Positioning troubleshooting system based on distributed architecture

Abstract

The invention relates to the technical field of complex system fault positioning, in particular to a distributed architecture-based positioning fault removal system, which comprises a fault identification module, a fault analysis module, a diffusion suppression module and a fusing module, and is characterized in that the fault identification module, the fault analysis module, the diffusion suppression module and the fusing module are arranged, so that the fault removal efficiency is improved. According to the method, a plurality of types of abnormal data are monitored, corresponding suspected fault information is identified, and the information flow direction of the suspected fault information is confirmed to determine a fault source and a fault influence range when a fault occurs finally, so that each related distributed device having the fault is identified effectively, and the fault detection efficiency is improved. And the problem of troubleshooting failure caused by the fact that the equipment which fails before is not processed is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of complex system fault location, and in particular to a location and troubleshooting system based on a distributed architecture. Background Art

[0002] In recent years, with the continuous expansion of corporate business, the number of services provided within the enterprise has increased, and the number of deployed systems has continued to rise. As a result, the complexity of interaction between systems has increased dramatically. Once a problem occurs, it is often necessary to query multiple systems and ask multiple system-related personnel to locate the cause of the failure. This process is both manpower-consuming and time-consuming. If the investment in this area can be reduced, it can save a lot of time for R&D personnel, allowing them to focus on more valuable work.

[0003] Chinese Patent Publication No.: CN118885324B discloses a server system and a method for locating a faulty device, a computer system, a program product, and a storage medium. The method includes: in response to detecting a link failure, triggering a system management interrupt; parsing the advanced error reporting register of the faulty device to determine the fault information of the faulty device; determining the device asset information of the faulty device based on the fault information of the faulty device; in response to the device asset information of the faulty device not containing the silkscreen information of the faulty device, determining the physical location of the faulty device based on the fault information of the faulty device and the allocation relationship table. By implementing the server system disclosed in the embodiment of the application and its method, device, system, computer program product, and readable storage medium for locating a faulty device, the utilization rate of server hardware resources can be greatly improved; the device with PCIe failure in the entire cabinet can be quickly located, the normal operation of the business can be restored in time, and the maintenance pressure of operation and maintenance personnel can be reduced.

[0004] It can be seen that the above invention is difficult to troubleshoot a more complex distributed architecture, and when the system is running, the equipment faults detected are closer to the end, making it difficult to locate and trace the starting point of the fault. Summary of the invention

[0005] To this end, the present invention provides a positioning and troubleshooting system based on a distributed architecture to overcome the problem that it is difficult to troubleshoot a more complex distributed architecture in the prior art, and that when the system is running, the detected equipment faults are closer to the end, making it difficult to locate and trace the starting point of the fault, resulting in the accumulation of system faults, thereby reducing the troubleshooting success rate.

[0006] To achieve the above object, the present invention provides a positioning and troubleshooting system based on a distributed architecture, comprising: The fault identification module collects data of each distributed device according to the collection frequency, and identifies and generates corresponding fault categories and corresponding suspected fault information based on the collected data; A fault analysis module, which responds to the suspected fault information, extracts the information flow characteristics of the upstream and downstream links according to the call information of the distributed device, calculates the fault characterization coefficient in combination with the physical address corresponding to the distributed device and the information flow parameter, and determines the corresponding fault tendency; a diffusion suppression module, which is connected to the fault identification module and the fault analysis module respectively, and adjusts the acquisition frequency, and performs fault prediction and information flow diffusion prediction based on the data of the fault identification module; The fusing module is connected to the diffusion suppression module and is used to calculate the corresponding scope impact index based on the fault prediction result and the information flow diffusion prediction result, and issue a corresponding warning signal.

[0007] Furthermore, the fault analysis module is used to extract the information flow characteristics of the upstream and downstream links, including: Used to identify the link stability in the target interface call to generate several stable links; It is used to track a number of characteristic points in each stable link, and determine whether the corresponding stable link is a continuous call sequence according to the information flow characteristics of each characteristic point; If there is any characteristic point of information flow feature in the stable link, the stable link is determined to be a continuous call sequence; Wherein, the characteristic point is a check code preset in each information; For a single feature point, its corresponding information flow feature includes sequential repetition at a time interval not higher than that corresponding to the acquisition frequency in any continuous call sequence; The link stability includes the packet loss rate and transmission rate of the link.

[0008] Further, the fault identification module includes an address collection unit for collecting target interface addresses, a parameter collection unit for collecting target interface parameters, a load collection unit for collecting target interface loads, and a call collection unit for collecting target interface calls; When the parameter collection unit, the load collection unit or the call collection unit collects corresponding data that is abnormal, the fault identification module generates the suspected fault information.

[0009] Furthermore, the fault analysis module determines the fault tendency according to the comparison result between the fault characterization coefficient and the preset fault characterization coefficient standard threshold, including: If the fault characterization coefficient exceeds the reference fault characterization coefficient standard threshold, the fault analysis module determines that the target interface has a fault tendency; If the fault characterization coefficient does not exceed the reference fault characterization coefficient standard threshold, it is determined that the target interface has no fault tendency.

[0010] Furthermore, the fault analysis module is also used to select the fault characterization coefficient standard threshold, wherein: The fault analysis module selects corresponding fault characterization coefficient standard thresholds within different time ranges.

[0011] Furthermore, the fault analysis module adjusts the acquisition frequency of the fault identification module based on the fault tendency and the fault characterization coefficient, wherein the acquisition frequency is proportional to the fault characterization coefficient.

[0012] Furthermore, the diffusion suppression module performs fault prediction based on the target interface call, including: It is used to extract several abnormal paths in the target interface call and determine the load as the diffusion direction; To compare the address changes of each abnormal path in the adjacent cycle calls collected by the fault identification module at the current collection frequency, determine each address change as a diffusion direction, and determine the diffusion speed of the fault for recording; To predict the address corresponding to the diffusion position of each abnormal path after a predetermined time according to the diffusion direction and diffusion speed; It is used to mark the diffused abnormal path in the target interface call, and connect the peripheral abnormal paths to obtain a fault prediction distribution map; The method is used to calculate each distributed device included in the fault prediction distribution map, and determine each distributed device in the fault prediction distribution map as a fault prediction result.

[0013] Furthermore, the diffusion suppression module predicts the information flow diffusion situation based on the target interface call, including: for extracting a number of information flow points in the target interface call, and determining the interface corresponding to the load as the diffusion direction; To compare the address changes of each information flow point in the adjacent cycle calls collected by the fault identification module at the current collection frequency to determine the diffusion speed of the information flow; To predict the diffusion position of each peripheral information flow point after a predetermined time according to the diffusion direction and the diffusion speed of information flow; Used to mark the peripheral information flow points after diffusion in the target interface call, and connect the peripheral information flow points to obtain a predicted distribution map of information flow diffusion; Calculating the area of ​​the information flow diffusion distribution map, and determining the area of ​​the information flow diffusion prediction distribution map as the information flow diffusion prediction result; The area of ​​the distribution diagram corresponds to a number of distributed devices in the distribution diagram that complete fault information transmission and / or execution.

[0014] Further, for a single distributed device, when each corresponding interface receives data, the distributed device processes the data and transmits the processing result to the next distributed device; The diffusion speed is related to the processing speed of each distributed device.

[0015] Furthermore, the fuse module divides the warning signal level based on the range impact index, wherein: If the scope impact index is greater than the baseline scope impact index standard threshold, it is classified as a high-risk warning signal level; If the range impact index is less than or equal to the benchmark range impact index standard threshold, it is classified as a low-risk warning signal level.

[0016] Compared with the prior art, the beneficial effect of the present invention lies in that, by setting up a fault identification module, a fault analysis module, a diffusion suppression module and a fuse module, several categories of abnormal data are monitored, corresponding suspected fault information is identified, and the information flow direction of the suspected fault information is confirmed to determine the source of the fault and the scope of the fault impact when the fault finally occurs, thereby effectively identifying the relevant distributed devices that have failed, and effectively reducing the problem of troubleshooting failure caused by not handling the equipment that failed earlier.

[0017] Furthermore, by identifying the transmission route, the transmission problems caused by data transmission are determined. At the same time, the abnormal paths that may be caused are determined based on the transmission problems. By setting and monitoring a number of characteristic points, the reliability of the transmission link is evaluated, thereby effectively avoiding troubleshooting failures caused by link problems, thereby effectively improving the accuracy of distributed architecture positioning.

[0018] Furthermore, the fault identification module is used to collect the interface address, interface parameters, interface load and calling method of each distributed device, and the collected and running data of each distributed device are verified. The information of the fault is confirmed based on the verification result, and the transmission path of the fault information is obtained through the transmission direction of the interface. When the fault is confirmed, the transmission direction of the interface can be used to confirm the location of the fault, thereby further improving the accuracy of distributed architecture positioning.

[0019] Furthermore, the distributed devices covered by a single fault are confirmed based on the load generated by the anomaly, and the fault severity of the fault is predicted based on the extent of the anomaly. This effectively avoids the overall failure caused by large-scale distributed equipment failures and effectively improves the problem of difficulty in determining the actual location of the fault when a distributed architecture failure is caused by several devices, thereby further improving the accuracy of distributed architecture positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a structural schematic diagram of the positioning and troubleshooting system of the present invention; Figure 2 This is a schematic diagram of the structure of a fault identification module according to an embodiment of the present invention; Figure 3 A fault prediction distribution diagram of a distributed device according to an embodiment of the present invention; Figure 4 The figure is a schematic diagram of the distribution of the scope affected by the fault according to the embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0022] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0023] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0024] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0025] See also Figure 1 As shown, it is a schematic diagram of the structure of the positioning and troubleshooting system of the present invention, including: The fault identification module collects data of each distributed device according to the collection frequency, and identifies and generates corresponding fault categories and corresponding suspected fault information based on the collected data; The fault analysis module responds to suspected fault information, extracts the information flow characteristics of the upstream and downstream links according to the call information of the distributed device, calculates the fault characterization coefficient based on the physical address corresponding to the distributed device and the information flow parameters, and determines the corresponding fault tendency; A diffusion suppression module is connected to the fault identification module and the fault analysis module respectively, and adjusts the acquisition frequency to perform fault prediction and information flow diffusion prediction based on the data of the fault identification module; The fusing module is connected to the diffusion suppression module and is used to calculate the corresponding scope impact index based on the fault prediction results and the information flow diffusion prediction results, and issue a corresponding warning signal.

[0026] By setting up a fault identification module, a fault analysis module, a diffusion suppression module and a fuse module, several categories of abnormal data are monitored, the corresponding suspected fault information is identified, and the information flow direction of the suspected fault information is confirmed to determine the source of the fault and the scope of the fault when the fault finally occurs, thereby effectively identifying the relevant distributed devices that have failed, and effectively reducing the problem of troubleshooting failure caused by not handling the previously failed equipment.

[0027] Example 1: Collect data such as CPU usage, memory usage, disk I / O, etc. of each server at a certain frequency. When the CPU usage of a server exceeds 90% for multiple consecutive times, the memory usage exceeds 80%, and the disk I / O waiting time increases significantly, it is identified that the server may have a performance bottleneck failure and a suspected failure information is generated.

[0028] In response to suspected fault information, extract the call information of the server in the distributed system, such as which services it provides data for as an upstream, and which services it obtains data from as a downstream, etc., and analyze the information flow characteristics of the upstream and downstream links. Combined with the physical address of the server and information flow parameters such as data transmission rate and packet loss rate, calculate the fault characterization coefficient to determine whether the server's fault tendency is caused by its own hardware aging or unreasonable system configuration.

[0029] Connected to the fault identification module and the fault analysis module, the collection frequency of the server data is adjusted from once per minute to once every 30 seconds according to the fault characterization coefficient determined by the fault tendency, so as to grasp the fault development in a more timely manner. At the same time, fault prediction is performed based on the data of the fault identification module, and the flow and diffusion of information are analyzed. It is predicted that if not handled in time, multiple downstream services that rely on the server may be delayed or unavailable.

[0030] Fuse module: connected to the diffusion suppression module, calculates the corresponding scope impact index based on the fault prediction results and the information flow diffusion prediction results. If it is predicted that the server failure will affect multiple key business services, a high-priority warning signal will be issued to notify the operation and maintenance personnel to take immediate measures, such as restarting the server, adjusting the system configuration or replacing the hardware, to prevent the fault from spreading further.

[0031] In the above embodiment, the acquisition frequency may be 50 Hz.

[0032] Embodiment 2: The voltage, current, power and other data of each distributed power generation equipment, substation equipment, etc. in the power grid are collected at a certain frequency. When the voltage of a substation fluctuates, and the fluctuation amplitude exceeds the set threshold, and the current also changes abnormally, it is identified that the substation may have an electrical fault, and suspected fault information is generated.

[0033] In response to suspected fault information, extract the upstream and downstream link information of the substation in the power grid, such as the power receiving situation from the upstream power generation equipment and the power distribution situation to the downstream users, and analyze the information flow characteristics. Combined with the physical address of the substation and information flow parameters such as line impedance and power factor, calculate the fault characterization coefficient to determine whether the fault is caused by aging of internal components of the equipment or external environmental factors (such as lightning strikes, heavy rains, etc.).

[0034] According to the fault characterization coefficient determined by the fault tendency, the frequency of data collection of the substation is adjusted to monitor the development of the fault more accurately. Fault prediction and information flow diffusion are predicted based on the data of the fault identification module. If not handled in time, it may cause power outages in local areas of the power grid, affecting the normal power consumption of multiple users in the surrounding area.

[0035] The scope impact index is calculated based on the fault prediction results and the information flow and diffusion prediction results. If the power outage is predicted to be wide, an emergency warning signal is issued to notify the power grid dispatching center to take measures, such as adjusting the power grid operation mode, starting the backup power supply, etc., to reduce the impact of the fault on the power grid operation and user power consumption.

[0036] In the above embodiment, the frequency of collection may be 1 minute / time.

[0037] Embodiment 3: The operation data of each distributed automation device on the production line is collected at a set frequency, such as the motion accuracy of the robot arm, the detection data of the sensor, the instruction execution status of the controller, etc. When the motion accuracy of a robot arm is lower than the standard value for many consecutive times, and the material position deviation detected by the sensor increases, it is identified that the robot arm may have a mechanical failure or a sensor failure, and a suspected failure information is generated.

[0038] Fault analysis module: responds to suspected fault information, extracts the call information of the robot arm in the production line, such as the previous and next process equipment in the production process, and analyzes the information flow characteristics of the upstream and downstream links. Combined with the physical address of the robot arm and information flow parameters, such as the real-time and accuracy of data transmission, the fault characterization coefficient is calculated to determine whether the fault is caused by wear of the mechanical structure of the robot arm itself or sensor failure.

[0039] Diffusion suppression module: According to the fault characterization coefficient determined by the fault tendency, the data collection frequency of the robot arm is adjusted to obtain fault-related information in a more timely manner. Fault prediction and information flow diffusion situation prediction are carried out based on the data of the fault identification module. If the analysis is not handled in time, the production rhythm of the entire production line may be disrupted, affecting the normal progress of subsequent processes.

[0040] Fuse module: Calculate the scope impact index based on the fault prediction results and the information flow and diffusion prediction results. If it is predicted that the production line will be shut down on a large scale due to the fault, a high-risk warning signal will be issued to notify production management personnel to take measures, such as suspending the production line and organizing maintenance personnel to perform emergency repairs, to avoid greater production losses caused by the fault.

[0041] In the above embodiment, the frequency of collection may be 5 minutes per time.

[0042] In implementation, the frequency of acquisition can be determined by the operating frequency of the distributed equipment when it is working, which is generally related to the operating rate of a single process.

[0043] Specifically, the fault analysis module is used to extract the information flow characteristics of the upstream and downstream links, including: Used to identify the link stability in the target interface call to generate several stable links; It is used to track a number of characteristic points in each stable link, and determine whether the corresponding stable link is a continuous call sequence according to the information flow characteristics of each characteristic point; If there is any characteristic point of information flow feature in the stable link, the stable link is determined to be a continuous call sequence; Among them, the characteristic point is the check code preset in each information; For a single feature point, its corresponding information flow characteristics include sequential recurrence at a time interval not higher than the acquisition frequency in any continuous call sequence; Link stability includes the packet loss rate and transmission rate of the link.

[0044] By identifying the transmission route, we can determine the transmission problems caused by data transmission. At the same time, we can determine the abnormal paths that may be caused based on the transmission problems. By setting and monitoring a number of feature points, we can evaluate the reliability of the transmission link, thereby effectively avoiding troubleshooting failures caused by link problems, thereby effectively improving the accuracy of distributed architecture positioning.

[0045] See also Figure 2As shown, it is a schematic diagram of the structure of a fault identification module according to an embodiment of the present invention, and the fault identification module includes an address collection unit for collecting target interface addresses, a parameter collection unit for collecting target interface parameters, a load collection unit for collecting target interface loads, and a call collection unit for collecting target interface calls; When the parameter collection unit, the load collection unit or the call collection unit collects corresponding data and an abnormality occurs, the fault identification module generates suspected fault information.

[0046] The fault identification module is used to collect the interface address, interface parameters, interface load and calling method of each distributed device, and the collected and running data of each distributed device are verified. The information of the fault is confirmed based on the verification result, and the transmission path of the fault information is obtained through the transmission direction of the interface. When the fault is confirmed, the transmission direction of the interface can be used to confirm the location of the fault, thereby further improving the accuracy of distributed architecture positioning.

[0047] Specifically, the fault analysis module determines the fault tendency according to the comparison result between the fault characterization coefficient and the preset fault characterization coefficient standard threshold, including: If the fault characterization coefficient exceeds the standard threshold of the benchmark fault characterization coefficient, the fault analysis module determines that the target interface has a fault tendency; If the fault characterization coefficient does not exceed the standard threshold of the benchmark fault characterization coefficient, it is determined that the target interface has no fault tendency.

[0048] Specifically, the fault analysis module is also used to select a standard threshold value of the fault characterization coefficient, where: The fault analysis module selects corresponding fault characterization coefficient standard thresholds within different time ranges.

[0049] Specifically, the fault analysis module adjusts the acquisition frequency of the fault identification module based on the fault tendency and the fault characterization coefficient, wherein the acquisition frequency is proportional to the fault characterization coefficient.

[0050] Specifically, the diffusion suppression module performs fault prediction based on target interface calls, including: It is used to extract several abnormal paths in the target interface call and determine the load as the diffusion direction; It is used to compare the address changes of each abnormal path in the adjacent cycle calls collected by the fault identification module at the current collection frequency, determine each address change as the diffusion direction, and determine the diffusion speed of the fault for recording; To predict the address corresponding to the diffusion position of each abnormal path after a predetermined time according to the diffusion direction and diffusion speed; It is used to mark the diffused abnormal path in the target interface call and connect the peripheral abnormal paths to obtain the fault prediction distribution map; It is used to calculate each distributed device included in the fault prediction distribution map, and determine each distributed device in the fault prediction distribution map as a fault prediction result.

[0051] See also Figure 3 As shown, it is a fault prediction distribution diagram of a distributed device according to an embodiment of the present invention, which includes 4 data transmission links: (1) Distributed device α→distributed device A1→distributed device ω1→distributed device α; (2) Distributed device α→distributed device A1→distributed device B2→distributed device ω2→distributed device α; (3) Distributed device α→distributed device A2→distributed device B1→distributed device ω2→distributed device α; (4) Distributed device α→distributed device A2→distributed device B2→distributed device ω2→distributed device α; In the above transmission links, the distributed device α, the distributed device A1 and the distributed device A2 involve no less than two different transmission links at the rear end of their transmission links. It is not difficult to see that when the above distributed devices fail, their fault prediction distribution diagrams will involve a large number of corresponding distributed devices; The distributed devices B1 and B2 involve only one transmission link at the rear end of their transmission links. When the distributed devices B1 and B2 fail, the number of distributed devices involved is relatively small.

[0052] In implementation, the above-mentioned means can be used to quickly predict the corresponding fault prediction distribution map.

[0053] Specifically, the diffusion suppression module predicts the information flow diffusion based on the target interface call, including: It is used to extract several information flow points in the target interface call and determine the interface corresponding to the load as the diffusion direction; To compare the address changes of each information flow point in the adjacent cycle calls collected by the fault identification module at the current collection frequency to determine the diffusion speed of the information flow; To predict the diffusion position of each peripheral information flow point after a predetermined time according to the diffusion direction and the diffusion speed of information flow; It is used to mark the peripheral information flow points after diffusion in the target interface call, and connect the peripheral information flow points to obtain the predicted distribution map of information flow diffusion; To calculate the area of ​​the information flow diffusion distribution map, and determine the area of ​​the information flow diffusion prediction distribution map as the information flow diffusion prediction result; The area of ​​the distribution diagram corresponds to a number of distributed devices in the distribution diagram that complete fault information transmission and / or execution.

[0054] The distributed devices covered by a single fault are confirmed based on the load generated by the anomaly, and the fault severity of the fault is predicted based on the extent of the anomaly. This effectively avoids the overall failure caused by large-scale distributed equipment failures. It also effectively improves the problem of difficulty in determining the actual location of the fault when a distributed architecture failure is caused by several devices, thereby further improving the accuracy of distributed architecture positioning.

[0055] Specifically, for a single distributed device, when each of its corresponding interfaces receives data, the distributed device processes the data and transmits the processing result to the next distributed device; The diffusion speed is related to the processing speed of each distributed device.

[0056] Specifically, the fuse module divides the warning signal level based on the scope impact index, where: If the scope impact index is greater than the baseline scope impact index standard threshold, it is classified as a high-risk warning signal level; If the range impact index is less than or equal to the benchmark range impact index standard threshold, it is classified as a low-risk warning signal level.

[0057] See also Figure 4 As shown, it is a schematic diagram of the distribution of the scope affected by the fault in the embodiment of the present invention. In the figure, when the distributed device A2 fails, the distributed device B2, the distributed device B1 and the distributed device ω2 are all affected; On this basis, when it is identified that the distributed device ω2 has a fault and the distributed device A2 has a suspected fault, it can be located that the impact range of the fault includes the above range.

[0058] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0059] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A positioning and troubleshooting system based on a distributed architecture, characterized in that: include: A fault identification module is used to collect data from each distributed device according to the collection frequency, and to identify and generate corresponding fault categories and corresponding suspected fault information based on the collected data; A fault analysis module, which responds to the suspected fault information, is used to extract the information flow characteristics of the upstream and downstream links according to the call information of the distributed device, calculate the fault characterization coefficient in combination with the physical address corresponding to the distributed device and the information flow parameter, and determine the corresponding fault tendency; a diffusion suppression module, which is connected to the fault identification module and the fault analysis module respectively, and adjusts the acquisition frequency, and performs fault prediction and information flow diffusion prediction based on the data of the fault identification module; The fusing module is connected to the diffusion suppression module and is used to calculate the corresponding scope impact index based on the fault prediction result and the information flow diffusion prediction result, and issue a corresponding warning signal.

2. The distributed architecture-based positioning and troubleshooting system according to claim 1, characterized in that: The fault analysis module is used to extract the information flow characteristics of the upstream and downstream links, including: Used to identify the link stability in the target interface call to generate several stable links; It is used to track a number of characteristic points in each stable link, and determine whether the corresponding stable link is a continuous call sequence according to the information flow characteristics of each characteristic point; If there is any characteristic point of information flow feature in the stable link, the stable link is determined to be a continuous call sequence; Wherein, the characteristic point is a check code preset in each information; For a single feature point, its corresponding information flow feature includes sequential repetition at a time interval not higher than that corresponding to the acquisition frequency in any continuous call sequence; The link stability includes the packet loss rate and transmission rate of the link.

3. The distributed architecture-based positioning and troubleshooting system according to claim 2, characterized in that: The fault identification module includes an address collection unit for collecting target interface addresses, a parameter collection unit for collecting target interface parameters, a load collection unit for collecting target interface loads, and a call collection unit for collecting target interface calls; When the parameter collection unit, the load collection unit or the call collection unit collects corresponding data that is abnormal, the fault identification module generates the suspected fault information.

4. The distributed architecture-based positioning and troubleshooting system according to claim 3, characterized in that: The fault analysis module determines the fault tendency according to the comparison result between the fault characterization coefficient and the preset fault characterization coefficient standard threshold, including: If the fault characterization coefficient exceeds the reference fault characterization coefficient standard threshold, the fault analysis module determines that the target interface has a fault tendency; If the fault characterization coefficient does not exceed the reference fault characterization coefficient standard threshold, it is determined that the target interface has no fault tendency.

5. The distributed architecture-based positioning and troubleshooting system according to claim 4, characterized in that: The fault analysis module is also used to select the fault characterization coefficient standard threshold, wherein: The fault analysis module selects corresponding fault characterization coefficient standard thresholds within different time ranges.

6. The distributed architecture-based troubleshooting system according to claim 5, characterized in that: The fault analysis module adjusts the acquisition frequency of the fault identification module based on the fault tendency and the fault characterization coefficient, wherein: The acquisition frequency is proportional to the fault characterization coefficient.

7. The distributed architecture-based positioning and troubleshooting system according to claim 6, characterized in that: The diffusion suppression module performs fault prediction based on target interface calls, including: It is used to extract several abnormal paths in the target interface call and determine the load as the diffusion direction; To compare the address changes of each abnormal path in the adjacent cycle calls collected by the fault identification module at the current collection frequency, determine each address change as a diffusion direction, and determine the diffusion speed of the fault for recording; To predict the address corresponding to the diffusion position of each abnormal path after a predetermined time according to the diffusion direction and diffusion speed; It is used to mark the diffused abnormal path in the target interface call, and connect the peripheral abnormal paths to obtain a fault prediction distribution map; The method is used to calculate each distributed device included in the fault prediction distribution map, and determine each distributed device in the fault prediction distribution map as a fault prediction result.

8. The distributed architecture-based positioning and troubleshooting system according to claim 7, characterized in that: The diffusion suppression module predicts the information flow diffusion situation based on the target interface call, include, for extracting a number of information flow points in the target interface call, and determining the interface corresponding to the load as the diffusion direction; To compare the address changes of each information flow point in the adjacent cycle calls collected by the fault identification module at the current collection frequency to determine the diffusion speed of the information flow; To predict the diffusion position of each peripheral information flow point after a predetermined time according to the diffusion direction and the diffusion speed of information flow; Used to mark the peripheral information flow points after diffusion in the target interface call, and connect the peripheral information flow points to obtain a predicted distribution map of information flow diffusion; Calculating the area of ​​the information flow diffusion distribution map, and determining the area of ​​the information flow diffusion prediction distribution map as the information flow diffusion prediction result; The area of ​​the distribution diagram corresponds to a number of distributed devices in the distribution diagram that complete fault information transmission and / or execution.

9. The distributed architecture-based troubleshooting system according to claim 8, characterized in that: For a single distributed device, when each corresponding interface receives data, the distributed device processes the data and transmits the processing result to the next distributed device; The diffusion speed is related to the processing speed of each distributed device.

10. The distributed architecture-based troubleshooting system according to claim 9, characterized in that: The fuse module divides the warning signal level based on the range impact index, wherein: If the scope impact index is greater than the baseline scope impact index standard threshold, it is classified as a high-risk warning signal level; If the range impact index is less than or equal to the benchmark range impact index standard threshold, it is classified as a low-risk warning signal level.

Images