CN112486683B - Processor control method, control apparatus, and computer-readable storage medium - Google Patents
Processor control method, control apparatus, and computer-readable storage medium Download PDFInfo
- Publication number
- CN112486683B CN112486683B CN202011368269.7A CN202011368269A CN112486683B CN 112486683 B CN112486683 B CN 112486683B CN 202011368269 A CN202011368269 A CN 202011368269A CN 112486683 B CN112486683 B CN 112486683B
- Authority
- CN
- China
- Prior art keywords
- processor
- intensity value
- determining
- predicted
- predicted intensity
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- 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)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Feedback Control In General (AREA)
- Power Sources (AREA)
Abstract
The application discloses a processor control method, control equipment and a computer readable storage medium, wherein the method comprises the following steps: determining a predicted intensity value of at least one processor in the distributed storage cluster at the current moment; determining an operating parameter of the processor according to the predicted intensity value; and adjusting the operation parameters according to the operation condition of the processor, and controlling the processor to operate according to the adjusted operation parameters so as to reduce the energy consumption consumed by the processor when executing tasks. The technical problem that the actual running requirement of the processor when executing the task can not be met when the cluster is controlled to run according to the result calculated by the energy consumption model is solved, and the energy consumption consumed by the processor when executing the task is reduced.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a processor control method, a control device, and a computer readable storage medium.
Background
With the rapid growth of the internet, the large amount of data that follows takes on an exponentially growing form. Among them, the distributed file system can be used to store and process a large amount of data, of which HDFS is the most representative, which enables reliable storage of a large amount of data of files and streaming of data at a high bandwidth.
The method for reducing the energy consumption of the HDFS in the prior art mainly comprises the following steps: firstly, changing CPU utilization rate and frequency, establishing a corresponding energy consumption model such as establishing a relation between computer power, CPU utilization rate and frequency, and adjusting system energy consumption according to different task demands; secondly, a prediction model is established, and the prediction control is used for optimizing indexes according to the performance of the control target design system, so that the performance indexes in a future prediction time domain are optimal; third, servers in a data center are logically organized in a plurality of dynamically preconfigured hot and cold zones by GreenHDFS, greenHDFS, each zone having unique performance, cost and power characteristics, each zone being managed by a power supply and data placement policy that best suits the data class in the zone, avoiding startup of servers in the cold zone, and maximizing utilization of existing started servers in their server allocation decisions to maximize energy savings.
Some of the current mainstream CPUs cannot regulate the frequency, most of the CPUs can be used for switching the core, but few researches for reducing the energy consumption in the working process of HDFS by switching the CPU core are performed. The method for reducing the energy consumption of the HDFS is mostly carried out by establishing an energy consumption model, and research on engineering realization is ignored. For large clusters in a working state, direct regulation and control by establishing an energy consumption model is unrealistic, the anti-interference capability of implementing the regulation and control is weak, and the actual requirements which cannot be met when the clusters are controlled to run according to the result of calculation of the energy consumption model are not satisfied.
Disclosure of Invention
The embodiment of the application aims to solve the problem that the actual running requirement of a processor when executing tasks can not be met when the cluster is controlled to run according to the result calculated by the energy consumption model at present by providing a processor control method, control equipment and computer readable storage medium.
To achieve the above object, an aspect of the present application provides a processor control method, including:
determining a predicted intensity value of at least one processor in the distributed storage cluster at the current moment;
determining an operating parameter of the processor according to the predicted intensity value;
and adjusting the operation parameters according to the operation condition of the processor, and controlling the processor to operate according to the adjusted operation parameters so as to reduce the energy consumption consumed by the processor when executing tasks.
Optionally, the step of adjusting the operation parameter according to the operation condition of the processor includes:
acquiring an actual intensity value of a processor in a first preset duration;
determining the maximum operation parameter corresponding to the actual intensity value;
when the processor operates according to the maximum parameter within a first preset duration, counting a time threshold value of the processor operating according to the maximum operation parameter;
and when the time threshold is larger than a first preset time threshold, controlling the processor to increase the current operation parameter.
Optionally, after the step of obtaining the actual intensity value of the processor within the first preset time period, the method includes:
determining the minimum operation parameter corresponding to the actual intensity value;
when the processor operates according to the minimum parameter within a first preset duration, counting a time threshold value of the processor operating according to the minimum operation parameter;
and when the time threshold is larger than a second preset time threshold, controlling the processor to reduce the current operation parameter.
