Operating system parameter automatic configuration method, device, equipment, medium and product
By using a pre-trained prediction model to predict the peak performance parameters of the target application and adjust the operating system parameters according to the prediction results, the problem of poor adaptive operating system parameter configuration in the prior art is solved, and more efficient and accurate system parameter configuration.
Patent Information
- Application Number
- CN202411208916.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-30
- Publication Date
- 2025-02-07
AI Technical Summary
In the prior art, operating system parameter configuration relies on manual preset rules and preset thresholds, and cannot adapt to dynamic changes in system workload, resulting in poor adaptation of system parameter configuration.
The monitoring data collected by the monitoring system is obtained by a preset interval, and the peak performance parameters of the target application are predicted using a pre-trained prediction model, and the system parameters of the operating system are adjusted based on the prediction parameter values and system monitoring data.
It improves the adaptability and accuracy of operating system system parameter configuration, and solves the problems of unreasonable allocation and low efficiency caused by manual configuration.
Smart Images
Figure CN119396481A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of data processing, and in particular to a method, device, equipment, medium and product for automatically configuring operating system parameters. Background Art
[0002] With the continuous development of computer technology, the functions of application software are becoming more and more abundant. Correspondingly, application software requires more and more system resources provided by the operating system to ensure the realization of all the functions of the application software.
[0003] When the operating system provides system resources for application software, different application software has different requirements for the operating system, so the system parameters of the operating system need to be configured accordingly. At present, when configuring system parameters, system resource allocation mainly relies on manually preset rules and preset thresholds. This system resource allocation method cannot adapt to the dynamic changes of system workload, resulting in poor system parameter configuration adaptability. Summary of the invention
[0004] In view of the above-mentioned defects or deficiencies in the related art, the purpose of this application is to provide a method, device, equipment, medium and product for automatic configuration of operating system parameters, which can effectively improve the adaptability and accuracy of system parameter configuration of the operating system.
[0005] To achieve the above objectives, this application provides the following solutions:
[0006] In a first aspect, the present application provides a method for automatically configuring operating system parameters, comprising: acquiring monitoring data collected by a monitoring system at preset intervals, the monitoring data comprising system monitoring data corresponding to the operating system and program monitoring data corresponding to a target application; using a pre-trained prediction model and the program monitoring data, predicting a peak value of at least one performance parameter of the target application corresponding to the program monitoring data, and obtaining at least one set of prediction parameter values for the target application; based on at least one set of prediction parameter values for the target application and the system monitoring data of the operating system, adjusting system parameters of the operating system related to at least one set of prediction parameter values for the target application, and obtaining target system parameter configuration values.
[0007] Optionally, after acquiring the monitoring data collected by the monitoring system at the preset time interval, the method also includes: performing data cleaning on the monitoring data to remove abnormal values and missing values in the monitoring data to obtain first monitoring data; normalizing the first monitoring data to obtain second monitoring data with a uniform scale; performing feature extraction on the second monitoring data to obtain the system monitoring data corresponding to the operating system and the program monitoring data corresponding to the target application.
[0008] Optionally, the training method of the trained prediction model includes: obtaining the first historical program monitoring data of the target application collected by the monitoring system; preprocessing the first historical program monitoring data to obtain preprocessed program monitoring data; marking the preprocessed program monitoring data to obtain a first training data set; the first training data set includes a training set, a verification set and a test set; using the training set to iteratively train a pre-constructed prediction model to obtain a trained prediction model; the pre-constructed prediction model includes an input layer, a long short-term memory layer and an output layer; using the verification set to verify the trained prediction model, and adjusting the hyperparameter values of the trained prediction model based on the verification results to obtain a verified prediction model; using the test set to evaluate the performance of the verified prediction model, and iteratively processing the verified prediction model based on the evaluation results until the error between the output result of the verified prediction model and the target value of the test set is less than a preset threshold, thereby obtaining the trained prediction model.
[0009] Optionally, based on at least one set of predicted parameter values of the target application and the system monitoring data of the operating system, the system parameters of the operating system related to the at least one set of predicted parameter values of the target application are adjusted to obtain target system parameter configuration values, including: based on the acquired parameter value range corresponding to the at least one set of predicted parameter values of the target application, at least one peak parameter value is determined in the at least one set of predicted parameter values of the target application; based on the at least one peak parameter value and the system monitoring data of the operating system, at least one system parameter to be configured in the system parameters of the operating system is determined; and an API interface corresponding to the at least one system parameter to be configured is called, and the at least one system parameter to be configured is adjusted based on the at least one peak parameter value to obtain the target system parameter configuration value.
[0010] Optionally, after adjusting the system parameters of the operating system related to at least one set of prediction parameter values of the target application based on at least one set of prediction parameter values of the target application and the system monitoring data of the operating system to obtain the target system parameter configuration values, the method further includes: using the monitoring system to monitor the target application in real time to obtain second historical program monitoring data; preprocessing and marking the second historical program monitoring data, and adding the preprocessed and marked second historical program monitoring data to the first training data set to obtain a second training data set; using the second training data set to train the trained prediction model to obtain an updated prediction model; using the updated prediction model to predict the peak value of at least one performance parameter of the target application, and adjusting the relevant system parameters of the operating system based on the prediction results to obtain the target system parameter configuration values.
[0011] Optionally, the program monitoring data includes: the application's CPU utilization, the application's memory utilization, the number of threads, the response time, the throughput, the error rate, the number of concurrent connections, the cache hit rate and the database interaction frequency; the performance parameters of the target application include: the application's CPU utilization, the application's memory utilization, the number of threads, the response time, the throughput, the error rate, the number of concurrent connections, the cache hit rate and the database interaction frequency; the system monitoring data includes: system CPU utilization, system memory utilization, swap space utilization, disk I / O, network bandwidth utilization, the number of network connections, context switching rate, the number of processes and / or system load; the system parameters of the operating system include: CPU configuration parameters, memory configuration parameters, network bandwidth configuration parameters and process configuration parameters.
[0012] In a second aspect, the present application provides an operating system parameter automatic configuration device, comprising:
[0013] An acquisition module, used to acquire monitoring data collected by the monitoring system at preset intervals, wherein the monitoring data includes system monitoring data corresponding to the operating system and program monitoring data corresponding to the target application program;
[0014] A prediction module, configured to predict a peak value of at least one performance parameter of the target application corresponding to the program monitoring data by using a pre-trained prediction model and the program monitoring data, and obtain at least one set of predicted parameter values of the target application;
[0015] A configuration module is used to adjust the system parameters of the operating system related to at least one set of predicted parameter values of the target application based on at least one set of predicted parameter values of the target application and system monitoring data of the operating system to obtain target system parameter configuration values.
[0016] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any one of the methods described above.
[0017] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any one of the methods described above when executed by a processor.
[0018] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the steps of any one of the methods described above when executed by a processor.
[0019] According to the specific embodiments provided in this application, this application discloses the following technical effects:
[0020] The present application provides a method, apparatus, device, medium and product for automatically configuring operating system parameters. The method inputs program monitoring data obtained at interval prediction time into a pre-trained prediction model to obtain at least one set of prediction parameter values for a target application program; the system parameters of the operating system are adjusted by at least one set of prediction parameter values for the target application program, thereby solving the problems of unreasonable allocation and low allocation efficiency caused by relying on manually preset rules and preset thresholds for system resource allocation, achieving the purpose of automatically configuring system parameters according to the monitoring data of the target application program, and effectively improving the adaptability and accuracy of the system parameter configuration of the operating system. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0022] Figure 1 A flowchart of a method for automatically configuring operating system parameters provided by an embodiment of the present application;
[0023] Figure 2 A network structure diagram of a pre-built prediction model provided in an embodiment of the present application;
[0024] Figure 3 A flowchart of a method for automatically configuring operating system parameters provided by another embodiment of the present application;
[0025] Figure 4 A schematic diagram of functional modules of an operating system parameter automatic configuration device provided by an embodiment of the present application;
[0026] Figure 5 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION
[0027] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0028] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.
[0029] With the continuous development of computer technology, the functions of application software are becoming more and more abundant. Correspondingly, application software requires more and more system resources provided by the operating system to ensure the realization of all the functions of the application software. When the operating system provides system resources for application software, different application software has different requirements for the operating system, so it is necessary to configure the system parameters of the operating system accordingly. At present, when configuring system parameters, it mainly relies on manual preset rules and preset thresholds to allocate system resources. This system resource allocation method cannot adapt to the dynamic changes of system workload, resulting in poor self-adaptation of system parameter configuration.
[0030] To solve the above problems, an embodiment of the present application provides a method for automatically configuring operating system parameters, which can automatically configure system parameters and effectively improve the adaptability and accuracy of the system parameter configuration of the operating system.
[0031] In an exemplary embodiment, Figure 1 As shown, a method for automatically configuring operating system parameters is provided, which is executed by a computer device, and can be specifically executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In an embodiment of the present application, the method for automatically configuring operating system parameters can include the following steps S110 to S130. Among them:
[0032] Step S110, acquiring monitoring data collected by the monitoring system at preset time intervals.
[0033] In an example embodiment, the monitoring system is a technology or tool for monitoring and collecting performance data of application programs and operating systems. In this embodiment, the monitoring data collected by the monitoring system includes system monitoring data corresponding to the operating system and program monitoring data corresponding to the target application program.
[0034] Among them, program monitoring data includes: application CPU utilization, application memory utilization, number of threads, response time, throughput, error rate, number of concurrent connections, cache hit rate and / or database interaction frequency. System monitoring data includes: system CPU utilization, system memory utilization, swap space utilization, disk I / O, network bandwidth utilization, number of network connections, context switching rate, number of processes and / or system load.
[0035] Step S120, using the pre-trained prediction model and program monitoring data, predict the peak value of at least one performance parameter of the target application corresponding to the program monitoring data to obtain at least one set of prediction parameter values of the target application.
[0036] In an exemplary embodiment, the performance parameters of the target application include: CPU utilization of the application, memory usage of the application, number of threads, response time, throughput, error rate, number of concurrent connections, cache hit rate, and database interaction frequency.
[0037] It can be understood that, for example, the program monitoring data includes the CPU utilization of the application, the memory utilization of the application, and the database interaction frequency, then at least one performance parameter of the target application corresponding to the program monitoring data is the CPU utilization of the application, the memory utilization of the application, and the database interaction frequency, and the CPU utilization of the application, the memory utilization of the application, and the database interaction frequency are input into a pre-trained prediction model to obtain a set of three prediction parameter values corresponding to the CPU utilization of the program, the memory utilization of the application, and the database interaction frequency.
[0038] It should be noted that the performance parameters of the target application include many parameters. The administrator can select the main performance parameters from the performance parameters of the target application as the monitoring object of the monitoring system, and then use the monitored program monitoring data and the pre-trained prediction model to predict the peak value of the main performance parameters. For example, if the target application software needs to cache video, the main performance parameters can be the application's memory usage and cache hit rate from the performance parameters of the target application.
[0039] Furthermore, the training method of the trained prediction model in step S120 includes: obtaining the first historical program monitoring data of the target application collected by the monitoring system; preprocessing the first historical program monitoring data to obtain preprocessed program monitoring data; marking the preprocessed program monitoring data to obtain a first training data set; the first training data set includes a training set, a verification set and a test set; iteratively training the pre-constructed prediction model using the training set to obtain a trained prediction model; the pre-constructed prediction model includes an input layer, a long short-term memory layer and an output layer; verifying the trained prediction model using the verification set, and adjusting the hyperparameter values of the trained prediction model based on the verification results to obtain a verified prediction model; evaluating the performance of the verified prediction model using the test set, and iteratively processing the verified prediction model based on the evaluation results until the error between the output result of the verified prediction model and the target value of the test set is less than a preset threshold, thereby obtaining a trained prediction model.
[0040] In an exemplary embodiment, in combination with Figure 2 It can be understood that the pre-built prediction model is an LSTM (Long Short-Term Memory) model. The LSTM model includes an input layer, a long short-term memory layer and an output layer, wherein the long short-term memory layer includes a forgetting layer and a memory update layer; the number of units and the gating mechanism are set in the forgetting layer and the memory update layer; the parameters of the number of units and the gating mechanism are adjusted through the verification set.
[0041] By predicting the peak value of at least one set of performance parameters of the target application using a pre-trained prediction model, the configuration efficiency of the system parameters of the operating system can be effectively improved.
[0042] Step S130, based on at least one set of predicted parameter values of the target application and system monitoring data of the operating system, adjusting system parameters of the operating system related to at least one set of predicted parameter values of the target application to obtain target system parameter configuration values.
[0043] In an exemplary embodiment, the system parameters of the operating system include: CPU configuration parameters, memory configuration parameters, network bandwidth configuration parameters, and process configuration parameters.
[0044] As can be understood in combination with the above embodiments, for example, the program monitoring data includes the CPU utilization of the application, the memory utilization of the application, and the database interaction frequency, then the system parameters of the operating system related to the program monitoring data including the CPU utilization of the application, the memory utilization of the application, and the database interaction frequency may include CPU configuration parameters, memory configuration parameters, and network bandwidth configuration parameters.
[0045] In a specific embodiment, the above step S130 may include the following steps S1301 to S1304, specifically:
[0046] Step S1301: determining at least one peak parameter value in at least one set of predicted parameter values of the target application based on the acquired parameter value range corresponding to at least one set of predicted parameter values of the target application.
[0047] Step S1302: determining at least one system parameter to be configured from system parameters of the operating system based on at least one peak parameter value and system monitoring data of the operating system.
[0048] Step S1303: calling an API interface corresponding to at least one system parameter to be configured, and adjusting at least one system parameter to be configured based on at least one peak parameter value to obtain a target system parameter configuration value.
[0049] It can be understood that, for example, the target application software needs to configure more system memory for caching videos, then the memory usage rate and cache hit rate of the application in the performance parameters of the corresponding target application are obtained; the value range corresponding to the memory usage rate and cache hit rate of the application is obtained, and it is determined whether the predicted values of the memory usage rate and cache hit rate of the corresponding application output by the trained prediction model exceed the preset threshold value; if the memory usage rate and cache hit rate of the application both exceed the preset threshold value, then the two predicted values are both peak parameter values; according to the two peak parameter values, the corresponding API interfaces are called to adjust the memory configuration parameters and network bandwidth configuration parameters of the operating system respectively, and the parameter configuration values of the memory configuration parameters and the parameter configuration values of the network bandwidth configuration are obtained.
[0050] It should be noted that, since the configuration of each target application is different, the value range corresponding to the performance parameter of the target application is different, and thus the preset threshold setting is different, which is not specifically limited in the embodiment of the present application.
[0051] In another exemplary embodiment of the present application, in order to improve the efficiency of system parameter configuration, ensure the quality and applicability of data, and facilitate the pre-trained prediction model to predict the peak value of at least one performance parameter of the target application, after the above step S110, the above method may also include: performing data cleaning on the monitoring data to remove outliers and missing values in the monitoring data to obtain first monitoring data; normalizing the first monitoring data to obtain second monitoring data with a uniform scale; performing feature extraction on the second monitoring data to obtain system monitoring data corresponding to the operating system and program monitoring data corresponding to the target application.
[0052] In another exemplary embodiment of the present application, in order to further improve the prediction accuracy of the peak value of at least one performance parameter of the target application, and thus further improve the accuracy of system parameter configuration, the above method may also include: using the monitoring system to monitor the target application in real time to obtain second historical program monitoring data; preprocessing and marking the second historical program monitoring data, and adding the preprocessed and marked second historical program monitoring data to the first training data set to obtain a second training data set; using the second training data set to train the trained prediction model to obtain an updated prediction model; using the updated prediction model to predict the peak value of at least one performance parameter of the target application, and adjusting relevant system parameters of the operating system based on the prediction results to obtain the target system parameter configuration value.
[0053] It can be understood from the above embodiments that Figure 2 As shown, S1: obtain the second historical program monitoring data collected by the monitoring system; then execute S2, that is, determine whether the second historical program monitoring data is clear. If the second historical program monitoring data is not clear, execute step S21, that is, preprocess the second historical program monitoring data, and execute step S3 after the preprocessing is completed; if the second historical program monitoring data is clear, there is no need to preprocess it and directly execute S3, that is, add the second historical program monitoring data to the second training data set, use the second training data set to train the LSTM model, and after the training is completed, predict the peak value of at least one performance parameter of the target application and output the prediction result; then execute S4, that is, call the API interface according to the prediction result; then execute step S5, that is, use the API interface to modify the configuration of relevant system parameters of the operating system; after the system parameter configuration is completed, execute step S6, and use the monitoring system to monitor the operating system and the target application in real time. Such a cycle can effectively improve the adaptability and accuracy of the system parameter configuration of the operating system.
[0054] Implement the above-mentioned steps S110 to S130, input the program monitoring data obtained at the interval prediction time into a pre-trained prediction model to obtain at least one set of prediction parameter values for the target application; adjust the system parameters of the operating system through at least one set of prediction parameter values for the target application, thereby solving the problems of unreasonable allocation and low allocation efficiency caused by relying on manually preset rules and preset thresholds for system resource allocation, and achieving the purpose of automatically configuring system parameters according to the monitoring data of the target application, effectively improving the adaptability and accuracy of the system parameter configuration of the operating system.
[0055] And the embodiments of the present application can ensure the data quality and the adaptability of the program monitoring data to a pre-trained prediction model by performing data preprocessing on the monitoring data, so that the pre-trained prediction model can predict the peak value of at least one performance parameter of the target application.
[0056] And the embodiment of the present application monitors the target application in real time, collects second historical program monitoring data, and obtains a second training data set by adding the second historical program monitoring data to the first training data set; and re-trains the pre-trained prediction model with the second training data set, which can effectively improve the accuracy of the prediction, thereby further improving the accuracy of the system parameter configuration.
[0057] Based on the same inventive concept, the embodiment of the present application also provides an operating system parameter automatic configuration device for implementing the operating system parameter automatic configuration method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more operating system parameter automatic configuration device embodiments provided below can refer to the limitations of the operating system parameter automatic configuration method above, and will not be repeated here.
[0058] In an exemplary embodiment, Figure 4 As shown, an operating system parameter automatic configuration device is provided, and the operating system parameter automatic configuration device 400 includes: an acquisition module 410, a prediction module 420 and a configuration module 430, wherein:
[0059] The acquisition module 410 is used to acquire monitoring data collected by the monitoring system at preset intervals, the monitoring data including system monitoring data corresponding to the operating system and program monitoring data corresponding to the target application program;
[0060] The prediction module 420 is used to predict the peak value of at least one performance parameter of the target application corresponding to the program monitoring data by using the pre-trained prediction model and the program monitoring data, and obtain at least one set of predicted parameter values of the target application;
[0061] The configuration module 430 is used to adjust the system parameters of the operating system related to at least one set of predicted parameter values of the target application based on at least one set of predicted parameter values of the target application and the system monitoring data of the operating system to obtain the target system parameter configuration values.
[0062] As an optional implementation, the operating system parameter automatic configuration device 400 also includes a data preprocessing module, which is used to perform data cleaning on the monitoring data to remove abnormal values and missing values in the monitoring data to obtain first monitoring data; normalize the first monitoring data to obtain second monitoring data with a uniform scale; perform feature extraction on the second monitoring data to obtain system monitoring data corresponding to the operating system and program monitoring data corresponding to the target application.
[0063] As an optional implementation, the operating system parameter automatic configuration device 400 is also used to obtain the first historical program monitoring data of the target application program collected by the monitoring system; preprocess the first historical program monitoring data to obtain preprocessed program monitoring data; mark the preprocessed program monitoring data to obtain a first training data set; the first training data set includes a training set, a verification set and a test set; iteratively train a pre-built prediction model using the training set to obtain a trained prediction model; the pre-built prediction model includes an input layer, a long short-term memory layer and an output layer; verify the trained prediction model using the verification set, and adjust the hyperparameter values of the trained prediction model based on the verification results to obtain a verified prediction model; evaluate the performance of the verified prediction model using the test set, and iteratively process the verified prediction model based on the evaluation results until the error between the output result of the verified prediction model and the target value of the test set is less than a preset threshold, thereby obtaining a trained prediction model.
[0064] As an optional implementation, the above-mentioned configuration module 430 is also used to determine at least one peak parameter value in at least one set of predicted parameter values of the target application based on the parameter value range corresponding to at least one set of predicted parameter values of the target application; determine at least one system parameter to be configured in the system parameters of the operating system based on at least one peak parameter value and system monitoring data of the operating system; call the API interface corresponding to at least one system parameter to be configured, and adjust at least one system parameter to be configured based on at least one peak parameter value to obtain the target system parameter configuration value.
[0065] As an optional implementation, the operating system parameter automatic configuration device 400 is also used to use the monitoring system to monitor the target application in real time to obtain second historical program monitoring data; preprocess and mark the second historical program monitoring data, and add the preprocessed and marked second historical program monitoring data to the first training data set to obtain a second training data set; use the second training data set to train the trained prediction model to obtain an updated prediction model; use the updated prediction model to predict the peak value of at least one performance parameter of the target application, and adjust the relevant system parameters of the operating system based on the prediction results to obtain the target system parameter configuration value.
[0066] As an optional implementation, the above-mentioned program monitoring data includes: the application's CPU utilization, the application's memory utilization, the number of threads, the response time, the throughput, the error rate, the number of concurrent connections, the cache hit rate and / or the database interaction frequency; the performance parameters of the target application include: the application's CPU utilization, the application's memory utilization, the number of threads, the response time, the throughput, the error rate, the number of concurrent connections, the cache hit rate and the database interaction frequency; the system monitoring data includes: the system CPU utilization, the system memory utilization, the swap space utilization, the disk I / O, the network bandwidth utilization, the number of network connections, the context switching rate, the number of processes and / or the system load; the system parameters of the operating system include: the CPU configuration parameters, the memory configuration parameters, the network bandwidth configuration parameters and the process configuration parameters.
[0067] Among them, this implementation method is implemented by inputting the program monitoring data obtained at the interval prediction time into a pre-trained prediction model to obtain at least one set of prediction parameter values of the target application; the system parameters of the operating system are adjusted by at least one set of prediction parameter values of the target application, which solves the problems of unreasonable allocation and low allocation efficiency caused by relying on manually preset rules and preset thresholds for system resource allocation, and achieves the purpose of automatically configuring system parameters according to the monitoring data of the target application, effectively improving the adaptability and accuracy of the system parameter configuration of the operating system.
[0068] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 5As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store video tag processing data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for automatically configuring operating system parameters is implemented.
[0069] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0070] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.
[0071] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0072] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0073] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0074] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
[0075] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.
[0076] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0077] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.
Claims
1. A method for automatically configuring operating system parameters, characterized in that: The automatic configuration of operating system parameters includes: Acquiring monitoring data collected by the monitoring system at preset intervals, the monitoring data including system monitoring data corresponding to the operating system and program monitoring data corresponding to the target application program; Using a pre-trained prediction model and the program monitoring data, predicting a peak value of at least one performance parameter of the target application corresponding to the program monitoring data, to obtain at least one set of prediction parameter values of the target application; Based on at least one set of predicted parameter values of the target application and system monitoring data of the operating system, system parameters of the operating system related to at least one set of predicted parameter values of the target application are adjusted to obtain target system parameter configuration values.
2. The method for automatically configuring operating system parameters according to claim 1, characterized in that: After acquiring the monitoring data collected by the monitoring system at the preset time interval, the method further includes: Performing data cleaning on the monitoring data to remove abnormal values and missing values in the monitoring data to obtain first monitoring data; Normalizing the first monitoring data to obtain second monitoring data with a unified scale; Feature extraction is performed on the second monitoring data to obtain the system monitoring data corresponding to the operating system and the program monitoring data corresponding to the target application program.
3. The method for automatically configuring operating system parameters according to claim 1, characterized in that: The training method of the trained prediction model includes: Acquire first historical program monitoring data of the target application program collected by the monitoring system; Preprocessing the first historical program monitoring data to obtain preprocessed program monitoring data; The preprocessing program monitoring data is labeled to obtain a first training data set; the first training data set includes a training set, a validation set and a test set; Iteratively training a pre-built prediction model using the training set to obtain a trained prediction model; the pre-built prediction model includes an input layer, a long short-term memory layer, and an output layer; Using the validation set to validate the trained prediction model, and adjusting the hyperparameter values of the trained prediction model based on the validation result to obtain a validated prediction model; The performance of the verified prediction model is evaluated using the test set, and the verified prediction model is iteratively processed based on the evaluation result until the error between the output result of the verified prediction model and the target value of the test set is less than a preset threshold, thereby obtaining the trained prediction model.
4. The method for automatically configuring operating system parameters according to claim 1, characterized in that: The adjusting, based on the at least one set of predicted parameter values of the target application and the system monitoring data of the operating system, the system parameters of the operating system related to the at least one set of predicted parameter values of the target application to obtain the target system parameter configuration values comprises: Determining at least one peak parameter value in the at least one set of predicted parameter values of the target application based on the acquired parameter value range corresponding to the at least one set of predicted parameter values of the target application; determining at least one system parameter to be configured among the system parameters of the operating system based on the at least one peak parameter value and the system monitoring data of the operating system; An API interface corresponding to the at least one system parameter to be configured is called, and the at least one system parameter to be configured is adjusted based on the at least one peak parameter value to obtain the target system parameter configuration value.
5. The method for automatically configuring operating system parameters according to claim 4, characterized in that: After adjusting the system parameters of the operating system related to the at least one set of predicted parameter values of the target application based on the at least one set of predicted parameter values of the target application and the system monitoring data of the operating system to obtain the target system parameter configuration values, the method further includes: Using the monitoring system to monitor the target application in real time to obtain second historical program monitoring data; Preprocessing and marking the second historical program monitoring data, and adding the preprocessed and marked second historical program monitoring data to the first training data set to obtain a second training data set; Using the second training data set to train the trained prediction model to obtain an updated prediction model; The updated prediction model is used to predict the peak value of at least one performance parameter of the target application program, and the relevant system parameters of the operating system are adjusted based on the prediction result to obtain the target system parameter configuration value.
6. The method for automatically configuring operating system parameters according to any one of claims 1 to 5, characterized in that: The program monitoring data includes: application CPU utilization, application memory usage, number of threads, response time, throughput, error rate, number of concurrent connections, cache hit rate and / or database interaction frequency; The performance parameters of the target application include: CPU utilization of the application, memory usage of the application, number of threads, response time, throughput, error rate, number of concurrent connections, cache hit rate, and database interaction frequency; The system monitoring data includes: system CPU utilization, system memory utilization, swap space utilization, disk I / O, network bandwidth utilization, number of network connections, context switching rate, number of processes and / or system load; The system parameters of the operating system include: CPU configuration parameters, memory configuration parameters, network bandwidth configuration parameters and process configuration parameters.
7. An automatic configuration device for operating system parameters, characterized in that: The operating system parameter automatic configuration device comprises: An acquisition module, used to acquire monitoring data collected by the monitoring system at preset intervals, wherein the monitoring data includes system monitoring data corresponding to the operating system and program monitoring data corresponding to the target application program; A prediction module, configured to predict a peak value of at least one performance parameter of the target application corresponding to the program monitoring data by using a pre-trained prediction model and the program monitoring data, and obtain at least one set of predicted parameter values of the target application; A configuration module is used to adjust the system parameters of the operating system related to at least one set of predicted parameter values of the target application based on at least one set of predicted parameter values of the target application and system monitoring data of the operating system to obtain target system parameter configuration values.
8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for automatically configuring operating system parameters according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for automatically configuring operating system parameters described in any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for automatically configuring operating system parameters described in any one of claims 1 to 6 are implemented.