Server resource utilization assessment methods and systems

Abstract

This application discloses a server resource utilization assessment method and system, relating to the field of computer technology. The method includes acquiring resource utilization data, comprehensively assessing the overall resource usage of the server, dynamically adjusting the weight of each resource, and determining the server resource utilization status. This solves the technical problem of limitations in resource assessment methods in related technologies and achieves the technical effect of accurately reflecting the server resource utilization status.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method and system for evaluating server resource utilization. Background Technology

[0002] The core objective of server resource testing technology is to continuously monitor and accurately evaluate the usage of server resources, aiming to ensure efficient resource allocation and utilization to meet business operational needs. Faced with increasingly complex business scenarios and diverse workloads, how to leverage technology to improve the intelligence level of resource testing while ensuring the security of the testing process is one of the key issues that urgently needs to be addressed.

[0003] Traditional server resource testing methods typically rely on fixed weights to assess resource usage. These weights are applied to resource utilization calculations across multiple dimensions, such as the Central Processing Unit (CPU), memory, disk input / output (Disk I / O), and network bandwidth. However, this fixed-weight assessment mechanism ignores the significant differences in resource requirements among different types of tasks, leading to distorted resource load assessments. Furthermore, traditional techniques depend on periodic data collection and analysis, lacking real-time monitoring and rapid response mechanisms. Especially when facing high concurrency traffic or sudden loads, the latency of data collection often delays resource allocation decisions, directly impacting service quality and user experience.

[0004] While existing resource demand forecasting algorithms can provide some predictions of future resource needs, their limitations lie in model complexity and parameter settings. Complex model structures may introduce overfitting risks, while inappropriate parameter settings often lead to decreased prediction accuracy. Therefore, in cloud environments and microservice architectures, the volatility and uncertainty of resource demand place higher demands on forecasting algorithms. How to accurately predict resource demand and avoid potential resource bottlenecks or overcapacity has become another major challenge for resource testing technology. Summary of the Invention

[0005] This application provides a method and system for evaluating server resource utilization, in order to at least address the technical problem that resource evaluation methods in related technologies have limitations.

[0006] This application provides a server resource utilization assessment method, comprising: acquiring resource utilization data of the server during operation; generating a task type identifier based on the task characteristics of the tasks carried by the server; determining a target weighting coefficient set matching the task type identifier; multiplying the target weighting coefficient set with the corresponding resource utilization data to determine a resource weighting value set; and weighting and summing the normalized resource utilization data with the corresponding resource weighting values ​​in the resource weighting value set to determine a target resource utilization score, wherein the target resource utilization score is used to characterize the target resource utilization status of the server.

[0007] This application also provides a server resource utilization assessment device, comprising: an acquisition module for acquiring resource utilization data during server operation; a generation module for generating a task type identifier based on the task characteristics of the tasks carried by the server; a first determination module for determining a target weighted coefficient set matching the task type identifier; a second determination module for multiplying the target weighted coefficient set with the corresponding resource utilization data to determine a resource weighted value set; and a third determination module for weighted summing the normalized resource utilization data with the corresponding resource weighted values ​​in the resource weighted value set to determine a target resource utilization score, wherein the target resource utilization score is used to characterize the target resource utilization status of the server.

[0008] This application also provides an electronic device, including: a memory for storing a computer program; and a processor for implementing the steps of any of the above-described server resource utilization assessment methods when executing the computer program.

[0009] This application also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the steps of any of the above-described server resource utilization assessment methods.

[0010] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above-described server resource utilization assessment methods.

[0011] This application, by acquiring resource utilization data, comprehensively assesses the overall resource usage of the server, dynamically adjusts the weight of each resource, and determines the server resource utilization status, solves the technical problem of the limitations of resource assessment methods in related technologies, and achieves the technical effect of accurately reflecting the server resource utilization status. Attached Figure Description

[0012] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a hardware structure block diagram of a computer terminal for a server resource utilization evaluation method according to an embodiment of the present invention.

[0014] Figure 2 This is a flowchart illustrating a server resource utilization evaluation method according to an embodiment of the present invention;

[0015] Figure 3 This is a system schematic diagram of a server resource utilization evaluation method according to an embodiment of the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0017] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. The terms "first," "second," etc., in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0018] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] The specific application environment architecture or specific hardware architecture on which the execution of the server resource utilization assessment method depends is described here.

[0020] The methods and embodiments provided in this application can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a computer terminal as an example, Figure 1 This is a hardware structure block diagram of a computer terminal for a server resource utilization evaluation method according to an embodiment of the present invention. Figure 1As shown, a computer terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The computer terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the computer terminal described above. For example, the computer terminal may also include components that are more complex than those described above. Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0021] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the server resource utilization assessment method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0022] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider for the computer terminal. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0023] The embodiments of this application provide a method for evaluating server resource utilization. Figure 2 This is a flowchart illustrating a server resource utilization assessment method according to an embodiment of the present invention, as shown below. Figure 2 As shown.

[0024] Step S202: Obtain resource utilization data during server operation.

[0025] For example, existing technologies often focus only on a single resource metric (such as memory or CPU), while this embodiment can collect multi-dimensional resource utilization data to comprehensively evaluate the overall resource utilization status of the server, avoiding scheduling imbalances caused by ignoring certain key resource dimensions.

[0026] In one exemplary embodiment, resource utilization data includes at least one of the following: CPU utilization, memory usage, disk I / O throughput, and network bandwidth usage.

[0027] For example, CPU time slice allocation information can be read through the operating system kernel interface to calculate CPU utilization; total physical memory and free memory information can be obtained from system files to calculate memory usage; disk I / O data can be obtained from files to calculate disk I / O throughput per unit time; and the number of bytes sent and received by each network interface can be obtained from files to calculate average network bandwidth usage per unit time.

[0028] It's worth noting that resource utilization data can be acquired periodically, and the sampling period can be flexibly adjusted according to the server's instantaneous load, achieving intelligent adaptive data collection frequency. When the load surges to a high level, it can sensitively accelerate the data capture rate to ensure that subtle changes in resource status are captured. Conversely, when the load drops to a low level, the collection frequency is reduced to avoid unnecessary resource waste. In this way, it can maintain the comprehensiveness and accuracy of the data while significantly reducing the resource load, achieving the dual goals of improving overall operating efficiency and performance, ensuring that the server operates smoothly like flowing water.

[0029] For example, the set of resource-weighted values ​​for resource utilization data can be determined based on the task characteristics of the tasks carried by the server.

[0030] For example, when assessing server resource utilization, the characteristics of the tasks the server is undertaking can be analyzed, and different weights can be assigned to different resource dimensions (such as CPU, memory, disk I / O, and network bandwidth) based on these characteristics. This is done to more accurately reflect the actual demand on server resources from the current task combination, as different types of business tasks may require certain resources far more than others. By dynamically adjusting the weighting values ​​of resource utilization data, a more realistic resource utilization score can be generated, leading to more reasonable and effective resource scheduling decisions, improving resource utilization, and optimizing server performance.

[0031] In one exemplary embodiment, the task features include at least one of the following: the request type of the task carried by the server, the number of concurrent accesses, and the resource call mode.

[0032] For example, request type refers to the different kinds of requests received by the server. In a web server environment, requests might include HTTP requests, database query requests, computational task requests, etc. Concurrent access count indicates the number of requests the server processes simultaneously. High concurrency usually means the server needs to handle a large number of simultaneous connections, which significantly increases CPU and memory load, especially when handling I / O-intensive tasks. Resource allocation pattern: refers to the pattern and order of resource usage during task execution. For example, some tasks may consume a large amount of memory resources in a short period while using less CPU resources; other tasks may frequently perform disk read / write operations.

[0033] Step S204: Generate a task type identifier based on the task characteristics.

[0034] Step S206: Determine the set of target weighted coefficients that match the task type identifier.

[0035] Step S208: Multiply the target weighted coefficient set with the corresponding resource utilization data to determine the resource weighted value set.

[0036] For example, based on the characteristics of tasks running on the current server, including request type, concurrent access volume, and resource call behavior patterns, a pre-built task classification model can be used to identify task types and generate task type identifiers. Subsequently, these identifiers are parsed using preset task classification rules to determine the task's type. These task classification rules can be based on a comprehensive consideration of request type, concurrent access volume, and resource call behavior patterns, effectively distinguishing task types.

[0037] For example, the pre-built task classification model can be a classifier trained based on supervised learning, selected from any one or a combination of decision trees, support vector machines, random forests, lightweight neural networks, or rule engines. By introducing contextual information such as request type, number of concurrent accesses, and resource call patterns, the accuracy of task classification is improved, providing basic support for subsequent differentiated resource evaluation and enhancing the targeting and effectiveness of resource scheduling strategies.

[0038] For example, the integration of a task type recognition mechanism significantly enhances the intelligence of resource assessment. Leveraging a task classification model trained through supervised learning, task type identifiers can be generated based on the specific nature of the request, the frequency of concurrent access, and the resource call patterns. This advanced feature overcomes the limitations of the traditional "one-size-fits-all" resource assessment system, enabling resource scheduling to more accurately match business needs and demonstrating stronger scenario adaptability and targeted decision-making.

[0039] For example, the initial set of weighting coefficients corresponding to the task type is determined from a preset weighting configuration table. ,in, To represent the resource dimension, then It can be .in, This represents the initial weighting coefficients for the CPU dimension. This represents the initial weighting coefficients for the memory dimension. This represents the initial weighting coefficients for the disk I / O dimension, and This represents the initial weighting coefficient for the network bandwidth dimension.

[0040] Function to obtain task type impact factor The function returns the corresponding impact coefficient based on the task type, where... This is the task type identifier.

[0041] Through regulating factors The influence coefficient is scaled to obtain the correction factor. ,in, Indicates resource dimension, This is a configurable parameter used to control the intensity of the impact of task type on weight adjustment.

[0042] Add the initial weighting coefficients of each dimension to the correction factor to obtain the target weighting coefficient set. , It can be Its calculation formula can be:

[0043] .

[0044] The target weighted coefficient set and the corresponding resource utilization data Multiplying them together yields a set of resource-weighted values. .

[0045] For example, based on the task type, an initial set of weighted coefficients is selected from a pre-defined list of weight configurations. Subsequently, by integrating the task type influence factor function with configurable adjustment factors, these initial coefficients are adjusted in real time to determine a set of resource weighting values ​​for various tasks.

[0046] For example, the resource weighted value set is dynamically generated based on the task type, avoiding the problem of inconsistent responses to different types of tasks under the traditional fixed weight evaluation method. By introducing the influence factor function and adjustment factor, the weight of resources in each dimension can be flexibly adjusted according to the task characteristics, which significantly improves the accuracy and adaptability of resource utilization evaluation, thereby enhancing the scientific nature of resource scheduling decisions.

[0047] For example, the target resource utilization status of a server can be determined based on resource utilization data and a set of resource weighted values.

[0048] For example, resource utilization data and a set of resource weighted values ​​can be used to determine the utilization status of target resources, which can reflect the overall utilization rate of server resources and whether they are in a healthy and efficient working state.

[0049] Step S210: The normalized resource utilization data is summed with the corresponding resource weighted values ​​in the resource weighted value set to determine the target resource utilization score, wherein the target resource utilization score is used to characterize the target resource utilization status of the server.

[0050] For example, resource utilization data Normalization is performed to ensure that the data in each dimension falls within the specified interval. Within, normalized resource utilization data are obtained. ,in, , and The first The historical minimum and maximum values ​​of the resource.

[0051] The target resource utilization score is obtained by calculating the normalized resource utilization data and the corresponding weighting coefficients using a weighted summation method. Its calculation formula can be:

[0052] ,

[0053] in, Indicates the first The server resource utilization score at any given time. , , , These are the normalized CPU, memory, disk I / O, and network bandwidth utilization rates, respectively. , , , These are the adjusted weighting coefficients for each dimension. This represents the overall resource score at the current moment, used to reflect the overall resource load level of the server.

[0054] For example, normalization unifies resource indicators of different dimensions into the same range, solving the problem of evaluation bias caused by differences in units. Combined with dynamically adjusted weighting coefficients, the generated server resource utilization score can comprehensively reflect the overall load level of the server, which facilitates the determination of the server resource utilization score at the next moment and improves the comparability and practicality of the evaluation results.

[0055] In one exemplary embodiment, the method further includes:

[0056] The resource utilization score for the next moment is determined based on the historical resource utilization score and the target resource utilization score. The historical resource utilization score is used to characterize the historical resource utilization status, and the resource utilization score for the next moment is used to characterize the resource utilization status for the next moment.

[0057] Determine the deviation between the resource utilization score at the next time step and the target resource utilization score;

[0058] Server resources are allocated based on the deviation.

[0059] For example, historical server resource utilization scores can be a sequence of historical server resource utilization scores, such as... ,in, Indicates the first The server resource utilization score at a given moment. An exponential smoothing prediction algorithm can be used to construct a predictive model for resource utilization trends. This model can determine the server resource utilization score for the next moment based on historical and target resource utilization scores, determine the deviation between the next moment's server resource utilization score and the target resource utilization score, thereby measuring the difference between actual and expected resource utilization, and allocating server resources based on this difference.

[0060] For example, maintaining a historical server resource utilization scoring sequence and target resource utilization score Set the exponential smoothing factor Its value range is 0 < ≤1 is used to control the degree of influence of historical data on the resource utilization score in the next moment.

[0061] Initialize the first server resource utilization score .

[0062] An exponentially weighted moving average algorithm is used to recursively calculate historical server resource utilization scores to predict the resource utilization score for the next time step. Its calculation formula can be:

[0063] .

[0064] in, To use historical server resource utilization scoring sequences The predicted server resource utilization score at time t. This is a score for the server resource utilization at the next predicted moment.

[0065] For example, the exponential smoothing prediction algorithm can quickly establish a resource utilization trend model without complex modeling by recursively calculating the comprehensive score of historical resources. This method has a fast response speed and low computational cost, and is particularly suitable for short-term prediction in scenarios of dynamic changes in server resources. It helps to identify potential resource bottlenecks in advance and provides a basis for forward-looking decision-making.

[0066] In one exemplary embodiment, allocating server resources based on the deviation degree includes:

[0067] In response to the deviation exceeding the preset value range, an abnormal alarm signal is generated;

[0068] Server resources are allocated based on abnormal alarm signals.

[0069] For example, determining the target resource utilization score. Server resource utilization score at the next moment absolute deviation between The calculation formula is as follows:

[0070] .

[0071] Obtain the preset fluctuation threshold (i.e., the preset numerical range). This threshold is derived by analyzing the standard deviation of resource scores in the server's historical operational data, and the expression is:

[0072] .

[0073] in, The standard deviation of the historical resource comprehensive score. This is an empirical coefficient.

[0074] Deviation value With preset numerical range Compare, if satisfied > If the current resource utilization status exceeds the normal fluctuation range, an abnormal alarm signal can be generated; otherwise, the resource utilization status is determined to be within the normal fluctuation range.

[0075] For example, a lightweight trend prediction model and a highly responsive anomaly detection mechanism were constructed. Using an exponential smoothing algorithm, a recursive calculation was performed on historical resource comprehensive score sequences to determine resource utilization trends. Simultaneously, a dynamic threshold setting based on the standard deviation of resource scores was introduced to improve the accuracy and responsiveness of anomaly detection.

[0076] It should be noted that the preset fluctuation threshold (i.e., the preset numerical range) is used. It can be set based on historical standard deviation, which can dynamically adapt to changes in the server operating environment. This avoids the risk of misjudgment caused by fixed thresholds due to environmental differences. By comparing the current score with the trend prediction results, it achieves high sensitivity detection of abnormal fluctuations, ensuring timely response when resources are overloaded or utilization drops sharply, and guaranteeing service stability and availability.

[0077] In one exemplary embodiment, the anomaly alarm signal may include at least one of the following information fields: current timestamp Deviation value Target resource utilization score The server resource utilization score at the next moment .

[0078] In one exemplary embodiment, allocating server resources based on deviation includes at least one of the following: increasing the number of container replicas, switching service nodes, increasing specific resource quotas, and activating a rate limiting mechanism.

[0079] In an exemplary embodiment, after allocating server resources according to the deviation, the method may further include: updating the training sample library of the task classification model and retraining the task classification model periodically at predetermined time intervals to improve the task recognition accuracy.

[0080] For example, the task type identifier, resource utilization data, scheduling response action, and scheduling effect feedback information corresponding to this resource allocation adjustment operation are recorded. The scheduling response action can be an action such as increasing the pressure on the hard disk or the network, and the scheduling effect feedback information can be the time feedback result after performing actions such as increasing the pressure on the hard disk or the network.

[0081] The above information is added as new samples to the training sample library of the task classification model. Each sample can be in the following format:

[0082] .

[0083] in, This is a task type identifier. For resource utilization data, To schedule response actions, This provides feedback on the scheduling effect.

[0084] Preset retraining cycle Every The time-based machine learning training module retrains the task classification model. During the training process, supervised learning algorithms are used to optimize the model parameters, enabling the model to more accurately identify the resource requirement characteristics of different task types. After retraining, the model is updated and deployed to the task classification model version to improve the accuracy of subsequent resource assessment.

[0085] For example, a closed-loop feedback and continuous optimization mechanism ensures the continuous optimization and evolution of resource management. Every scheduling action and its resulting feedback are recorded, building a scheduling case knowledge base. Through a periodic task classification model retraining process, past experience is learned to improve the model's recognition accuracy and the quality of scheduling decisions. This self-learning and improving closed-loop mechanism effectively fills the gap in the self-evolution capabilities of traditional technologies, maintaining high efficiency and intelligence in resource management over a long period.

[0086] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0087] Embodiments of this application also provide a server resource utilization assessment system. Figure 3 This is a system schematic diagram of a server resource utilization evaluation method according to an embodiment of the present invention, such as... Figure 3 As shown, the system 300 includes:

[0088] Module 302 is used to acquire resource utilization data during server operation;

[0089] Generation module 304 is used to generate a task type identifier based on the task characteristics carried by the server;

[0090] The first determining module 306 is used to determine the set of target weighting coefficients that match the task type identifier;

[0091] The second determining module 308 is used to multiply the target weighted coefficient set with the corresponding resource utilization data to determine the resource weighted value set;

[0092] The third determining module 310 is used to sum the normalized resource utilization data with the corresponding resource weighting values ​​in the resource weighting value set to determine the target resource utilization score, wherein the target resource utilization score is used to characterize the target resource utilization status of the server.

[0093] In an exemplary embodiment, the first determining module 306 is further configured to determine, from a preset weighting configuration table, an initial set of weighting coefficients corresponding to the task type. ,in, Represents resource dimensions; influence factor function based on task type. Determine the impact coefficient corresponding to the task type, where, As a task type identifier; through preset adjustment factors Scaling the impact factor to determine the correction factor The formula for calculating the correction factor is as follows: ; set the initial weighting coefficients Add to the correction factor to determine the target set of weighted coefficients. The formula for calculating the target weighted coefficient set is as follows: .

[0094] In one exemplary embodiment, the system further includes:

[0095] The fourth determination module is used to determine the resource utilization score for the next moment based on the historical resource utilization score and the target resource utilization score. The historical resource utilization score is used to characterize the historical resource utilization status, and the resource utilization score for the next moment is used to characterize the resource utilization status for the next moment.

[0096] The fifth determining module is used to determine the deviation between the resource utilization score at the next time step and the target resource utilization score. The formula for calculating the deviation is: , Score the utilization of the target resources. Score the resource utilization for the next moment;

[0097] The allocation module is used to allocate server resources based on the deviation.

[0098] In an exemplary embodiment, the allocation module is further configured to generate an abnormal alarm signal in response to the deviation exceeding a preset numerical range; and allocate server resources according to the abnormal alarm signal.

[0099] For a description of the features in the embodiment corresponding to the server resource utilization assessment system, please refer to the relevant description of the embodiment corresponding to the server resource utilization assessment method, which will not be repeated here.

[0100] Embodiments of this application also provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any of the above-described server resource utilization assessment method embodiments.

[0101] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above-described server resource utilization assessment method embodiments when it is run.

[0102] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0103] Embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above-described server resource utilization assessment method embodiments.

[0104] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in any of the above-described server resource utilization evaluation method embodiments.

[0105] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0106] The above provides a detailed description of a server resource utilization evaluation method and system provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are merely for the purpose of helping to understand the method and its core ideas. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A method for evaluating server resource utilization, characterized in that, include: Obtain resource utilization data during server operation; Generate a task type identifier based on the task characteristics of the tasks carried by the server; Determine the target weighted coefficient set that matches the task type identifier; The target weighted coefficient set is multiplied by the corresponding resource utilization data to determine the resource weighted value set; The normalized resource utilization data is summed with the corresponding resource weighted values ​​in the resource weighted value set to determine the target resource utilization score, wherein the target resource utilization score is used to characterize the target resource utilization status of the server.

2. The method according to claim 1, characterized in that, Determining the target set of weighted coefficients that match the task type identifier includes: Determine the initial set of weighting coefficients corresponding to the task type from the preset weighting configuration table. ,in, Indicates resource dimensions; Impact factor function based on task type Determine the influence coefficient corresponding to the task type, where, For task type identifier; By preset adjustment factor Scaling the influence coefficients to determine the correction factor The formula for calculating the correction factor is as follows: ; The initial weighting coefficient set Add to the correction factor to determine the target set of weighted coefficients. The formula for calculating the target weighted coefficient set is as follows: .

3. The method according to claim 1, characterized in that, The method further includes: The resource utilization score for the next moment is determined based on the historical resource utilization score and the target resource utilization score, wherein the historical resource utilization score is used to characterize the historical resource utilization status, and the resource utilization score for the next moment is used to characterize the resource utilization status for the next moment. Determine the deviation between the next time-instance resource utilization score and the target resource utilization score. The formula for calculating the deviation is as follows: , Score the utilization of the target resource. Score the resource utilization for the next time step; Server resources are allocated based on the deviation.

4. The method according to claim 3, characterized in that, Allocating server resources based on the deviation includes: In response to the deviation exceeding a preset value range, an abnormal alarm signal is generated; Server resources are allocated based on the aforementioned abnormal alarm signals.

5. The method according to any one of claims 1 to 4, characterized in that, The resource utilization data includes at least one of the following: CPU utilization, memory usage, disk I / O throughput, and network bandwidth usage.

6. The method according to any one of claims 1 to 4, characterized in that, The task characteristics include at least one of the following: the request type of the task carried by the server, the number of concurrent accesses, and the resource call mode.

7. A server resource utilization evaluation system, characterized in that, include: The acquisition module is used to acquire resource utilization data during server operation. The generation module is used to generate a task type identifier based on the task characteristics of the tasks carried by the server; The first determining module is used to determine the set of target weighted coefficients that match the task type identifier; The second determining module is used to multiply the target weighted coefficient set with the corresponding resource utilization data to determine the resource weighted value set; The third determining module is used to perform a weighted summation of the normalized resource utilization data and the corresponding resource weight values ​​in the resource weight value set to determine the target resource utilization score, wherein the target resource utilization score is used to characterize the target resource utilization status of the server.

8. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the method as claimed in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 6.

Images