Server cluster capacity evaluation method, device, electronic device and storage medium

Abstract

The disclosed embodiment discloses a server cluster capacity assessment method, system, device, electronic device and storage medium, wherein the method includes: obtaining the service request volume per second, service average response time and server central processor average load of the current server cluster to be assessed; estimating the service request volume per second peak value of the current server cluster to be assessed based on the real-time functional relationship between the server central processor average load and the service request volume per second; based on the service request volume per second, service request volume peak value, service average response time, preset service average response time threshold and server central processor average load, according to the preset server cluster capacity assessment logic, obtaining the current capacity assessment result of the server cluster to be assessed. The technical solution disclosed in the disclosed embodiment can efficiently and dynamically assess the server cluster capacity in real time to efficiently guide server resource management.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to a method, device, electronic device, and storage medium for evaluating the capacity of a server cluster. Background Art

[0002] In Internet business, the service architecture will be expanded according to business growth. At the same time, in order to ensure the stability of the service, the capacity of the server cluster needs to be managed. Currently, in order to predict the service traffic pressure at major events or special time nodes, evaluate the capacity of the server cluster, and guide resource adjustments such as service expansion or reduction, server cluster stress testing is usually performed to evaluate the capacity and performance of the server cluster.

[0003] However, the operational cost of obtaining server cluster capacity assessment through stress testing is high, the testing process can easily affect service performance, cause online failures, and has low timeliness. Summary of the invention

[0004] The embodiments of the present disclosure provide a server cluster capacity assessment method, device, electronic device and storage medium, which can efficiently assess the server cluster capacity in real time.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for evaluating the capacity of a server cluster, comprising:

[0006] Obtain the service request volume per second, average service response time, and average server CPU load of the current server cluster to be evaluated;

[0007] Estimate the peak value of the service requests per second of the server cluster to be evaluated according to the real-time functional relationship between the average load of the server central processing unit and the service requests per second;

[0008] Based on the service requests per second, the peak service requests per second, the service average response time, the preset service average response time threshold and the average load of the server central processing unit, according to the preset server cluster capacity evaluation logic, the current capacity evaluation result of the server cluster to be evaluated is obtained.

[0009] In a second aspect, an embodiment of the present disclosure further provides a server cluster capacity assessment device, including:

[0010] A data acquisition module is used to obtain the service request volume per second, the average service response time and the average load of the server central processor of the current server cluster to be evaluated;

[0011] A peak estimation module, used to estimate the peak value of the service requests per second of the current server cluster to be evaluated based on the real-time functional relationship between the average load of the server central processing unit and the service requests per second;

[0012] The capacity assessment module obtains the current capacity assessment result of the server cluster to be assessed according to the preset server cluster capacity assessment logic based on the service request volume per second, the service request volume peak per second, the service average response time, the preset service average response time threshold and the average load of the server central processing unit.

[0013] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0014] one or more processors;

[0015] a storage device for storing one or more programs,

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the server cluster capacity assessment method as described in any one of the embodiments of the present disclosure.

[0017] In a fourth aspect, an embodiment of the present disclosure further provides a storage medium comprising computer executable instructions, wherein the computer executable instructions, when executed by a computer processor, are used to execute a server cluster capacity assessment method as described in any one of the embodiments of the present disclosure.

[0018] The technical solution of the disclosed embodiment obtains the service request volume per second, service average response time and server central processing unit average load of the current server cluster to be evaluated in real time; then, estimates the peak service request volume per second of the current server cluster to be evaluated based on the real-time functional relationship between the server central processing unit average load and the service request volume per second; finally, based on the service capacity evaluation parameters such as service request volume per second, service request volume peak value, service average response time, preset service average response time threshold and server central processing unit average load, and in accordance with the preset server cluster capacity evaluation logic, obtains the current capacity evaluation result of the server cluster to be evaluated, which solves the problems of high cost and low timeliness of server cluster performance evaluation in the existing technology center, and can efficiently and dynamically evaluate the server cluster capacity in real time, reduce the cost of evaluating the server cluster performance, and efficiently guide server resource management. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0020] Figure 1A flow chart of a server cluster capacity assessment method provided in Embodiment 1 of the present disclosure;

[0021] Figure 2 A dynamic curve of service request volume per second data within a specified historical time period provided by the first embodiment of the present disclosure;

[0022] Figure 3 The dynamic curve of the average load data of the central processing unit of the server within a specified historical time period provided by the first embodiment of the present disclosure;

[0023] Figure 4 This is a schematic diagram of the linear fitting results of the service request volume per second data and the average load data of the server central processing unit in the same time period provided by the first embodiment of the present disclosure;

[0024] Figure 5 A flow chart of a server cluster capacity assessment method provided in Embodiment 2 of the present disclosure;

[0025] Figure 6 A flow chart of a server cluster capacity assessment method provided in Embodiment 3 of the present disclosure;

[0026] Figure 7 A schematic diagram of the structure of a server cluster capacity assessment device provided in Embodiment 4 of the present disclosure;

[0027] Figure 8 This is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present disclosure. DETAILED DESCRIPTION

[0028] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0029] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0030] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0031] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0032] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0033] Embodiment 1

[0034] Figure 1 This is a flow chart of a server cluster capacity assessment method provided by the first embodiment of the present disclosure. The embodiment of the present disclosure is applicable to situations where the operating status of a server cluster is assessed, and is particularly applicable to situations where service resource management is required based on the operating status of the server cluster. The method can be executed by a server cluster capacity assessment device, which can be implemented in the form of software and / or hardware, and can be configured in an electronic device, such as a mobile terminal or a server device.

