Database performance capacity evaluation method and device, equipment, storage medium and computer program product

Abstract

The invention discloses a performance capacity evaluation method and device of a database, equipment, a storage medium and a computer program product, and relates to the technical field of database management, and the method comprises the following steps: obtaining initial performance index data of the database, and carrying out exception processing on the initial performance index data to obtain target performance index data of the database; performing periodic classification judgment on the target performance index data, and determining an acceleration prediction model corresponding to the target performance index data according to a periodic classification judgment result; performing speed increase prediction based on the target performance index data through a speed increase prediction model to obtain predicted performance index data; and performing performance capacity evaluation on the database according to the target performance index data and the predicted performance index data to obtain a performance capacity evaluation result corresponding to the database. And according to the performance index data, determining the corresponding speed increase prediction model to perform speed increase prediction, so that the efficiency and accuracy of performance capacity evaluation can be improved.

Description

Technical Field

[0001] This application relates to the technical field of database management, and particularly to a method, device, equipment, storage medium, and computer program product for evaluating the performance and capacity of a database. Background Art

[0002] At present, databases are widely used in all walks of life, including many fields such as finance, telecommunications, education, and entertainment. Databases are not only an important part of the informatization construction of modern enterprises but also the foundation for the operation of enterprise services. As a product for storing persistent data, databases provide important data guarantees for aspects such as social livelihood and enterprise management.

[0003] To ensure the stable operation of the database and improve the performance and efficiency of the database system, database administrators need to carry out daily database operation and maintenance work. At the same time, as the content and users of enterprise external services continue to grow, the data scale and access volume are also continuously increasing, which makes the database operation and maintenance management work become increasingly important, especially performance monitoring and capacity planning.

[0004] However, with the increasing scale of the number of databases, there are situations of insufficient manpower and inaccurate evaluation when manually evaluating the performance and capacity of each set of databases. This not only increases the operation and maintenance costs but also may affect the accuracy and reliability of the evaluation results. Therefore, there is an urgent need to propose an efficient and accurate method for evaluating the performance of databases.

[0005] The above content is only used to assist in understanding the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0006] The main purpose of this application is to provide a method, device, equipment, storage medium, and computer program product for evaluating the performance and capacity of a database, aiming to solve the technical problem of low efficiency in evaluating the performance and capacity of a database.

[0007] To achieve the above purpose, this application proposes a method for evaluating the performance and capacity of a database, and the method includes:

[0008] Obtain the initial performance index data of the database, perform anomaly processing on the initial performance index data to obtain the target performance index data of the database;

[0009] Perform periodic classification determination on the target performance index data, and determine the growth rate prediction model corresponding to the target performance index data according to the result of the periodic classification determination;

[0010] Perform growth rate prediction based on the target performance index data through the growth rate prediction model to obtain predicted performance index data;

[0011] Based on the target performance index data and the predicted performance index data, perform a performance capacity evaluation on the database to obtain the performance capacity evaluation result corresponding to the database.

[0012] In one embodiment, the step of performing anomaly processing on the initial performance index data to obtain the target performance index data of the database includes:

[0013] Determine outliers in the initial performance index data. When there are outliers in the initial performance index data, perform outlier filtering on the initial performance index data;

[0014] Perform continuity determination on the initial performance index data after filtering. When the initial performance index data is discontinuous, perform interpolation on the initial performance index data to obtain the target performance index data.

[0015] In one embodiment, the step of performing periodic classification determination on the target performance index data and determining the growth rate prediction model corresponding to the target performance index data according to the result of the periodic classification determination includes:

[0016] Perform periodic classification determination on the target performance index data through a period model to obtain the period classification determination result of the target performance index data;

[0017] When the period classification determination result is non-periodic data, determine that the growth rate prediction model corresponding to the target performance index data is a non-periodic sequence growth rate prediction model;

[0018] When the period classification determination result is periodic data, determine that the growth rate prediction model corresponding to the target performance index data is a periodic sequence growth rate prediction model.

[0019] In one embodiment, the periodic sequence growth rate prediction model includes an autoregressive model, a quantile regression model, and a dilated convolution model. The step of determining that the growth rate prediction model corresponding to the target performance index data is a periodic sequence growth rate prediction model when the period classification determination result is periodic data includes:

[0020] When the periodic data is the first sequence data, determine that the growth rate prediction model corresponding to the target performance index data is the autoregressive model;

[0021] When the periodic data is the second sequence data, determine that the growth rate prediction model corresponding to the target performance index data is the quantile regression model;

[0022] When the periodic data is the third sequence data, determine that the growth rate prediction model corresponding to the target performance index data is the dilated convolution model.

[0023] In one embodiment, the step of predicting the growth rate based on the target performance index data through the growth rate prediction model to obtain the predicted performance index data includes:

[0024] Perform change point detection on the target performance index data to determine the change point position of the target performance index data;

[0025] Based on the change point position and the target performance index data, perform linear growth rate calculation through the growth rate prediction model to generate the predicted performance index data of the target performance index data.

