Performance index prediction method, device and equipment for distributed database system

Abstract

The invention discloses a performance index prediction method, device and equipment for a distributed database system. The method comprises the following steps: creating a prediction data set, wherein the prediction data set comprises a prediction time period; inputting the prediction data set into a trained time sequence prediction model, and predicting performance index data of the distributed database system in a prediction time period according to the parameters and rules obtained by fitting through the time sequence prediction model to obtain a prediction result; determining abnormal performance index data according to the prediction result, and performing early warning; wherein the time sequence prediction model is obtained by performing model training according to historical performance index data of each component of the distributed database system. According to the method, the time sequence prediction model is used for predicting the performance indexes of the distributed database system, the overall trend of the data can be accurately captured, abnormal index data can be quickly positioned in advance, early warning is performed in advance, and risks are effectively reduced.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of artificial intelligence technology, and in particular to a method, device and equipment for predicting performance indicators of a distributed database system. Background Art

[0002] Distributed databases provide great convenience for financial services due to their large capacity, easy expansion, and high performance.

[0003] The existing performance indicator analysis method of distributed database systems only monitors a single performance indicator for a period of time, such as the CPU usage, memory usage, file read rate and other performance indicator data of the monitoring system; then manually judges whether the single performance indicator data is normal based on experience, and issues an alarm for abnormal performance indicators.

[0004] In the above methods, often before the alarm occurs, the performance indicators have already shown abnormal values ​​or abnormal trends, resulting in untimely operation and maintenance. In addition, the above methods discover abnormal performance indicators based on human experience and cannot accurately locate abnormal performance indicators. Summary of the invention

[0005] The present invention provides a performance indicator prediction method, device and equipment for a distributed database system to solve the problem that the prior art cannot accurately locate abnormal performance indicators.

[0006] According to one aspect of the present invention, a method for predicting performance indicators of a distributed database system is provided, comprising:

[0007] Creating a prediction data set, wherein the prediction data set includes a prediction time period;

[0008] The prediction data set is input into the trained time series prediction model, and the performance indicator data of the distributed database system within the prediction time period is predicted by the time series prediction model according to the fitted parameters and rules to obtain the prediction result;

[0009] Determine abnormal performance indicator data according to the prediction results and issue an early warning;

[0010] The time series prediction model is obtained after model training based on historical performance indicator data of each component of the distributed database system.

[0011] According to another aspect of the present invention, a performance indicator prediction device for a distributed database system is provided, comprising:

[0012] A creation module, used to create a prediction data set, wherein the prediction data set includes a prediction time period;

[0013] A prediction module is used to input the prediction data set into the trained time series prediction model, and predict the performance indicator data of the distributed database system within the prediction time period according to the fitted parameters and rules through the time series prediction model to obtain the prediction result;

[0014] A determination module, used to determine abnormal performance indicator data according to the prediction results and issue an early warning;

[0015] The time series prediction model is obtained after model training based on historical performance indicator data of each component of the distributed database system.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] at least one processor;

[0018] and a memory communicatively coupled to the at least one processor;

[0019] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the performance indicator prediction method of the distributed database system described in any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the performance indicator prediction method of a distributed database system described in any embodiment of the present invention when executed.

[0021] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the performance indicator prediction method of the distributed database system described in any embodiment of the present invention is implemented.

[0022] The technical solution of the embodiment of the present invention, by using a time series prediction model to predict the performance indicators of a distributed database system, solves the problem that the existing technical methods cannot accurately locate abnormal performance indicators, and achieves the beneficial effects of accurately capturing the overall trend of the data, quickly locating abnormal indicator data in advance, and providing early warning.