[0035] like Figure 1 As shown, the server cluster capacity assessment method provided in this embodiment includes:

[0036] S110 , obtaining the service request volume per second, service average response time, and server CPU average load of the current server cluster to be evaluated.

[0037] A server cluster refers to multiple servers that handle the same service. The cluster can use multiple computers for parallel computing to achieve a very high computing speed, and can also use multiple computers for backup. For the client, a service cluster is equivalent to having only one server. Generally, the performance evaluation of a server cluster can include parameters such as the number of service requests per second (QPS), the average service response time (COST), and the average load of the server's central processing unit (CPU_rate) from different perspectives, especially for CPU-intensive services.

[0038] Among them, the average service response time reflects the quality of the service to a certain extent. Usually, in order to ensure the quality of service and give users a good service experience, an upper limit of the average service response time is set. The number of service requests per second shows the processing capacity of the service cluster. The larger the number of requests that the server cluster can handle per second, the better. However, after the number of service requests processed per second reaches a certain level, the average response time of the service will become longer, and the load of the server's central processing unit (CPU) will be too large. That is, when the service request volume is too large and the service response time reaches a certain level, it is considered that the server cluster can no longer work at normal performance, or when the CPU load reaches a certain level, the performance of the overall service cannot work at normal performance due to hardware bottlenecks. When the cluster size is certain, there must be an upper limit to the number of requests that the service can carry. Therefore, it is necessary to comprehensively evaluate the capacity of the service cluster by considering multiple factors such as the number of service requests per second, the average service response time, and the average load of the server's central processing unit.

[0039] Data such as the number of service requests per second, average service response time, and average server CPU load can be obtained by directly reading from the server cluster operation monitoring data, or by first integrating the data to be obtained through the data processing function and then reading the corresponding data from the integrated data set.

[0040] S120 , estimating the peak value of the service requests per second of the current server cluster to be evaluated according to the real-time functional relationship between the average load of the server central processing unit and the service requests per second.

[0041] For a server cluster, stress testing is usually used to determine its performance limit. However, as time goes by and service logic is optimized and adjusted and the architecture changes, stress testing cannot dynamically and in real time determine the extreme performance of the cluster. Stress testing is also time-consuming and risky.

[0042] In this embodiment, a functional relationship between the average load of the server CPU and the service request volume per second data is established, and the functional relationship between the two can be updated according to the new data collected dynamically. Then, according to the linear relationship established between the average load of the server CPU and the service request volume per second data, the peak value of the service request volume per second of the current server cluster to be evaluated is estimated.

[0043] For details, please refer to Figure 2 and Figure 3As shown, the intercepted data curve of the server cluster request volume per second and the server central processing unit average load (i.e., CPU usage rate) data curve in the same time period. It can be observed from the figure that the change trend of the server central processing unit average load data is consistent with the change trend of the service request volume per second data, that is, there is an obvious correlation between QPS and CPU_rate, which can be described as within a certain time range, CPU_rate will increase with the increase of QPS, and the overall trend of the two is consistent. Therefore, in this embodiment, the curve is fitted by the server central processing unit average load and the service request volume per second data to determine the fitting relationship between the two, that is, the functional relationship.

[0044] In the data fitting process, the average load data of the server CPU and the service request volume per second data in the first historical time period before the current moment can be obtained for the relationship fitting between the two. The first historical time period can be seven days, 14 days or other time lengths before the current moment, which can be determined comprehensively based on indicators such as data calculation amount and calculation efficiency. In a specific example, Figure 2 and Figure 3 The data in is used as an example for fitting calculation. There are 288 groups of original data, of which 230 groups of data are used for linear fitting training data and 58 groups of data are used for fitting result testing. The fitting results can be referred to Figure 4 The best fit line shown in Figure 4 The horizontal axis is CPU-rate, and the vertical axis is QPS. The intercept of the best fit line is 40845.11716930033, the regression coefficient is 2554071.37846435, and the evaluation model score is 0.9855894892189563. According to the best fit line, when the CPU-rate is 30%, the QPS is 807067.0; when the CPU-rate is 40%, the QPS is 1062474.0; when the CPU-rate is 50%, the QPS is 1317881.0; when the CPU-rate is 60%, the QPS is 1573288.0. Therefore, according to the above fitting relationship, the service requests per second when the average load of the server central processor is taken as the preset upper limit load value can be taken as the peak value of the service requests per second. The preset upper limit load value is usually 70% or other values. If a processor such as a GPU is provided in the server, the preset upper limit load value can also be adaptively set to a higher value.

[0045] S130. Based on the service requests per second, the service requests per second peak, the service average response time, the preset service average response time threshold and the average load of the server central processing unit, according to the preset server cluster capacity evaluation logic, obtain the current capacity evaluation result of the server cluster to be evaluated.

[0046] Specifically, the service cluster capacity assessment process can be, first, calculating the ratio of the service request volume per second to the service request volume per second peak value, to obtain the first service capacity assessment parameter; then, calculating the ratio of the service average response time to the preset service average response time threshold, to obtain the second service capacity assessment parameter; finally, respectively calculating the product of the first service capacity assessment parameter, the second service capacity assessment parameter and the service central processor average load and the corresponding parameter weight coefficient, and taking the cumulative sum of the obtained product results as the current capacity assessment result of the server cluster to be assessed. Expressed in mathematical formula, the server cluster capacity usage water level value at time t can be expressed as: Among them, QPS t Expressed as the number of service requests per second at time t, QPS peak Indicates the peak number of service requests per second at time t, COST t represents the average service response time at time t, COST thread Indicates the preset service average response time threshold, CPU.rate t represents the average load of the server CPU at time t, A, B and C represent the first service capacity evaluation parameter, the second service capacity evaluation parameter and the average load of the service CPU and the corresponding parameter weight coefficient, respectively, Level t The value range is 0-100%.