Optionally, the step of determining a predicted intensity value of the current time of at least one processor in the distributed storage cluster includes:
acquiring the current system time of a processor;
and determining a historical intensity value corresponding to the system time as a predicted intensity value of the current moment.
Optionally, the step of determining a predicted intensity value of the current time of at least one processor in the distributed storage cluster includes:
acquiring each historical intensity value of the processor in a first preset time period;
and establishing a data model for the historical intensity value, and obtaining the predicted intensity value through the data model.
Optionally, the step of obtaining the actual intensity value of each running time period of the processor includes:
acquiring the number of times the processor reads data and writes data in the running time period;
and determining the actual intensity value according to the times of reading data and writing data.
Optionally, the step of determining an operating parameter of the processor according to the predicted intensity value includes:
determining a band function corresponding to the predicted intensity value;
and determining the operation parameters corresponding to the band functions as the operation parameters of the processor.
Optionally, the step of determining the band function corresponding to the predicted intensity value includes:
and comparing the predicted intensity value with the historical intensity value, and confirming that the band function corresponding to the historical intensity value pair with consistent comparison is the band function of the predicted intensity value.
In addition, in order to achieve the above object, another aspect of the present application further provides a processor control system, where the control system includes a processor, a memory, and a processor control program stored on the memory and executable on the processor, and the processor control program when executed by the processor implements the steps of the method controlled by the processor as above.
In addition, in order to achieve the above object, another aspect of the present application further provides a computer-readable storage medium having stored thereon a processor control program which, when executed by a processor, implements the steps of the method of processor control as above.
In the method, the predicted intensity value of at least one processor in the distributed storage cluster at the current moment is determined, then the operation parameters of the processor are determined according to the predicted intensity value, the operation condition of the processor is obtained, the operation parameters are adjusted according to the operation condition of the processor, the processor is controlled to operate according to the adjusted operation parameters, so that the energy consumption consumed by the processor when executing tasks is reduced, the operation parameters can be adjusted according to the actual operation condition of the processor, and the problem of processing clamping caused by the fact that the operation parameters obtained according to the predicted intensity value are smaller than the operation parameters required by the processor when executing the tasks at the current moment is avoided.
Drawings
Fig. 1 is a schematic diagram of a terminal structure of a hardware running environment according to an embodiment of the present application;
FIG. 2 is a flow chart of an embodiment of a processor control method according to the present application;
fig. 3 is a flowchart of a processor control method according to another embodiment of the present application.
The realization, functional characteristics and advantages of the present application will be further described with reference to the embodiments, referring to the attached drawings.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The main solutions of the embodiments of the present application are: determining a predicted intensity value of at least one processor in the distributed storage cluster at the current moment; determining an operating parameter of the processor according to the predicted intensity value; and adjusting the operation parameters according to the operation condition of the processor, and controlling the processor to operate according to the adjusted operation parameters so as to reduce the energy consumption consumed by the processor when executing tasks.
Because the energy consumption generated in the prior art for adjusting the distributed storage clusters is generated by establishing a prediction model, each processor in the distributed storage clusters is controlled to run according to predicted running parameters when executing each stage of task. However, when the operation parameters obtained in a prediction mode are used for controlling the operation of the processor, the difference between the actual intensity value and the predicted intensity value of the processor in the actual operation process is not considered, so that the problem that the operation parameter setting is too large or too small when the operation parameters obtained according to the prediction model are operated by the processor, and the problem that the data operation requirements cannot be met or the waste power consumption is caused when the operation parameter setting is too large is caused when the operation parameters of the processor are operated.
As shown in fig. 1, fig. 1 is a schematic diagram of a terminal structure of a hardware running environment according to an embodiment of the present application.
As shown in fig. 1, the terminal may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Optionally, the terminal may further include a camera, an RF (Radio Frequency) circuit, a sensor, a remote control, an audio circuit, a WiFi module, a detector, and the like. Of course, the terminal may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a temperature sensor, etc., which will not be described herein.
It will be appreciated by those skilled in the art that the terminal structure shown in fig. 1 is not limiting of the terminal device and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a processor control program may be included in a memory 1005, which is a computer-readable storage medium.
In the terminal shown in fig. 1, the network interface 1004 is mainly used for connecting to a background server and performing data communication with the background server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to call a processor control program stored in the memory 1005 and perform the following operations:
determining a predicted intensity value of at least one processor in the distributed storage cluster at the current moment;
determining an operating parameter of the processor according to the predicted intensity value;
and adjusting the operation parameters according to the operation condition of the processor, and controlling the processor to operate according to the adjusted operation parameters so as to reduce the energy consumption consumed by the processor when executing tasks.
Referring to fig. 2, fig. 2 is a flowchart illustrating an embodiment of a processor control method according to the present application.
The present embodiments provide embodiments of a processor control method, it being noted that although a logic sequence is shown in the flow diagrams, in some cases the steps shown or described may be performed in a different order than that shown or described herein.
The processor control method comprises the following steps:
step S10, determining a predicted intensity value of at least one processor in a distributed storage cluster at the current moment;
the distributed storage cluster is formed by constructing a network topology through a plurality of storage servers, and the storage server cluster can be used for operations such as data reading and writing through a related algorithm, namely, when a plurality of processors share the data processing, the problem of overlarge storage load caused by the fact that a large amount of data needs to be analyzed and processed is solved.
In practical use, each process in the server cluster is independent of the other and processes different data. Therefore, the operation parameters of the processors contained in the distributed storage cluster can be managed by calculating the intensity values of the processors at different moments, so that the operation of each processor meets the task requirement of current required execution.
In this embodiment, the predicted intensity value is the intensity value predicted by the processor at the current time. Specifically, in the present embodiment, the method for obtaining the predicted intensity value may be obtained according to obtaining the historical intensity value of each processor.
The step of determining the predicted intensity value of the current moment of at least one processor in the distributed storage cluster comprises the following steps:
step S11, acquiring the current system time of a processor;
and step S12, determining a historical intensity value corresponding to the system time as a predicted intensity value at the current moment.
The historical intensity value is the intensity value actually operated by the processor when executing the task. In this embodiment, the strength value actually operated by the processor at different time is obtained as the historical strength value, the time period of each strength value when the processor executes the task is recorded, and the historical strength of the time period is obtained as the predicted strength at the current time by analyzing the specific time period of the time period to which the system time belongs.
Optionally, in this embodiment, the preset time range may be further divided into a plurality of time periods, and the historical intensity value of the processor actually running in each time is obtained, so that when the predicted intensity value of the current time of the processor is obtained, the time period in which the system time of the current time is located is determined, and further the historical intensity value of the time period is obtained, and the historical intensity value is used as the predicted intensity value. Specifically, with time as a period (24 h), 24 hours are equally divided into different time periods (one time period is set for each hour), and then the actual running intensity value (historical intensity value) of each processor in the different time periods is obtained. On the next day, 24 hours are equally divided into time periods equal to the duration of each time period of the previous day. When the current predicted intensity value of the processor is acquired, the current system time is acquired, the time period where the current system time is located is determined, and the intensity value corresponding to the time period is further determined to be the predicted intensity value of the current moment.
In this embodiment, by acquiring the system time of the processor in the actual running process, determining the time period in which the system time is located, further obtaining the historical intensity value of the system in the time period, determining that the historical intensity value is the predicted intensity value of the current system time, and determining the historical intensity value corresponding to the time period to which the current moment belongs as the predicted intensity value of the processor, the accuracy of the predicted intensity value is improved.
The step of determining the predicted intensity value of the current moment of at least one processor in the distributed storage cluster comprises the following steps:
step S111, each historical intensity value of the processor in a first preset duration is obtained;
and step S112, establishing a data model according to the historical intensity value to obtain the predicted intensity value.
In this embodiment, the first preset time period may be set to one week, that is, the historical intensity value of each processor in the previous week is obtained as data for obtaining the predicted intensity value of the next week, where the setting of the first preset time period may be determined according to the case of performing data processing by using the processor, and specifically, the first preset time period may also be set to one month. The historical intensity value in the first preset duration may include a plurality of historical intensity values, specifically, the historical intensity values in different time periods are periodically obtained every one hour, and the historical intensity values and the time periods are mapped and stored. For example, 00:00-01:00, wherein the historical intensity values from monday to sunday are x1, x2 and x3 … … x7 respectively, the historical intensity values corresponding to 168 time periods in a week are obtained respectively, the historical intensity values and the time periods are taken as independent variables and are brought into a data model (SARIMA model) to carry out data analysis, and further the predicted intensity values corresponding to the time periods of 24 hours in the future are obtained.
The step of obtaining each historical intensity value of the processor in a first preset time period comprises the following steps:
step S1111, obtaining the number of times of data reading and data writing of the processor in each time period of the first preset duration;
step S1112, determining the historical intensity value according to the number of times of reading data and writing data.
Analyzing the storage log on the datinode, wherein the method can be adopted to collect the read-write times in each time period of the first preset duration, and the sampling time is set as a i The number of writes is b i Let the historical intensity value be D i Then
Wherein θ is i And gamma i For example, the coefficient of the read data corresponding to the processor 1 is θ 1 The coefficient of the written data is gamma 1 They convert the number of reads to a historical intensity value D representing the processing tasks in each time period of the processor i . A predicted intensity value is then determined based on the plurality of historical intensity values and the corresponding each time period. In this embodiment, by acquiring the historical intensity values of the processor in the first preset time period when executing the task, further determining the predicted intensity value of the processor at the current time, and determining the predicted intensity value of the predicted current time according to the historical intensity values by means of data analysis, the accuracy of acquiring the predicted intensity value of the current time is improved.
Step S20, determining the operation parameters of the processor according to the predicted intensity value;
the operation parameters of the processor are the core number and the operation frequency of the task of the processor at the current execution moment.
Specifically, in the present application, the operating frequency of the processor includes powersave, performance two gears, the number of cores of the processor is 1 to 8, and when the operating frequencies of different gears and the core combinations execute tasks, the power of the processor is different, and the intensity values of the power are also different. In the method, the corresponding relation between the intensity value and the operating frequency and the core number is established by utilizing the power difference corresponding to the intensity value of the processor and the power difference of the processor when the processor performs the combined execution task with different operating frequencies and core numbers, and further, the operating parameter at the current moment of the processor can be determined through the predicted intensity value by acquiring the corresponding relation between the operating frequency corresponding to the intensity value consistent with the predicted parameter value and the core number.
And step S30, adjusting the operation parameters according to the operation condition of the processor, and controlling the processor to operate according to the adjusted operation parameters so as to reduce the energy consumption consumed by the processor when executing tasks.
It can be understood that in the actual use process, because the executed task strength is different from the predicted strength obtained by predicting according to the historical parameters, the operation parameters can be adjusted according to the operation condition of the current processor, and the processor is controlled to operate according to the adjusted operation parameters, so that the operation parameters of the processor are matched with the operation parameters required by executing the task at the current moment.
In the method, the predicted intensity value of at least one processor in the distributed storage cluster at the current moment is determined, then the operation parameters of the processor are determined according to the predicted intensity value, the operation condition of the processor is obtained, the operation parameters are adjusted according to the operation condition of the processor, the processor is controlled to operate according to the adjusted operation parameters, so that the energy consumption consumed by the processor when executing tasks is reduced, the operation parameters can be adjusted according to the actual operation condition of the processor, and the problem of processing clamping caused by the fact that the operation parameters obtained according to the predicted intensity value are smaller than the operation parameters required by the processor when executing the tasks at the current moment is avoided.
Based on the above embodiment, another embodiment of the present application is presented. The step of adjusting the operation parameters according to the operation condition of the processor comprises the following steps:
step S41, acquiring an actual intensity value of a processor in a first preset time period;
step S42, determining the maximum operation parameter corresponding to the actual intensity value;
step S43, counting a time threshold value of the processor running according to the maximum running parameter when the processor runs according to the maximum parameter within a first preset duration;
and S44, controlling the processor to increase the current operation parameter when the time threshold is larger than a first preset time threshold.
The actual intensity value can be obtained through an installed measuring device, namely a smart meter. Specifically, the smart meter may establish a wired connection with the processor, with different connection interfaces representing different connected processors. And when the actual intensity value is obtained, the actual intensity value fed back in the intelligent ammeter is obtained by designing a script program corresponding to the processor. The first preset duration is a duration from a system time counted from the beginning to a system time at a current moment in the process of executing a task by a current processor, and the current moment is 12: at 00, the system time for starting statistics is 11:00 represents a first preset time period of 1 hour. And counting the actual intensity value of the processor in the hour, further determining the maximum operation parameter of the processor according to the actual intensity value, and when the operation time of the processor according to the maximum operation parameter is longer than a first preset time threshold (30 minutes), confirming that the operation parameter obtained by the processor according to the predicted intensity value is smaller than the operation parameter of the processor when executing the task, increasing the operation parameter, for example, from the core number of 4, the gear of the operation frequency of powersave, the adjustment of the gear of the operation frequency of 5, and the operation frequency of powersave. Thus, the processor can smoothly execute the processing task when the processor runs according to the adjusted running parameters.
After the step of obtaining the actual intensity value of the processor in the first preset time period, the method comprises the following steps:
step S45, determining the minimum operation parameter corresponding to the actual intensity value;
step S46, counting a time threshold value of the processor running according to the minimum running parameter when the processor runs according to the minimum parameter within a first preset duration;
and step S47, when the time threshold is larger than a second preset time threshold, controlling the processor to reduce the current operation parameters.
Further, if the first preset duration is one hour, the actual intensity value of the processor in the hour is counted, the minimum operation parameter of the processor is determined according to the actual intensity value, when the duration of the operation of the processor according to the minimum operation parameter is greater than the second preset time threshold (20 minutes), the operation parameter obtained by the processor according to the predicted intensity value is confirmed to be greater than the operation parameter of the processor when executing the task, the operation parameter is reduced, for example, the operation parameter is adjusted to be 3 from the core number, the gear of the operation frequency is power save, and the operation frequency is power save. Thus, the energy consumption of the processor when executing tasks is reduced.
Referring to fig. 3, fig. 3 is a further embodiment of the present application. The step of determining the operating parameters of the processor according to the predicted intensity values comprises the following steps:
step S21, determining a wave band function corresponding to the predicted intensity value;
step S22, determining the operation parameters corresponding to the band functions as the operation parameters of the processor.
The band function is a piecewise function corresponding to the historical intensity value and the power of the processor, and it can be understood that in practical application, the relation between the intensity value of the processor and the power is many-to-one, and then the relation between the historical intensity value and the operation parameter of the processor is many-to-one. In this embodiment, the operating parameter corresponding to the band function is determined to be the operating parameter of the processor by using the band function corresponding to the predicted intensity value.
The step of determining the band function corresponding to the predicted intensity value comprises the following steps:
and S23, comparing the predicted intensity value with the historical intensity value, and confirming that the band function corresponding to the historical intensity value pair with the same comparison is the band function of the predicted intensity value.
It can be understood that in this embodiment, the obtained band function is determined according to the historical intensity value, so when the band function of the predicted intensity is obtained, the predicted intensity value and the historical intensity value need to be compared, so as to obtain the band function matched with the predicted intensity value, and further, the running power of the processor is determined according to the value of the band function, so that the number of cores and the running frequency of the processor required to be started when the processor executes the task are obtained, the accuracy of controlling the running parameters when the processor executes the processing task is improved, and the energy loss is reduced.
In addition, the application further provides a processor control device, which comprises a processor, a memory and a processor control program stored on the memory and capable of running on the processor, wherein the processor control program is executed by the processor to realize the steps of the processor control method.
Furthermore, the present application provides a computer-readable storage medium having stored thereon a processor control program which, when executed by a processor, implements the steps of any one of the processor control methods described above.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.
While alternative embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following appended claims be interpreted as including alternative embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (6)
1. A processor control method, the processor control method comprising:
determining a predicted intensity value of at least one processor in the distributed storage cluster at the current moment;
the step of determining the predicted intensity value of the current moment of at least one processor in the distributed storage cluster comprises the following steps:
acquiring the current system time of a processor;
determining a historical intensity value corresponding to the system time as a predicted intensity value at the current moment;
determining an operation parameter of the processor according to the predicted intensity value, wherein the operation parameter is the core number and the operation frequency of the task of the processor at the current execution moment;
acquiring an actual intensity value of a processor in a first preset duration;
the step of obtaining the actual intensity value of each operation time period of the processor comprises the following steps:
acquiring the number of times the processor reads data and writes data in the running time period;
determining the actual intensity value according to the read data and the number of times of writing data;
determining the minimum operation parameter corresponding to the actual intensity value;
when the processor operates according to the minimum operation parameter within a first preset duration, counting a time threshold value of the processor operating according to the minimum operation parameter;
when the time threshold is larger than a second preset time threshold, controlling the processor to reduce the current operation parameters;
determining the maximum operation parameter corresponding to the actual intensity value;
when the processor operates according to the maximum operation parameter within a first preset duration, counting a time threshold value of the processor operating according to the maximum operation parameter;
when the time threshold is larger than a first preset time threshold, the processor is controlled to increase the current operation parameter;
and controlling the processor to run according to the adjusted running parameters so as to reduce the energy consumption consumed by the processor when executing the tasks.
2. The processor control method of claim 1, wherein the step of determining a predicted intensity value for a current time of at least one processor in the distributed storage cluster comprises:
acquiring each historical intensity value of the processor in a first preset time period;
and establishing a data model for the historical intensity value, and obtaining the predicted intensity value through the data model.
3. The processor control method of claim 1, wherein said step of determining an operating parameter of said processor based on said predicted intensity value comprises:
determining a band function corresponding to the predicted intensity value;
and determining the operation parameters corresponding to the band functions as the operation parameters of the processor.
4. The processor control method of claim 3, wherein said step of determining a band function corresponding to said predicted intensity value comprises:
and comparing the predicted intensity value with the historical intensity value, and confirming that the band function corresponding to the historical intensity value pair with the same comparison is the band function of the predicted intensity value.
5. A processor control device, characterized in that it comprises a processor, a memory and a processor control program stored on the memory and executable on the processor, which processor control program, when executed by the processor, implements the steps of the processor control method according to any one of claims 1-4.
6. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a processor control program which, when executed by a processor, implements the steps of the processor control method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011368269.7A CN112486683B (en) | 2020-11-27 | 2020-11-27 | Processor control method, control apparatus, and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011368269.7A CN112486683B (en) | 2020-11-27 | 2020-11-27 | Processor control method, control apparatus, and computer-readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112486683A CN112486683A (en) | 2021-03-12 |
| CN112486683B true CN112486683B (en) | 2023-05-19 |
Family
ID=74937113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011368269.7A Active CN112486683B (en) | 2020-11-27 | 2020-11-27 | Processor control method, control apparatus, and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112486683B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113238648B (en) * | 2021-05-11 | 2023-05-09 | 成都海光集成电路设计有限公司 | Power consumption adjusting method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103646670A (en) * | 2013-12-05 | 2014-03-19 | 华为技术有限公司 | Method and device for evaluating performances of storage system |
| CN104808770A (en) * | 2015-04-23 | 2015-07-29 | 南京大学 | Data center energy consumption management method and system based on dynamic frequency modulation |
| CN107122036A (en) * | 2017-04-18 | 2017-09-01 | 青岛海信移动通信技术股份有限公司 | CPU frequency adjusting method and device |
| CN107515663A (en) * | 2016-06-15 | 2017-12-26 | 北京京东尚科信息技术有限公司 | The method and apparatus for adjusting central processor core running frequency |
| CN108200473A (en) * | 2018-02-01 | 2018-06-22 | 深圳创维－Rgb电子有限公司 | Cpu power control method, intelligent TV set and storage medium |
| CN108845659A (en) * | 2018-01-30 | 2018-11-20 | 武汉大学 | A kind of embeded processor real-time task distribution method that power consumption is preferential |
| CN110308782A (en) * | 2018-03-22 | 2019-10-08 | 阿里巴巴集团控股有限公司 | Power consumption prediction, control method, equipment and computer readable storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8190939B2 (en) * | 2009-06-26 | 2012-05-29 | Microsoft Corporation | Reducing power consumption of computing devices by forecasting computing performance needs |
| US20170206111A1 (en) * | 2016-01-15 | 2017-07-20 | Qualcomm Innovation Center, Inc. | Managing processing capacity provided to threads based upon load prediction |
| US10303482B2 (en) * | 2017-03-07 | 2019-05-28 | Red Hat, Inc. | Dynamic processor frequency selection |
-
2020
- 2020-11-27 CN CN202011368269.7A patent/CN112486683B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103646670A (en) * | 2013-12-05 | 2014-03-19 | 华为技术有限公司 | Method and device for evaluating performances of storage system |
| CN104808770A (en) * | 2015-04-23 | 2015-07-29 | 南京大学 | Data center energy consumption management method and system based on dynamic frequency modulation |
| CN107515663A (en) * | 2016-06-15 | 2017-12-26 | 北京京东尚科信息技术有限公司 | The method and apparatus for adjusting central processor core running frequency |
| CN107122036A (en) * | 2017-04-18 | 2017-09-01 | 青岛海信移动通信技术股份有限公司 | CPU frequency adjusting method and device |
| CN108845659A (en) * | 2018-01-30 | 2018-11-20 | 武汉大学 | A kind of embeded processor real-time task distribution method that power consumption is preferential |
| CN108200473A (en) * | 2018-02-01 | 2018-06-22 | 深圳创维－Rgb电子有限公司 | Cpu power control method, intelligent TV set and storage medium |
| CN110308782A (en) * | 2018-03-22 | 2019-10-08 | 阿里巴巴集团控股有限公司 | Power consumption prediction, control method, equipment and computer readable storage medium |
Non-Patent Citations (4)
| Title |
|---|
| Linear combinations of dvfs-enabled processor frequencies to modify the energy-aware scheduling algorithms;N.B.Rizvandi等;《2010 10th IEEE/ACM International Conference on Cluster,Cloud and Grid Computing》;388-397 * |
| 云计算环境下基于预测算法的负载均衡机制研究;彭洁;《中国优秀硕士学位论文全文数据库 信息科技辑》(第03期);I139-357 * |
| 基于BP神经网络的处理器节能技术研究;郭兵等;《工程科学与技术》;第50卷(第01期);107-112 * |
| 异构Spark集群下自适应任务调度策略;杨志伟等;《计算机工程》;第42卷(第01期);31-35+40 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112486683A (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11765754B2 (en) | Resource scheduling method and terminal device | |
| CN112529301B (en) | Power consumption prediction method, device and storage medium | |
| CN107515663B (en) | Method and device for adjusting running frequency of central processing unit kernel | |
| EP3454210B1 (en) | Prescriptive analytics based activation timetable stack for cloud computing resource scheduling | |
| CN108446795B (en) | Power system load fluctuation analysis method and device and readable storage medium | |
| WO2021129086A1 (en) | Traffic prediction method, device, and storage medium | |
| CN103218263A (en) | Dynamic determining method and device for MapReduce parameter | |
| Saglam | Optimal pattern of technology adoptions under embodiment: A multi‐stage optimal control approach | |
| CN112954707A (en) | Energy saving method and device for base station, base station and computer readable storage medium | |
| CN112486683B (en) | Processor control method, control apparatus, and computer-readable storage medium | |
| CN112907064A (en) | Electric quantity prediction method and device based on self-adaptive window, storage medium and terminal | |
| CN114285042A (en) | Method and device for determining load electricity utilization operation mode | |
| CN112015326B (en) | Cluster data processing method, device, equipment and storage medium | |
| WO2021042368A1 (en) | Power consumption control and scheme generation method, device, system, and storage medium | |
| CN109062396B (en) | Method and device for controlling equipment | |
| Zhou et al. | CPU frequency scheduling of real-time applications on embedded devices with temporal encoding-based deep reinforcement learning | |
| CN105824809B (en) | A kind of implementation method and device of ETL scheduling | |
| CN113360203B (en) | Task unloading method and device for electric power Internet of things | |
| CN117196256B (en) | Scheduling method and equipment for data center workload in power market environment | |
| CN117973727A (en) | Customer service scheduling intelligent optimization method based on mathematical programming and electronic equipment | |
| DE102022126087A1 (en) | IDENTIFICATION OF HOTSPOTS AND COLDSPOTS IN FORECASTED POWER CONSUMPTION DATA IN AN IT DATA CENTER FOR WORKLOAD PLANNING | |
| US20230118253A1 (en) | Method and a system for power management of the one or more base stations in a wireless communication network | |
| CN116566986A (en) | Intelligent building network task scheduling optimization algorithm based on deep reinforcement learning | |
| CN109274545A (en) | A kind of cycle storage method based on mixed cloud | |
| Zhang et al. | Research on cloud-side collaborative task migration strategy based on simulated annealing-Bee Colony Algorithm in Power IoT |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |