CPU server power consumption intelligent control method, system and device and storage medium

Abstract

The invention discloses a CPU server power consumption intelligent control method, system and device and a storage medium, and the control method can achieve the precise control of the power consumption of a server through the real-time monitoring of the power consumption state of the CPU server. The problem of energy waste caused by traditional fixed power consumption control is avoided, the power consumption of the server can be dynamically adjusted according to actual requirements, and therefore effective utilization of energy and energy conservation and emission reduction are achieved. By executing the power consumption capping strategy, it can be ensured that the power consumption of the server is always kept within a reasonable range set by a user. And when the power consumption is close to or exceeds the capping value, the performance grade of the server can be automatically lowered, and the voltage can be reduced, so that the problems of server overheating, performance reduction, even damage and the like caused by overhigh power consumption are effectively prevented. And meanwhile, the power consumption is relatively low, and the operation of lowering the performance level is triggered in the adjustment process, so that the performance level of the server can be timely increased, the voltage can be correspondingly increased, and normal operation and stable performance of the server are ensured.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of computers and relates to a CPU server power consumption intelligent control method, system, device and storage medium. BACKGROUND

[0002] With the rapid development of information technology, the information industry technology in China has been significantly improved, especially in the field of servers. The performance of domestic Feiteng CPU servers has been greatly enhanced and has been widely used in various large data centers. Large data centers bear massive data processing tasks, and large-scale deployment and high-density operation environment of servers have become the norm. However, such a high-density operation environment also brings the problem of huge power consumption.

[0003] The power consumption of servers in large data centers often accounts for a large part of the operating cost during operation. With the continuous increase in the number of servers, the dramatic increase in power consumption not only leads to high operating costs, but also brings great challenges to the power supply and power consumption management of data centers. The traditional power consumption management method often uses static control, that is, according to the total power distribution capacity of the data center to limit the number of servers. Although this method is simple, it ignores the load changes of servers in actual operation, resulting in waste of power resources.

[0004] In order to prevent the domestic Feiteng CPU server from triggering overcurrent protection due to power consumption exceeding the capacity, the existing technology usually estimates the number of servers by dividing the total power distribution capacity by the maximum power of a single server. However, this estimation method ignores the actual load of the server. Each server is not in full load state at all times. In actual situations, the load of the server will change with time, business demand and other factors. Therefore, only relying on the maximum power to estimate the number of servers cannot truly reflect the actual demand for power resources, resulting in a large amount of power resources being wasted and additional power resources not being effectively utilized. SUMMARY

[0005] The purpose of the present application is to solve the problem that the power consumption of the CPU server in the prior art cannot be dynamically controlled, resulting in ineffective use of power resources, and to provide a CPU server power consumption intelligent control method, system, device and storage medium.

[0006] To achieve the above purpose, the technical scheme is adopted as follows:

[0007] A CPU server power consumption intelligent control method comprises the following steps:

[0008] Obtain the maximum and minimum values of the performance of the CPU server to determine the performance adjustable range of the server;

[0009] obtaining a current initial performance level of the CPU server;

[0010] reading the power consumption of the power chip of the CPU through multiple polling to monitor the power consumption state of the server in real time;

[0011] performing a power consumption capping strategy, specifically including:

[0012] reading the capping value set by the user and the current CPU power consumption;

[0013] if the current CPU power consumption is less than the capping value set by the user and greater than the error capping value, automatically adjusting the performance level of the server and reducing the voltage;

[0014] if the current CPU power consumption is less than the error capping value and greater than the reference power consumption value, keeping the current performance level of the server unchanged;

[0015] if the current CPU power consumption is less than the reference power consumption value and the performance level adjustment operation has been triggered in the adjustment process, increasing the performance level of the server and correspondingly increasing the voltage;

[0016] when the input performance level exceeds the preset range, i.e. less than the minimum CPU performance level or greater than the maximum CPU performance level, the server is placed in an error state, and the corresponding error handling mechanism is triggered.

[0017] The performance maximum and minimum of the CPU server are obtained by the following steps:

[0018] performing performance testing on the CPU server and recording its performance data under different loads;

[0019] extracting the maximum and minimum from the performance data as the performance adjustable range of the server.

[0020] The current initial performance level of the CPU server is obtained by the following steps:

[0021] reading the preset initial performance level data of the CPU server when it starts;

[0022] taking the read initial performance level data as the current initial performance level.

[0023] The power chip power consumption of the CPU is read by periodically sending a read instruction to the power chip and receiving the returned power consumption data.

[0024] The power chip power consumption of the CPU is read by periodically sending a read instruction to the power chip and receiving the returned power consumption data.

[0025] setting the time interval of polling;

[0026] sending a read power consumption instruction to the power chip at a set time interval;

[0027] receiving power consumption data returned by the power chip and recording and analyzing the power consumption data.