[0047] Furthermore, the values ​​of A, B, and C are set and selected based on empirical values. The number of service requests per second, the average service response time, and the average load of the server CPU have different impacts on the server cluster capacity overload. Specifically, for CPU-intensive services, the following situations exist:

[0048] Without considering the cache, the QPS value increases, and theoretically the CPU-rate value increases; when the QPS value increases, the CPU-rate value increases within a reasonable range, and the COST value may not increase; when an exception occurs downstream of the service cluster (such as thread blocking / accumulation), the QPS value does not increase, but the COST value and the CPU-rate value increase; when an exception occurs downstream of the service cluster but the thread is not blocked, the QPS value does not increase, the COST value increases, and the CPU-rate value does not increase.

[0049] Under normal circumstances, the abnormal increase in CPU-rate values ​​will generally be 2-3 times higher than the normal level. For example, the normal response time is 50ms, but it may reach 300ms in an abnormal situation. Secondly, the QPS value may also experience temporary abnormal fluctuations. During the initial adjustment of the weight coefficient, the weight of the factors with large fluctuations can be lowered to minimize abnormal interference. Based on the above assumptions, multiple parameter weight coefficient groups can be set up, which serve as control groups in the actual online regression process, and the final coefficients are determined based on the fitting situation after running for a period of time. That is, the server cluster capacity is evaluated according to the server cluster capacity evaluation logic under each group of parameter weight coefficient values; the evaluation results of the server cluster capacity evaluation logic under each group of parameter weight coefficient values ​​within the preset time period are used as control groups for regression testing, and the final parameter weight coefficient values ​​are determined based on the regression test results. Exemplarily, the parameter weight coefficient values ​​can be set in the following groups: A, B, C = [[0.25, 0.25, 0.5], [0.3, 0.2, 0.5], [0.3, 0.15, 0.55], [0.4, 0.1, 0.5], [0.3, 0.1, 0.6], [0.6, 0.1, 0.3], [0.7, 0.1, 0.2]].

[0050] In a preferred embodiment, the preset service average response time threshold can be adjusted in stages. The service average response time data in the second historical time period before the current moment can be obtained and statistically analyzed to obtain the distribution characteristics of the service average response time data; then, a new preset service average response time threshold is determined based on the distribution characteristics, and the newly determined value is used as the current preset service average response time threshold. For example, according to the threshold calculation theory of the service average response, it is determined that the service average response time conforms to the normal distribution theory, and the historical service average response time monitoring data of a period of time (such as the nearly 7 days of the current time) is substituted into the calculation, and updated on a daily basis. Then, the preset service average response time threshold is equal to the arithmetic mean of the service average response time in the statistical time period, and the sum of three times the standard deviation of the service average response time.

[0051] Of course, the service's established response timeout threshold can also be used as the preset service average response time threshold. However, considering that the response timeout thresholds defined by various services are not standardized and have subjective deviations, and cannot reflect the service's ultimate performance, it is better to calculate the service average response time threshold using the above preferred implementation.

[0052] The technical solution of the disclosed embodiment can obtain the service request volume per second, service average response time and server CPU average load of the current server cluster to be evaluated in real time; then, according to the real-time functional relationship between the server CPU average load and the service request volume per second, estimate the service request volume per second peak value of the current server cluster to be evaluated; finally, based on the service capacity evaluation parameters such as service request volume per second, service request volume per second peak value, service average response time, preset service average response time threshold and server CPU average load, according to the preset server cluster capacity evaluation logic, obtain the current capacity evaluation result of the server cluster to be evaluated, solve the problem of high cost and low timeliness of the existing technical center for evaluating the performance of the server cluster, can efficiently and dynamically evaluate the capacity of the server cluster in real time, reduce the cost of evaluating the performance of the server cluster, and guide the server resource management efficiently. In the whole server cluster capacity evaluation process, the relevant data is obtained in real time for capacity evaluation, and the service cluster request pressure can be perceived at the hour level or even the minute level. When the server cluster capacity water level value is higher than the warning value, an alarm can be issued in time to notify the capacity risk, which is now fully automated without human intervention. Compared with evaluating the service cluster load risk through empirical analysis, using data as the basis for evaluation is more accurate, and the evaluation results are all based on a unified standard.

[0053] Embodiment 2

[0054] The server cluster capacity assessment method provided in the embodiment of the present disclosure can be combined with the various optional solutions in the server cluster capacity assessment method provided in the above embodiment. The server cluster capacity assessment method provided in this embodiment further describes the process of predicting the service request volume at a future time and adjusting the server cluster resources according to the prediction result and the capacity assessment result.

[0055] Figure 5 This is a flow chart of a server cluster capacity assessment method provided by Embodiment 2 of the present disclosure. Figure 5 As shown, the server cluster capacity assessment method provided in this embodiment includes:

[0056] S210: Input the service request volume per second data in the third historical time period before the current moment into a preset request volume prediction model to obtain the result of the service request volume per second at the preset moment.