[0026] In one embodiment, the step of evaluating the performance capacity of the database according to the target performance index data and the predicted performance index data to obtain the performance capacity evaluation result corresponding to the database includes:

[0027] Determine the performance capacity evaluation strategy of the database;

[0028] According to the performance capacity evaluation strategy, perform performance capacity evaluation on the target performance index data and the predicted performance index data to obtain the performance capacity evaluation result corresponding to the database.

[0029] In addition, to achieve the above object, the present application also proposes a performance capacity evaluation device for a database, and the performance capacity evaluation device for the database includes:

[0030] A data acquisition module, configured to acquire the initial performance index data of the database, and perform anomaly processing on the initial performance index data to obtain the target performance index data of the database;

[0031] A classification determination module, configured to perform periodic classification determination on the target performance index data, and determine the growth rate prediction model corresponding to the target performance index data according to the result of the periodic classification determination;

[0032] A growth rate prediction module, configured to predict the growth rate based on the target performance index data through the growth rate prediction model to obtain the predicted performance index data;

[0033] A capacity evaluation module, configured to evaluate the performance capacity of the database according to the target performance index data and the predicted performance index data to obtain the performance capacity evaluation result corresponding to the database.

[0034] In addition, to achieve the above object, the present application also proposes a performance capacity evaluation device for a database. The device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. The computer program is configured to implement the steps of the performance capacity evaluation method for the database as described above.

[0035] In addition, to achieve the above object, the present application further provides a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the performance capacity evaluation method of the database as described above are implemented.

[0036] In addition, to achieve the above object, the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the performance capacity evaluation method of the database as described above are implemented.

[0037] One or more technical solutions proposed by the present application have at least the following technical effects:

[0038] An embodiment of the present application provides a method, device, equipment, storage medium and computer program product for evaluating the performance capacity of a database, including: obtaining initial performance index data of the database, performing anomaly processing on the initial performance index data to obtain target performance index data of the database; performing periodic classification determination on the target performance index data, and determining a growth rate prediction model corresponding to the target performance index data according to the result of the periodic classification determination; performing growth rate prediction based on the target performance index data through the growth rate prediction model to obtain predicted performance index data; and performing performance capacity evaluation on the database according to the target performance index data and the predicted performance index data to obtain a performance capacity evaluation result corresponding to the database. By determining a corresponding growth rate prediction model according to the performance index data and performing growth rate prediction through the growth rate prediction model, the efficiency and accuracy of database performance capacity evaluation can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0040] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0041] Figure 1 It is a schematic flowchart provided for Embodiment 1 of the method for evaluating the performance capacity of the database of the present application;

[0042] Figure 2 It is a schematic flowchart for performing anomaly processing on initial performance index data provided by the present application;

[0043] Figure 3 It is an example diagram of six-dimensional radar evaluation of the database provided by the embodiment of the present application;

[0044] Figure 4 It is a schematic diagram of the module structure of the performance capacity evaluation device of the database in the embodiment of the present application;

[0045] Figure 5 It is a schematic diagram of the device structure of the hardware operating environment involved in the performance capacity evaluation method of the database in the embodiment of the present application.

[0046] The implementation, functional features and advantages of the present application will be further described in conjunction with the embodiments with reference to the accompanying drawings. Specific embodiments

[0047] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0048] In order to better understand the technical solutions of the present application, the following will be described in detail in conjunction with the accompanying drawings of the specification and specific embodiments.

[0049] The main solution of the embodiment of the present application is: obtaining the initial performance index data of the database, performing anomaly processing on the initial performance index data to obtain the target performance index data of the database; performing periodic classification determination on the target performance index data, and determining the growth rate prediction model corresponding to the target performance index data according to the result of the periodic classification determination; performing growth rate prediction based on the target performance index data through the growth rate prediction model to obtain predicted performance index data; and performing performance capacity evaluation on the database according to the target performance index data and the predicted performance index data to obtain the performance capacity evaluation result corresponding to the database.

[0050] In this embodiment, for the sake of easy description, the following will be described with the performance capacity evaluation device of the database as the execution subject.

[0051] At present, the application of databases in all walks of life is very extensive, including many fields such as finance, telecommunications, education, and entertainment. Databases are not only an important part of the informatization construction of modern enterprises, but also the foundation for the operation of enterprise business. As a product for storing persistent data, databases provide important data guarantees for aspects such as social livelihood and enterprise management.

[0052] In order to ensure the stable operation of the database and improve the performance and efficiency of the database system, database administrators need to carry out daily database operation and maintenance work. At the same time, as the content and users of enterprise external services continue to grow, the data scale and access volume are also continuously increasing, which makes the database operation and maintenance management work become increasingly important, especially performance monitoring and capacity planning.