[0028] A CPU server power consumption intelligent control system, comprising a performance detection module, a power consumption monitoring module and a power consumption control module, wherein:

[0029] The performance detection module is used to obtain the maximum value, minimum value and current initial performance level of the CPU server.

[0030] The power consumption monitoring module is used to read the power chip power consumption of the CPU multiple times.

[0031] The power consumption control module is used to execute a power consumption cap strategy, adjust the performance level and voltage of the server according to the cap value set by the user and the current CPU power consumption, and perform error processing during the performance level adjustment process.

[0032] Further comprising a data recording and analysis module for recording and analyzing the performance data and power consumption data of the server to provide a basis for power consumption management.

[0033] The performance detection module, the power consumption monitoring module, the power consumption control module and the data recording and analysis module communicate with each other through a data bus to realize real-time transmission and sharing of data.

[0034] An apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method of any of the preceding items when executing the computer program.

[0035] A computer readable storage medium storing a computer program, the computer program implementing the steps of the method of any of the preceding items when executed by a processor.

[0036] Compared with the prior art, the present application has the following beneficial effects:

[0037] The application provides a CPU server power consumption intelligent control method, which can realize accurate control of server power consumption by monitoring the power consumption state of the CPU server in real time. The method avoids the energy waste problem caused by traditional fixed power consumption control, enables the power consumption of the server to be dynamically adjusted according to actual needs, and thus realizes effective use of energy and energy saving and emission reduction. By executing a power consumption capping strategy, the power consumption of the server can be ensured to always remain within a reasonable range set by a user. When the power consumption approaches or exceeds the capping value, the performance level of the server can be automatically lowered and the voltage can be reduced, effectively preventing problems such as server overheating, performance degradation, and even damage caused by excessively high power consumption. Meanwhile, when the power consumption is low and the performance level has been lowered during the adjustment process, the performance level of the server can be timely raised and the voltage can be correspondingly raised, ensuring normal operation and stable performance of the server.

[0038] The CPU server power consumption intelligent control system in the application can dynamically adjust power consumption according to the actual load of the server, enabling energy to be more efficiently utilized, helping to reduce overall energy consumption, and realizing the goal of energy saving and emission reduction. The system can ensure that the power consumption of the server always remains within a reasonable range set by a user by executing a power consumption capping strategy. When the power consumption approaches or exceeds the capping value, the system can automatically lower the performance level of the server and reduce the voltage, effectively preventing problems such as server overheating, performance degradation, and even damage caused by excessively high power consumption. This helps to protect the hardware of the server and prolong its service life. Moreover, when the power consumption is low and the performance level has been lowered during the adjustment process, the system can timely raise the performance level of the server and correspondingly raise the voltage, ensuring that the server is in normal operation while maintaining stable performance. This intelligent adjustment mechanism enables the server to be dynamically optimized according to actual needs, improving the operation efficiency and stability of the server. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the application, and therefore should not be considered as a limitation to the scope. For those skilled in the art, other related drawings can also be obtained without creative labor.

[0040] Figure 1 The application provides a CPU server power consumption intelligent control method flowchart. DETAILED DESCRIPTION

[0041] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some but not all of the embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0042] Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0043] The present application will be described in further detail below with reference to the drawings:

[0044] Reference is made to Figure 1 , the flow chart of the CPU server power consumption intelligent control method in the present application,

[0045] S1, obtain the maximum and minimum values of the performance of the CPU server, and determine the performance adjustable range of the server;

[0046] S1.1, perform performance test on the CPU server, and record the performance data under different loads;

[0047] S1.2, extract the maximum and minimum values from the performance data as the performance adjustable range of the server.

[0048] S2, obtain the current initial performance level of the CPU server;

[0049] S2.1, read the preset initial performance level data of the CPU server at the start of the CPU server;

[0050] S2.2, take the read initial performance level data as the current initial performance level.

[0051] S3, read the power consumption of the power chip of the CPU through multiple polling to monitor the power consumption state of the server in real time;

[0052] S3.1, set the time interval of polling;

[0053] S3.2, periodically send the instruction of reading power consumption to the power chip according to the set time interval;

[0054] S3.3, receive the power consumption data returned by the power chip, and record and analyze them.

[0055] S4, execute the power consumption capping strategy, specifically including:

[0056] S4.1, read the user-set cap value and the current CPU power consumption;

[0057] If the current CPU power consumption is less than the user-set cap value and greater than the error cap value, automatically lower the server's performance level and reduce the voltage;

[0058] If the current CPU power consumption is less than the error cap value and greater than the reference power consumption value, keep the current server's performance level unchanged;

[0059] If the current CPU power consumption is less than the reference power consumption value and the performance level lowering operation has been triggered during the adjustment process, increase the server's performance level and correspondingly increase the voltage;

[0060] When the input performance level exceeds the preset range, i.e., less than the minimum CPU performance level or greater than the maximum CPU performance level, the server is placed in an error state, and the corresponding error handling mechanism is triggered.

