Application failure root cause location method and system

By integrating the moving average autoregressive model and scoring criteria, combining performance and monitoring indicator data, the root cause scores of faults are automatically calculated, which solves the problem of low fault positioning efficiency in the existing technology, and achieves efficient and accurate root cause identification, improving the root cause of faults. The reliability of the application.

CN112346936BActive Publication Date: 2024-11-12INDUSTRIAL AND COMMERCIAL BANK OF CHINA
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202011353855.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-11-27
Publication Date
2024-11-12
Estimated Expiration
2040-11-27

AI Technical Summary

Technical Problem

In the prior art, the application of root cause of failure depends on manual analysis, resulting in inefficiency and positioning delay, making it difficult to quickly and accurately identify the root cause of failure, especially in the complex Internet financial transaction environment, which affects the expansion of the impact of failure.

Method used

Using preset baseline fitting model, scoring criteria and weight value groups based on integrated moving average autoregressive model, combined with performance indicator data and monitoring indicator data, the root cause positioning score of each node is calculated by weighted summing, and monitoring is automatically obtained in real time. Intelligent root cause positioning of data can reduce manual intervention and improve fault positioning efficiency and accuracy.

Benefits of technology

Implement automated fault root cause positioning, improve the accuracy and efficiency of fault positioning, reduce data delivery delay, provide high-accurate fault root cause identification, reduce model complexity and positioning time, and improve application reliability sex.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112346936B_ABST
    Figure CN112346936B_ABST
Patent Text Reader

Abstract

The present application provides a method and system for locating the root cause of application failures, which can be used in the financial field or other fields. The method includes: obtaining an indicator data group of each node corresponding to the target application; applying a preset baseline fitting model, scoring criteria, weight value group and the indicator data group to determine the root cause location score of each node, wherein the baseline fitting model is pre-trained based on an integrated moving average autoregressive model; and determining the root cause node of the target application according to the root cause location score of each node. The present application can improve the accuracy and efficiency of locating the root cause of application failures, thereby improving the reliability of the application.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and system for locating the root cause of an application failure. Background Art

[0002] With the development of Internet technology and financial technology, online transactions are becoming more and more frequent, and the transaction amount is also increasing. While online transactions bring convenience to people, there are also more and more transaction problems. In addition, the calling relationship between different types of nodes has become more complicated. Once a failure or performance bottleneck occurs in a certain link, the troubleshooting of simple problems usually spans multiple platforms and teams, which greatly reduces the efficiency of problem analysis and location and greatly increases the impact of failures. Therefore, the Internet financial era has put forward higher requirements for fault location.

[0003] Currently, fault root cause location is mainly based on manual analysis. After a fault occurs, R&D personnel obtain application operation data such as log data, monitoring information, and link information from multiple monitoring platforms, and then compare and analyze the possible nodes of the problem from a large amount of application operation data based on the alarm information. On the one hand, this method requires filtering out valid alarms from a large amount of alarm information, and on the other hand, it takes a lot of time for R&D personnel to analyze and locate the root cause of the problem from the application operation data based on the filtered valid alarms, resulting in low efficiency in problem location and resolution. Summary of the invention

[0004] In view of the problems in the prior art, the present application proposes a method and system for locating the root cause of application failures, which can improve the accuracy and efficiency of locating the root cause of application failures, thereby improving the reliability of the application.

[0005] In order to solve the above technical problems, this application provides the following technical solutions:

[0006] In a first aspect, the present application provides a method for locating the root cause of an application failure, comprising:

[0007] Obtain the indicator data group of each node corresponding to the target application;

[0008] Applying a preset baseline fitting model, scoring criteria, weight value group and the indicator data group to determine the root cause location score of each node, wherein the baseline fitting model is pre-trained based on an integrated moving average autoregressive model;

[0009] According to the root cause location score of each node, the fault root cause node of the target application is determined.

[0010] Further, determining the fault root cause node of the target application according to the root cause location score of each node includes:

[0011] Determine the node with the lowest final score as the fault root cause node of the target application;

[0012] The final score of each node is the sum of the root cause location scores of the node and its child nodes.

