Abnormality positioning method, device, equipment and medium

By identifying the process with the highest CPU occupancy rate in the BMC system and comparing it with the normal historical processes, the performance degradation caused by excessive CPU occupancy rate in the BMC system is solved, and accurate positioning of abnormal processes and rapid problem investigation are achieved.

CN118916200APending Publication Date: 2024-11-08NINGCHANG INFORMATION TECH (HANGZHOU) CO LTD +1
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202410990366.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

When monitoring servers, the CPU usage rate of existing BMC systems leads to degradation of system performance, and existing methods are difficult to accurately locate abnormal locations, resulting in inaccurate positioning.

Method used

By obtaining the CPU occupancy rate of each process in the BMC system, identifying the first N processes with the highest CPU occupancy rate, and comparing it with the historical normal processes, determining the abnormal process to ensure the accuracy of abnormal detection.

Benefits of technology

It realizes accurate positioning of abnormal processes in the BMC system, reduces problem troubleshooting time, and improves system performance and user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118916200A_ABST
    Figure CN118916200A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides an exception positioning method, device and equipment and a medium, and aims to solve the problem of inaccurate exception positioning in the prior art. The method comprises the following steps: acquiring a first CPU (Central Processing Unit) occupancy rate of each process in a to-be-monitored BMC (Baseboard Management Controller) system within a first preset time; according to the method, the first N target processes with the highest first CPU occupancy rate in the to-be-monitored BMC system are identified, the first N historical target normal processes with the highest CPU occupancy rate corresponding to the to-be-monitored BMC system are obtained, and the target processes different from the first N historical target normal processes in the first N target processes are determined as the abnormal processes, so that the abnormal processes in the BMC system can be accurately positioned, and the accuracy of the abnormal processes in the BMC system is improved. The accuracy of anomaly detection is ensured, meanwhile, research and development personnel can locate problems timely and quickly, and time consumption for troubleshooting is reduced.
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 an abnormality positioning method, device, equipment and medium. Background Art

[0002] In modern data centers and information technology (IT) infrastructure, remote monitoring and management of servers is critical. To achieve remote monitoring and management of servers, servers are usually equipped with a baseboard management controller (BMC). BMC is used to enable administrators to remotely monitor the status of the server, perform hardware diagnostics, and even remotely start or restart the server in some cases.

[0003] However, in the process of developing BMC systems and implementing software functions, developers tend to focus on the realization of functional integrity, and often ignore the consumption of the BMC system's own central processing unit (CPU) resources. However, since CPU resources are limited, if the CPU usage of the BMC system is too high, it will lead to system performance degradation, such as: a service responds too slowly, timeouts, and other problems. Even when the CPU usage and load are continuously too high, it will cause the entire system to hang, causing the remote management function of the server to fail.

[0004] To avoid these problems, BMC system developers need to take into account the consumption of CPU resources when designing and implementing software functions. In the official version of the BMC system currently released, the current CPU usage of the BMC system is obtained and compared with the preset fixed alarm value. If it exceeds the alarm value, a log is recorded and an alarm is issued. After the alarm is issued, the problem is located or reproduced through the log. However, the method of determining whether there is an abnormality based only on the CPU usage of the BMC system may not accurately locate the specific location of the abnormality, resulting in inaccurate positioning. Summary of the invention

[0005] The embodiments of the present application provide an abnormality positioning method, device, equipment and medium to solve the problem of inaccurate abnormality positioning in the prior art.

[0006] In a first aspect, an embodiment of the present application provides an abnormality location method, the method comprising:

[0007] Obtaining a first CPU occupancy rate of each process in the baseboard management controller BMC system to be monitored within a first preset time;

[0008] Identify the top N target processes with the highest first CPU occupancy rate in the BMC system to be monitored, obtain the top N historical target normal processes with the highest CPU occupancy rate corresponding to the BMC system to be monitored, and determine the target processes among the top N target processes that are different from the top N historical target normal processes as abnormal processes.

[0009] In a second aspect, an embodiment of the present application further provides an abnormality locating device, the device comprising:

[0010] An acquisition module, used for acquiring a first CPU occupancy rate of each process in a baseboard management controller BMC system to be monitored within a first preset time;

[0011] A positioning module is used to identify the top N target processes with the highest first CPU occupancy rate in the BMC system to be monitored, obtain the top N historical target normal processes with the highest CPU occupancy rate corresponding to the BMC system to be monitored, and determine the target processes among the top N target processes that are different from the top N historical target normal processes as abnormal processes.

[0012] In a third aspect, an embodiment of the present application further provides an electronic device, which includes at least a processor and a memory, and the processor is used to implement the steps of the abnormality locating method as described in any one of the above items when executing a computer program stored in the memory.

[0013] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the abnormality locating method as described in any one of the above items.

[0014] In an embodiment of the present application, the CPU occupancy rate of the first central processing unit of each process in the baseboard management controller BMC system to be monitored within the first preset time is obtained; the first N target processes with the highest first CPU occupancy rate in the BMC system to be monitored are identified, and the first N historical target normal processes with the highest CPU occupancy rate corresponding to the BMC system to be monitored are obtained, and the target processes in the first N target processes that are different from the first N historical target normal processes are determined as abnormal processes. Since the first N target processes with the highest CPU occupancy rate are determined by the CPU occupancy rate of each process in the BMC system to be monitored, and the first N target processes are compared with the historical target normal processes to determine the abnormal process, it is possible to accurately locate the abnormal process in the BMC system, ensure the accuracy of abnormal detection, and facilitate R&D personnel to locate problems in a timely and rapid manner, reducing the time spent on troubleshooting. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments 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.

[0016] Figure 1 A schematic diagram of an abnormality locating process provided in an embodiment of the present application;

[0017] Figure 2 A schematic diagram of a display process of a report display module provided in an embodiment of the present application;

[0018] Figure 3 A schematic diagram of a process for performing secondary verification of an abnormality location module provided in an embodiment of the present application;

[0019] Figure 4 A schematic diagram of a process for obtaining CPU occupancy data by a data collection module provided in an embodiment of the present application;

[0020] Figure 5 A schematic diagram of a flow chart of an abnormal analysis of CPU occupancy by a data processing and analysis module provided in an embodiment of the present application;

[0021] Figure 6 A schematic diagram of an abnormality location process provided in an embodiment of the present application;

[0022] Figure 7 A schematic diagram of the structure of an abnormality locating device provided in an embodiment of the present application;

[0023] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose and implementation method of the present application clearer, the exemplary implementation method of the present application will be clearly and completely described below in conjunction with the drawings in the exemplary embodiments of the present application. Obviously, the described exemplary embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0025] It should be noted that the brief description of terms in this application is only for the convenience of understanding the embodiments described below, and is not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their common and usual meanings.

[0026] The terms "first", "second", "third", etc. in the specification and claims of this application and the above drawings are used to distinguish similar or similar objects or entities, and do not necessarily mean to limit a specific order or sequence, unless otherwise noted. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances.

[0027] The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device comprising a list of components is not necessarily limited to all the components expressly listed but may include other components not expressly listed or inherent to such product or device.

[0028] The term "module" refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functions associated with that element.

[0029] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0030] For the convenience of explanation, the above description has been made in conjunction with specific embodiments. However, the above exemplary discussion is not intended to be exhaustive or limit the embodiments to the specific forms disclosed above. Based on the above teachings, various modifications and variations can be obtained. The selection and description of the above embodiments are to better explain the principles and practical applications, so that those skilled in the art can better use the embodiments and various different variations of the embodiments suitable for specific use considerations.

[0031] The embodiment of the present application provides an abnormality location method, device, equipment and medium, in which the first central processing unit CPU occupancy rate of each process in the baseboard management controller BMC system to be monitored within a first preset time is obtained; the first N target processes with the highest first CPU occupancy rate in the BMC system to be monitored are identified, the first N historical target normal processes with the highest CPU occupancy rate corresponding to the BMC system to be monitored are obtained, and the target processes in the first N target processes that are different from the first N historical target normal processes are determined as abnormal processes. Since the first N target processes with the highest CPU occupancy rate are determined by the CPU occupancy rate of each process in the BMC system to be monitored, and the first N target processes are compared with the historical target normal processes to determine the abnormal process, it is possible to accurately locate the abnormal process in the BMC system, ensure the accuracy of the abnormality detection, and facilitate R&D personnel to locate the problem in a timely and rapid manner, reducing the time spent on troubleshooting.

[0032] Embodiment 1:

[0033] Figure 1 A schematic diagram of an abnormality location process provided in an embodiment of the present application, the process includes:

[0034] S101: Obtain a first CPU occupancy rate of each process in a BMC system to be monitored within a first preset time.

[0035] The abnormality locating method provided in the embodiment of the present application is applied to an electronic device, which may be a personal computer (PC), a server, etc.

[0036] It is understandable that, in the currently released official version of the BMC system, the CPU occupancy rate of the current BMC system is compared with the preset fixed alarm value. If the alarm value is exceeded, a log is recorded and an alarm is issued. After the alarm is issued, the problem is located or reproduced through the log. However, this method presents the system performance status by issuing an alarm message when the official version is running. Frequent alarms will not only reduce the user's recognition of the quality and performance of the BMC system, but also the after-sales personnel will not be able to rely on the alarm information to locate the problem in time. In addition, this method starts the monitoring program in the official version and continuously obtains background data, which will increase the system overhead and affect the user experience. Therefore, the abnormality positioning method provided in the embodiment of the present application is applied in the development stage of the BMC system, and when the official version of the BMC system is released, in order to weaken the problem of the monitoring program itself occupying CPU resources and affecting system performance, the CPU occupancy rate monitoring of the BMC system will be turned off, thereby avoiding the problem of reducing the user's recognition of the quality and performance of the BMC system and affecting the user experience.

[0037] In a possible implementation, a BMC system to be monitored is deployed in an electronic device, and a data collection module of the electronic device obtains a first CPU occupancy rate of each process in the BMC system to be monitored within a first preset time in the BMC system to be monitored deployed by the electronic device through in-band collection. In-band collection is to directly collect the CPU occupancy rate on the BMC system to be monitored deployed by the electronic device.

[0038] In another possible implementation, the electronic device monitors the BMC system to be monitored deployed on other devices, and the data collection module of the electronic device obtains the first CPU occupancy rate of each process in the BMC system to be monitored within a first preset time by out-of-band collection. The out-of-band collection is to collect the CPU occupancy rate of the BMC system to be monitored deployed in the external communication device through the interface of the electronic device.

[0039] It can be understood that in-band collection can avoid the additional CPU resource occupation caused by the external communication device being connected to the electronic device when collecting data using the out-of-band collection method. Therefore, in the embodiments of the present application, the in-band collection method is usually used to collect the CPU occupancy rate, thereby minimizing the impact on the performance of the electronic device.

[0040] Among them, the first CPU occupancy rate can be the average value of the first CPU occupancy rate of each process in the BMC system to be monitored collected within the first preset time, or the first CPU occupancy rate of each process at each preset time point. Among them, for example, in order to be able to perform regular detection on the BMC system after the developer adds a new function or modifies a function every day, in the embodiment of the present application, the first preset time can be a whole night, for example, the whole night can be from 22:00 on a certain night to 6:00 in the morning of the next day, and there is no restriction here, so as to timely feedback the status after the code is merged (that is, the code of the new function or the code of the modified function is written into the BMC system to be monitored), and accurately locate whether the new or modified function has an impact on the CPU occupancy rate of the system.

[0041] S102: Identify the top N target processes with the highest first CPU occupancy rate in the BMC system to be monitored, obtain the top N historical target normal processes with the highest CPU occupancy rate corresponding to the BMC system to be monitored, and determine the target processes among the top N target processes that are different from the top N historical target normal processes as abnormal processes.

[0042] In the embodiment of the present application, the data processing and analysis module of the electronic device identifies the first N target processes with the highest first CPU occupancy rates in the BMC system to be monitored according to the first CPU occupancy rates of each process in the BMC system to be monitored, where N is a positive integer, and N can be 10 by way of example.

[0043] The electronic device can filter out the top N historical target normal processes with the highest CPU occupancy corresponding to the BMC system to be monitored within the historical preset time period from each historical process based on information such as the CPU occupancy rate of each historical process within the saved historical preset time period (the CPU occupancy rate corresponding to the BMC system to be monitored), wherein if the first preset time is a certain day, the historical preset time can be the day before that day. In an embodiment of the present application, the electronic device obtains the top N historical target normal processes with the highest CPU occupancy rate corresponding to the BMC system to be monitored saved by itself. It can be understood that the top N historical target normal processes are all historical normal processes, excluding historical abnormal processes.

[0044] After obtaining the top N historical target normal processes with the highest CPU occupancy corresponding to the BMC system to be monitored, in a possible implementation, the data processing and analysis module of the electronic device directly compares the names of the top N target processes with the names of the top N historical target normal processes, and determines whether there are target processes different from the top N historical target normal processes in the top N target processes. If so, the target processes different from the top N historical target normal processes in the top N target processes are determined as abnormal processes, and an abnormal alarm is issued, and a first data analysis report containing abnormal processes is generated; if not, it is determined that there are no abnormal processes in the top N target processes, and a second data analysis report is generated that there are no abnormal processes in the top N target processes. For example, the abnormal process may be a process corresponding to a newly added function in the BMC system to be monitored, and the CPU occupancy of the process corresponding to the newly added function is large and the CPU occupancy ranks in the top N of all processes. In the embodiment of the present application, by comparing the historical data (i.e., the historical target normal process), the impact of the integration of the new function code can be inferred from the data fluctuation of the first CPU occupancy rate, and real-time feedback is given to the corresponding developers, providing data support for design optimization and performance improvement.

[0045] In another possible implementation, the data processing and analysis module of the electronic device inputs the names of the first N target processes and the names of the first N historical target normal processes into a trained process strategy model, and based on the process strategy model, compares the names of the first N target processes with the names of the first N historical target normal processes to determine whether there are target processes in the first N target processes that are different from the first N historical target normal processes. If so, the process strategy model will output an abnormal process (i.e., a target process in the first N target processes that is different from the first N historical target normal processes). After the electronic device recognizes that the process strategy model outputs an abnormal process, it issues an abnormal alarm, and the data processing and analysis module generates a first data analysis report containing the abnormal process; if not, the process strategy model will output information that there is no abnormal process, and the data processing and analysis module generates a second data analysis report that there is no abnormal process in the first N target processes.

[0046] If the abnormality location module of the electronic device identifies an abnormality alarm, the abnormality location module of the electronic device parses the first data analysis report containing the abnormal process and obtains the abnormal process in the first data analysis report. In a possible implementation, the abnormal process of the BMC system to be monitored is retested in the electronic device (i.e., secondary verification).

[0047] In another possible implementation, in an embodiment of the present application, when generating the first data analysis report, the model configuration information of the BMC system to be monitored can also be recorded in the first data analysis report. Therefore, in an embodiment of the present application, based on the model configuration information recorded in the first data analysis report, a candidate BMC system with the same model as the BMC system to be monitored is determined, and a retest operation (i.e., secondary verification) is performed on the abnormal process of the candidate BMC system in the electronic device.

[0048] Among them, the retest operation is that the data collection module of the electronic device obtains the third CPU occupancy rate of each process in the corresponding BMC system within the second preset time, and identifies the top N retest target processes with the highest third CPU occupancy rate in the BMC system according to the third CPU occupancy rate of each process; compares the top N retest target processes with the top N historical target normal processes to determine whether there is a retest target process different from the top N historical target normal processes among the top N retest target processes, if so, determines the retest target process different from the top N historical target normal processes among the top N retest target processes as an abnormal process, and saves the abnormal process in the retest result; if not, determines that the retest result is that there is no abnormal process; determines whether the abnormal process included in the retest result is the same as the abnormal process recorded in the first data analysis report, if the abnormal process included in the retest result is the same as the abnormal process in the first data analysis report, generates a first final analysis report containing the abnormal process, and if the retest result is different from the first data analysis report, generates a first final analysis report of the failure of the secondary verification for manual screening of the cause.

[0049] The duration of the second preset time may be slightly shorter than that of the first preset time. For example, the duration of the first preset time may be one day, and the duration of the second preset time may be one hour.

[0050] After the first final analysis report is generated, the report display module of the electronic device displays the first final analysis report. In order to meet the needs of obtaining and displaying the generated first final analysis report in different scenarios, a variety of flexible configuration options are provided in the embodiment of the present application, such as Figure 2As shown, the display methods include an email report sending method and a tool page display method. Among them, the email report sending method supports sending the first final analysis report to a designated recipient via email, and the email includes an email attachment and an email body. In the embodiment of the present application, the first final analysis report is used as an email attachment, and the email body is a text that briefly summarizes the content of the first final analysis report; the tool page display method displays the first final analysis report on a network (web) page, and also supports browsing and online viewing of the first final analysis report on the web page, and supports fast retrieval according to time and the identifier of the machine where the BMC system is deployed (i.e. Figure 2 The selected corresponding date and the selected corresponding machine are shown in the figure), and a download option is provided and support is provided for viewing the downloaded analysis report.

[0051] In the embodiment of the present application, since the top N target processes with the highest CPU occupancy rates are determined by measuring the CPU occupancy rates of each process in the BMC system to be monitored, and the top N target processes are compared with the historical target normal processes to determine the abnormal processes, the abnormal processes in the BMC system can be accurately located, thereby ensuring the accuracy of anomaly detection, and facilitating R&D personnel to locate problems in a timely and rapid manner, thereby reducing the time spent on troubleshooting.

[0052] Embodiment 2:

[0053] In order to accurately determine the top N target processes, based on the above embodiment, in the embodiment of the present application, identifying the top N target processes with the highest first CPU occupancy in the BMC system to be monitored includes:

[0054] For each preset moment within the first preset time, determine the top N candidate processes with the highest CPU occupancy at the preset moment according to the first CPU occupancy of each process in the BMC system to be monitored at the preset moment;

[0055] The number of times the top N candidate processes appear at each preset time is counted, and the top N candidate processes with the largest number of appearances are determined as target processes.

[0056] In an embodiment of the present application, the first preset time includes multiple preset moments, and the first CPU occupancy rate of each process in the BMC system to be monitored within the first preset time includes the first CPU occupancy rate of each process at the multiple preset moments, wherein the time interval between any two adjacent preset moments may be the same or different, and is not limited here.

[0057] For each preset moment within the first preset time, according to the first CPU occupancy rate of each process in the BMC system to be monitored at the preset moment, the processes in the BMC system to be monitored are arranged in descending order according to the first CPU occupancy rate, and the top N candidate processes are selected from the arranged processes as the top N candidate processes with the highest CPU occupancy rate at the preset moment.

[0058] According to the top N candidate processes with the highest occupancy rates at each preset time, the number of times the top N candidate processes appear at each preset time is counted, and the top N candidate processes with the largest number of appearances are determined as target processes.

[0059] In an embodiment of the present application, the top N candidate processes at each preset time are counted, and the number of times each candidate process appears in the top N is counted, and the top N candidate processes with the largest number of appearances are determined as target processes, thereby accurately determining the top N target processes.

[0060] Embodiment 3:

[0061] In order to further ensure the accuracy of anomaly detection, based on the above embodiments, in the embodiment of the present application, the method further includes:

[0062] Obtaining the second CPU occupancy rate of the BMC system to be monitored at each preset time within the first preset time;

[0063] Determine, according to the number of preset occupancy rates in each second CPU occupancy rate, a BMC Zero Idle Percentage (BMC-ZIP) indicator value of a BMC system corresponding to the BMC system to be monitored;

[0064] It is determined whether the BMC-ZIP indicator value exceeds the saved initial baseline. If so, it is determined that the BMC system to be monitored has an abnormality.

[0065] In the embodiment of the present application, in addition to performing anomaly detection on each process in the monitored BMC system, anomaly detection and anomaly location may also be performed on the entire monitored BMC system at the same time, thereby further ensuring the accuracy of anomaly detection.

[0066] Specifically, in an embodiment of the present application, if the BMC system to be monitored is deployed in an electronic device, the data collection model of the electronic device obtains the second CPU occupancy rate of the BMC system to be monitored within the first preset time by means of in-band collection, that is, obtains the second CPU occupancy rate of the BMC system to be monitored at each preset time within the first preset time; if the BMC system to be monitored is not deployed in the electronic device, the data collection module of the electronic device obtains the second CPU occupancy rate of the BMC system to be monitored within the first preset time by means of out-of-band collection, that is, obtains the second CPU occupancy rate of the BMC system to be monitored at each preset time within the first preset time. Among them, the in-band collection method and the out-of-band collection method are similar to those shown in S101, and will not be repeated here.

[0067] For each second CPU occupancy rate, determine whether the second CPU occupancy rate is a preset occupancy rate; count the number of second CPU occupancy rates whose occupancy values ​​are the preset occupancy rates, and determine the BMC-ZIP indicator value corresponding to the BMC system to be monitored based on the number of second CPU occupancies that are the preset occupancy rates and the number of all second CPU occupancies.

[0068] Among them, the BMC-ZIP indicator value represents the proportion of the CPU idle state of 0% in the entire BMC system to be monitored during operation, and the BMC-ZIP indicator value can reflect whether the BMC system to be monitored is in a high load state for a long time. In the embodiment of the present application, the preset occupancy rate can be 100%, and the CPU idle state of the BMC system to be monitored is 0%.

[0069] In the embodiment of the present application, an initial baseline is stored in the electronic device, and the initial baseline can be set according to prior experience, or can be the initial baseline corresponding to the historical BMC-ZIP indicator value of the BMC system to be monitored output by the policy model in the previous cycle. The electronic device obtains the initial baseline stored by itself, and determines whether the BMC-ZIP indicator value corresponding to the BMC system to be monitored exceeds the initial baseline. If so, it is determined that the BMC system to be monitored is abnormal, and an abnormal alarm is issued, and the data processing and analysis module generates a third data analysis report of the abnormal BMC system to be monitored; if not, it is determined that the BMC system to be monitored is normal, and the data processing and analysis module generates a fourth data analysis report of the normal BMC system to be monitored.

[0070] In addition, it can be understood that, in a possible implementation, in addition to determining whether the CPU occupancy rate is abnormal according to the BMC-ZIP indicator value corresponding to the BMC system to be monitored, it is also possible to determine whether the CPU occupancy rate is abnormal according to the average value of the CPU occupancy rate of the BMC system to be monitored. Specifically, according to the second CPU occupancy rate of the BMC system to be monitored at each preset time, the average value of the second CPU occupancy rate is determined, and it is determined whether the average value of the second CPU occupancy rate exceeds the initial baseline. If so, it is determined that the BMC system to be monitored is abnormal, and an abnormal alarm is issued, and the data processing and analysis module generates a third data analysis report of the abnormal BMC system to be monitored; if not, it is determined that the BMC system to be monitored is normal, and the data processing and analysis module generates a fourth data analysis report of the normal BMC system to be monitored.

[0071] If the abnormality location module of the electronic device identifies an abnormality alarm, the abnormality location module of the electronic device analyzes the third data analysis report to determine the abnormal BMC system to be monitored. In a possible implementation, a retest operation (ie, secondary verification) is performed on the BMC system to be monitored.

[0072] In another possible implementation, in an embodiment of the present application, the model configuration information of the BMC system to be monitored may also be recorded in the second data analysis report when generating the third data analysis report. Therefore, in an embodiment of the present application, a candidate BMC system with the same model as the BMC system to be monitored is determined based on the model configuration information recorded in the third data analysis report, and a retest operation (i.e., secondary verification) is performed on the candidate BMC system.

[0073] Among them, the retest operation is that the data collection module of the electronic device obtains the fourth CPU occupancy rate of the corresponding BMC system at each second preset moment within the second preset time, determines the second BMC-ZIP indicator value corresponding to the BMC system according to the fourth CPU occupancy rate of the BMC system at each second preset moment as the number of preset occupancy rates, judges whether the second BMC-ZIP indicator value exceeds the saved initial baseline, and obtains the retest result of whether the BMC system is abnormal; judges whether the result of whether the BMC system is abnormal contained in the retest result is the same as the result of the BMC system abnormality contained in the third data analysis report; if the result of whether the BMC system is abnormal contained in the retest result is the same as the result of the BMC system abnormality contained in the third data analysis report, then generates a second final analysis report containing the same abnormal BMC; if the result of whether the BMC system is abnormal contained in the retest result is different from the result of the BMC system abnormality contained in the third data analysis report, then generates a second final analysis report of secondary verification failure for manual screening of reasons.

[0074] After generating the second final analysis report, the report display module of the electronic device displays the second final analysis report. The second final analysis report can be displayed by the email report sending method or tool page display method provided in the above embodiment, which is not specifically limited here.

[0075] Furthermore, in a possible implementation, if the result of whether the BMC system is abnormal contained in the retest result is the same as the result of the abnormality of the BMC system contained in the second data analysis report, that is, it is determined that the BMC system to be monitored is abnormal, in order to more accurately locate the process that causes the abnormality of the BMC system to be monitored, in the embodiment of the present application, the electronic device can also use the abnormality location method provided in the embodiment of the present application to locate the process with abnormal CPU occupancy in the BMC system to be monitored, and record the key information of the located process, and add the key information to the second final analysis report. Among them, the implementation process of the abnormality location method can refer to the above embodiment, and will not be repeated here.

[0076] Based on the above embodiments, Figure 3 The process of secondary verification of the abnormal location module is shown, including the following steps:

[0077] Step 1: Input the data analysis report into the abnormality analysis module, wherein the data analysis report may include the first data analysis report or the third data analysis report.

[0078] Step 2: The abnormal analysis module analyzes the data analysis report to determine abnormal alarm machine information, where the abnormal alarm machine information includes an abnormal BMC system or an abnormal process in the BMC system.

[0079] Step 3: According to the abnormal alarm machine included in the abnormal alarm machine information, retest the same machine within the second preset time, obtain the CPU occupancy rate of the abnormal alarm machine and analyze the CPU occupancy rate to determine whether the abnormal alarm machine has an abnormality. If so, determine that the abnormal BMC system or process included in the secondary verification result is consistent with the abnormal BMC system or process (i.e., abnormal alarm machine information) included in the data analysis report, then determine that the verification is passed, and execute step 4; if not, determine that the abnormal BMC system or process included in the secondary verification result is inconsistent with the abnormal BMC system or process included in the data analysis report, then determine that the verification fails, and execute step 5. Among them, the abnormal alarm machine is the abnormal BMC system or the BMC system where the abnormal process is located.

[0080] Step 4: locate the abnormality of the abnormal alarm machine and execute step 5. The process of locating the abnormality can refer to the implementation process of the abnormality locating method provided in the above embodiment, which will not be repeated here.

[0081] Step 5: Generate a final analysis report, wherein the final analysis report may be the first final analysis report or the second final analysis report, and the final analysis report includes an abnormal BMC system or an abnormal process in the BMC system.

[0082] Embodiment 4:

[0083] In order to further ensure the accuracy of anomaly detection, based on the above embodiments, in the embodiment of the present application, the process of determining the initial baseline includes:

[0084] Obtaining the environment adjustment parameter value corresponding to the configuration environment of the BMC system to be monitored in the previous cycle and the change rule adjustment parameter value corresponding to the previous cycle;

[0085] A first preset number of historical BMC-ZIP indicator values, environment adjustment parameter values, and change rule adjustment parameter values ​​corresponding to the previous period in the previous period are input into the strategy model, and an initial baseline is determined based on the strategy model.

[0086] In an embodiment of the present application, the strategy model is used to determine the baseline corresponding to the BMC-ZIP indicator in each cycle according to the first preset number of BMC-ZIP indicator values, environmental adjustment parameter values ​​and periodic change law adjustment parameter values ​​of the BMC system to be monitored in the cycle.

[0087] In order to determine the initial baseline, in an embodiment of the present application, the configuration environment of the previous cycle of the BMC system to be monitored is obtained. Since the correspondence between the configuration environment and the environment adjustment parameter value is stored in the electronic device, the environment adjustment parameter value corresponding to the configuration environment of the previous cycle of the BMC system to be monitored is determined based on the configuration environment of the previous cycle and the correspondence between the configuration environment and the environment adjustment parameter value.

[0088] By way of example, the configuration environment of the BMC system to be monitored includes but is not limited to: the BMC system to be monitored is deployed in a bare board machine (i.e., a minimum machine environment set); the BMC system to be monitored is deployed in a machine without an expandable high-speed serial computer expansion bus standard (Peripheral Component Interconnect Express, PCIe) device inserted (such as a disk array (Redundant Arrays of Independent Disks, RAID), a graphics processing unit (Graphics Processing Unit, GPU), etc.); the BMC system to be monitored is deployed in a fully configured machine.

[0089] In addition, the electronic device obtains the first preset number of historical BMC-ZIP indicator values ​​in the previous cycle of the BMC system to be monitored and the change rule adjustment parameter value corresponding to the previous cycle. The number of holidays included in the previous cycle is different, and the corresponding change rule adjustment parameter value is also different. Therefore, when specifically determining the change rule adjustment parameter value corresponding to the previous cycle, the number of holidays included in the previous cycle can be counted, and the change rule adjustment parameter value corresponding to the number of days can be identified, so as to obtain the change rule adjustment parameter value corresponding to the previous cycle.

[0090] After obtaining a first preset number of historical BMC-ZIP indicator values, environmental adjustment parameter values, and periodic change law adjustment parameter values ​​in the previous cycle, the first preset number of historical BMC-ZIP indicator values, environmental adjustment parameter values, and change law adjustment parameter values ​​corresponding to the previous cycle are input into a trained strategy model; based on the strategy model, according to the first preset number of historical BMC-ZIP indicator values, environmental adjustment parameter values, and change law adjustment parameter values ​​corresponding to the previous cycle in the previous cycle, an initial baseline corresponding to the BMC system to be monitored is determined and saved.

[0091] Since in the relevant technology, the alarm is realized by setting a fixed alarm value, the threshold value (i.e., the fixed alarm value) itself is not universal and is set only based on prior experience. If dynamic feedback adjustment according to the actual state cannot be achieved, the accuracy of state tracking cannot be improved. Therefore, based on the above embodiments, according to the above method of determining the initial baseline, in the embodiment of the present application, the current cycle environment adjustment parameter value corresponding to the current cycle configuration environment of the BMC system expected to be monitored this week and the current cycle change law adjustment parameter value corresponding to the current cycle are obtained. In a possible implementation, the first preset number of BMC-ZIP indicator values, current cycle environment adjustment parameter values, and current cycle change law adjustment parameter values ​​of the BMC system to be monitored obtained in this cycle are input into the policy model. Based on the policy model, the phased baseline corresponding to the BMC system expected to be monitored this week is obtained, which is used to use the phased baseline in the next cycle to control the BMC-ZIP indicator value corresponding to the CPU occupancy rate of the BMC system to be monitored. Once a BMC-ZIP indicator value is detected to exceed the phased baseline, an alarm is triggered, thereby ensuring that abnormal problems can be paid attention to and handled in a timely manner.

[0092] In another possible implementation, in this cycle, the environment adjustment parameter value of this cycle and the change law adjustment parameter value of this cycle are input into the strategy model, and each time a BMC-ZIP indicator value corresponding to the BMC system to be monitored is obtained, the BMC-ZIP indicator value is input into the strategy model. When the number of BMC-ZIP indicator values ​​input into the strategy model reaches a first preset number, the strategy model outputs a phased baseline corresponding to the BMC system to be monitored this week.

[0093] In an embodiment of the present application, the BMC-ZIP indicator value determined in each cycle based on the real-time CPU occupancy data determines a phased baseline that is dynamically updated in each cycle, further ensuring the accuracy of anomaly detection and the stability of the policy model.

[0094] Embodiment 5:

[0095] In order to accurately determine the initial baseline, based on the above embodiments, in the embodiment of the present application, the initial baseline is determined based on the policy model, including:

[0096] In the strategy model, according to the first preset number of historical BMC-ZIP indicator values ​​in the previous period, an expected value corresponding to the first preset number of historical BMC-ZIP indicator values ​​in the previous period is determined;

[0097] Adjust the parameter value according to the expected value, the environmental adjustment parameter value and the change pattern corresponding to the previous cycle, and determine the initial baseline corresponding to the BMC system expected to be monitored last week.

[0098] The strategy model determines the expected value corresponding to the first preset number of historical BMC-ZIP indicator values ​​in the previous cycle according to the first preset number of historical BMC-ZIP indicator values ​​in the previous cycle. The process of determining the expected value corresponding to the first preset number of historical BMC-ZIP indicator values ​​in the previous cycle is a prior art and will not be described in detail here.