[0061] The CPU server power consumption intelligent control method in the present application realizes accurate control of server power consumption by real-time monitoring and adjusting the performance level and voltage of the CPU server, and can dynamically adjust the power consumption according to the real-time load and performance demand of the server, thereby avoiding the energy waste problem caused by traditional fixed power consumption control. Not only can it improve the energy efficiency ratio of the server and reduce operating costs, but also can prolong the service life of the server and reduce the risk of hardware damage caused by excessive power consumption. By adopting the power consumption cap strategy, the system can automatically reduce the performance level and reduce the voltage when the server power consumption approaches or exceeds the set upper limit, thereby effectively preventing problems such as server overheating, performance degradation, and even failure caused by excessive power consumption, ensuring the stable operation of the server and improving the reliability and stability of the system. Moreover, the control method also considers the adjustment range of the performance level and the error handling mechanism. When the performance level exceeds the preset range, the system will place the server in an error state and trigger the corresponding error handling mechanism, thereby avoiding performance problems caused by misoperation or incorrect configuration, reducing maintenance costs, and improving user experience on the basis of improving system fault tolerance.

[0062] Another embodiment of the present application provides a CPU power consumption automatic control method based on the Feiteng platform, which is based on the BMC (Baseboard Management Controller) and S5000C SE (server model) of the Feiteng platform to automatically control power consumption. The specific implementation steps are as follows:

[0063] Step 1, send a request to S5000C SE through BMC to get the performance adjustable range of the server, which includes the maximum and minimum values of the server performance, and is the basis for subsequent power control.

[0064] Step 2, BMC sends a request to S5000C SE again to get the performance level (frequency) of the current server, which reflects the current running state and workload of the server.

[0065] Step 3, BMC starts multiple polling to S5000C SE to request the current CPU power consumption, in order to monitor the power consumption state of the server in real time and ensure the accuracy and real-time of the power consumption data.

[0066] Step 4, according to the user-set power cap value and the current CPU power consumption, BMC executes the power cap strategy, adjusts the performance level of the server according to the real-time power consumption data, in order to control the power consumption.

[0067] If the current CPU power consumption is less than the user-set cap value but greater than the preset error cap value, BMC will automatically lower the performance level of the server and reduce the voltage by sending a request to S5000C SE, in order to reduce the power consumption.

[0068] If the current CPU power consumption is less than the error cap value but greater than the reference power consumption value, BMC will keep the current performance level of the server unchanged to maintain the stable operation of the server.

[0069] If the current CPU power consumption is less than the reference power consumption value and the performance level lowering operation has been triggered during the adjustment process, BMC will send a request to S5000C SE to increase the performance level of the server and the corresponding voltage to restore the performance of the server.

[0070] Step 5, if the input performance level exceeds the preset range during the performance level adjustment process, i.e. less than the minimum value of the CPU performance level or greater than the maximum value of the CPU performance level, BMC will put the server into an error state and trigger the corresponding error handling mechanism, such as sending an alarm message or automatically restarting the server, etc.

[0071] Through the CPU power automatic control method based on Feiteng platform in this embodiment, precise control of server power consumption can be achieved, and the performance level of the server is dynamically adjusted according to real-time power consumption data and user-set cap value, so as to reduce power consumption and improve energy efficiency while ensuring stable operation of the server.

[0072] An embodiment of the present application provides a CPU server power consumption intelligent control system, specifically comprising a performance detection module, a power consumption monitoring module, a power consumption control module and a data recording and analysis module, wherein the performance detection module is used for obtaining a maximum value, a minimum value and a current initial performance level of the CPU server, so as to determine a performance adjustable range of the server, thereby providing an important basis for subsequent power consumption control, and enabling the system to accurately adjust according to actual performance requirements. The power consumption monitoring module is used for reading the power consumption of the power supply chip of the CPU multiple times, so as to realize real-time monitoring of the power consumption state of the server, not only can the power consumption abnormality be found in time, but also real-time data support can be provided for the power consumption control module, so as to ensure that the system can quickly respond and take corresponding control measures. The power consumption control module is used for executing a power consumption capping strategy, adjusting the performance level and voltage of the server according to the capping value set by the user and the current CPU power consumption, and performing error processing in the performance level adjustment process, so that when the power consumption approaches or exceeds the capping value, the system can automatically reduce the performance level and the voltage, thereby effectively preventing server failure caused by excessively high power consumption. Meanwhile, when the power consumption is low, the system can timely increase the performance level and the voltage, so as to ensure the stable operation and optimal performance of the server. In addition, the power consumption control module also has an error processing mechanism, which can detect and process errors in the performance level adjustment process, so as to ensure the stability and reliability of the system. The data recording and analysis module is used for recording and analyzing the performance data and power consumption data of the server, so as to provide a basis for power consumption management, through analysis of historical data, the system can find the rules and trends of power consumption changes, thereby providing strong support for formulating more reasonable power consumption control strategies. The various modules communicate with each other through a data bus, so as to realize real-time transmission and sharing of data.