[0053] However, with the increasing scale of the number of databases, there are situations of insufficient manpower and inaccurate evaluation when manually evaluating the performance capacity of each set of databases. This not only increases the operation and maintenance costs but also may affect the accuracy and reliability of the evaluation results. Therefore, there is an urgent need to propose an efficient and accurate method for evaluating the performance of databases.

[0054] This application provides a solution. By determining the corresponding growth rate prediction model according to the performance index data and performing growth rate prediction through the growth rate prediction model, the efficiency and accuracy of database performance capacity evaluation can be improved.

[0055] It should be noted that the execution entity of this embodiment can be a computing service device with data processing, network communication, and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device, a database performance capacity evaluation device, etc. that can implement the above functions. Hereinafter, taking the database performance capacity evaluation device as an example, this embodiment and the following embodiments will be described.

[0056] Based on this, the embodiments of this application provide a method for evaluating the performance capacity of a database. Refer to Figure 1 , Figure 1 which is a schematic flowchart of the first embodiment of the method for evaluating the performance capacity of the database in this application.

[0057] In this embodiment, the method for evaluating the performance capacity of the database includes steps S11 to S14:

[0058] Step S11, obtain the initial performance index data of the database, and perform anomaly processing on the initial performance index data to obtain the target performance index data of the database.

[0059] It should be noted that the initial performance index data refers to data in six dimensions of the database, namely CPU (Central Processing Unit), memory, number of connections, disk IO (Input / Output), network throughput, and database capacity. The number of connections refers to the number of client devices simultaneously connected to the database, that is, the number of user sessions currently processed by the database.

[0060] In addition, it should be noted that the target performance index data is the database performance data after preprocessing and outlier processing. These data reflect the key performance indicators of the database in the normal running state, such as CPU usage rate, memory usage amount, disk IO, network throughput, number of connections, and database capacity. These data are the basis for periodic classification determination, growth rate prediction, and performance capacity evaluation.

[0061] Specifically, determine the initial performance metric data of the database to be obtained, including data such as the CPU, memory, number of connections, disk I / O, network throughput, and database capacity of the database. Determine the monitoring tool for data monitoring and collection, install the monitoring tool on the server where the database is located, determine the frequency of data collection according to the specific actual situation. In an embodiment of the present application, the data collection frequency is set to be collected once per minute. Set the data collection frequency by modifying the configuration parameters of the monitoring tool, and set the data metric to be collected in the monitoring tool. Start the monitoring tool to collect various performance metric data in the database according to the set frequency to obtain the initial performance metric data of the database.

[0062] Further, perform an outlier determination on the initial performance metric data. When there are outliers in the initial performance metric data, perform an outlier filtering process on the initial performance metric data; perform a continuity determination on the initial performance metric data after the filtering process. When the initial performance metric data is discontinuous, perform an interpolation process on the initial performance metric data to obtain the target performance metric data.

[0063] Step S12, perform a periodic classification determination on the target performance metric data, and determine the growth rate prediction model corresponding to the target performance metric data according to the result of the periodic classification determination.

[0064] It should be noted that the growth rate prediction model refers to a model used to predict future predicted performance metric data. Based on the target performance metric data, perform growth rate prediction by analyzing the statistical characteristics and patterns of the data to predict future data changes. There is a model pool set in the device, and the growth rate prediction model is stored in the model pool. Determine the corresponding growth rate prediction model in the model pool according to the result of the periodic classification determination of the target performance metric data.

[0065] Specifically, perform a periodic classification determination on the target performance metric data through a period model to obtain the periodic classification determination result of the target performance metric data; when the periodic classification determination result is non-periodic data, determine that the growth rate prediction model corresponding to the target performance metric data is a non-periodic sequence growth rate prediction model; when the periodic classification determination result is periodic data, determine that the growth rate prediction model corresponding to the target performance metric data is a periodic sequence growth rate prediction model.

[0066] Step S13, perform growth rate prediction based on the target performance metric data through the growth rate prediction model to obtain the predicted performance metric data.

[0067] It should be noted that the predicted performance metric data is the result obtained by predicting the future value of the performance metric data of the database based on the target performance metric data by applying the growth rate prediction model, which reflects the prediction estimate of the model for the future trend.

[0068] Specifically, perform change point detection on the target performance index data to determine the change point position of the target performance index data; perform linear growth rate calculation on the basis of the change point position and the target performance index data through the growth rate prediction model to generate the predicted performance index data of the target performance index data.

[0069] Step S14: Perform performance capacity evaluation on the database according to the target performance index data and the predicted performance index data to obtain the performance capacity evaluation result corresponding to the database.

[0070] It should be noted that the performance capacity evaluation result refers to

[0071] Specifically, determine the performance capacity evaluation strategy of the database; perform performance capacity evaluation on the target performance index data and the predicted performance index data according to the performance capacity evaluation strategy to obtain the performance capacity evaluation result corresponding to the database.