[0023] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 A schematic diagram of a flow chart of a method for predicting performance indicators of a distributed database system provided in Embodiment 1 of the present invention;

[0026] Figure 2 A schematic diagram of a flow chart of a method for predicting performance indicators of a distributed database system provided in Embodiment 2 of the present invention;

[0027] Figure 3 A schematic diagram of the structure of a performance indicator prediction device for a distributed database system provided in Embodiment 3 of the present invention;

[0028] Figure 4 The present invention is a schematic diagram of the structure of an electronic device for a method for predicting performance indicators of a distributed database system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only an embodiment of a part of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work should belong to the scope of protection of the present invention. It should be understood that the various steps recorded in the method implementation of the present invention can be performed in different orders and / or in parallel. In addition, the method implementation may include additional steps and / or omit the steps shown. The scope of the present invention 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 terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] It should be noted that the modifications of "one" and "plurality" mentioned in the present invention 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] The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only used for illustrative purposes, and are not used to limit the scope of these messages or information.

[0034] Embodiment 1

[0035] Figure 1 A flow chart of a performance indicator prediction method for a distributed database system provided in Embodiment 1 of the present invention is applicable to situations where an abnormal performance indicator in a distributed database system is given in advance. The method can be executed by a performance indicator prediction device for a distributed database system, wherein the device can be implemented by software and / or hardware and is generally integrated on an electronic device. In this embodiment, the electronic device includes but is not limited to: a computer device.

[0036] like Figure 1 As shown, a performance indicator prediction method for a distributed database system provided in Embodiment 1 of the present invention includes the following steps:

[0037] S110: Create a prediction data set, where the prediction data set includes a prediction time period.

[0038] To predict the performance indicator data of the distributed database system in the future, you need to create a data set for prediction, namely the prediction data set. Usually, it is based on the time series of the original performance indicator data and extends it to a certain period of time. For example, to predict the performance indicator data for the next 5 days, you need to create a data set that includes the next 5 days. The prediction data set only has the ds column, which represents the future time.

[0039] S120, inputting the prediction data set into the trained time series prediction model, and using the time series prediction model to predict the performance indicator data of the distributed database system within the prediction time period according to the fitted parameters and rules to obtain a prediction result.

[0040] Among them, the time series prediction model is obtained after model training based on the historical performance indicator data of each component of the distributed database system.

[0041] The distributed database is a self-controllable, highly consistent, distributed database product compatible with MySQL. It supports automatic horizontal splitting, with complete logical tables for business experience, while data is evenly split into multiple physical shards, which can effectively solve online transaction processing scenarios with ultra-large concurrency, ultra-high performance, and ultra-large capacity. Its core features are strong data consistency, high performance and low cost, linear horizontal expansion, financial-grade high availability, enterprise-grade security, and convenient operation and maintenance.

[0042] In this embodiment, the historical performance indicator data may include the historical performance indicator data of the data node, the historical performance indicator data of the computing node, and the historical performance indicator data of the distributed database system. Among them, the historical performance indicator data of the data node at least includes: the number of slow queries of the data node, the master-slave delay time of the data node, and the number of waiting threads of the data node; the historical performance indicator data of the computing node at least includes: the average response time of the computing node, the connection utilization rate of the computing node, and the total number of SQL; the historical performance indicator data of the distributed database system includes: the number of requests consumed at different times by the computing node and the number of SQL errors of the computing node.

[0043] Illustratively, Table 1 is an example table of performance indicator data of each component, as shown in Table 1.

[0044]

[0045]

[0046] Table 1

[0047] In this embodiment, the time series prediction model can be a Prophet model, which is a nonlinear regression model based on an additive model and is used to predict time series data with strong seasonal characteristics; the main components of the model include trend terms, seasonal terms, holiday factors, and error terms. It is designed specifically for processing data with trend, seasonal and holiday effects; it can capture the overall trend of the data, consider periodic patterns, and allow users to specify the impact of special dates; the model has the function of automatically detecting change points and providing interpretable results.

[0048] In this embodiment, the prediction data set is input into the trained time series prediction model, and the prediction is performed by the predict function of the Prophet model using the created prediction data frame. The prediction data frame is passed to the predict function, which returns a new data frame containing the prediction result.

