CN116755982A - Method and system for calculating energy consumption ratio of server - Google Patents
Method and system for calculating energy consumption ratio of server Download PDFInfo
- Publication number
- CN116755982A CN116755982A CN202310542133.0A CN202310542133A CN116755982A CN 116755982 A CN116755982 A CN 116755982A CN 202310542133 A CN202310542133 A CN 202310542133A CN 116755982 A CN116755982 A CN 116755982A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- server
- power
- data
- ratio
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 385
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000004364 calculation method Methods 0.000 claims abstract description 26
- 230000005540 biological transmission Effects 0.000 claims description 27
- 238000006243 chemical reaction Methods 0.000 claims description 25
- 230000017525 heat dissipation Effects 0.000 claims description 21
- 238000012423 maintenance Methods 0.000 abstract description 10
- 238000004134 energy conservation Methods 0.000 abstract description 8
- 230000009467 reduction Effects 0.000 abstract description 8
- 230000002035 prolonged effect Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3058—Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations
- G06F11/3062—Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations where the monitored property is the power consumption
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
- G06F11/324—Display of status information
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- Power Sources (AREA)
Abstract
The invention provides a method and a system for calculating the energy consumption ratio of a server, wherein the method comprises the following steps: based on the category of the energy consumption of the pre-divided server, acquiring corresponding energy consumption data of the single server; calculating energy consumption ratio information of the server according to the energy consumption data; and configuring the server based on the server energy consumption ratio information so as to realize the optimal energy consumption ratio of the server. According to the method for calculating the energy consumption ratio of the server, various energy consumption data of the server can be accurately obtained through accurately dividing various energy consumption in the single server, so that accurate calculation of the energy consumption ratio of the single server can be realized, objective basis is provided for server configuration, operation and maintenance personnel can conveniently grasp the running state of the server, the optimal energy consumption ratio of the server is found, the purposes of energy conservation and emission reduction are achieved, and the service life of the server is prolonged.
Description
Technical Field
The invention relates to the technical field of server operation and maintenance, in particular to a method and a system for calculating the energy consumption ratio of a server.
Background
PUE (Power Usage Effectiveness), i.e. the efficiency of electrical energy utilization. Is an index proposed by The United states Green Grid organization (TGG) in 2007 for evaluating The energy utilization efficiency of data centers, and is widely used by The domestic and foreign data center industries at present. The data center is used as a large power consumption user, and the energy consumption conversion efficiency is very critical.
The PUE is the ratio of the power consumed by heat dissipation in a data center to the power consumed by the entire data center for such large systems as data centers. But no relevant information is presented to the client for a single server. Because the energy consumption ratio of a single server is not higher than the related data information, clients cannot optimize the server level aiming at the server, so that the energy consumption of the server is high, and the service life of the server is shortened.
Disclosure of Invention
The invention aims to provide a method and a system for calculating the energy consumption ratio of a server, which realize the accurate calculation of the energy consumption ratio of a single server, are convenient for operation and maintenance personnel to master the running state of the server and find the optimal energy consumption ratio of the server, thereby realizing the purposes of energy conservation and emission reduction and prolonging the service life of the server.
In order to solve the technical problems, the invention provides a method for calculating the energy consumption ratio of a server, which comprises the following steps:
based on the category of the energy consumption of the pre-divided server, acquiring corresponding energy consumption data of the single server;
calculating energy consumption ratio information of the server according to the energy consumption data;
and configuring the server based on the server energy consumption ratio information so as to realize the optimal energy consumption ratio of the server.
According to the scheme, various energy consumption data of the servers can be accurately obtained through accurately dividing various energy consumption in the single server, so that accurate calculation of the energy consumption ratio of the single server can be realized, objective basis is provided for server configuration, operation and maintenance personnel can conveniently master the running state of the server, and the optimal energy consumption ratio of the server is found, so that the purposes of energy conservation and emission reduction are realized, and the service life of the server is prolonged.