[0073] An embodiment of the present application provides a terminal device. The terminal device of the embodiment comprises a processor, a memory, and a computer program stored in the memory and executable on the processor. The processor implements the steps in each of the method embodiments when executing the computer program. Alternatively, the processor implements the functions of each module / unit in each of the device embodiments when executing the computer program.

[0074] The computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present application.

[0075] The device / terminal device can be a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The device / terminal device can include, but is not limited to, a processor and a memory.

[0076] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc.

[0077] The memory can be used to store the computer programs and / or modules, and the processor realizes various functions of the apparatus / terminal device by running or executing the computer programs and / or modules stored in the memory, and calling data stored in the memory.

[0078] The modules / units integrated in the apparatus / terminal device, if realized in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program can realize the steps of the above-mentioned various method embodiments when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the computer readable medium can include or exclude contents according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0079] The above only describes the preferred embodiments of the present application and is not used to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A CPU server power consumption intelligent control method, characterized in that, The method comprises the following steps: obtaining the maximum and minimum values of the performance of the CPU server to determine the adjustable range of the performance of the server; obtaining the current initial performance level of the CPU server; reading the power consumption of the power chip of the CPU through multiple polling to monitor the power consumption state of the server in real time; performing the power consumption capping strategy, which specifically comprises: reading the capping value set by the user and the current power consumption of the CPU power supply; if the current power consumption of the CPU power supply is less than the capping value set by the user and greater than the error capping value, automatically adjusting the performance level of the server and reducing the voltage; if the current power consumption of the CPU power supply is less than the error capping value and greater than the reference power consumption value, keeping the current performance level of the server unchanged; if the current power consumption of the CPU power supply is less than the reference power consumption value and the performance level adjustment operation has been triggered in the adjustment process, adjusting the performance level of the server and correspondingly increasing the voltage; when the input performance level exceeds the preset range, i.e. less than the minimum value of the CPU performance level or greater than the maximum value of the CPU performance level, the server is placed in an error state, and the corresponding error handling mechanism is triggered.

2. The CPU server power consumption intelligent control method of claim 1, wherein, The obtaining of the maximum and minimum values of the performance of the CPU server is specifically achieved through the following steps: performing performance testing on the CPU server and recording the performance data under different loads; extracting the maximum and minimum values from the performance data as the adjustable range of the performance of the server.

3. The CPU server power consumption intelligent control method of claim 1, wherein, The obtaining of the current initial performance level of the CPU server is specifically achieved through the following steps: when the CPU server starts, reading the preset initial performance level data of the server; taking the read initial performance level data as the current initial performance level.

4. The CPU server power consumption intelligent control method of claim 1, wherein, The polling reading of the power chip power consumption of the CPU is achieved by periodically sending a reading instruction to the power chip and receiving the returned power consumption data.

5. The CPU server power consumption intelligent control method of claim 1, wherein, The polling reading of the power chip power consumption of the CPU specifically comprises the following steps: setting the time interval of polling; periodically sending a power consumption reading instruction to the power chip according to the set time interval; receiving the power consumption data returned by the power chip and recording and analyzing the data.

6. A CPU server power consumption intelligent control system, characterized in that, The method comprises a performance detection module, a power consumption monitoring module and a power consumption control module, wherein: the performance detection module is used to obtain the maximum and minimum values of the performance of the CPU server and the current initial performance level; the power consumption monitoring module is used to read the power chip power consumption of the CPU through multiple polling; the power consumption control module is used to perform the power consumption capping strategy, adjust the performance level and voltage of the server according to the capping value set by the user and the current power consumption of the CPU power supply, and perform error handling during the performance level adjustment process.

7. The CPU server power consumption intelligent control system of claim 6, wherein, The method further comprises a data recording and analysis module for recording and analyzing the performance data and power consumption data of the server to provide a basis for power consumption management.

8. The CPU server power consumption intelligent control system of claim 7, wherein, The performance detection module, the power consumption monitoring module, the power consumption control module and the data recording and analysis module communicate with each other through a data bus to realize real-time transmission and sharing of data.

9. An apparatus comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein, The processor executes the computer program to realize the steps of the method according to any one of claims 1-5.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to realize the steps of the method according to any one of claims 1-5.

Images