[0072] In this embodiment, through the above solution, by obtaining the initial performance index data of the database, performing anomaly processing on the initial performance index data to obtain the target performance index data of the database; performing periodic classification determination on the target performance index data, and determining the growth rate prediction model corresponding to the target performance index data according to the result of the periodic classification determination; performing growth rate prediction on the basis of the target performance index data through the growth rate prediction model to obtain the predicted performance index data; performing performance capacity evaluation on the database according to the target performance index data and the predicted performance index data to obtain the performance capacity evaluation result corresponding to the database. By determining the corresponding growth rate prediction model according to the performance index data and performing growth rate prediction through the growth rate prediction model, the efficiency and accuracy of the performance capacity evaluation of the database can be improved.

[0073] Based on the above implementation solution, in a feasible implementation manner, the steps of performing anomaly processing on the initial performance index data to obtain the target performance index data of the database include S21 - S22:

[0074] Step S21: Perform outlier determination on the initial performance index data. When there are outliers in the initial performance index data, perform outlier filtering processing on the initial performance index data.

[0075] It should be noted that the existence of outliers in the initial performance index data means that there is data missing collection, or the collected data deviates from the rule without meaning, that is, the generation of meaningful initial performance index data has a certain rule, and a large deviation from this rule means the existence of outliers.

[0076] Specifically, an outlier determination is performed on the collected initial performance index data. When there are outliers in the initial performance index data, outlier filtering processing is performed on the initial performance index data.

[0077] In an embodiment of the present application, the interquartile range method IQR (Interquartile Range) is used for outlier determination and outlier filtering processing. The interquartile range method is to sort a set of data from smallest to largest and then divide the data into four equal parts of values. The first quartile (Q1) is the 25th percentile of the data, indicating that 25% of the data is less than or equal to it; the third quartile (Q3) is the 75th percentile of the data, indicating that 75% of the data is less than or equal to it. The interquartile range IQR is the difference between Q3 and Q1, that is, IQR = Q3 - Q1. Data values less than Q1 - 1.5 * IQR or greater than Q3 + 1.5 * IQR are defined as outliers, and the data values determined to be outliers are deleted.

[0078] In another embodiment of the present application, a low-pass finite impulse filter LPFIF (Low Pass Finite Impulse Filtering) is used for outlier determination and outlier filtering processing. The low-pass finite impulse filter is a digital signal processing technology used to filter out high-frequency components in the initial performance index data and only allow low-frequency components to pass through. Outlier filtering processing is performed on the initial performance index data through the low-pass finite impulse filter.

[0079] Step S22, a continuity determination is performed on the initial performance index data after the filtering processing. When the initial performance index data is discontinuous, interpolation processing is performed on the initial performance index data to obtain the target performance index data.

[0080] Specifically, a continuous determination is made on the time series of the initial performance index data after the filtering process to determine whether there are missing values or discontinuous data points. If there are missing values or discontinuous data points, an appropriate interpolation method is selected according to the data characteristics and requirements to perform interpolation processing on the data. Common interpolation methods include linear interpolation, polynomial interpolation, and spline interpolation methods. Linear interpolation is suitable for data with a short time series. Assuming that the data changes smoothly over time, the linear relationship between two adjacent known data points is used to estimate the missing value. Polynomial interpolation uses a polynomial to fit the known points and predict the missing points, and is suitable for time series with large fluctuations. Spline interpolation, such as cubic spline interpolation, is a relatively smooth interpolation method and is suitable for processing time series with certain fluctuations. The selected interpolation method is used to perform interpolation processing on the discontinuous time series. After the interpolation is completed, the interpolation result is verified to ensure that the interpolated data is reasonable and meets the expectations. After the initial performance index data is completed with outlier filtering processing and interpolation processing, the target performance index data is obtained.

[0081] As Figure 2 shown is the flowchart for performing anomaly processing on the initial performance index data. After inputting the initial performance index data, first determine whether there are outliers in the data. If there are no outliers, directly determine whether the data is continuous; if there are outliers, perform outlier filtering processing on the data and then determine whether the data is continuous. If the data is continuous, directly complete the anomaly processing; if the data is discontinuous, perform interpolation processing on the data and then end the anomaly processing.

[0082] Through the above solution in this embodiment, through outlier determination and filtering processing, data points that deviate from the normal pattern can be identified and removed or corrected, thereby improving the overall quality of the data; performing interpolation processing on the discontinuous time series can ensure the continuity of the data, better reflect the trend and pattern of the data changing over time, and provide a more reliable basis for analysis and prediction.

[0083] Based on the above implementation scheme, in a feasible implementation manner, the steps of performing periodic classification determination on the target performance index data and determining the growth rate prediction model corresponding to the target performance index data according to the result of the periodic classification determination include S31 to S33:

[0084] Step S31, perform periodic classification determination on the target performance index data through a periodic model to obtain the periodic classification determination result of the target performance index data.

[0085] It should be noted that the periodic model is a statistical model used to analyze and identify the periodic characteristics of the target performance index data based on the time series.