Further, based on the category of the energy consumption of the pre-divided server, the corresponding energy consumption data of the single server is obtained, specifically: the categories of the energy consumption of the server are divided into power input energy consumption, power output energy consumption and power conversion loss in advance, and then the following steps are included: power input energy consumption = power output energy consumption + power conversion loss; wherein: the power supply output energy consumption comprises main board energy consumption, CPU energy consumption, memory energy consumption, hard disk energy consumption, heat dissipation energy consumption, GPU energy consumption and transmission loss; and acquiring corresponding energy consumption data of the single server.
Further, based on the category of the energy consumption of the pre-divided server, the corresponding energy consumption data of the single server is obtained, specifically: based on the category of the pre-divided server energy consumption, acquiring the main board energy consumption, CPU energy consumption, memory energy consumption, hard disk energy consumption, heat dissipation energy consumption and GPU energy consumption of a single server through a power consumption sensor; directly acquiring power input energy consumption and power output energy consumption through a power supply; the transmission loss is obtained by an indirect method.
Further, the calculating the energy consumption ratio information of the server according to the energy consumption data specifically includes:
the calculation of the server energy consumption ratio information K is expressed as:
wherein P is PSU_IN Representing the input energy consumption of a power supply; p (P) SYS Representing the energy consumption of the main board; p (P) CPU Representing CPU energy consumption; p (P) MEM Representing the energy consumption of the memory; p (P) HDD Representing the energy consumption of the hard disk; p (P) GPU Representing GPU power consumption.
Further, the method also comprises the step of converting the energy consumption data and the energy consumption ratio information of the server into graphic information for display, wherein the graphic information comprises heat dissipation energy consumption and transmission loss.
The method solves the problem that the energy consumption utilization rate of a single server cannot be visually represented, can realize the energy consumption utilization rate display of the server level by calculating the energy consumption ratio of the single server, and is convenient for clients and operation and maintenance personnel to master the running state of the server and find the optimal energy consumption ratio of the server, thereby realizing the purposes of energy conservation and emission reduction.
The invention also provides a server energy consumption ratio calculation system for realizing the method, which comprises an energy consumption data acquisition module, an energy consumption ratio information calculation module and a configuration module; wherein:
the energy consumption data acquisition module is used for acquiring corresponding energy consumption data of the single server based on the category of the energy consumption of the pre-divided server;
the energy consumption ratio information calculation module is used for calculating the energy consumption ratio information of the server according to the energy consumption data;
the configuration module configures the server based on the server energy consumption ratio information so as to realize the optimal energy consumption ratio of the server.
The system architecture provided by the scheme is simple and convenient to build, the method can be used for realizing a calculation method of the energy consumption ratio of the server, various energy consumption data of the server can be accurately obtained through accurately dividing various energy consumption in a single server, so that accurate calculation of the energy consumption ratio of the single server can be realized, objective basis is provided for server configuration, operation and maintenance personnel can conveniently grasp the running state of the server, and the optimal energy consumption ratio of the server is found, so that the purposes of energy conservation and emission reduction are realized, and the service life of the server is prolonged.
Further, the energy consumption data acquisition module is configured to acquire corresponding energy consumption data of a single server based on a category of energy consumption of the pre-divided server, and specifically includes: the categories of the energy consumption of the server are divided into power input energy consumption, power output energy consumption and power conversion loss in advance, and then the following steps are included:
power input energy consumption=power output energy consumption+power conversion loss
Wherein: the power supply output energy consumption comprises main board energy consumption, CPU energy consumption, memory energy consumption, hard disk energy consumption, heat dissipation energy consumption, GPU energy consumption and transmission loss; and acquiring corresponding energy consumption data of the single server.
Further, in the energy consumption data obtaining module, the obtaining of the energy consumption data corresponding to the single server based on the category of the energy consumption of the pre-divided server specifically includes: based on the category of the pre-divided server energy consumption, acquiring the main board energy consumption, CPU energy consumption, memory energy consumption, hard disk energy consumption, heat dissipation energy consumption and GPU energy consumption of a single server through a power consumption sensor; directly acquiring power input energy consumption and power output energy consumption through a power supply; the transmission loss is obtained by an indirect method.