[0013] Furthermore, each group of the indicator data includes: performance indicator data and monitoring indicator data; the preset scoring criteria include: a first scoring standard and a second scoring standard;

[0014] Correspondingly, the application of the preset baseline fitting model, scoring criteria, weight value group and the indicator data group to determine the root cause location score of each node includes:

[0015] Applying the preset baseline fitting model, the first scoring standard and the performance indicator data of each node to obtain a performance indicator score of the node;

[0016] Applying the second scoring standard and the monitoring indicator data of each node to obtain a monitoring indicator score of the node;

[0017] The preset weight value group, performance indicator score and monitoring indicator score are applied to obtain the root cause location score of each node.

[0018] Furthermore, the applying the preset baseline fitting model, the first scoring standard and the performance indicator data of each node to obtain the performance indicator score of the node includes:

[0019] Applying the preset baseline fitting model and the performance indicator data of each node to obtain a performance indicator prediction value of the node;

[0020] According to the first scoring criteria and the predicted value of the performance indicator of each node, a performance indicator score of the node is obtained.

[0021] Furthermore, before obtaining the performance index score of each node according to the first scoring standard and the predicted performance index value of each node, the method further includes:

[0022] The first scoring criterion is determined according to the standard deviation and mean corresponding to the performance indicator prediction values ​​of all nodes.

[0023] Furthermore, the method for locating the root cause of an application failure further includes:

[0024] The weight value group is obtained by applying multiple groups of historical indicator data groups and a polynomial fitting algorithm.

[0025] Further, after determining the fault root cause node of the target application according to the root cause location score of each node, the method further includes:

[0026] The fault root cause node and the corresponding sub-nodes are output and displayed in the form of a topology diagram.

[0027] In a second aspect, the present application provides a system for locating the root cause of an application failure, comprising:

[0028] An acquisition module is used to obtain the indicator data group of each node corresponding to the target application;

[0029] A weighted summation module, used to apply a preset baseline fitting model, scoring criteria, a weight value group and the indicator data group to determine the root cause location score of each node, wherein the baseline fitting model is pre-trained based on an integrated moving average autoregressive model;

[0030] The determination module is used to determine the fault root cause node of the target application according to the root cause location score of each node.

[0031] In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for locating the root cause of an application failure when executing the program.

[0032] In a fourth aspect, the present application provides a computer-readable storage medium having computer instructions stored thereon, which implement the method for locating the root cause of an application failure when the instructions are executed.

[0033] It can be seen from the above technical solution that the present application provides a method and system for locating the root cause of application faults. The method includes: obtaining the index data group of each node corresponding to the target application; applying the preset baseline fitting model, scoring criteria, weight value group and the index data group to determine the root cause location score of each node, wherein the baseline fitting model is pre-trained based on the integrated moving average autoregressive model; determining the fault root cause node of the target application according to the root cause location score of each node, which can improve the accuracy and efficiency of the root cause location of the application fault, and thus improve the reliability of the application; it can solve the problem that the current method of root cause location of application faults depends on manual analysis by R&D personnel, which is time-consuming and inefficient, and its advantages are as follows: it can automatically obtain monitoring data and performance indicator data in real time, and perform intelligent root cause location based on these data, which can avoid high delay caused by data transmission among different teams, and provide multiple candidate root cause points based on the intelligent model of historical data, and the root cause location has high accuracy; the model used is of low complexity and the root cause location time is fast. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 It is a flowchart of a method for locating the root cause of a fault applied in an embodiment of the present application;

[0036] Figure 2 is a flowchart of a method for locating a root cause of a fault in another embodiment of the present application;

[0037] Figure 3 is a structural diagram of a fault root cause location system applied in an embodiment of the present application;

[0038] Figure 4 It is a flowchart of a method for locating the root cause of an application fault in an application example of the present application;

[0039] Figure 5 A schematic block diagram of the system structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0041] In order to improve the accuracy and efficiency of locating the root cause of application failures, and thus improve the reliability of applications, an embodiment of the present application provides an application failure root cause locating system, which can be a server or a client device, and the client device can include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, and a smart wearable device, etc. Among them, the smart wearable device can include smart glasses, smart watches, and smart bracelets, etc.

[0042] In actual applications, the part of locating the root cause of the application failure can be performed on the server side as described above, or all operations can be completed in the client device. The specific selection can be based on the processing capability of the client device and the limitations of the user's usage scenario. This application does not limit this. If all operations are completed in the client device, the client device may also include a processor.

[0043] The client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission with the server. The server may include a server on the task scheduling center side, and other implementation scenarios may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, or a server cluster consisting of multiple servers, or a server structure of a distributed device.

[0044] The server and the client device may communicate using any suitable network protocol, including network protocols that have not yet been developed on the date of filing this application. The network protocol may include, for example, TCP / IP protocol, UDP / IP protocol, HTTP protocol, HTTPS protocol, etc. Of course, the network protocol may also include, for example, RPC protocol (Remote Procedure Call Protocol) and REST protocol (Representational State Transfer) used on top of the above protocols.

[0045] It should be noted that the method and system for locating the root cause of an application failure disclosed in the present application can be used in the field of financial technology, and can also be used in any field other than the field of financial technology. The application field of the method and system for locating the root cause of an application failure disclosed in the present application is not limited.

[0046] The details are described through the following embodiments.

[0047] In order to improve the accuracy and efficiency of locating the root cause of application faults, and thus improve the reliability of applications, this embodiment provides an application fault root cause locating method, in which the execution subject is an application fault root cause locating system, and the application fault root cause locating system includes but is not limited to a server, such as Figure 1 As shown, the method specifically includes the following contents:

[0048] Step 101: Obtain the indicator data group of each node corresponding to the target application.

[0049] Specifically, after receiving the fault root cause location trigger instruction sent by the front end, the indicator data group of each node corresponding to the target application can be obtained; the indicator data group can include performance indicator data and monitoring indicator data; the performance indicator data can be one or more, for example, CPU usage, memory usage, disk usage and response time, etc., and the monitoring indicator data can be one or more, for example, monitoring the number of valid alarms, monitoring alarm levels, network timeouts and whether access is successful, etc.; the nodes in this application can refer to the various nodes of the deployment link; the target application can be a distributed application.

[0050] Step 102: applying a preset baseline fitting model, scoring criteria, weight value group and the indicator data group to determine the root cause location score of each node, wherein the baseline fitting model is pre-trained based on an integrated moving average autoregressive model.

[0051] Specifically, the root cause location score of each node can be a score obtained by weighted summing up the performance index score and monitoring index score obtained by applying the preset baseline fitting model, scoring criteria and the index data group of the node; the integrated moving average autoregressive model, namely the ARIMA model, is used to analyze and predict time series data.

[0052] Step 103: Determine the fault root cause node of the target application according to the root cause location score of each node.

[0053] From the above description, it can be seen that the application fault root cause location method provided in this embodiment obtains the indicator data group of each node corresponding to the target application; applies a preset baseline fitting model, scoring criteria, weight value group and the indicator data group to determine the root cause location score of each node, wherein the baseline fitting model is pre-trained based on the integrated moving average autoregressive model; according to the root cause location score of each node, the fault root cause node of the target application is determined, and the baseline fitting model of the application has low complexity and high intelligence, which can improve the accuracy and efficiency of application fault root cause location, thereby improving the reliability of the application.

[0054] In order to further improve the accuracy of locating the root cause of the fault, in one embodiment of the present application, step 103 includes:

[0055] Step 201: Determine the node with the lowest final score as the fault root cause node of the target application; wherein the final score of each node is the sum of the root cause location scores of the node and its child nodes.

[0056] Specifically, multiple nodes with the lowest final scores may be determined as fault root cause nodes; the final score of each node may be the result of summing up the root cause location score of the node and the root cause location scores of each of the child nodes of the node; the final score may be equivalent to the health of the node.

[0057] In order to further reduce the complexity of fault root cause location and improve the efficiency and accuracy of fault root cause location, in one embodiment of the present application, each group of the indicator data group includes: performance indicator data and monitoring indicator data; the preset scoring criteria include: a first scoring standard and a second scoring standard; correspondingly, see Figure 2 , step 102 comprises:

[0058] Step 301: Apply the preset baseline fitting model, the first scoring standard and the performance indicator data of each node to obtain the performance indicator score of the node.

[0059] Specifically, the first scoring criterion is used to determine the performance indicator score of each node; each node may have one or more performance indicator data, such as the current CPU usage, memory usage, disk usage and response time, or the average values ​​of the CPU usage, memory usage, disk usage and response time within a preset time window; the performance indicator score of each node corresponds to the type of performance indicator data.

[0060] Step 302: Apply the second scoring standard and the monitoring indicator data of each node to obtain the monitoring indicator score of the node.

[0061] Specifically, the second scoring criterion is used to determine the monitoring indicator score of each node, and may include a correspondence between preset monitoring indicator data and monitoring indicator scores, which may be set according to actual needs and is not limited in the present application; each node may have one or more monitoring indicator data, for example, the number of effective monitoring alarms, monitoring alarm levels, number of network timeouts, whether access is successful, etc. within a preset time window, which may be within one minute before the current time point; the monitoring indicator score of each node corresponds to the type of monitoring indicator data one by one. Since a node may have multiple monitoring indicator data of the same type, the scores corresponding to the monitoring indicator data of the same type in the same node may be averaged as the monitoring indicator score corresponding to this type of monitoring indicator data in the node.

[0062] For example, the second scoring criteria may include: assigning different scores, i.e., monitoring indicator scores, to the number of effective monitoring alarms according to different alarm magnitudes in the same time window, 0 is 100 points, 1 is 80 points, 2-5 is 60 points, 5-10 is 50 points, and more than 10 is 0 point; the monitoring alarm level may be pre-set by the application, and normal application alarms are graded, with different scores assigned to different alarm levels, i.e., 90 points for a minor level, 80 points for a lighter level, 70 points for a general level, 50 points for a more serious level, and 0 point for a very serious level. If the alarm occurs multiple times in the same time window, the average value of the monitoring alarm level score is used as the corresponding monitoring indicator score; the number of network timeouts is assigned different scores, i.e., monitoring indicator scores, according to the timeout magnitude in the same time window, 0 is 100 points, 1 is 90 points, 2-5 is 60 points, 5-10 is 50 points, and more than 10 is 0 point; whether the access is successful, 100 points for success, and 0 points for failure. If there are multiple accesses in the same time window, the average value of the scores is used as the corresponding monitoring indicator score.

[0063] Step 303: Apply the preset weight value group, performance indicator score and monitoring indicator score to obtain the root cause location score of each node.

[0064] Specifically, the preset weight value group, the performance index score of each node, and the monitoring index score may be applied to perform weighted summation to obtain the root cause location score of the node.

[0065] In order to efficiently and accurately obtain the performance index score, and then use the reliable performance index score to determine the root cause node of the fault, in one embodiment of the present application, step 301 includes:

[0066] Step 401: Apply the preset baseline fitting model and the performance indicator data of each node to obtain a predicted value of the performance indicator of the node.

[0067] Specifically, before step 301, the historical performance indicator data within a preset time range can be used to train the integrated moving average autoregressive model to obtain the baseline fitting model. The preset time range can be set as needed, such as within one month; the performance indicator data can be input into the preset baseline fitting model, and the output result of the baseline fitting model is used as the performance indicator prediction value of the node; the number of performance indicator prediction values ​​and performance indicator data of each node is the same, and corresponds one to one.

[0068] Step 402: Obtain the performance index score of each node according to the first scoring standard and the predicted value of the performance index of the node.

[0069] Specifically, before step 402, the method further includes:

[0070] Step 501: Determine the first scoring standard according to the standard deviation and mean corresponding to the performance indicator prediction values ​​of all nodes.

[0071] Specifically, we can use the standard deviation sigma and mean V pred , determine the first scoring standard: the performance indicator prediction value is V pred -sigma to V pred +sigma range is 100 points, at V pred -2sigma to V pred +2sigma range is 80 points, at V pred -3sigma to V pred +3sigma range is 60 points, at V pred -3sigma to V pred The score outside the +3sigma range is 0. If each node has multiple performance indicator prediction values, the standard deviation and mean corresponding to each performance indicator prediction value can be calculated respectively to determine the first scoring standard.

[0072] In order to improve the accuracy of the weight value group and thus improve the accuracy of fault root cause location, in one embodiment of the present application, before step 102, the following is further included:

[0073] Step 601: Apply multiple groups of historical indicator data groups and a polynomial fitting algorithm to obtain the weight value group.

[0074] Specifically, if there are multiple types of performance indicator data and monitoring indicator data, the weight value group may include the weight values ​​of each type of performance indicator data and monitoring indicator data.

[0075] In order to improve the visualization of fault root cause location and facilitate subsequent fault root cause node processing, in one embodiment of the present application, after step 103, the following steps are further included:

[0076] Step 701: output and display the fault root cause node and corresponding sub-nodes in the form of a topology diagram.

[0077] To further illustrate the present solution, the present application also provides an application example of the fault root cause location method, which is specifically described as follows:

[0078] Step 1: The nodes of the present invention refer to the nodes of the deployment link. The nodes in the deployment link can have a multi-layer sub-node relationship. From the perspective of cloud computing, the nodes include applications, clusters, templates, containers, virtual machines, physical machines, and application services include operating databases, interacting with other application nodes, etc., analyzing historical logs, which include a lot of indicator data, such as CPU usage, number of effective monitoring alarms, monitoring alarm levels, memory usage, disk usage, network timeouts, response time, and whether the access is successful. For each node and service of the application, fields with representative significance are selected as feature values. The feature selection of the node may include: CPU usage, number of effective monitoring alarms, monitoring alarm levels, memory usage, disk usage, and network timeouts, etc. The features selected by the application service node may include: access response time and whether the access is successful, etc.

[0079] Step 2: Use the artificial intelligence algorithm ARIMA to train features such as CPU usage, memory usage, disk usage, and response time. One month of data can be used as training data to establish a baseline fitting model for these features. The baseline fitting model can be used to detect anomalies in various indicators and to compare predicted indicators with real-time indicators.

[0080] Step 3: Based on historical data, fit the scores of feature fields such as the number of effective monitoring alarms, monitoring alarm levels, network timeouts, and whether access is successful, and apply polynomial fitting to obtain the weights of each indicator, that is, apply historical data to fit a formula.

[0081] Specifically, the number of monitored effective alarms is assigned different scores according to the different alarm magnitudes in the same time window, 0 is 100 points, 1 is 80 points, 2-5 is 60 points, 5-10 is 50 points, and more than 10 is 0 point; the monitoring alarm level, the alarm level is set by the application itself, and normal application alarms are graded, with 90 points for minor level, 80 points for lighter level, 70 points for general level, 50 points for more serious level, and 0 point for very serious level; the number of network timeouts is assigned different scores according to the timeout magnitude in the same time window, 0 is 100 points, 1 is 90 points, 2-5 is 60 points, 5-10 is 50 points, and more than 10 is 0 point; whether the access is successful, multiple visits in the same time window are performed, and the average value is calculated, 100 points for success and 0 point for failure.

[0082] Step 4: CPU usage, memory usage, disk usage, response time and other characteristics are overflowed and floated down by a certain number of sigma values, i.e. standard deviations, based on the prediction of the ARIMA algorithm to evaluate the score of each indicator. pred -sigma to V pred +sigma range is 100 points, at V pred -2sigma to V pred+2sigma range is 80 points, at V pred -3sigma to V pred +3sigma range is 60 points, at V pred -3sigma to V pred Outside the +3sigma range, the score is 0.

[0083] Step 5: Based on the above steps and one month of historical data, use polynomial weighting to fit the weights of each feature. The score of each node is equal to the weighted sum of the node's child nodes and the services involved (nodes have child nodes and also call other services).

[0084] Step 6: Based on the above steps and one month of historical data, the weights of the features of each node are fitted using a polynomial algorithm. When the root cause location analysis function is triggered, the root cause location system established in this study will receive an alarm, thereby triggering the execution of the location system. The system will obtain the real-time monitoring and indicator data of the application for analysis, and analyze the weighted sum of each node on the application deployment node. The lower the score, the less healthy and more abnormal it is. Finally, the nodes and services on the minimum weighted distribution link are displayed for application reference.

[0085] From the above description, it can be seen that in order to solve the problem that the root cause location of application failures relies on manual analysis by R&D personnel, which is time-consuming and inefficient, the application failure root cause location method provided by this application example is based on application node monitoring data and log data, and uses artificial intelligence algorithms to evaluate the health of each node and service of the application. The weight of each node and service is trained based on the contribution of each node and service to the overall application, and the weighted health is used to locate the root cause of the failure, which can improve the accuracy and efficiency of locating the root cause of application failures, thereby improving the reliability of the application.

[0086] From the software level, in order to improve the accuracy and efficiency of locating the root cause of application faults, and thus improve the reliability of applications, the present application provides an embodiment of an application fault root cause locating system for implementing all or part of the content of the application fault root cause locating method, see Figure 3 The application fault root cause location system specifically includes the following contents:

[0087] An acquisition module 10 is used to acquire an indicator data group of each node corresponding to the target application;

[0088] A weighted summation module 20 is used to apply a preset baseline fitting model, a scoring criterion, a weight value group and the indicator data group to determine the root cause location score of each node, wherein the baseline fitting model is pre-trained based on an integrated moving average autoregressive model;

[0089] The determination module 30 is used to determine the fault root cause node of the target application according to the root cause location score of each node.

[0090] The embodiment of the application fault root cause locating system provided in this specification can be specifically used to execute the processing flow of the embodiment of the above-mentioned application fault root cause locating method. Its functions are not repeated here, and reference can be made to the detailed description of the embodiment of the above-mentioned application fault root cause locating method.

[0091] In order to further illustrate the present solution, the present application also provides an application example of an application fault root cause location system. In the application example, the application fault root cause location system includes five parts: a data collection module, an offline modeling and analysis module, an online real-time analysis module, a data storage module, and a platform display module. The specific description is as follows:

[0092] The data collection module and data storage module can be developed using SpringBoot projects, made into images and deployed in a K8s cluster for real-time operation. They are used to obtain monitoring and indicator data from the Kafka distributed publish-subscribe message system in real time, and are stored in the ElasticSearch search server after data cleaning and preprocessing. At the same time, the application fault root cause location system will obtain alarm data from the alarm system in real time, and will automatically trigger the fault root cause location system when the alarm information is obtained.

[0093] The offline modeling and analysis module is mainly based on machine learning algorithms. It uses one month's worth of stock data to train the model and weights, and builds a dynamic intelligent fault location model. The functions achieved by this intelligent fault location model are equivalent to the functions achieved by the formula obtained by applying the above-mentioned polynomial fitting and the baseline fitting model.

[0094] When the online fault root cause location module receives an alarm message, it will obtain the training data required by the model from ElasticSearch. The data can be one month's data, including monitoring data and indicator data. The obtained data will be preprocessed and feature processed before being passed to the model for prediction. At the same time, the weight value of each feature value trained during offline training is obtained from the database, which is equivalent to the weight value in the formula obtained by applying the polynomial fitting above. Then, the weighted sum of each feature value is calculated, and the health of each parent node is calculated using the weighted sum and stored in ElasticSearch.

[0095] The data storage module is used to store metadata and the health value of each node, including application, cluster, template, container, virtual machine, physical machine, application service and other nodes. The characteristics of the nodes involved include CPU usage, number of effective monitoring alarms, monitoring alarm level, memory usage, disk usage, number of network timeouts, etc. The characteristics of application service nodes include: access response time, whether the access is successful, etc. Metadata is retained for one month, and the positioning result value can be retained for one week.

[0096] The platform display module is used when the application is displayed on the front end. When a time period is selected for viewing (the default value is the time of the latest alarm), the background code obtains the metadata and positioning nodes in the time period selected by the application from ElasticSearch in real time and displays them in the form of a topology map. Red indicates faulty nodes, green indicates healthy nodes, and each node is identified by a health score.

[0097] In combination with the above application fault root cause location system, the present application also provides an application example of application fault root cause location, such as Figure 4 The specific description is as follows:

[0098] S01: Historical data storage (ElasticSearch); that is, historical data is stored in ElasticSearch through the data collection interface.

[0099] S02: Model offline training.

[0100] S03: Offline parameter storage.

[0101] S04: Online data storage (ElasticSearch); that is, storing online data in ElasticSearch through the data collection interface.

[0102] S05: Online real-time fault root cause location.

[0103] S06: Acquisition of alarm data.

[0104] S07: Positioning result storage (ElasticSearch).

[0105] S08: Front desk display.

[0106] From the above description, it can be seen that the application fault root cause location method and system provided by the present application can improve the accuracy and efficiency of application fault root cause location, thereby improving the reliability of the application; it can solve the problem that the current application fault root cause location method relies on manual analysis by R&D personnel, which is time-consuming and inefficient. Its advantages are as follows: it can automatically obtain monitoring data and performance indicator data in real time, and perform intelligent root cause location based on these data to avoid high delays caused by data transmission between different teams, and the intelligent model based on historical data provides multiple candidate fault root cause points, and the root cause location accuracy is high; the model used has low complexity and the root cause location time is fast.

[0107] From a hardware perspective, in order to improve the accuracy and efficiency of locating the root cause of an application fault, and thus improve the reliability of the application, the present application provides an embodiment of an electronic device for implementing all or part of the content of the method for locating the root cause of an application fault. The electronic device specifically includes the following content:

[0108] A processor, a memory, a communications interface and a bus; wherein the processor, the memory and the communications interface communicate with each other through the bus; the communications interface is used to implement information transmission between the application fault root cause location system and related devices such as user terminals; the electronic device can be a desktop computer, a tablet computer and a mobile terminal, etc., but the present embodiment is not limited thereto. In the present embodiment, the electronic device can be implemented with reference to the embodiments for implementing the application fault root cause location method and the embodiments for implementing the application fault root cause location system, and the contents thereof are incorporated herein, and the repeated parts are not repeated.

[0109] Figure 5 FIG. 9 is a schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Figure 5 As shown, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is worth noting that Figure 5 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0110] In one or more embodiments of the present application, the application fault root cause location function may be integrated into the central processor 9100. The central processor 9100 may be configured to perform the following control:

[0111] Step 101: Obtain the indicator data group of each node corresponding to the target application.

[0112] Step 102: applying a preset baseline fitting model, scoring criteria, weight value group and the indicator data group to determine the root cause location score of each node, wherein the baseline fitting model is pre-trained based on an integrated moving average autoregressive model.

[0113] Step 103: Determine the fault root cause node of the target application according to the root cause location score of each node.

[0114] It can be seen from the above description that the electronic device provided by the embodiments of the present application can improve the accuracy and efficiency of locating the root cause of application failures, thereby improving the reliability of the application.

[0115] In another embodiment, the application fault root cause locating system may be configured separately from the central processor 9100. For example, the application fault root cause locating system may be configured as a chip connected to the central processor 9100, and the application fault root cause locating function may be implemented under the control of the central processor.

[0116] like Figure 5 As shown, the electronic device 9600 may also include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Figure 5 In addition, the electronic device 9600 may also include Figure 5 For components not shown, reference may be made to the prior art.

[0117] like Figure 5 As shown, the central processing unit 9100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor device and / or logic device. The central processing unit 9100 receives input and controls the operation of various components of the electronic device 9600.

[0118] The memory 9140 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. The above-mentioned information related to the failure may be stored, and a program for executing the relevant information may also be stored. The CPU 9100 may execute the program stored in the memory 9140 to implement information storage or processing, etc.

[0119] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display may be, for example, an LCD display, but is not limited thereto.

[0120] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142, which is used to store application programs and function programs or processes for executing the operation of the electronic device 9600 through the central processor 9100.

[0121] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0122] The communication module 9110 is a transmitter / receiver 9110 that sends and receives signals via an antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0123] Based on different communication technologies, multiple communication modules 9110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless LAN module, etc. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby realizing a common telecommunication function. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processor 9100, so that recording can be performed on the local machine through the microphone 9132, and the sound stored on the local machine can be played through the speaker 9131.

[0124] It can be seen from the above description that the electronic device provided by the embodiments of the present application can improve the accuracy and efficiency of locating the root cause of application failures, thereby improving the reliability of the application.

[0125] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the method for locating the root cause of an application fault in the above embodiment. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, all the steps of the method for locating the root cause of an application fault in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0126] Step 101: Obtain the indicator data group of each node corresponding to the target application.

[0127] Step 102: applying a preset baseline fitting model, scoring criteria, weight value group and the indicator data group to determine the root cause location score of each node, wherein the baseline fitting model is pre-trained based on an integrated moving average autoregressive model.

[0128] Step 103: Determine the fault root cause node of the target application according to the root cause location score of each node.

[0129] It can be seen from the above description that the computer-readable storage medium provided in the embodiments of the present application can improve the accuracy and efficiency of locating the root cause of application failures, thereby improving the reliability of the application.

[0130] In this application, each embodiment of the above method is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. For relevant parts, refer to the partial description of the method embodiment.

[0131] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0132] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0135] Specific embodiments are used in this application to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core idea of ​​this application. At the same time, for those skilled in the art, according to the idea of ​​this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on this application.

Claims

1. A method for locating the root cause of an application failure, characterized in that: include: Obtaining an indicator data group of each node corresponding to the target application, each indicator data group includes: performance indicator data and monitoring indicator data; the performance indicator data includes: at least one of CPU usage, memory usage, disk usage and response time, and the monitoring indicator data includes: at least one of monitoring effective alarm number, monitoring alarm level, network timeout number and access success; Applying a preset baseline fitting model, scoring criteria, weight value group and the indicator data group to determine the root cause location score of each node, wherein the baseline fitting model is pre-trained based on an integrated moving average autoregressive model; Determine the root cause node of the target application according to the root cause location score of each node; The determining the fault root cause node of the target application according to the root cause location score of each node includes: Determine the node with the lowest final score as the fault root cause node of the target application; The final score of each node is the sum of the root cause location scores of the node and its child nodes.

2. The method for locating the root cause of an application failure according to claim 1, characterized in that: The preset scoring criteria include: a first scoring standard and a second scoring standard; Correspondingly, the application of the preset baseline fitting model, scoring criteria, weight value group and the indicator data group to determine the root cause location score of each node includes: Applying the preset baseline fitting model, the first scoring standard and the performance indicator data of each node to obtain a performance indicator score of the node; Applying the second scoring standard and the monitoring indicator data of each node to obtain a monitoring indicator score of the node; The preset weight value group, performance indicator score and monitoring indicator score are applied to obtain the root cause location score of each node.

3. The method for locating the root cause of an application failure according to claim 2, characterized in that: The applying the preset baseline fitting model, the first scoring standard and the performance indicator data of each node to obtain the performance indicator score of the node includes: Applying the preset baseline fitting model and the performance indicator data of each node to obtain a performance indicator prediction value of the node; According to the first scoring criteria and the predicted value of the performance indicator of each node, a performance indicator score of the node is obtained.

4. The method for locating the root cause of an application failure according to claim 3, characterized in that: Before obtaining the performance index score of the node according to the first scoring standard and the predicted performance index value of each node, the method further includes: The first scoring criterion is determined according to the standard deviation and mean corresponding to the performance indicator prediction values ​​of all nodes.

5. The method for locating the root cause of an application failure according to claim 1, characterized in that: Also includes: The weight value group is obtained by applying multiple groups of historical indicator data groups and a polynomial fitting algorithm.

6. The method for locating the root cause of an application failure according to claim 1, characterized in that: After determining the fault root cause node of the target application according to the root cause location score of each node, the method further includes: The fault root cause node and the corresponding sub-nodes are output and displayed in the form of a topology diagram.

7. A system for locating the root cause of an application failure, characterized in that: include: An acquisition module is used to acquire an indicator data group of each node corresponding to the target application, each indicator data group includes: performance indicator data and monitoring indicator data; the performance indicator data includes: at least one of CPU usage, memory usage, disk usage and response time, and the monitoring indicator data includes: at least one of monitoring effective alarm number, monitoring alarm level, network timeout number and access success; A weighted summation module, used to apply a preset baseline fitting model, scoring criteria, a weight value group and the indicator data group to determine the root cause location score of each node, wherein the baseline fitting model is pre-trained based on an integrated moving average autoregressive model; A determination module, configured to determine the root cause node of the target application according to the root cause location score of each node; The determination module is specifically used for: Determine the node with the lowest final score as the fault root cause node of the target application; The final score of each node is the sum of the root cause location scores of the node and its child nodes.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for locating the root cause of an application failure according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed, the method for locating the root cause of an application failure as described in any one of claims 1 to 6 is implemented.