[0057] Specifically, the preset request volume prediction model can be a Prophet prediction model, which is a time series prediction model. Specifically, the model formula can be expressed as y(t)=g(t)+s(t)+h(t)+ε(t). Among them, g(t) belongs to the trend term, s(t) belongs to the season term, h(t) belongs to the holiday term, and ε(t) is the error term or the residual term, which represents the fluctuation not predicted by the model. When predicting the service requests per second at any future preset moment, it is necessary to input the known time series timestamp, the corresponding service request value per second, and the length of the time series to be predicted into the prediction model; then the prediction model will output the future time series trend based on the input data.

[0058] For example, assume that on December 13, 2020, the daily service requests per second monitoring data of the past 24 months is used as a training sample to train the model and predict the peak service requests per second in the next 7 days. That is, the date of each day and the corresponding service requests per second for the past two years are input into the prediction model. The length of the time series to be predicted is 7 days, and the output results shown in Table 1 are obtained.

[0059] Table 1. Prediction results of the number of requests per second for the next 7 days at the daily level

[0060]

[0061] Among them, ds represents the date, yhat represents the predicted value in the corresponding time series, yhat_lower represents the lower bound of the predicted value, and yhat_upper represents the upper bound of the predicted value.

[0062] For example, on December 22, 2020, the hourly service requests per second monitoring data of the past 14 days was used as a training sample to train a model to predict the peak service requests per second and the request trend in the next 6 hours. That is, the service requests per second in each hour of each day in the past 14 days are input into the prediction model. The length of the time series to be predicted is 6 hours, and the output results shown in Table 2 are obtained.

[0063] Table 2 Hourly level forecast results of service requests per second in the next 6 hours

[0064]

[0065] By predicting the number of service requests per second, we can understand the service pressure faced by the service cluster at a certain moment in the future, so that we can adjust the capacity of the service cluster in time to avoid failures in the services provided by the server cluster.

[0066] S220: Obtain the peak value of the service requests per second of the server cluster to be evaluated at the preset service requests per second reference time in the dynamic server cluster capacity evaluation result.

[0067] In order to further guide the adjustment of server cluster resources, a peak value of service requests per second at a reference time can be selected as a reference to determine whether to adjust server resources. For example, it is now five o'clock in the afternoon on a certain day of a certain month of a certain year. The service requests per second predicted at 8 o'clock this evening through step S210 can be used as the peak value of service requests per second at 8 o'clock this evening. The estimated peak value of service requests per second that the server cluster can withstand yesterday, the day before yesterday, or other historical times can be used as a reference to determine whether the server cluster can undertake the predicted service requests per second at the upcoming 8 o'clock in the evening. Alternatively, the service requests per second at a time close to eight o'clock in the evening can also be used as a reference. Assuming that it is now 6:10 this evening, the estimated peak value of service requests per second corresponding to the current moment can be used as a reference.

[0068] S230: Calculate the difference between the peak value of the service requests per second and the service requests per second at the preset time, and adjust the server resources of the server cluster to be evaluated according to the difference.

[0069] Specifically, since a load balancing algorithm is used during the operation of the server cluster so that each server can bear service requests evenly, when adjusting server resources, the upper threshold of the number of service requests per second that each server can undertake can be determined by using the peak value of the number of service requests per second as a reference and the number of existing servers in the server cluster to be evaluated. Then, the number of servers required is determined by the predicted number of service requests per second and the upper threshold of the number of service requests per second that each server can undertake. If the number of servers required is greater than the number of existing servers, the server cluster to be evaluated needs to be expanded. If the number of servers required is less than the number of existing servers, the server cluster to be evaluated can be reduced in size or left unprocessed, thereby completing the server resource adjustment of the server cluster.

[0070] The technical solution of the disclosed embodiment can achieve real-time capacity risk assessment and expansion and contraction guidance for server clusters by predicting the service requests per second at a preset time in the future, and comparing the predicted service requests per second with the estimated peak service requests per second corresponding to the set reference time, and then timely adjusting server resources according to the comparison results. In particular, the estimation of service requests and service cluster capacity at major events or special holidays can provide data guidance in terms of service maintenance and resource management, and can also optimize the normal service resource structure on a daily basis and provide guidance on tapping the potential of redundant resources. It solves the problems of high cost and low timeliness of server cluster performance evaluation in existing technical centers, and can efficiently and dynamically evaluate server cluster capacity in real time, reduce the cost of evaluating server cluster performance, and efficiently guide server resource management.

[0071] Embodiment 3

[0072] The server cluster capacity assessment method provided in the embodiment of the present disclosure can be combined with the various optional solutions in the server cluster capacity assessment method provided in the above embodiment. The server cluster capacity assessment method provided in this embodiment further illustrates the specific process of storing and managing the server cluster operation data, and realizes the overall operation plan from data acquisition to server capacity assessment.

[0073] Figure 6 This is a flow chart of a server cluster capacity assessment method provided by Embodiment 3 of the present disclosure. Figure 6 As shown, the server cluster capacity assessment method provided in this embodiment includes:

[0074] S310 , obtaining server cluster operation data from server cluster operation monitoring data and storing it in a preset database.

[0075] Specifically, during the operation of the server, the server cluster operation data can be monitored through Metrics and stored in a preset database. In the preset database, the operation data stored are all parameters that can be monitored during the operation of the service cluster, such as service content, service request volume, average service response time, number of servers in the server cluster, CPU-rate and other data.

[0076] S320: extracting preset field data from the preset database, and preprocessing the extracted data to obtain a server cluster capacity assessment data set.