Further, the energy consumption ratio information calculating module is configured to calculate server energy consumption ratio information according to energy consumption data, specifically:
the calculation of the server energy consumption ratio information K is expressed as:
wherein P is PSU_IN Representing the input energy consumption of a power supply; p (P) SYS Representing the energy consumption of the main board; p (P) CPU Representing CPU energy consumption; p (P) MEM Representing the energy consumption of the memory; p (P) HDD Representing the energy consumption of the hard disk; p (P) GPU Representing GPU power consumption.
Further, the system also comprises a graphic display module, wherein the graphic display module is used for converting the energy consumption data and the energy consumption ratio information of the server into graphic information for display, and the graphic information comprises heat dissipation energy consumption and transmission loss.
Drawings
FIG. 1 is a schematic flow chart of a method for calculating energy consumption ratio of a server according to an embodiment of the present invention;
FIG. 2 is a graph of energy consumption class relationships in a single server according to an embodiment of the present invention;
FIG. 3 is a diagram of an energy consumption data acquisition architecture according to an embodiment of the present invention;
FIG. 4 is a graph of server power consumption versus energy consumption information provided in an embodiment of the present invention;
FIG. 5 is a schematic diagram showing the proportions of the energy consumption classes according to an embodiment of the present invention;
FIG. 6 is a diagram of a server power consumption ratio computing system architecture according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present embodiment provides a method for calculating a server energy consumption ratio, including the following steps:
s1: based on the category of the energy consumption of the pre-divided server, acquiring corresponding energy consumption data of the single server;
s2: calculating energy consumption ratio information of the server according to the energy consumption data;
s3: and configuring the server based on the server energy consumption ratio information so as to realize the optimal energy consumption ratio of the server.
In the embodiment, various energy consumption data of the server can be accurately obtained by accurately dividing various energy consumption in the single server, so that accurate calculation of the energy consumption ratio of the single server can be realized, objective basis is provided for server configuration, operation and maintenance personnel can conveniently grasp the running state of the server, and the optimal energy consumption ratio of the server is found, so that the purposes of energy conservation and emission reduction are realized, and the service life of the server is prolonged.
Further, based on the category of the energy consumption of the pre-divided server, the corresponding energy consumption data of the single server is obtained, specifically: the categories of the energy consumption of the server are divided into power input energy consumption, power output energy consumption and power conversion loss in advance, and then the following steps are included: power input energy consumption = power output energy consumption + power conversion loss; wherein: the power supply output energy consumption comprises main board energy consumption, CPU energy consumption, memory energy consumption, hard disk energy consumption, heat dissipation energy consumption, GPU energy consumption and transmission loss; and acquiring corresponding energy consumption data of the single server.
It should be noted that, in the design process of the server in this embodiment, power supply and monitoring are performed according to modules, and a single server is divided into several parts such as p12v_sys, p12v_cpu, p12v_mem, p12v_hdd, p12v_fan, p12v_gpu, etc., where:
the P12V_PSU is the output of the power PSU and is the total power input source of the server;
the p12v_sys is the power consumption of the system or the motherboard, and is mainly used for supplying power to circuit modules and devices on the motherboard, such as PCIe Switch, clock unit, some logic devices, etc.;
the P12V_CPU supplies power for the CPU related module;
the P12V_MEM mainly supplies power to a memory buffer and a memory bank on the memory sub-card;
the P12V_GPU mainly supplies power to the GPU card;
the P12V_FAN supplies power for the FAN backboard and the FAN module;
the P12V_HDD mainly supplies power to the hard disk module and the hard disk backboard.
The above power consumption divides the power supply according to the functions in the design of the server, and besides, transmission loss and conversion loss which are unavoidable in the operation of the server, and these power consumption constitute the total power consumption of the server. Wherein:
the transmission loss is the loss generated when the PCB wiring of the main board and the connector between the PSU and the main board transmit current; the conversion loss is a loss generated by the voltage regulator (VR, voltage regulator) when performing voltage conversion.