[0086] In addition, it should be noted that the periodic classification determination result includes aperiodic data and periodic data. Aperiodic data refers to the target performance index data being an aperiodic sequence; periodic data refers to the target performance index data being a periodic sequence.

[0087] Specifically, through the analysis and identification of the periodic model, it is determined whether the target performance index data presents a periodic sequence according to the time series, and whether the target performance index data is periodic data, so as to obtain the periodic classification determination result.

[0088] Step S32, when the periodic classification determination result is aperiodic data, determine that the growth rate prediction model corresponding to the target performance index data is an aperiodic sequence growth rate prediction model.

[0089] It should be noted that aperiodic data does not have an obvious and regular repeated pattern in time series data, showing trends or random fluctuations, but does not have periodic characteristics.

[0090] In addition, it should be noted that the aperiodic sequence growth rate prediction model is a model that predicts the future data change by analyzing the statistical characteristics and patterns of the data based on the aperiodic target performance index data sequence. The aperiodic sequence growth rate prediction model includes a multi-layer perceptron model and a Transformer model. The multi-layer perceptron is a typical artificial neural network composed of multiple neurons (i.e., nodes), mainly used for supervised learning tasks and widely applied in fields such as classification, regression, and prediction. The Transformer model is a deep learning model architecture used for natural language processing and other sequence-to-sequence tasks. The Transformer architecture introduces a self-attention mechanism, which allows the model to assign different attention weights according to different parts of the input sequence, so as to better capture semantic relationships.

[0091] Specifically, when the periodic classification determination result of the target performance index data is aperiodic data, determine that the growth rate prediction model corresponding to the target performance index data is an aperiodic sequence growth rate prediction model.

[0092] Step S33, when the periodic classification determination result is periodic data, determine that the growth rate prediction model corresponding to the target performance index data is a periodic sequence growth rate prediction model.

[0093] It should be noted that the periodic sequence growth rate prediction model is a model that predicts the future data change by analyzing the statistical characteristics and patterns of the data based on the periodic target performance index data sequence.

[0094] Specifically, when the periodic classification determination result of the target performance metric data is periodic data, determine that the growth rate prediction model corresponding to the target performance metric data is a periodic sequence growth rate prediction model.

[0095] Through the above solution, this embodiment can improve the prediction accuracy by distinguishing aperiodic data and periodic data and selecting the most suitable growth rate prediction model for each type; by predicting future performance metrics, potential performance bottlenecks can be identified in advance. This enables database administrators to take preventive measures, such as upgrading hardware or adjusting configurations, to avoid performance problems.

[0096] Based on the above implementation, in a feasible implementation, the periodic sequence growth rate prediction model includes an autoregressive model, a quantile regression model, and a dilated convolutional model. The steps of determining that the growth rate prediction model corresponding to the target performance metric data is a periodic sequence growth rate prediction model when the periodic classification determination result is periodic data include S41 to S43:

[0097] Step S41, when the periodic data is the first sequence data, determine that the growth rate prediction model corresponding to the target performance metric data is the autoregressive model.

[0098] It should be noted that the first sequence data refers to data with relatively gentle periods, having periodic changes, but these periodic changes are relatively stable, with small change amplitudes and relatively fixed period lengths. For example, the memory usage of a database may reach a peak at a fixed time every day, such as during user active periods, but this periodic change is relatively gentle and there will be no large fluctuations.

[0099] In addition, it should be noted that the autoregressive model is a time series prediction model that assumes that future values can be predicted based on the current value and the values at several past time points.

[0100] Specifically, when the periodic data is a data sequence with relatively gentle periods, the autoregressive model is used to predict the growth rate of the target performance metric data.

[0101] Step S42, when the periodic data is the second sequence data, determine that the growth rate prediction model corresponding to the target performance metric data is the quantile regression model.

[0102] It should be noted that the second sequence data refers to a sequence with a large range span that is periodic, not only having periodicity, but also having a large data fluctuation range within the period, that is, within each period, the gap between the maximum value and the minimum value of the data is significant. For example, the CPU usage of a database may show obvious periodic changes between weekdays and weekends, and the range of this change is large. For example, the CPU usage during peak hours on weekdays may be much higher than that during low hours on weekends.

[0103] In addition, it should be noted that the quantile regression model is a regression analysis method that not only predicts the median (ie, the 50% quantile), but also predicts the corresponding variable value of any specified quantile.

[0104] Specifically, when the periodic data is a data series with a large range, the quantile regression model is used to predict the growth rate of the target performance indicator data.

[0105] Step S43: When the periodic data is the third sequence data, determine that the growth rate prediction model corresponding to the target performance indicator data is the dilated convolution model.

[0106] It should be noted that the third series data refers to a series with a periodicity and a high spike frequency. It has periodicity, but there will be frequent and short-term extreme values (spikes) in the period. These spikes may be caused by some emergencies or abnormal situations. For example, the number of database connections may show a certain periodicity under normal circumstances, but in certain periods of time, the number of connections may suddenly surge due to emergencies (such as system failures or attacks), forming spikes.

[0107] In addition, it should be noted that the dilated convolution model is a technology used in convolutional neural networks (CNNs), which expands the receptive field by zero padding in the convolution kernel, thereby capturing a wider range of contextual information without increasing the number of parameters.

[0108] Specifically, when the periodic data is a data sequence with a high spike frequency, the dilated convolution model is used to predict the growth rate of the target performance indicator data.

[0109] Through the above solution, this embodiment selects the most appropriate prediction model for different types of periodic data, which can more accurately capture the inherent laws and characteristics of the data, thereby improving the prediction accuracy.

[0110] Based on the above implementation scheme, in a feasible implementation manner, the step of performing growth rate prediction based on the target performance indicator data by using the growth rate prediction model to obtain predicted performance indicator data includes S51-S52:

[0111] Step S51, performing change point detection on the target performance indicator data to determine the change point position of the target performance indicator data.

[0112] It should be noted that the change point position refers to the point in time series data where the statistical characteristics identified by the change point detection method change significantly. These points mark the change in data behavior or trend, such as from growth to decline, or from stable to fluctuating, etc.

[0113] Specifically, this application performs change point detection through the online Bayesian change point detection method, and the target performance index data includes historical performance index data and current performance index data.

[0114] Furthermore, initialize the online Bayesian change point detection model, define the prior distribution for the model parameters to reflect the prior knowledge of the parameters, and initialize the model parameters such as the mean, variance, etc.; obtain the historical performance index data within a recent period of time, input each data point into the model according to the time series. When a data point arrives, use this point to update the posterior distribution of the model and calculate the posterior probability of a change point occurring at this point; preset a change point threshold, compare the calculated posterior probability with the preset change point threshold. If the posterior probability exceeds the threshold, it is determined that a change point has occurred at this time point.

[0115] Step S52, perform a linear growth rate calculation based on the change point position and the target performance index data through the growth rate prediction model to generate the predicted performance index data of the target performance index data.

[0116] Specifically, output the change point position closest to the latest moment. Based on the data points between the closest change point position and the current latest moment, perform a linear growth rate calculation through the growth rate prediction model. When no change point is detected in the obtained historical performance index data, perform a linear growth rate calculation starting from the starting position of the data to generate the predicted performance index data of the historical performance index data. Based on the current capacity and growth rate of the database, the time required to reach a certain capacity can be predicted.

[0117] Through the above solution in this embodiment, more accurate linear growth rate calculations are performed based on the change point position and the target performance index data through change point detection, thereby generating more accurate predicted performance index data; accurate performance index prediction can help database administrators better plan and allocate resources, such as adding hardware resources or optimizing configurations before predicting performance bottlenecks to avoid potential performance problems.

[0118] Based on the above implementation scheme, in a feasible implementation manner, the step of performing a performance capacity assessment on the database according to the target performance index data and the predicted performance index data to obtain the performance capacity assessment result corresponding to the database includes S61 - S62:

[0119] Step S61, determine the performance capacity assessment strategy of the database.

[0120] It should be noted that the performance capacity evaluation strategy is used to evaluate the performance of a database system in multiple key performance indicators (such as CPU, memory, number of connections, disk I / O, network throughput, and database capacity) to determine whether it can meet the current and future performance requirements. For example, assume that in actual operation and maintenance, it is necessary to evaluate whether the database meets three times the performance capacity, such as Figure 3 The database six-dimensional radar evaluation diagram of an embodiment of the present application is shown in Figure 3 It can be seen that the corresponding database is an I / O intensive database, not a CPU intensive database. Figure 3 The current value in is the current performance indicator data currently obtained, and the predicted average value is the average value taken from the predicted performance indicator data. Except for the CPU, other indicators do not meet the requirement of three times the performance capacity. For example, the current value of disk I / O is 30%, and the predicted average value is 35%. According to the requirement of three times the performance capacity, the predicted value of three times the disk I / O of this database is 105%, exceeding 100%, which may trigger the physical limit of the database disk I / O. It is recommended that the database reduce the disk I / O load.

[0121] Specifically, the performance capacity evaluation strategy of the database is determined. The determination of the strategy is affected by factors such as the type of the database, the usage scenario of the database, and the type of the initial performance indicator data. The determination of the strategy is determined according to the specific actual situation.

[0122] Step S62, perform performance capacity evaluation on the target performance indicator data and the predicted performance indicator data according to the performance capacity evaluation strategy to obtain the performance capacity evaluation result corresponding to the database.

[0123] Specifically, after determining the performance capacity evaluation strategy, perform performance capacity evaluation on the target performance indicator data and the predicted performance indicator data to obtain the performance capacity evaluation result corresponding to the database, analyze the evaluation result, identify the performance bottleneck, and propose optimization suggestions, such as increasing resources and optimizing the configuration.

[0124] Through the above solution in this embodiment, through the evaluation strategy, the current and future capacity requirements of the database can be determined more accurately; potential performance bottlenecks can be identified in advance, allowing preventive measures to be taken, such as expanding hardware resources or optimizing software configuration, to avoid performance problems; at the same time, performance capacity evaluation helps to ensure that the database system can support the continuous growth and change of the business, thereby enhancing business continuity.

[0125] It should be noted that the above examples are only for understanding the present application and do not constitute a limitation to the performance capacity evaluation method of the database of the present application. Based on this technical concept, more forms of simple transformations are within the protection scope of the present application.

[0126] The present application also provides a performance capacity evaluation device for a database. Please refer toFigure 4 , the performance capacity evaluation device of the database includes:

[0127] A data acquisition module 401, configured to acquire initial performance index data of the database, perform anomaly processing on the initial performance index data, and obtain target performance index data of the database;

[0128] A classification determination module 402, configured to perform periodic classification determination on the target performance index data, and determine a growth rate prediction model corresponding to the target performance index data according to the result of the periodic classification determination;

[0129] A growth rate prediction module 403, configured to perform growth rate prediction based on the target performance index data through the growth rate prediction model to obtain predicted performance index data;

[0130] A capacity evaluation module 404, configured to perform performance capacity evaluation on the database according to the target performance index data and the predicted performance index data, and obtain a performance capacity evaluation result corresponding to the database.

[0131] The performance capacity evaluation device of the database provided in this application adopts the performance capacity evaluation method of the database in the above embodiment, and can solve the technical problem of low efficiency in evaluating the performance capacity of the database. Compared with the prior art, the beneficial effects of the performance capacity evaluation device of the database provided in this application are the same as those of the performance capacity evaluation method of the database provided in the above embodiment, and other technical features in the performance capacity evaluation device of the database are the same as the features disclosed in the method of the above embodiment, and will not be elaborated here.

[0132] This application provides a performance capacity evaluation device for a database. The performance capacity evaluation device for the database includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the performance capacity evaluation method of the database in the first embodiment above.

[0133] Next, refer to Figure 5, which shows a schematic structural diagram of a performance capacity evaluation device suitable for implementing the database of the embodiments of the present application. The performance capacity evaluation device of the database in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The shown performance capacity evaluation device of the database is merely an example and should not impose any limitation on the functions and scope of use of the embodiments of the present application.

[0134] As Figure 5 shown, the performance capacity evaluation device of the database may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory 1002 or the program loaded from the storage device 1003 into the random access memory 1004. In the random access memory 1004, various programs and data required for the operation of the performance capacity evaluation device of the database are also stored. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are connected to each other through a bus 1005. The input / output interface 1006 is also connected to the bus. Generally, the following systems may be connected to the input / output interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the performance capacity evaluation device of the database to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows a performance capacity evaluation device of the database with various systems, it should be understood that it is not required to implement or have all the shown systems. More or fewer systems may be implemented or had alternatively.

[0135] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by a processing device 1001, the above functions defined in the methods of the embodiments disclosed in the present application are executed.

[0136] The performance capacity evaluation device of the database provided by the present application adopts the performance capacity evaluation method of the database in the above embodiment, and can solve the technical problem of low efficiency in evaluating the performance capacity of the database. Compared with the prior art, the beneficial effects of the performance capacity evaluation device of the database provided by the present application are the same as those of the performance capacity evaluation method of the database provided in the above embodiment, and other technical features in the performance capacity evaluation device of the database are the same as the features disclosed in the method of the previous embodiment, and will not be elaborated here.

[0137] It should be understood that each part disclosed in the present application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0138] As described above, only the specific embodiments of the present application are provided, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claimed rights.

[0139] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the performance capacity evaluation method of the database in the above embodiment.

[0140] The computer-readable storage medium provided by this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0141] The above computer-readable storage medium can be included in a performance capacity evaluation device of a database; it can also exist independently and not be assembled into a performance capacity evaluation device of a database.

[0142] The above computer-readable storage medium carries one or more programs. When the one or more programs are executed by a performance capacity evaluation device of a database, the performance capacity evaluation device of the database is caused to: obtain initial performance index data of the database, perform anomaly processing on the initial performance index data to obtain target performance index data of the database; perform periodic classification determination on the target performance index data, and determine a growth rate prediction model corresponding to the target performance index data according to the result of the periodic classification determination; perform growth rate prediction based on the target performance index data through the growth rate prediction model to obtain predicted performance index data; and perform performance capacity evaluation on the database according to the target performance index data and the predicted performance index data to obtain a performance capacity evaluation result corresponding to the database.

[0143] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, by connecting through the Internet using an Internet service provider).

[0144] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and this module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the block may occur in a different order from that marked in the accompanying drawings. For example, two consecutively represented blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0145] The modules involved in the embodiments described in this application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation on the unit itself in some cases.

[0146] The readable storage medium provided in this application is a computer-readable storage medium. The computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for performing the above-mentioned performance capacity evaluation method of the database, and can solve the technical problem of low efficiency in evaluating the performance capacity of the database. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the performance capacity evaluation method of the database provided in the above embodiments, and will not be elaborated here.

[0147] The present application also provides a computer program product, including a computer program which, when executed by a processor, implements the steps of the method for evaluating the performance capacity of a database as described above.

[0148] The computer program product provided by the present application can solve the technical problem of low efficiency in evaluating the performance capacity of a database. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the method for evaluating the performance capacity of a database provided in the above embodiments, and will not be elaborated herein.

[0149] The above are only partial embodiments of the present application, and thus do not limit the patent scope of the present application. Any equivalent structural transformation made under the technical concept of the present application by using the content of the specification and drawings of the present application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. A method for evaluating the performance capacity of a database, characterized in that, The method for evaluating the performance capacity of the database includes: Obtain the initial performance index data of the database, perform anomaly processing on the initial performance index data, and obtain the target performance index data of the database; Perform periodic classification determination on the target performance index data, and determine the growth rate prediction model corresponding to the target performance index data according to the result of the periodic classification determination; Perform growth rate prediction based on the target performance index data through the growth rate prediction model to obtain predicted performance index data; According to the target performance index data and the predicted performance index data, evaluate the performance capacity of the database to obtain the performance capacity evaluation result corresponding to the database.

2. The performance capacity evaluation method of the database according to claim 1, characterized in that, The step of performing anomaly processing on the initial performance index data to obtain the target performance index data of the database includes: Perform anomaly value determination on the initial performance index data. When there are anomaly values in the initial performance index data, perform anomaly value filtering processing on the initial performance index data; Perform continuity determination on the initial performance index data after filtering processing. When the initial performance index data is discontinuous, perform interpolation processing on the initial performance index data to obtain the target performance index data.

3. The method for evaluating the performance capacity of the database according to claim 1, characterized in that The step of performing periodic classification determination on the target performance index data and determining the growth rate prediction model corresponding to the target performance index data according to the result of the periodic classification determination includes: Perform periodic classification determination on the target performance index data through a period model to obtain the period classification determination result of the target performance index data; When the period classification determination result is non-periodic data, determine that the growth rate prediction model corresponding to the target performance index data is a non-periodic sequence growth rate prediction model; When the period classification determination result is periodic data, determine that the growth rate prediction model corresponding to the target performance index data is a periodic sequence growth rate prediction model.

4. The method for evaluating the performance capacity of a database according to claim 3, wherein The periodic sequence growth rate prediction model includes an autoregressive model, a quantile regression model, and a dilated convolution model. The step of determining that the growth rate prediction model corresponding to the target performance index data is a periodic sequence growth rate prediction model when the period classification determination result is periodic data includes: When the periodic data is the first sequence data, determine that the growth rate prediction model corresponding to the target performance index data is the autoregressive model; When the periodic data is the second sequence data, determine that the growth rate prediction model corresponding to the target performance index data is the quantile regression model; When the periodic data is the third sequence data, determine that the growth rate prediction model corresponding to the target performance index data is the dilated convolution model.

5. The method for evaluating the performance capacity of a database according to claim 1, wherein The step of performing growth rate prediction based on the target performance index data through the growth rate prediction model to obtain predicted performance index data includes: Perform change point detection on the target performance index data to determine the change point position of the target performance index data; Perform linear growth rate calculation based on the change point position and the target performance index data through the growth rate prediction model to generate the predicted performance index data of the target performance index data.

6. The performance capacity evaluation method of the database according to claim 1, characterized in that The step of performing a performance capacity assessment on the database according to the target performance index data and the predicted performance index data to obtain a performance capacity assessment result corresponding to the database includes: Determine a performance capacity assessment strategy for the database; Perform a performance capacity assessment on the target performance index data and the predicted performance index data according to the performance capacity assessment strategy to obtain a performance capacity assessment result corresponding to the database.

7. A performance capacity evaluation device for a database, characterized in that The performance capacity assessment device for the database includes: A data acquisition module, configured to acquire initial performance index data of the database, perform anomaly processing on the initial performance index data to obtain target performance index data of the database; A classification determination module, configured to perform periodic classification determination on the target performance index data, and determine a growth rate prediction model corresponding to the target performance index data according to the result of the periodic classification determination; A growth rate prediction module, configured to perform growth rate prediction based on the target performance index data through the growth rate prediction model to obtain predicted performance index data; A capacity assessment module, configured to perform a performance capacity assessment on the database according to the target performance index data and the predicted performance index data to obtain a performance capacity assessment result corresponding to the database.

8. A performance capacity evaluation device for a database, characterized in that The device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the computer program is configured to implement the steps of the performance capacity assessment method for the database according to any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the performance capacity assessment method for the database according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that, The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the performance capacity assessment method for the database according to any one of claims 1 to 6 are implemented.

Images