[0077] In this step, it is equivalent to establishing a personalized database based on the preset database to store the parameters under each field read from the preset database. Exemplarily, the data fields read include those shown in Table 3:

[0078] Table 3 Reading data field diagram

[0079]

[0080] Furthermore, after the data is read, it is necessary to pre-process the data, such as converting the data format, unifying the data format into the format used in the server cluster capacity assessment process, deleting duplicate or invalid data, etc.

[0081] S330: Obtain, from the server cluster capacity assessment data set, the service request volume per second, the service average response time, and the average load of the server central processing unit of the server cluster to be assessed.

[0082] S340, estimating the peak value of the service requests per second of the current server cluster to be evaluated according to the real-time functional relationship between the average load of the server central processing unit and the service requests per second.

[0083] S350. Based on the service request volume per second, the service request volume peak per second, the service average response time, the preset service average response time threshold and the average load of the server central processing unit, according to the preset server cluster capacity evaluation logic, obtain the current capacity evaluation result of the server cluster to be evaluated.

[0084] For steps S330 - S350 , reference may be made to the relevant contents in the first and second embodiments.

[0085] In a specific example, a complete closed loop of resource assessment, resource redundancy recovery and resource reuse can also be achieved. Specifically, by measuring the capacity of a large number of services with redundant resources in normal conditions, redundant resources can be recovered while retaining a certain margin as mobile resources. At the same time, combined with real-time capacity assessment, services with resource gaps can be backfilled to achieve "resource reuse", improve overall resource utilization, reduce resource fragmentation, and alleviate the problem of insufficient normal resources.

[0086] The technical solution of the disclosed embodiment monitors the operation data of the server cluster in real time, extracts and processes the operation data statically, and then evaluates the server cluster capacity based on the processed data, providing a complete solution from data acquisition, data storage management, query display, evaluation logic establishment, model evaluation, and output of evaluation results. It solves the problem of high cost and low timeliness of server cluster performance evaluation in the existing technical center, and can efficiently and dynamically evaluate the server cluster capacity in real time, reduce the cost of evaluating server cluster performance, and effectively guide server resource management.

[0087] Embodiment 4

[0088] Figure 7This is a schematic diagram of the structure of a server cluster capacity assessment device provided in Embodiment 4 of the present disclosure. The server cluster capacity assessment device provided in this embodiment is suitable for assessing the operating status of a server cluster.

[0089] like Figure 7 As shown, the server cluster capacity assessment device includes: a data acquisition module 410 , a peak estimation module 420 and a capacity assessment module 430 .

[0090] Among them, the data acquisition module 410 is used to obtain the service request volume per second, the average service response time and the average load of the server central processor of the current server cluster to be evaluated; the peak estimation module 420 is used to estimate the peak value of the service request volume per second of the current server cluster to be evaluated based on the real-time functional relationship between the average load of the server central processor and the service request volume per second; the capacity assessment module 430, based on the service request volume per second, the peak value of the service request volume per second, the average service response time, the preset service average response time threshold and the average load of the server central processor, obtains the current capacity assessment result of the server cluster to be evaluated according to the preset server cluster capacity assessment logic.

[0091] The technical solution of the disclosed embodiment obtains the service request volume per second, service average response time and server central processing unit average load of the current server cluster to be evaluated in real time; then, estimates the peak service request volume per second of the current server cluster to be evaluated based on the real-time functional relationship between the server central processing unit average load and the service request volume per second; finally, based on the service capacity evaluation parameters such as service request volume per second, service request volume peak value, service average response time, preset service average response time threshold and server central processing unit average load, and in accordance with the preset server cluster capacity evaluation logic, obtains the current capacity evaluation result of the server cluster to be evaluated, which solves the problems of high cost and low timeliness of server cluster performance evaluation in the existing technology center, and can efficiently and dynamically evaluate the server cluster capacity in real time, reduce the cost of evaluating the server cluster performance, and efficiently guide server resource management.

[0092] In some optional implementations, the peak value estimation module 420 is specifically configured to:

[0093] Obtain the average load data of the server CPU and the service request volume per second data in the first historical time period before the current moment;

[0094] Establishing a fitting relationship between the average load data of the central processing unit of the server and the data of the number of requests per second of the service;

[0095] Based on the fitting relationship, the service requests per second when the average load of the server central processing unit is taken as a preset upper limit load value is taken as the peak value of the service requests per second.

[0096] In some optional implementations, the server cluster capacity assessment device further includes a service average response time threshold determination module, which is used to:

[0097] Obtaining service average response time data in a second historical time period before the current moment, and performing statistical analysis to obtain distribution characteristics of the service average response time data;

[0098] The preset service average response time threshold is determined according to the distribution characteristics.

[0099] In some optional implementations, the capacity assessment module 430 is specifically configured to:

[0100] Calculate the ratio of the service request volume per second to the service request volume per second peak value to obtain a first service capacity evaluation parameter;

[0101] Calculating the ratio of the service average response time to the preset service average response time threshold to obtain a second service capacity evaluation parameter;

[0102] The products of the first service capacity evaluation parameter, the second service capacity evaluation parameter and the average load of the service central processor and the corresponding parameter weight coefficient are calculated respectively, and the cumulative sum of the obtained product results is used as the current capacity evaluation result of the server cluster to be evaluated.

[0103] In some optional implementations, the server cluster capacity assessment device further includes a parameter weight coefficient determination module, which is used to:

[0104] Get the weight coefficient value of the preset number group parameter;

[0105] Evaluate the server cluster capacity according to the server cluster capacity evaluation logic under each group of parameter weight coefficient values;

[0106] The evaluation results of the server cluster capacity evaluation logic under each group of parameter weight coefficient values ​​within a preset time period are used as a control group to perform regression testing, and the final parameter weight coefficient value is determined according to the regression test results.

[0107] In some optional implementations, the server cluster capacity assessment device further includes a service resource adjustment module, which is used to:

[0108] Inputting the service request volume per second data in the third historical time period before the current moment into the preset request volume prediction model to obtain the result of the service request volume per second at the preset moment;

[0109] The difference between the peak value of the service request volume per second and the service request volume per second at the preset time is calculated, and server resources of the server cluster to be evaluated are adjusted according to the difference.

[0110] In some optional implementations, the server cluster capacity assessment device further includes a parameter management module, which is used to:

[0111] Obtain server operation data from server operation monitoring data and store it in a preset database;

[0112] Extracting preset field data from the preset database, and preprocessing the extracted data to obtain a server cluster capacity assessment data set, wherein the preset fields include data collection time, service requests per second, service average response time, and service central processor average load;

[0113] Accordingly, the data acquisition module 410 is also used for:

[0114] In the server cluster capacity assessment data set, the service request volume per second, the service average response time, and the average load of the server central processing unit of the current server cluster to be assessed are obtained.

[0115] The server cluster capacity assessment device provided in the embodiments of the present disclosure can execute the server cluster capacity assessment method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0116] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

[0117] Embodiment 5

[0118] Reference below Figure 8 , which shows an electronic device (eg, Figure 8 The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0119] like Figure 8 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 506 to a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0120] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 8 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0121] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 506, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the server cluster capacity assessment method of the embodiment of the present disclosure are executed.

[0122] The functions that can be achieved by the electronic device provided in the embodiment of the present disclosure belong to the same public concept as the server cluster capacity assessment method provided in the above embodiment. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0123] Embodiment 6

[0124] An embodiment of the present disclosure provides a computer storage medium on which a computer program is stored. When the program is executed by a processor, the server cluster capacity assessment method provided by the above embodiment is implemented.

[0125] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM) or a flash memory (FLASH), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0126] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0127] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0128] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

[0129] Obtain the service request volume per second, average service response time, and average server CPU load of the current server cluster to be evaluated;

[0130] Estimate the peak value of the service requests per second of the server cluster to be evaluated according to the real-time functional relationship between the average load of the server central processing unit and the service requests per second;

[0131] Based on the service requests per second, the peak service requests per second, the service average response time, the preset service average response time threshold and the average load of the server central processing unit, according to the preset server cluster capacity evaluation logic, the current capacity evaluation result of the server cluster to be evaluated is obtained.

[0132] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0133] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0134] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The names of the units and modules do not, in some cases, limit the units and modules themselves. For example, the data generation module may also be described as a "video data generation module".

[0135] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Parts (ASSP), System on Chip (SOC), Complex Programmable Logic Device (CPLD), etc.

[0136] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0137] According to one or more embodiments of the present disclosure, [Example 1] provides a server cluster capacity assessment method, the method comprising:

[0138] Obtain the service request volume per second, average service response time, and average server CPU load of the current server cluster to be evaluated;

[0139] Estimate the peak value of the service requests per second of the server cluster to be evaluated according to the real-time functional relationship between the average load of the server central processing unit and the service requests per second;

[0140] Based on the service requests per second, the peak service requests per second, the service average response time, the preset service average response time threshold and the average load of the server central processing unit, according to the preset server cluster capacity evaluation logic, the current capacity evaluation result of the server cluster to be evaluated is obtained.

[0141] According to one or more embodiments of the present disclosure, [Example 2] provides a server cluster capacity assessment method, further comprising:

[0142] In some optional implementations, estimating the peak value of the number of service requests per second of the current server cluster to be evaluated based on the real-time functional relationship between the average load of the server central processing unit and the number of service requests per second includes:

[0143] Obtain the average load data of the server CPU and the service request volume per second data in the first historical time period before the current moment;

[0144] Establishing a fitting relationship between the average load data of the central processing unit of the server and the data of the number of requests per second of the service;

[0145] Based on the fitting relationship, the service requests per second when the average load of the server central processing unit is taken as a preset upper limit load value is taken as the peak value of the service requests per second.

[0146] According to one or more embodiments of the present disclosure, [Example 3] provides a server cluster capacity assessment method, further comprising:

[0147] In some optional implementations, the server cluster capacity assessment method further includes:

[0148] Obtaining service average response time data in a second historical time period before the current moment, and performing statistical analysis to obtain distribution characteristics of the service average response time data;

[0149] The preset service average response time threshold is determined according to the distribution characteristics.

[0150] According to one or more embodiments of the present disclosure, [Example 4] provides a server cluster capacity assessment method, further comprising:

[0151] In some optional implementations, the current capacity assessment result of the server cluster to be assessed is obtained according to a preset server cluster capacity assessment logic based on the service request volume per second, the service request volume peak per second, the service average response time, a preset service average response time threshold, and the average load of the server central processing unit, including:

[0152] Calculate the ratio of the service request volume per second to the service request volume per second peak value to obtain a first service capacity evaluation parameter;

[0153] Calculating the ratio of the service average response time to the preset service average response time threshold to obtain a second service capacity evaluation parameter;

[0154] The products of the first service capacity evaluation parameter, the second service capacity evaluation parameter and the average load of the service central processor and the corresponding parameter weight coefficient are calculated respectively, and the cumulative sum of the obtained product results is used as the current capacity evaluation result of the server cluster to be evaluated.

[0155] According to one or more embodiments of the present disclosure, [Example 5] provides a server cluster capacity assessment method, further comprising:

[0156] In some optional implementations, the process of determining the parameter weight coefficients corresponding to the first service capacity evaluation parameter, the second service capacity evaluation parameter, and the average load of the service central processor respectively includes:

[0157] Get the weight coefficient value of the preset number group parameter;

[0158] Evaluate the server cluster capacity according to the server cluster capacity evaluation logic under each group of parameter weight coefficient values;

[0159] The evaluation results of the server cluster capacity evaluation logic under each group of parameter weight coefficient values ​​within a preset time period are used as a control group to perform regression testing, and the final parameter weight coefficient value is determined according to the regression test results.

[0160] According to one or more embodiments of the present disclosure, [Example 6] provides a server cluster capacity assessment method, further comprising:

[0161] In some optional implementations, the server cluster capacity assessment method further includes:

[0162] Inputting the service request volume per second data in the third historical time period before the current moment into the preset request volume prediction model to obtain the result of the service request volume per second at the preset moment;

[0163] The difference between the peak value of the service request volume per second and the service request volume per second at the preset time is calculated, and server resources of the server cluster to be evaluated are adjusted according to the difference.

[0164] According to one or more embodiments of the present disclosure, [Example 7] provides a server cluster capacity assessment method, further comprising:

[0165] In some optional implementations, before obtaining the service request volume per second, service average response time, and server central processing unit average load of the current server cluster to be evaluated, the method further includes:

[0166] Obtain server cluster operation data from server cluster operation monitoring data and store it in a preset database;

[0167] Extracting preset field data from the preset database, and preprocessing the extracted data to obtain a server cluster capacity assessment data set, wherein the preset fields include data collection time, service requests per second, service average response time, and service central processor average load;

[0168] Accordingly, the method of obtaining the service request volume per second, the average service response time, and the average load of the server central processing unit of the current server cluster to be evaluated includes:

[0169] In the server cluster capacity assessment data set, the service request volume per second, the service average response time, and the average load of the server central processing unit of the current server cluster to be assessed are obtained.

[0170] According to one or more embodiments of the present disclosure, [Example 8] provides a server cluster capacity assessment device, including:

[0171] A data acquisition module is used to obtain the service request volume per second, the average service response time and the average load of the server central processor of the current server cluster to be evaluated;

[0172] A peak estimation module, used to estimate the peak value of the service requests per second of the current server cluster to be evaluated based on the real-time functional relationship between the average load of the server central processing unit and the service requests per second;

[0173] The capacity assessment module obtains the current capacity assessment result of the server cluster to be assessed according to the preset server cluster capacity assessment logic based on the service request volume per second, the service request volume peak per second, the service average response time, the preset service average response time threshold and the average load of the server central processing unit.

[0174] According to one or more embodiments of the present disclosure, [Example 9] provides a server cluster capacity assessment device, further comprising:

[0175] In some optional implementations, the peak value estimation module is specifically used to:

[0176] Obtain the average load data of the server CPU and the service request volume per second data in the first historical time period before the current moment;

[0177] Establishing a fitting relationship between the average load data of the central processing unit of the server and the data of the number of requests per second of the service;

[0178] Based on the fitting relationship, the service requests per second when the average load of the server central processing unit is taken as a preset upper limit load value is taken as the peak value of the service requests per second.

[0179] According to one or more embodiments of the present disclosure, [Example 10] provides a server cluster capacity assessment device, further comprising:

[0180] In some optional implementations, the server cluster capacity assessment device further includes a service average response time threshold determination module, which is used to:

[0181] Obtaining service average response time data in a second historical time period before the current moment, and performing statistical analysis to obtain distribution characteristics of the service average response time data;

[0182] The preset service average response time threshold is determined according to the distribution characteristics.

[0183] According to one or more embodiments of the present disclosure, [Example 11] provides a server cluster capacity assessment device, further comprising:

[0184] In some optional implementations, the capacity assessment module is specifically used to:

[0185] Calculate the ratio of the service request volume per second to the service request volume per second peak value to obtain a first service capacity evaluation parameter;

[0186] Calculating the ratio of the service average response time to the preset service average response time threshold to obtain a second service capacity evaluation parameter;

[0187] The products of the first service capacity evaluation parameter, the second service capacity evaluation parameter and the average load of the service central processor and the corresponding parameter weight coefficient are calculated respectively, and the cumulative sum of the obtained product results is used as the current capacity evaluation result of the server cluster to be evaluated.

[0188] According to one or more embodiments of the present disclosure, [Example 12] provides a server cluster capacity assessment device, further comprising:

[0189] In some optional implementations, the server cluster capacity assessment device further includes a parameter weight coefficient determination module, which is used to:

[0190] Get the weight coefficient value of the preset number group parameter;

[0191] Evaluate the server cluster capacity according to the server cluster capacity evaluation logic under each group of parameter weight coefficient values;

[0192] The evaluation results of the server cluster capacity evaluation logic under each group of parameter weight coefficient values ​​within a preset time period are used as a control group to perform regression testing, and the final parameter weight coefficient value is determined according to the regression test results.

[0193] According to one or more embodiments of the present disclosure, [Example 13] provides a server cluster capacity assessment device, further comprising:

[0194] In some optional implementations, the server cluster capacity assessment device further includes a service resource adjustment module, which is used to:

[0195] Inputting the service request volume per second data in the third historical time period before the current moment into the preset request volume prediction model to obtain the result of the service request volume per second at the preset moment;

[0196] The difference between the peak value of the service request volume per second and the service request volume per second at the preset time is calculated, and server resources of the server cluster to be evaluated are adjusted according to the difference.

[0197] According to one or more embodiments of the present disclosure, [Example 14] provides a server cluster capacity assessment device, further comprising:

[0198] In some optional implementations, the server cluster capacity assessment device further includes a parameter management module, which is used to:

[0199] Obtain server cluster operation data from server cluster operation monitoring data and store it in a preset database;

[0200] Extracting preset field data from the preset database, and preprocessing the extracted data to obtain a server cluster capacity assessment data set, wherein the preset fields include data collection time, service requests per second, service average response time, and service central processor average load;

[0201] Accordingly, the data acquisition module 410 is also used for:

[0202] In the server cluster capacity assessment data set, the service request volume per second, the service average response time, and the average load of the server central processing unit of the current server cluster to be assessed are obtained.

[0203] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other.

[0204] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0205] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A server cluster capacity assessment method, characterized in that: include: Obtain the service request volume per second, average service response time, and average server CPU load of the current server cluster to be evaluated; Estimate the peak value of the service requests per second of the server cluster to be evaluated according to the real-time functional relationship between the average load of the server central processing unit and the service requests per second; Calculate the ratio of the service request volume per second to the service request volume per second peak value to obtain a first service capacity evaluation parameter; Calculating a ratio of the service average response time to a preset service average response time threshold to obtain a second service capacity evaluation parameter; The products of the first service capacity evaluation parameter, the second service capacity evaluation parameter and the average load of the service central processor and the corresponding parameter weight coefficient are calculated respectively, and the cumulative sum of the obtained product results is used as the current capacity evaluation result of the server cluster to be evaluated.

2. The method according to claim 1, characterized in that: The estimating the peak value of the service requests per second of the current server cluster to be evaluated based on the real-time functional relationship between the average load of the server central processor and the service requests per second includes: Obtain the average load data of the server CPU and the service request volume per second data in the first historical time period before the current moment; Establishing a fitting relationship between the average load data of the central processing unit of the server and the data of the number of requests per second of the service, and using the fitting relationship as the real-time function relationship; Based on the real-time function relationship, the service requests per second when the average load of the server central processing unit is taken as a preset upper limit load value is taken as the peak value of the service requests per second.

3. The method according to claim 1, characterized in that The method further comprises: Obtaining service average response time data in a second historical time period before the current moment, and performing statistical analysis to obtain distribution characteristics of the service average response time data; The preset service average response time threshold is determined according to the distribution characteristics.

4. The method according to claim 1, characterized in that: The process of determining the parameter weight coefficients corresponding to the first service capacity evaluation parameter, the second service capacity evaluation parameter and the average load of the service central processor respectively includes: Get the weight coefficient value of the preset number group parameter; Evaluate the server cluster capacity according to the server cluster capacity evaluation logic under each group of parameter weight coefficient values; The evaluation results of the server cluster capacity evaluation logic under each group of parameter weight coefficient values ​​within a preset time period are used as a control group to perform regression testing, and the final parameter weight coefficient value is determined according to the regression test results.

5. The method according to claim 1, characterized in that The method further comprises: Inputting the service request volume per second data in the third historical time period before the current moment into the preset request volume prediction model to obtain the result of the service request volume per second at the preset moment; The difference between the peak value of the service request volume per second and the service request volume per second at the preset time is calculated, and server resources of the server cluster to be evaluated are adjusted according to the difference.

6. The method according to claim 1, characterized in that Before obtaining the service request volume per second, service average response time, and server central processing unit average load of the current server cluster to be evaluated, the method further includes: Obtain server cluster operation data from server cluster operation monitoring data and store it in a preset database; Extracting preset field data from the preset database, and preprocessing the extracted data to obtain a server cluster capacity assessment data set, wherein the preset fields include data collection time, service requests per second, service average response time, and service central processor average load; Accordingly, the method of obtaining the service request volume per second, the average service response time, and the average load of the server central processing unit of the current server cluster to be evaluated includes: In the server cluster capacity assessment data set, the service request volume per second, the service average response time, and the average load of the server central processing unit of the current server cluster to be assessed are obtained.

7. A server cluster capacity assessment device, characterized in that: include: A data acquisition module is used to obtain the service request volume per second, the average service response time and the average load of the server central processor of the current server cluster to be evaluated; A peak estimation module, used to estimate the peak value of the service requests per second of the current server cluster to be evaluated based on the real-time functional relationship between the average load of the server central processing unit and the service requests per second; A capacity evaluation module, used to calculate the ratio of the service request volume per second to the service request volume per second peak value, and obtain a first service capacity evaluation parameter; Calculating a ratio of the service average response time to a preset service average response time threshold to obtain a second service capacity evaluation parameter; The products of the first service capacity evaluation parameter, the second service capacity evaluation parameter and the average load of the service central processor and the corresponding parameter weight coefficient are calculated respectively, and the cumulative sum of the obtained product results is used as the current capacity evaluation result of the server cluster to be evaluated.

8. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the server cluster capacity assessment method as described in any one of claims 1-6.

9. A storage medium comprising computer executable instructions, wherein the computer executable instructions are used to execute the server cluster capacity assessment method according to any one of claims 1 to 6 when executed by a computer processor.

Images