It should be further noted that the relationship between the energy consumption categories in the single server may be shown in fig. 2. Among them, there are:
P total (S) ＝P PSU_IN ＝P PSU_OUT +P PSU_VR
Wherein P is Total (S) Representing the total energy consumption of the server; p (P) PSU_IN Representing the input energy consumption of a power supply; p (P) PSU_OUT Representing the power output energy consumption; p (P) PSU_VR Indicating power conversion loss. Wherein: the power output energy consumption comprises the main board energy consumption P SYS CPU power consumption P CPU Memory power consumption P MEM Energy consumption P of hard disk HDD Heat dissipation energy consumption P FAN GPU energy consumption P GPU And transmission loss P Transmission of The method comprises the steps of carrying out a first treatment on the surface of the Motherboard energy consumption P SYS Comprising main power consumption P of a main board SYS_VR_OUT And motherboard conversion power consumption P SYS_VR The method comprises the steps of carrying out a first treatment on the surface of the CPU power consumption P CPU Comprising CPU main power consumption P CPU_VR_OUT And CPU conversion power consumptionP CPU_VR The method comprises the steps of carrying out a first treatment on the surface of the Memory power consumption P MEM Comprising main energy consumption P of memory MEM_VR_OUT And memory conversion energy consumption P MEM_VR 。
Further, based on the category of the energy consumption of the pre-divided server, the corresponding energy consumption data of the single server is obtained, specifically: based on the category of the pre-divided server energy consumption, acquiring the main board energy consumption, CPU energy consumption, memory energy consumption, hard disk energy consumption, heat dissipation energy consumption and GPU energy consumption of a single server through a power consumption sensor; directly acquiring power input energy consumption and power output energy consumption through a power supply; the transmission loss is obtained by an indirect method.
In this embodiment, the collection of the energy consumption data may be jointly implemented by the controller APSS, the power consumption sensors of each module, and the main control terminal for reading the power consumption information, and the architecture of the energy consumption data acquisition may be referred to fig. 3. Wherein: the power consumption sensor is mainly used for sampling voltage information and current data flowing to each module, and current flows to each module after passing through the power consumption sensor from the PSU. The principle is that a current signal flowing through a precision resistor is changed into a voltage signal through ohm's law. Wherein the voltage information and the current information are analog signals; the controller APSS is provided with an analog-to-digital conversion (ADC) channel, and the voltage data quantity and the current-voltage data quantity acquired by the power consumption sensor are converted into data through the ADC channel; the main control terminal can be realized by adopting BMC or CPU and the like, and can read the power consumption information in the controller APSS.
In this embodiment, the CPU may be connected to the APSS through the SPI bus, and used to read power consumption information of the entire server; the BMC can be connected with the APSS through the I2C bus and is used for acquiring the power consumption information of the whole server; the BMC is connected with the CPU through the I2C and used for data interaction between the BMC and the CPU. After sampling and conversion, the APSS can calculate the power consumption information of each module through the obtained voltage information and current information, and the calculation formula is as follows:
P＝I×V
wherein I is the current consumed by the power consumption sensor and each module during operation; v is the sampling voltage input by the module. So far, the main board energy consumption P can be obtained SYS CPU power consumption P CPU Memory power consumption P MEM Energy consumption P of hard disk HDD Heat dissipation energy consumption P FAN And GPU power consumption P GPU 。
It should be noted that, part of the energy consumption data in the server cannot be directly collected, and needs to be obtained through an indirect method, such as transmission loss, conversion loss and the like. For the transmission loss, the calculation mode can be as follows:
P transmission of ＝P PSU_OUT -P SYS -P CPU -P MEM -P HDD -P FAN -P GPU
In the server, the motherboard, CPU and memory need to be used after voltage conversion by VR. Because VR during operation efficiency is not 100%, consequently can produce the loss at VR conversion's in-process, BMC obtains VR's main energy consumption from the VR controller, obtains VR's input energy consumption from APSS, has:
P SYS_VR ＝P SYS -P SYS_VR_OUT
P CPU_VR ＝P CPU -P CPU_VR_OUT
P MEM_VR ＝P MEM -P MEM_VR_OUT
further, the calculating the energy consumption ratio information of the server according to the energy consumption data specifically includes:
the calculation of the server energy consumption ratio information K is expressed as:
wherein P is PSU_IN Representing the input energy consumption of a power supply; p (P) SYS Representing the energy consumption of the main board; p (P) CPU Representing GPU energy consumption; p (P) MEM Representing the energy consumption of the memory; p (P) HDD Representing the energy consumption of the hard disk; p (P) GPU Representing GPU power consumption. The closer the above-mentioned energy consumption ratio information K is to 1 in theory, the higher the utilization ratio of energy.