[0049] In this embodiment, the prediction result may include a predicted value, a confidence interval of the predicted value, a trend item, a seasonal item, and a holiday item.

[0050] Among them, the predicted value is the performance indicator data of the distributed database system within the prediction time period; the confidence interval of the predicted value includes the lower limit estimate of the predicted value and the upper limit estimate of the predicted value. The yhat_lower column provides the lowest value range that the predicted value may reach under a certain confidence level, and the yhat_upper column provides the highest value range that the predicted value may reach under a certain confidence level; the trend value in the trend item reflects the value of the long-term trend part in the performance indicator data at each prediction time point; the seasonal component value in the season item shows the specific contribution value of the seasonal factor in the performance indicator data at each prediction time point. If the performance indicator data has daily seasonality, there will be a "daily_seasonal" column in the prediction result data frame, which shows the seasonal fluctuation of the time series data within each day; the holiday impact value in the holiday item indicates the degree of influence of the holiday factor on the predicted value at each prediction time point.

[0051] S130. Determine abnormal performance indicator data according to the prediction result and issue an early warning.

[0052] In this embodiment, the abnormal prediction value and abnormal trend in the prediction result are used as abnormal performance indicator data, and early warning information is generated and sent to the operation and maintenance personnel so that the operation and maintenance personnel can perform operation and maintenance in advance.

[0053] A performance indicator prediction method for a distributed database system provided in a first embodiment of the present invention first creates a prediction data set, wherein the prediction data set includes a prediction time period; then the prediction data set is input into a trained time series prediction model, and the performance indicator data of the distributed database system within the prediction time period is predicted by the time series prediction model according to the parameters and rules obtained by fitting, to obtain a prediction result; finally, abnormal performance indicator data is determined according to the prediction result, and an early warning is issued. The above method uses a time series prediction model to predict the performance indicators of a distributed database system, which can accurately capture the overall trend of the data, quickly locate abnormal indicator data in advance, and issue an early warning, effectively reducing the occurrence of risks. In addition, the prior art cannot accurately locate abnormal points by detecting a single indicator. The historical performance indicator data used by this method includes multiple performance indicator data of multiple components for model training, so multiple performance indicator data can be comprehensively considered to locate abnormal points in all aspects.

[0054] Furthermore, the training process of the time series prediction model includes:

[0055] Obtaining historical performance indicator data of each component of the distributed database system, wherein the historical performance indicator data is time series data;

[0056] After determining the correctness of the historical performance indicator data, preprocessing the correct historical performance indicator data to obtain complete historical performance indicator data;

[0057] Constructing the complete historical performance indicator data into historical performance indicator data in a preset format as training set data;

[0058] Create a time series forecasting model instance and configure model parameters;

[0059] The training set data is input into the created time series prediction model instance, so that the time series prediction model automatically fits the trend, seasonal characteristics and holiday characteristics in the data, and the best fitting method is determined by continuously adjusting the model parameters.

[0060] The historical performance indicator data of each component of the distributed database system can be obtained through the data interaction interface of the distributed database. The historical performance indicator data can be understood as the performance indicator data of each component of the distributed database system in the past period of time. The historical performance indicator data has a time sequence and is time series data; the historical performance data must be correct and complete.

[0061] Further, determining the correctness of the historical performance indicator data includes:

[0062] For each performance indicator data in the historical performance indicator data, perform the following steps:

[0063] Statistical analysis of the mathematical value of the same performance indicator data, the stability of the same performance indicator data, and the correlation of each data in the same performance indicator data;

[0064] Whether the same type of performance indicator data is correct is determined according to the mathematical value, the stability and the correlation.

[0065] Among them, since the historical performance indicator data includes multiple performance indicator data, it is necessary to judge the correctness of each performance indicator data separately.

[0066] Among them, the mathematical values ​​of the same performance indicator data may include mean, standard deviation, maximum, minimum and quantile, etc.; the describe method of the Pandas tool can be used: data.describe() to count the mathematical values ​​of the same performance indicator data; the plot() method of the Pandas tool can be used to draw time series graphs and distribution histograms to intuitively understand the volatility, stability and skewed distribution of the same performance indicator data; the corr() method of the Pandas tool and the heatmap() method of the seaborn tool can be used to draw correlation heat maps to obtain the correlation between the same performance indicator data.

[0067] In this embodiment, preprocessing the correct historical performance indicator data includes supplementing the missing values ​​in the correct historical performance indicator data to obtain the complete historical performance indicator data. The supplementation method is not specifically limited here, and the missing value can be supplemented by the adjacent value or the average value.

[0068] Furthermore, the historical performance indicator data in a preset format includes two columns of values, one of the two columns of values ​​is the date value of the data, and the other of the two columns of values ​​is the value of the data.

[0069] The historical performance indicator data needs to be organized into the DataFrame format in the Pandas tool, with one column representing time, such as the ds column, and the data type is date and time type, and the other column represents the corresponding performance indicator data, such as the y column.

[0070] Furthermore, the model parameters include: trend growth type parameters, trend change point parameters, daily seasonal fluctuation parameters, weekly seasonal fluctuation parameters, annual seasonal fluctuation parameters, confidence interval parameters and holiday parameters.

[0071] As shown in Table 2, Table 2 is a model parameter example table provided by an embodiment of the present invention. Among them, growth = 'logistic' indicates that the trend term adopts the logistic function form, daily_seasonality = True indicates that daily seasonal effects are considered, yearly_seasonality = True indicates that annual seasonal effects are considered, and weekly_seasonality = True indicates that weekly seasonal effects are considered.

[0072]

[0073]

[0074] Table 2

[0075] Embodiment 2

[0076] Figure 2 This is a flow chart of a performance indicator prediction method for a distributed database system provided by Embodiment 2 of the present invention. Embodiment 2 is optimized based on the above embodiments. For details not yet provided in this embodiment, please refer to Embodiment 1.

[0077] like Figure 2 As shown, a performance indicator prediction method for a distributed database system provided by Embodiment 2 of the present invention includes the following steps:

[0078] S210: Create a prediction data set, where the prediction data set includes a prediction time period.

[0079] S220, inputting the predicted data set into the trained time series prediction model, and using the time series prediction model to predict the performance indicator data of the distributed database system within the prediction time period according to the fitted parameters and rules to obtain a prediction result.

[0080] The time series prediction model is obtained after model training based on historical performance indicator data of each component of the distributed database system.

[0081] S230: Visually display the prediction results.

[0082] In this embodiment, a drawing library can be used to draw various chart forms including observed values, predicted values, confidence intervals, etc.

[0083] S240: Determine abnormal performance indicator data according to the prediction result and issue an early warning.

[0084] A performance indicator prediction method for a distributed database system provided in a second embodiment of the present invention can visualize the prediction results so that users can view the prediction results more intuitively.

[0085] Embodiment 3

[0086] Figure 3 A schematic diagram of the structure of a performance indicator prediction device for a distributed database system provided in Example 3 of the present invention, wherein the device can be used to provide early warning of abnormal performance indicators in a distributed database system, wherein the device can be implemented by software and / or hardware and is generally integrated on an electronic device.

[0087] like Figure 3 As shown, the device includes: a creation module 110 , a prediction module 120 and a determination module 130 .

[0088] A creation module 110, configured to create a prediction data set, wherein the prediction data set includes a prediction time period;

[0089] The prediction module 120 is used to input the prediction data set into the trained time series prediction model, and predict the performance indicator data of the distributed database system within the prediction time period according to the fitted parameters and rules through the time series prediction model to obtain the prediction result;

[0090] A determination module 130, configured to determine abnormal performance indicator data according to the prediction result and issue an early warning;

[0091] The time series prediction model is obtained after model training based on historical performance indicator data of each component of the distributed database system.

[0092] In this embodiment, the device first creates a prediction data set through a creation module 110, wherein the prediction data set includes a prediction time period; then, the prediction data set is input into a trained time series prediction model through a prediction module 120, and the performance indicator data of the distributed database system within the prediction time period is predicted according to the fitted parameters and rules through the time series prediction model to obtain a prediction result; finally, the determination module 130 determines abnormal performance indicator data according to the prediction result and issues an early warning.

[0093] This embodiment provides a performance indicator prediction device for a distributed database system, which can accurately capture the overall trend of data, quickly locate abnormal indicator data in advance, and issue early warnings, effectively reducing the occurrence of risks.

[0094] Furthermore, the training process of the time series prediction model includes:

[0095] Obtaining historical performance indicator data of each component of the distributed database system, wherein the historical performance indicator data is time series data;

[0096] After determining the correctness of the historical performance indicator data, preprocessing the correct historical performance indicator data to obtain complete historical performance indicator data;

[0097] Constructing the complete historical performance indicator data into historical performance indicator data in a preset format as training set data;

[0098] Create a time series forecasting model instance and configure model parameters;

[0099] The training set data is input into the created time series prediction model instance, so that the time series prediction model automatically fits the trend, seasonal characteristics and holiday characteristics in the data, and the best fitting method is determined by continuously adjusting the model parameters.

[0100] Based on the above technical solution, determining the correctness of the historical performance indicator data includes:

[0101] For each performance indicator data in the historical performance indicator data, perform the following steps:

[0102] Statistical analysis of the mathematical value of the same performance indicator data, the stability of the same performance indicator data, and the correlation of each data in the same performance indicator data;

[0103] Whether the same type of performance indicator data is correct is determined according to the mathematical value, the stability and the correlation.

[0104] Furthermore, the historical performance indicator data in the preset format includes two columns of values, one of the two columns of values ​​is the date value of the data, and the other of the two columns of values ​​is the value of the data.

[0105] Furthermore, the model parameters include:

[0106] Trend growth type parameters, trend change point parameters, daily seasonal fluctuation parameters, weekly seasonal fluctuation parameters, annual seasonal fluctuation parameters, confidence interval parameters and holiday parameters.

[0107] Furthermore, the prediction results include the predicted value, the confidence interval of the predicted value, the trend item, the seasonal item and the holiday item;

[0108] The predicted value is the performance indicator data of the distributed database system within the predicted time period.

[0109] Furthermore, the historical performance index data includes historical performance index data of data nodes in the distributed database system, historical performance index data of computing nodes, and historical performance index data of the distributed database system;

[0110] Among them, the historical performance indicator data of the data node includes at least: the number of slow queries of the data node, the master-slave delay time of the data node, and the number of waiting threads of the data node; the historical performance indicator data of the computing node includes at least: the average response time of the computing node, the connection utilization rate of the computing node, and the total number of SQL; the historical performance indicator data of the distributed database system includes: the number of requests consumed by the computing node at different times and the number of SQL errors of the computing node.

[0111] Furthermore, the device also includes a display module for visually displaying the prediction results.

[0112] The performance indicator prediction device of the distributed database system can execute the performance indicator prediction method of the distributed database system provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0113] Embodiment 4

[0114] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0115] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0116] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0117] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a performance indicator prediction method for a distributed database system.

[0118] In some embodiments, the performance indicator prediction method for a distributed database system may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps in the performance indicator prediction method for a distributed database system described above may be executed. Alternatively, in other embodiments, the processor 11 may be configured to execute the performance indicator prediction method for a distributed database system in any other appropriate manner (e.g., by means of firmware).

[0119] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0120] In some embodiments, the performance indicator prediction method of a distributed database system can be implemented as a computer program, which is invisibly included in a computer program product. When the computer program is executed by a processor, the performance indicator prediction method of the distributed database system of the present invention is implemented. The computer program product can be understood as a software product that mainly implements its solution through a computer program. The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, as an independent software package, partially on the machine and partially on a remote machine, or completely on a remote machine or server.

[0121] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. 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.

[0122] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0123] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by 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), a blockchain network, and the Internet.

[0124] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0125] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0126] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A performance indicator prediction method for a distributed database system, characterized in that: The method comprises: Creating a prediction data set, wherein the prediction data set includes a prediction time period; The prediction data set is input into the trained time series prediction model, and the performance indicator data of the distributed database system within the prediction time period is predicted by the time series prediction model according to the fitted parameters and rules to obtain the prediction result; Determine abnormal performance indicator data according to the prediction results and issue an early warning; The time series prediction model is obtained through model training based on historical performance indicator data of each component of the distributed database system.

2. The method according to claim 1, characterized in that The training process of the time series prediction model includes: Obtaining historical performance indicator data of each component of the distributed database system, wherein the historical performance indicator data is time series data; After determining the correctness of the historical performance indicator data, preprocessing the correct historical performance indicator data to obtain complete historical performance indicator data; Constructing the complete historical performance indicator data into historical performance indicator data in a preset format as training set data; Create a time series forecasting model instance and configure model parameters; The training set data is input into the created time series prediction model instance, so that the time series prediction model automatically fits the trend, seasonal characteristics and holiday characteristics in the data, and the best fitting method is determined by continuously adjusting the model parameters.

3. The method according to claim 2, characterized in that Determine the accuracy of the historical performance indicator data, including: For each performance indicator data in the historical performance indicator data, perform the following steps: Statistical analysis of the mathematical value of the same performance indicator data, the stability of the same performance indicator data, and the correlation of each data in the same performance indicator data; Whether the same type of performance indicator data is correct is determined according to the mathematical value, the stability, and the correlation.

4. The method according to claim 2, characterized in that: The historical performance indicator data in the preset format includes two columns of values, one of the two columns of values ​​is the date value of the data, and the other of the two columns of values ​​is the value of the data.

5. The method according to claim 2, characterized in that: The model parameters include: Trend growth type parameters, trend change point parameters, daily seasonal fluctuation parameters, weekly seasonal fluctuation parameters, annual seasonal fluctuation parameters, confidence interval parameters and holiday parameters.

6. The method according to claim 2, characterized in that The prediction results include the predicted value, the confidence interval of the predicted value, the trend item, the seasonal item and the holiday item; The predicted value is the performance indicator data of the distributed database system within the predicted time period.

7. The method according to claim 2, characterized in that The historical performance index data includes historical performance index data of data nodes in the distributed database system, historical performance index data of computing nodes, and historical performance index data of the distributed database system; Among them, the historical performance indicator data of the data node includes at least: the number of slow queries of the data node, the master-slave delay time of the data node, and the number of waiting threads of the data node; the historical performance indicator data of the computing node includes at least: the average response time of the computing node, the connection utilization rate of the computing node, and the total number of SQL; the historical performance indicator data of the distributed database system includes: the number of requests consumed by the computing node at different times and the number of SQL errors of the computing node.

8. The method according to claim 2, characterized in that: After getting the prediction results, it also includes: The prediction results are displayed visually.

9. A performance indicator prediction device for a distributed database system, characterized in that: The device comprises: A creation module, used to create a prediction data set, wherein the prediction data set includes a prediction time period; A prediction module is used to input the prediction data set into the trained time series prediction model, and predict the performance indicator data of the distributed database system within the prediction time period according to the fitted parameters and rules through the time series prediction model to obtain the prediction result; A determination module, used to determine abnormal performance indicator data according to the prediction results and issue an early warning; The time series prediction model is obtained through model training based on historical performance indicator data of each component of the distributed database system.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the performance indicator prediction method for a distributed database system according to any one of claims 1 to 8.

Images