Intelligent error reporting system of server

Abstract

The invention relates to the technical field of equipment management, in particular to a server intelligent error reporting system which comprises a monitoring module used for monitoring server operation key indexes; submodules are arranged in the monitoring module and in the lower level, and each submodule comprises a control unit used for controlling the operation frequency of the monitoring module; the storage unit is used for synchronously running along with the monitoring module, receiving the server running key indexes monitored by the monitoring module, and storing the server running key indexes; the busy weight of the server in each time period is measured through collection of the server operation key indexes and reference of the historical operation indexes, the health of the service state is further predicted according to the server operation key indexes, and the health state prediction result of the server is corrected in combination with the busy weight of the server in each time period. And finally, the state security of the server is judged according to a correction result, so that daily operation management of the server obtains a certain degree of predictive monitoring effect.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment management, and in particular to an intelligent error reporting system for a server. Background Art

[0002] Server management is a key task to ensure stable and efficient operation of the server. It includes hardware maintenance, such as monitoring equipment status and handling failures in a timely manner; software management, such as installing and updating systems and applications. At the same time, it is necessary to optimize performance, allocate resources reasonably, and ensure data security to meet business needs and improve service quality.

[0003] The invention patent with application number 202010110187.6 discloses a method for detecting errors in a server diagnostic system, which is characterized in that it includes the following steps: deploying a monitoring server and connecting the monitoring server to the website where the server diagnostic system publishes information to the outside world; enabling the monitoring server to obtain order information in the website every threshold time: analyzing the order information to calculate error information based on the order information, and judging the logical relationship between a first error threshold and a second error threshold in the monitoring server; in response to the logical relationship being and the error information satisfying the first error threshold and the second error threshold, issuing a warning message to the administrator; in response to the logical relationship being or and the error information satisfying one of the first error threshold or the second error threshold, issuing a warning message to the administrator.

[0004] This application aims to solve the problem that "during the production of servers, a system diagnosis process is required, during which batch errors may occur for the same order. Currently, the method of discovering batch error orders mainly relies on production line personnel to discover them or system diagnosis engineers to continuously query the website where the server diagnosis system releases information. Both methods require personnel to pay continuous attention to production line information, which is time-consuming and labor-intensive, and there is a risk of not discovering problems in a timely manner."

[0005] However, during the daily operation of the server, the probability of server failure errors changes in real time due to changes in usage scenarios and users. If the server's operating status cannot be monitored in real time, it will be impossible to make a series of predictive protection strategies in response to server failure errors.

[0006] Therefore, a server intelligent error reporting system is proposed. Summary of the invention

[0007] In view of the above-mentioned shortcomings of the prior art, the present invention provides a server intelligent error reporting system, which solves the technical problems raised in the above-mentioned background technology.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] A server intelligent error reporting system, comprising:

[0010] A monitoring module is used to monitor the key operating indicators of the server; the monitoring module is provided with submodules inside and below, including: a control unit, used to control the operating frequency of the monitoring module; a storage unit, used to run synchronously with the monitoring module, receive the key operating indicators of the server monitored by the monitoring module, and store the key operating indicators of the server; an analysis module is used to upload the historical operating indicators of the server, and analyze the busy weight of the server in each time period based on the historical operating indicators of the server; a prediction module is used to receive the key operating indicators of the server monitored in the monitoring module, and predict the health of the server status based on the key operating indicators of the server; the prediction module is provided with submodules below, including: a decision unit, used to determine the prediction accuracy of the prediction module when predicting the health of the server status ; A calling unit is used to receive the prediction accuracy decision result in the decision unit, call the key server operation indicators based on the prediction accuracy decision result, and forward it to the prediction module. The prediction module is used to receive the key server operation indicators forwarded by the calling unit to predict the health of the server status; a correction module is used to receive the server status security prediction result in the prediction module and the busy weight of the corresponding time period of the analysis module prediction result, and apply the busy weight to correct the server status security prediction result; a judgment module is used to set a security judgment threshold, synchronously obtain the server status security prediction result that has been corrected in the correction module, and compare the corrected prediction result with the security judgment threshold to determine whether the server has a security problem; a feedback module is used to receive the judgment result in the judgment module and output the judgment result;

[0011] The monitoring module is internally interactively connected to a control unit via a wireless network, the monitoring module is interactively connected to a storage unit at a lower level via a wireless network, the monitoring module is interactively connected to an analysis module and a prediction module via a wireless network, the prediction module is interactively connected to a decision unit and a retrieval unit at a lower level via a wireless network, the prediction module is interactively connected to the storage unit via a wireless network, the prediction module is interactively connected to a correction module and a determination module via a wireless network, and the determination module is interactively connected to a feedback module via a wireless network.

[0012] Furthermore, the key indicators of server operation include: server CPU utilization, load and temperature; server memory utilization and bandwidth utilization; server disk space utilization, I / O utilization and read / write speed; server network bandwidth utilization, number of connections, delay and packet loss rate;

[0013] Before the key indicators of server operation are stored in the storage unit, monitoring timestamp marking is synchronously performed. The storage unit stores the key indicators of server operation separately based on the marking timestamps of the key indicators of server operation.

[0014] Furthermore, the control unit is provided with a monitoring module operation frequency control logic, and the control unit controls the monitoring module to run continuously based on the control logic to perform the monitoring of key indicators of server operation. The monitoring module operation frequency control logic provided in the control unit is expressed as:

[0015] Logic1: The time interval between two consecutive operations of the monitoring module shall not exceed five seconds;

[0016] Logic2: Among the two groups of server operation key indicators that are most recently monitored, if the difference between the indicator values ​​in the latest group of server operation key indicators and the corresponding indicator values ​​in one group of server operation key indicators exceeds ±5%, the monitoring module will run once;

[0017] Among them, the interval time between the initial two operations of the monitoring module is not less than five seconds. When the monitoring module is in operation based on Logic2 control and the monitoring module does not operate for five seconds, the monitoring module is operated based on Logic1 control.

[0018] Furthermore, the server historical operation indicators uploaded in the analysis module correspond to a time domain of no less than seven days, and in the time domain corresponding to the server historical operation indicators uploaded in the analysis module, no operation errors occurred in the server. When the analysis module analyzes the busy weight of each time period of the server, it uses hours as a unit to analyze the busy weight of each hour of the server. The analysis logic is:

[0019]

[0020] Where: ω is the busy weight; n is the total amount of the server's historical operation indicators corresponding to the time domain; is the average CPU usage; is the average memory usage; is the average disk I / O usage; is the average network bandwidth usage;

[0021] in, represents the normalized average CPU usage, average memory usage, average disk I / O usage, and average network bandwidth usage in the same period of the i-th day. Based on the above formula, we have ω1, ω2, ...ω 23 ,ω 24 ,The subscript of each busy weight represents the corresponding time period of the busy weight.

[0022] Furthermore, the decision prediction module in the decision unit operates the prediction accuracy of the server status health, that is, the decision on the number of server operation key indicators to be retrieved. The decision unit is operated by the system user, so that the higher the requirement for the server status health prediction accuracy, the more server operation key indicators to be retrieved. When retrieving the server operation key indicators, the retrieving unit uses all the server operation key indicators collected by the monitoring module once as a group of server operation key indicators.

[0023] Furthermore, the prediction logic for the health of the server status in the prediction module is expressed as:

[0024] S=a×SCPU+b×SMEM+c×SDISK+d×SNET;

[0025] Where: S is the health performance value of the server status; a, b, c, d are weights; S CPU S is the health of the server CPU level; MEM S is the health of the server memory level; DISK S is the health of the server disk layer; NET The health of the server network layer;

[0026] The larger the server health performance value S is, the healthier the server is, and vice versa. The weights a, b, c, and d are customized by the system user, and the sum of the weights a, b, c, and d is 1, and a≥b≥d>c.

[0027] The calculation formula for the server health level at each level in the server health prediction logic is:

[0028]

[0029] Where: U CPU is the CPU usage; L CPU is the server load; C is the number of server cores; T CPU is the current temperature of the CPU; T max 、T min The highest and lowest temperatures for safe operation of the CPU; U MEM is the memory usage; is the memory bandwidth usage; is the disk space usage; U IO is the disk I / O usage; The current average disk read and write speed; The maximum read and write speed of the disk; is the network bandwidth utilization rate; C NET is the number of connections; C max , C minThe maximum and minimum values ​​of the allowed range of the number of connections; D NET Delay; D max , D min is the maximum and minimum value of the allowed delay range; P NET is the packet loss rate.

[0030] Furthermore, the correction operation for the server status security prediction result in the correction module is:

[0031]

[0032] Where: S′ is the corrected server health performance value; q is the total amount of key server operation indicators used in server health prediction for the corresponding period; ω p is the corresponding busy weight of the p-th time period;

[0033] in, Express Seeking the average.

[0034] Furthermore, the feedback module is connected to a mobile computer held by a system user via a wireless network. The feedback module transmits the determination result of the determination module and the corrected server status security prediction result in the correction module to the mobile computer, and the system user reads the determination result and the corrected server status security prediction result on the mobile computer.

[0035] Compared with the known public technology, the technical solution provided by the present invention has the following beneficial effects:

[0036] The present invention provides a server intelligent error reporting system. During operation, the system measures the busy weight of each time period of the server by collecting key operating indicators of the server and referring to historical operating indicators. The health of the service status is further predicted based on the key operating indicators of the server. The server health status prediction result is corrected in combination with the busy weight of each time period of the server. Finally, the server status security is determined based on the corrected result, so that the daily operation management of the server can obtain a certain degree of predictive monitoring effect. Based on the monitoring information of the system, a predictive protection strategy is configured for the server to ensure the long-term stable operation of the service. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 The figure is a structural diagram of a server intelligent error reporting system. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] The present invention will be further described below in conjunction with the embodiments.

[0041] Embodiment 1:

[0042] A server intelligent error reporting system of this embodiment, such as Figure 1 As shown, including:

[0043] Monitoring module, used to monitor key indicators of server operation;

[0044] The key indicators of server operation include: server CPU usage, load and temperature; server memory usage and bandwidth usage; server disk space usage, I / O usage and read / write speed; server network bandwidth usage, number of connections, delay and packet loss rate. The monitoring module is internally and sub-modules are provided, including:

[0045] A control unit, used to control the operating frequency of the monitoring module;

[0046] The storage unit is used to run synchronously with the monitoring module, receive the key indicators of server operation monitored by the monitoring module, and store the key indicators of server operation;

[0047] Before the key indicators of server operation are stored in the storage unit, monitoring timestamps are synchronously performed, and the storage unit stores the key indicators of server operation separately based on the timestamps of the key indicators of server operation;

[0048] The analysis module is used to upload the historical operation indicators of the server and analyze the busy weight of the server in each period based on the historical operation indicators of the server;

[0049] The time domain corresponding to the historical operation indicators of the server uploaded in the analysis module is not less than seven days, and the server has no operation errors in the time domain corresponding to the historical operation indicators of the server uploaded in the analysis module. When the analysis module analyzes the busy weight of the server in each period, it uses hours as a unit to analyze the busy weight of the server in each hour. The analysis logic is:

[0050]

[0051] Where: ω is the busy weight; n is the total amount of the server's historical operation indicators corresponding to the time domain; is the average CPU usage; is the average memory usage; is the average disk I / O usage; is the average network bandwidth usage;

[0052] in, represents the normalized average CPU usage, average memory usage, average disk I / O usage, and average network bandwidth usage in the same period of the i-th day. Based on the above formula, we have ω1, ω2, ...ω 23 ,ω 24 , the subscript of each busy weight represents the corresponding time period of the busy weight;

[0053] The prediction module is used to receive the key operating indicators of the server monitored by the monitoring module and predict the health of the server status based on the key operating indicators of the server;

[0054] The prediction module is provided with submodules at the lower level, including:

[0055] The decision unit is used to determine the prediction accuracy of the server status health when the decision prediction module predicts the server status health;

[0056] A calling unit is used to receive the prediction accuracy decision result in the decision unit, call the key indicators of server operation based on the prediction accuracy decision result, and forward it to the prediction module. The prediction module predicts the health of the server status based on the key indicators of server operation forwarded by the calling unit;

[0057] Among them, the operation of the prediction accuracy of the server status health by the decision prediction module in the decision unit, that is, the decision on the number of server operation key indicators to be retrieved, the decision unit is operated by the system end user, so that the higher the server status health prediction accuracy requirement, the more server operation key indicators to be retrieved, and when the retrieval unit retrieves the server operation key indicators, all the server operation key indicators collected by the monitoring module once are used as a group of server operation key indicators;

[0058] The prediction logic for server health in the prediction module is expressed as:

[0059] S=a×SCPU+b×SMEM+c×SDISK+d×SNET;

[0060] Where: S is the health performance value of the server status; a, b, c, d are weights; SCPU S is the health of the server CPU level; MEM S is the health of the server memory level; DISK S is the health of the server disk layer; NET The health of the server network layer;

[0061] The larger the server health performance value S is, the healthier the server is, and vice versa. The weights a, b, c, and d are customized by the system user, and the sum of the weights a, b, c, and d is 1, and a≥b≥d>c.

[0062] The calculation formula for the server health level at each level in the server health prediction logic is:

[0063]

[0064] Where: U CPU is the CPU usage; L CPU is the server load; C is the number of server cores; T CPU is the current temperature of the CPU; T max 、T min The highest and lowest temperatures for safe operation of the CPU; U MEM is the memory usage; is the memory bandwidth usage; is the disk space usage; U IO is the disk I / O usage; The current average disk read and write speed; The maximum read and write speed of the disk; is the network bandwidth utilization rate; C NET is the number of connections; C max , C min The maximum and minimum values ​​of the allowed range of the number of connections; D NET Delay; D max , D min is the maximum and minimum value of the allowed delay range; P NET is the packet loss rate;

[0065] A correction module is used to receive the server status security prediction result in the prediction module and the busy weight of the time period corresponding to the prediction result of the analysis module, and apply the busy weight to correct the server status security prediction result;

[0066] The correction operation for the server status security prediction result in the correction module is:

[0067]

[0068] Where: S′ is the corrected server health performance value; q is the total amount of key server operation indicators used in server health prediction for the corresponding period; ω p is the corresponding busy weight of the p-th time period;

[0069] in, Express ;

[0070] The determination module is used to set a security determination threshold, synchronously obtain the security prediction result of the server status corrected in the correction module, and determine whether the server has a security problem based on the comparison between the corrected prediction result and the security determination threshold;

[0071] A feedback module is used to receive the determination result from the determination module and output the determination result;

[0072] The monitoring module is internally interactively connected to a control unit via a wireless network, the monitoring module is interactively connected to a storage unit at a lower level via a wireless network, the monitoring module is interactively connected to an analysis module and a prediction module via a wireless network, the prediction module is interactively connected to a decision unit and a retrieval unit at a lower level via a wireless network, the prediction module is interactively connected to the storage unit via a wireless network, the prediction module is interactively connected to a correction module and a determination module via a wireless network, and the determination module is interactively connected to a feedback module via a wireless network.

[0073] In this embodiment, the monitoring module runs to monitor the key indicators of server operation, the control unit synchronously controls the operating frequency of the monitoring module, the storage unit runs synchronously with the monitoring module, receives the key indicators of server operation monitored by the monitoring module, and stores the key indicators of server operation. The analysis module is post-operated to upload the historical operating indicators of the server, and the busy weight of the server in each period is analyzed based on the historical operating indicators of the server. The prediction module further receives the key indicators of server operation monitored in the monitoring module, and predicts the health of the server state based on the key indicators of server operation. The decision unit makes a real-time decision on the prediction accuracy of the prediction module when predicting the health of the server state. The retrieval unit receives the prediction accuracy decision result in the decision unit in real time, retrieves the key indicators of server operation based on the prediction accuracy decision result, and forwards it to the prediction module.

[0074] At this time, the prediction module predicts the health of the server status based on the key server operation indicators forwarded by the call-receiving unit. The correction module then receives the server status security prediction result in the prediction module and the busy weight of the corresponding time period of the analysis module prediction result, and applies the busy weight to correct the server status security prediction result. Finally, the judgment module sets the security judgment threshold, and synchronously obtains the server status security prediction result corrected in the correction module. Based on the comparison between the corrected prediction result and the security judgment threshold, it is determined whether the server has a security problem. The feedback module receives the judgment result in the judgment module and outputs the judgment result.

[0075] Based on the operation of the above system, through the analysis of key indicator information of daily service operation, the server's operating status security is effectively predicted to maintain the server, ensuring that the server backend management users can make more predictive service management work based on the results of system operation output, providing effective guarantee for the long-term and stable operation of the service.

[0076] Example 2

[0077] In terms of specific implementation, based on Example 1, this example refers to Figure 1 A server intelligent error reporting system in Example 1 is further described in detail:

[0078] The control unit is provided with a monitoring module operation frequency control logic. The control unit controls the monitoring module to run continuously based on the control logic to monitor the key indicators of the server operation. The monitoring module operation frequency control logic provided in the control unit is expressed as:

[0079] Logic1: The time interval between two consecutive operations of the monitoring module shall not exceed five seconds;

[0080] Logic2: Among the two groups of server operation key indicators that are most recently monitored, if the difference between the indicator values ​​in the latest group of server operation key indicators and the corresponding indicator values ​​in one group of server operation key indicators exceeds ±5%, the monitoring module will run once;

[0081] Among them, the interval time between the initial two operations of the monitoring module is not less than five seconds. When the monitoring module is in operation based on Logic2 control and the monitoring module does not operate for five seconds, the monitoring module is operated based on Logic1 control.

[0082] Through the above settings, the operating frequency control logic of the monitoring module running application of the system in Example 1 is further limited to ensure the stable and continuous operation of the monitoring module and provide necessary operating data support for the operation of subsequent modules in the system.

[0083] like Figure 1As shown, the feedback module is connected to the mobile computer held by the system end user through a wireless network. The feedback module transmits the determination result of the determination module and the server status security prediction result after correction processing in the correction module to the mobile computer, and the system end user reads the determination result and the server status security prediction result after correction processing on the mobile computer.

[0084] Through the above settings, the operation logic of feeding back the output results of the system operation to the system end user in Example 1 is further limited.

[0085] In summary, during the operation of the system in the above embodiment, the busy weight of the server in each time period is measured by collecting the key indicators of server operation and referring to the historical operation indicators, and the health of the service status is further predicted based on the key indicators of server operation. The server health status prediction result is then corrected in combination with the busy weight of the server in each time period, and finally the server status security is determined based on the corrected result, so that the daily operation management of the server can obtain a certain degree of predictive monitoring effect, and thus, based on the system monitoring information, a predictive protection strategy is configured for the server to ensure the long-term and stable operation of the service.

[0086] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A server intelligent error reporting system, characterized in that: include: Monitoring module, used to monitor key indicators of server operation; The analysis module is used to upload the historical operation indicators of the server and analyze the busy weight of the server in each period based on the historical operation indicators of the server; The prediction module is used to receive the key operating indicators of the server monitored by the monitoring module and predict the health of the server status based on the key operating indicators of the server; A correction module is used to receive the server status security prediction result in the prediction module and the busy weight of the time period corresponding to the prediction result of the analysis module, and apply the busy weight to correct the server status security prediction result; The determination module is used to set a security determination threshold, synchronously obtain the security prediction result of the server status corrected in the correction module, and determine whether the server has a security problem based on the comparison between the corrected prediction result and the security determination threshold; The feedback module is used to receive the determination result in the determination module and output the determination result.

2. A server intelligent error reporting system according to claim 1, characterized in that: The key indicators of server operation include: server CPU usage, load and temperature; server memory usage and bandwidth usage; server disk space usage, I / O usage and read / write speed; server network bandwidth usage, number of connections, delay and packet loss rate. The monitoring module is internally and sub-modules are provided, including: A control unit, used to control the operating frequency of the monitoring module; The storage unit is used to run synchronously with the monitoring module, receive the key indicators of server operation monitored by the monitoring module, and store the key indicators of server operation; Before the key indicators of server operation are stored in the storage unit, monitoring timestamp marking is synchronously performed, and the storage unit stores the key indicators of server operation separately based on the marking timestamps of the key indicators of server operation.

3. A server intelligent error reporting system according to claim 1, characterized in that: The control unit is provided with a monitoring module operation frequency control logic. The control unit controls the monitoring module to run continuously based on the control logic to monitor the key indicators of the server operation. The monitoring module operation frequency control logic provided in the control unit is expressed as: Logic1: The time interval between two consecutive operations of the monitoring module shall not exceed five seconds; Logic2: Among the two groups of server operation key indicators that are most recently monitored, if the difference between the indicator values ​​in the latest group of server operation key indicators and the corresponding indicator values ​​in one group of server operation key indicators exceeds ±5%, the monitoring module will run once; Among them, the interval time between the initial two operations of the monitoring module is not less than five seconds. When the monitoring module is in operation based on Logic2 control and the monitoring module does not operate for five seconds, the monitoring module is operated based on Logic1 control.

4. A server intelligent error reporting system according to claim 1, characterized in that: The time domain corresponding to the historical operation indicators of the server uploaded in the analysis module is not less than seven days, and the server has no operation errors in the time domain corresponding to the historical operation indicators of the server uploaded in the analysis module. When the analysis module analyzes the busy weight of the server in each period, it uses hours as a unit to analyze the busy weight of the server in each hour. The analysis logic is: Where: ω is the busy weight; n is the total amount of the server's historical operation indicators corresponding to the time domain; is the average CPU usage; is the average memory usage; is the average disk I / O usage; is the average network bandwidth usage; in, represents the normalized average CPU usage, average memory usage, average disk I / O usage, and average network bandwidth usage in the same period of the i-th day. Based on the above formula, we have ω1, ω2, ...ω 23 ,ω 24 ,The subscript of each busy weight represents the corresponding time period of the busy weight.

5. A server intelligent error reporting system according to claim 1, characterized in that: The prediction module is provided with submodules at the lower level, including: The decision unit is used to determine the prediction accuracy of the server status health when the decision prediction module predicts the server status health; A calling unit is used to receive the prediction accuracy decision result in the decision unit, call the key indicators of server operation based on the prediction accuracy decision result, and forward it to the prediction module. The prediction module predicts the health of the server status based on the key indicators of server operation forwarded by the calling unit; Among them, the decision prediction module in the decision unit operates the prediction accuracy of the server status health, that is, the decision on the number of server operation key indicators to be retrieved. The decision unit is operated by the system end user, so that the higher the requirement for the server status health prediction accuracy, the more server operation key indicators to be retrieved. When retrieving the server operation key indicators, the retrieving unit uses all the server operation key indicators collected by the monitoring module once as a group of server operation key indicators.

6. A server intelligent error reporting system according to claim 1, characterized in that: The prediction logic for server health in the prediction module is expressed as: S=a×SCPU+b×SMEM+c×SDISK+d×SNET; Where: S is the health performance value of the server status; a, b, c, d are weights; S CPU S is the health of the server CPU level; MEM S is the health of the server memory level; DISK S is the health of the server disk layer; NET The health of the server network layer; Among them, the larger the server status health performance value S is, the healthier the server status is, and vice versa, the unhealthier the server status is. The values ​​of weights a, b, c, and d are customized by system users and the sum of weights a, b, c, and d is 1, and a≥b≥d>c.

7. A server intelligent error reporting system according to claim 6, characterized in that: The calculation formula for the server health level at each level in the server health prediction logic is: Where: U CPU is the CPU usage; L CPU is the server load; C is the number of server cores; T CPU is the current temperature of the CPU; T max , T min The highest and lowest temperatures for safe operation of the CPU; U MEM is the memory usage; is the memory bandwidth usage; is the disk space usage; U IO is the disk I / O usage; The current average disk read and write speed; The maximum read and write speed of the disk; is the network bandwidth utilization rate; C NET is the number of connections; C max , C min The maximum and minimum values ​​of the allowed range of the number of connections; D NET Delay; D max , D min is the maximum and minimum value of the allowed delay range; P NET is the packet loss rate.

8. A server intelligent error reporting system according to claim 1, characterized in that: The correction operation for the server status security prediction result in the correction module is: Where: S′ is the corrected server health performance value; q is the total amount of key server operation indicators used in server health prediction for the corresponding period; ω p is the corresponding busy weight of the p-th time period; in, Express Seeking the average.

9. A server intelligent error reporting system according to claim 1, characterized in that: The feedback module is connected to a mobile computer held by a system user via a wireless network. The feedback module transmits the determination result of the determination module and the server status security prediction result after correction processing in the correction module to the mobile computer. The system user reads the determination result and the server status security prediction result after correction processing on the mobile computer.

10. A server intelligent error reporting system according to claim 1, characterized in that: The monitoring module is internally interactively connected to a control unit via a wireless network, the monitoring module is interactively connected to a storage unit at a lower level via a wireless network, the monitoring module is interactively connected to an analysis module and a prediction module via a wireless network, the prediction module is interactively connected to a decision unit and a retrieval unit at a lower level via a wireless network, the prediction module is interactively connected to the storage unit via a wireless network, the prediction module is interactively connected to a correction module and a determination module via a wireless network, and the determination module is interactively connected to a feedback module via a wireless network.

Images