It should be noted that, the essential objective of the server is operation, and according to the effect of energy consumption of each part on operation, the energy consumption can be further divided into three types:
1. energy consumption directly involved in the operation-useful energy consumption: the following are listed belowThe power consumption is directly used for operation, and in order to promote the system power consumption, the power consumption ratio should be promoted as much as possible under the same operation requirement. Such energy consumption is: p (P) SYS_VR_OUT 、P CPU_VR_OUT 、P MEM_VR_OUT 、P HDD 、P GPU 。
2. The method is used for maintaining the normal operation energy consumption-useless energy consumption of the system: in practice, the system operates to generate heat. P (P) FAN In order to ensure the normal operation of the system and the power consumption of the heat generated by each module in the server to the outside of the system by the fan, the part of power consumption is not directly involved in the function realization of the operation of the server, and is passive power consumption, but the whole power consumption is not small in proportion. Note that this partial power consumption is not wasteful power consumption in a strict sense, but rather is wasteful power consumption without directly participating in the operation.
3. Unavoidable wasted power loss-wasted power consumption: there is also a part of the power consumption in the server that is inevitably reduced optimally to make the ratio as small as possible. P (P) Transmission of Is the power consumption of the transmission path, such as the PCB wiring resistance, the contact resistance of the connector, etc., which is unavoidable. P (P) PSU_VR 、P SYS_VR 、P CPU_VR And P MEM_VR Is the inevitable loss of power consumption for VR module operation.
Further, the method also comprises the step of converting the energy consumption data and the energy consumption ratio information of the server into graphic information for display, wherein the graphic information comprises heat dissipation energy consumption and transmission loss.
The method solves the problem that the energy consumption utilization rate of a single server cannot be visually represented, and can realize the energy consumption utilization rate display of the server level by calculating the energy consumption ratio of the single server, so that clients and operation and maintenance personnel can conveniently master the running state of the server and find the optimal energy consumption ratio of the server, and the purposes of energy conservation and emission reduction are realized.
In order to more intuitively embody the technical key points of the invention and highlight the technical advantages, the embodiment displays the energy consumption data and the server energy consumption ratio information through a BMC WEB interface.
One implementation is to directly display the K value, which is closer to 1, the higher the utilization. Another implementation schematic diagram can be seen in fig. 4, which shows through an energy consumption ratio curve, the BMC calculates and records the energy consumption ratio under each power consumption, and feeds back the utilization trend under each power consumption by drawing a server power consumption-energy consumption ratio curve display. The optimal power consumption point of the server can be found through the curve, so that the optimal efficiency is obtained.
Fig. 4 shows a power consumption curve of a server, where the base power consumption is about 100 watts and the full power consumption is 2000 watts. When the power consumption is about 1500 watts, namely about 75% of full load, the energy consumption ratio is the lowest, and the efficiency is the best. The operation and maintenance personnel can set about 1500 watts through power consumption capping, so that an energy consumption optimal mode is obtained.
In view of this curve, the server may set some modes of operation, such as:
the performance mode, i.e. the server does not set a power consumption limit to obtain maximum performance.
Compatible mode, that is, the server gives consideration to efficiency and performance, and makes proper limitation of power consumption.
And in the energy-saving mode, the server acquires optimal energy consumption efficiency, and limits the power consumption to an optimal power consumption point.
In view of the curve, the data center can adjust the installed number of the servers according to the calculation power scale and the demand scale, so that the machines in the machine room work at the optimal point of energy consumption efficiency, and further improvement of the PUE is realized.
The embodiment can also intuitively display the proportion of the power consumption of each part in the system, optimize the server in a targeted manner, introduce the power consumption ratio display besides the information of the energy consumption ratio, and can adopt pie chart display, and particularly can see fig. 5. Wherein VR-MB in the upper figure represents P SYS_VR 、P CPU_VR And P MEM_VR And (3) summing.
The embodiment can know the relation between the consumed power of the server for calculation under different power consumption and the total consumed power of the server, and grasp the energy consumption utilization condition of the server. By calculating and drawing the curve of the energy consumption ratio, the optimal power consumption ratio interval of the server can be recorded and found, so that the working power consumption with the highest efficiency is mined. And the energy consumption ratio curve can provide reference for planning the machine room, and the installed number of the servers is planned.
Referring to fig. 6, the present embodiment further provides a server energy consumption ratio computing system, configured to implement a server energy consumption ratio computing method, which includes an energy consumption data obtaining module, an energy consumption ratio information computing module, and a configuration module; wherein:
the energy consumption data acquisition module is used for acquiring corresponding energy consumption data of the single server based on the category of the energy consumption of the pre-divided server;
the energy consumption ratio information calculation module is used for calculating the energy consumption ratio information of the server according to the energy consumption data;
the configuration module configures the server based on the server energy consumption ratio information so as to realize the optimal energy consumption ratio of the server.
The system provided by the embodiment is simple in architecture and convenient to build, can be used for realizing a server energy consumption ratio calculation method, can accurately acquire various energy consumption data of a server through accurately dividing various energy consumption in a single server, thereby realizing accurate calculation of the energy consumption ratio of the single server, providing objective basis for server configuration, facilitating operation and maintenance personnel to master the running state of the server, searching for realizing the optimal energy consumption ratio of the server, realizing the purposes of energy conservation and emission reduction, and prolonging the service life of the server.
Further, the energy consumption data acquisition module is configured to acquire corresponding energy consumption data of a single server based on a category of energy consumption of the pre-divided server, and specifically includes: the categories of the energy consumption of the server are divided into power input energy consumption, power output energy consumption and power conversion loss in advance, and then the following steps are included:
power input energy consumption=power output energy consumption+power conversion loss
Wherein: the power supply output energy consumption comprises main board energy consumption, CPU energy consumption, memory energy consumption, hard disk energy consumption, heat dissipation energy consumption, GPU energy consumption and transmission loss; and acquiring corresponding energy consumption data of the single server.
Further, in the energy consumption data obtaining module, the obtaining of the energy consumption data corresponding to the single server based on the category of the energy consumption of the pre-divided server specifically includes: based on the category of the pre-divided server energy consumption, acquiring the main board energy consumption, CPU energy consumption, memory energy consumption, hard disk energy consumption, heat dissipation energy consumption and GPU energy consumption of a single server through a power consumption sensor; directly acquiring power input energy consumption and power output energy consumption through a power supply; the transmission loss is obtained by an indirect method.
Further, the energy consumption ratio information calculating module is configured to calculate server energy consumption ratio information according to energy consumption data, specifically:
the calculation of the server energy consumption ratio information K is expressed as:
wherein P is PSU_IN Representing the input energy consumption of a power supply; p (P) SYS Representing the energy consumption of the main board; p (P) CPU Representing CPU energy consumption; p (P) MEM Representing the energy consumption of the memory; p (P) HDD Representing the energy consumption of the hard disk; p (P) GPU Representing GPU power consumption.
Further, the system also comprises a graphic display module, wherein the graphic display module is used for converting the energy consumption data and the energy consumption ratio information of the server into graphic information for display, and the graphic information comprises heat dissipation energy consumption and transmission loss.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the invention, such changes and modifications are also intended to be within the scope of the invention.
Claims (10)
1. The method for calculating the energy consumption ratio of the server is characterized by comprising the following steps of:
based on the category of the energy consumption of the pre-divided server, acquiring corresponding energy consumption data of the single server;
calculating energy consumption ratio information of the server according to the energy consumption data;
and configuring the server based on the server energy consumption ratio information so as to realize the optimal energy consumption ratio of the server.
2. The method for calculating the energy consumption ratio of the server according to claim 1, wherein the obtaining the corresponding energy consumption data of the single server based on the category of the energy consumption of the pre-divided server specifically comprises:
the categories of the energy consumption of the server are divided into power input energy consumption, power output energy consumption and power conversion loss in advance, and then the following steps are included: power input energy consumption = power output energy consumption + power conversion loss; wherein:
the power supply output energy consumption comprises main board energy consumption, CPU energy consumption, memory energy consumption, hard disk energy consumption, heat dissipation energy consumption, GPU energy consumption and transmission loss;
and acquiring corresponding energy consumption data of the single server.
3. The method for calculating the energy consumption ratio of the server according to claim 2, wherein the obtaining the corresponding energy consumption data of the single server based on the category of the energy consumption of the pre-divided server specifically comprises:
based on the category of the pre-divided server energy consumption, acquiring the main board energy consumption, CPU energy consumption, memory energy consumption, hard disk energy consumption, heat dissipation energy consumption and GPU energy consumption of a single server through a power consumption sensor; directly acquiring power input energy consumption and power output energy consumption through a power supply; the transmission loss is obtained by an indirect method.
4. A method for calculating a server energy consumption ratio according to claim 3, wherein the calculating the server energy consumption ratio information according to the energy consumption data specifically comprises:
the calculation of the server energy consumption ratio information K is expressed as:
wherein P is PSU_IN Representing the input energy consumption of a power supply; p (P) SYS Representing the energy consumption of the main board; p (P) CPU Representing CPU energy consumption; p (P) MEM Representing the energy consumption of the memory; p (P) HDD Representing the energy consumption of the hard disk; p (P) GPU Representing GPU power consumption.
5. The method according to claim 3 or 4, further comprising converting the energy consumption data and the server energy consumption ratio information into graphic information for display, including heat dissipation energy consumption and transmission loss.
6. The server energy consumption ratio computing system is characterized by comprising an energy consumption data acquisition module, an energy consumption ratio information computing module and a configuration module; wherein:
the energy consumption data acquisition module is used for acquiring corresponding energy consumption data of the single server based on the category of the energy consumption of the pre-divided server;
the energy consumption ratio information calculation module is used for calculating the energy consumption ratio information of the server according to the energy consumption data;
the configuration module configures the server based on the server energy consumption ratio information so as to realize the optimal energy consumption ratio of the server.
7. The server energy consumption ratio computing system according to claim 6, wherein the energy consumption data obtaining module is configured to obtain corresponding energy consumption data of a single server based on a category of energy consumption of the pre-divided server, specifically:
the categories of the energy consumption of the server are divided into power input energy consumption, power output energy consumption and power conversion loss in advance, and then the following steps are included: power input energy consumption = power output energy consumption + power conversion loss; wherein:
the power supply output energy consumption comprises main board energy consumption, CPU energy consumption, memory energy consumption, hard disk energy consumption, heat dissipation energy consumption, GPU energy consumption and transmission loss;
and acquiring corresponding energy consumption data of the single server.
8. The server energy consumption ratio calculating system according to claim 7, wherein in the energy consumption data obtaining module, the obtaining, based on the category of the pre-divided server energy consumption, the corresponding energy consumption data of the single server is specifically:
based on the category of the pre-divided server energy consumption, acquiring the main board energy consumption, CPU energy consumption, memory energy consumption, hard disk energy consumption, heat dissipation energy consumption and GPU energy consumption of a single server through a power consumption sensor; directly acquiring power input energy consumption and power output energy consumption through a power supply; the transmission loss is obtained by an indirect method.
9. The server energy consumption ratio calculation system according to claim 8, wherein the energy consumption ratio information calculation module is configured to calculate server energy consumption ratio information according to energy consumption data, specifically:
the calculation of the server energy consumption ratio information K is expressed as:
wherein P is PSU_IN Representing the input energy consumption of a power supply; p (P) SYS Representing the energy consumption of the main board; p (P) CPU Representing CPU energy consumption; p (P) MEM Representing the energy consumption of the memory; p (P) HDD Representing the energy consumption of the hard disk; p (P) GPU Representing GPU power consumption.
10. The server energy consumption ratio computing system of claim 8 or 9, further comprising a graphic display module for converting the energy consumption data and the server energy consumption ratio information into graphic information for display, including heat dissipation energy consumption and transmission loss.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310542133.0A CN116755982A (en) | 2023-05-15 | 2023-05-15 | Method and system for calculating energy consumption ratio of server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310542133.0A CN116755982A (en) | 2023-05-15 | 2023-05-15 | Method and system for calculating energy consumption ratio of server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116755982A true CN116755982A (en) | 2023-09-15 |
Family
ID=87957915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310542133.0A Pending CN116755982A (en) | 2023-05-15 | 2023-05-15 | Method and system for calculating energy consumption ratio of server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116755982A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105607726A (en) * | 2015-12-24 | 2016-05-25 | 浪潮(北京)电子信息产业有限公司 | Method and device for lowering internal storage power consumption of high-performance computing cluster |
| CN113204429A (en) * | 2021-05-31 | 2021-08-03 | 深圳供电局有限公司 | Resource scheduling method and system of data center, scheduling equipment and medium |
| CN113849365A (en) * | 2021-08-19 | 2021-12-28 | 苏州浪潮智能科技有限公司 | Server performance power consumption ratio regulation and control method, system, terminal and storage medium |
| CN114721488A (en) * | 2022-03-18 | 2022-07-08 | 上海燧原科技有限公司 | Fan rotating speed control method and system |
-
2023
- 2023-05-15 CN CN202310542133.0A patent/CN116755982A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105607726A (en) * | 2015-12-24 | 2016-05-25 | 浪潮(北京)电子信息产业有限公司 | Method and device for lowering internal storage power consumption of high-performance computing cluster |
| CN113204429A (en) * | 2021-05-31 | 2021-08-03 | 深圳供电局有限公司 | Resource scheduling method and system of data center, scheduling equipment and medium |
| CN113849365A (en) * | 2021-08-19 | 2021-12-28 | 苏州浪潮智能科技有限公司 | Server performance power consumption ratio regulation and control method, system, terminal and storage medium |
| CN114721488A (en) * | 2022-03-18 | 2022-07-08 | 上海燧原科技有限公司 | Fan rotating speed control method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100541392C (en) | Temperature detecting system and method | |
| CN109611367B (en) | Fan control system and server based on CPLD | |
| US8193799B2 (en) | Interposer including voltage regulator and method therefor | |
| US9020655B2 (en) | Thermal management for integrated circuits | |
| US20090119523A1 (en) | Managing Power Consumption Based on Historical Average | |
| CN103036816B (en) | Fan rotating speed controlling method and switchboard equipment | |
| US8996192B2 (en) | Thermal management for integrated circuits | |
| US9785134B2 (en) | Fan duty control for multi-node computing device | |
| US7349828B1 (en) | Estimating an electronic device condition | |
| US20070046281A1 (en) | Power metering using current-indicative signal | |
| CN106911254A (en) | Electronic device | |
| CN105045701A (en) | Server system with high-precision PCIE equipment power consumption monitoring function | |
| CN112650651A (en) | Power consumption detection IP (Internet protocol), management method and system | |
| Hsu et al. | Power measurement for high performance computing: State of the art | |
| CN116755982A (en) | Method and system for calculating energy consumption ratio of server | |
| CN103729279A (en) | Hard disk temperature detecting system | |
| CN210776379U (en) | GPU Box system | |
| US7586287B2 (en) | Computer housing temperature control device | |
| US20140016259A1 (en) | Multi-motherboard power data communication architecture for power supplies | |
| CN102414568B (en) | AD converter is used to perform multiplying | |
| CN110018730B (en) | Server device capable of detecting power supply load | |
| TW201443633A (en) | System for energy management | |
| US20040246675A1 (en) | Instrumentation console for personal computers | |
| CN202031862U (en) | Machine cabinet provided with fan module controller, fan module and machine frame type cutting blade | |
| CN203311245U (en) | Power monitoring circuit and power monitoring device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |