination step of the power supply unit further comprises: in response to determining that the on-site signal of the power supply unit has not changed, detecting time synchronization information between the power supply unit and the power control device; and in response to determining that the time deviation between the power supply unit and the power control device exceeds a preset time length according to the time synchronization information, the power control device sends time synchronization information to the power supply unit to ensure that the time stamps of the power supply unit and the power control device match.

15. The server power management method of claim 11, wherein, The method further comprises: According to the user input main backup mode instruction, the power supply redundant power supply mode setting is carried out; wherein, the power supply redundant power supply mode includes: current sharing redundant power supply mode, forced master-slave power supply mode master, forced master-slave redundant power supply mode slave and automatic master-slave redundant power supply mode master.

16. The server power management method of claim 11, wherein, The method further comprises: in response to detecting the power supply abnormal alarm signal of the power supply unit, collecting the power supply abnormal alarm signal and writing the power supply abnormal alarm signal into an abnormal log.

17. The server power management method of claim 11, wherein, The method further comprises: in response to determining that the server is a non-storage server, the evaluation control unit in the server monitors the power supply unit; and in response to detecting the power supply abnormal alarm signal sent by the power supply unit, the server is controlled to perform frequency reduction processing.

18. An electronic device comprising: one or more processors; and a memory associated with the one or more processors, the memory being configured to store computer readable instructions which, when read and executed by the one or more processors, implement the server power management method of any one of claims 11 to 17.

19. A non-transitory computer readable storage medium having stored thereon computer readable instructions which, when executed by one or more processors, implement the server power management method of any one of claims 11 to 17.

20. A computer program product comprising computer readable instructions, characterized in that, The computer readable instructions, when executed by one or more processors, implement the server power management method of any one of claims 11 to 17.

Images