[0099] After obtaining the expected value corresponding to the first preset number of historical BMC-ZIP indicator values ​​in the previous period, the strategy model determines the addition result of the expected value, the environment adjustment parameter value and the change law adjustment parameter value corresponding to the previous period, and determines the addition result as the initial baseline corresponding to the BMC system expected to be monitored in the previous week.

[0100] Specifically, the initial baseline can satisfy the following formula:

[0101] P b =E(p)+f(p)+S(p)

[0102] Among them, P brepresents the initial baseline, E(p) represents the expected value corresponding to the first preset number of historical BMC-ZIP indicator values ​​in the previous period, p represents the historical BMC-ZIP indicator value, f(p) represents the change rule adjustment parameter value corresponding to the previous period, and S(p) represents the environment adjustment parameter value.

[0103] In the embodiment of the present application, not only the influence of the BMC-ZIP indicator value on the initial baseline is taken into account, but also the influence of the deployment environment and the influence of the time change law are taken into account, so that the initial baseline can be determined more accurately.

[0104] Embodiment 6:

[0105] In order to reduce the impact of erroneous data on anomaly detection, based on the above embodiments, in the embodiment of the present application, the process of obtaining any CPU occupancy rate includes:

[0106] Collecting the original CPU occupancy rate corresponding to the BMC system to be monitored within a first preset time; wherein the original CPU occupancy rate includes the first original CPU occupancy rate of each process in the BMC system to be monitored and the second original CPU occupancy rate of the BMC system to be monitored;

[0107] The original CPU occupancy is cleaned to determine a first CPU occupancy and a second CPU occupancy corresponding to the BMC system to be monitored.

[0108] First, the process of obtaining the first CPU occupancy rate is described:

[0109] The electronic device collects the first original CPU occupancy rate corresponding to each process in the BMC system to be monitored within the first preset time, wherein the first original CPU occupancy rate is the process-level CPU occupancy rate, and the complete first original CPU occupancy rate should at least include the user state CPU occupancy rate, the kernel state CPU occupancy rate, the idle state CPU occupancy rate and the interrupt state CPU occupancy rate.

[0110] The first original CPU occupancy rate may be collected by an in-band collection method or an out-of-band collection method, which will not be described in detail herein.

[0111] Since some data may be missing or incomplete in the first original CPU occupancy rate obtained, in an embodiment of the present application, the first original CPU occupancy rate data is cleaned to filter out incomplete and erroneous data to obtain the cleaned first original CPU occupancy rate.

[0112] Based on the cleaned first original CPU occupancy, key data, namely, idle CPU occupancy, is extracted from the cleaned first original CPU occupancy to obtain the first CPU occupancy corresponding to each process in the BMC system to be monitored, and stored in the corresponding data structure.

[0113] Then, the process of obtaining the second CPU occupancy rate is described:

[0114] The electronic device collects the second original CPU occupancy rate corresponding to the BMC system to be monitored within the second preset time, wherein the second original CPU occupancy rate is the BMC system-level CPU occupancy rate, and the complete second original CPU occupancy rate should at least include the user state CPU occupancy rate, the kernel state CPU occupancy rate, the idle state CPU occupancy rate and the interrupt state CPU occupancy rate.

[0115] The second original CPU occupancy rate may be collected by an in-band collection method or an out-of-band collection method, which will not be described in detail herein.

[0116] Since some data may be missing or incomplete in the acquired second original CPU occupancy rate, in an embodiment of the present application, the second original CPU occupancy rate data is cleaned, and incomplete and erroneous data are filtered out to obtain the cleaned second original CPU occupancy rate.

[0117] Based on the cleaned second original CPU occupancy, key data, ie, idle CPU occupancy, is extracted from the cleaned second original CPU occupancy to obtain the second CPU occupancy corresponding to the BMC system to be monitored and store it in the corresponding data structure.

[0118] In an embodiment of the present application, the collected original CPU occupancy rate is cleaned, and subsequent anomaly detection is performed based on the cleaned CPU occupancy rate, thereby reducing the impact of erroneous data on anomaly detection.

[0119] Based on the above embodiments, Figure 4 The process of obtaining CPU usage data by the data collection module is shown, including the following steps:

[0120] Step 1: The electronic equipment pulls the code and compiles the image from the BMC system to be monitored on a daily basis to obtain the daily test set.

[0121] Among them, the process of pulling code, compiling images, and obtaining daily test sets is existing technology and will not be repeated here.

[0122] Step 2: Input the daily test set into the data collection module, and the data collection module obtains the original CPU occupancy rate in the daily test set through the command set. The original CPU occupancy rate includes the system-level CPU occupancy rate (i.e., the second original CPU occupancy rate of the BMC system to be monitored) and the process-level CPU occupancy rate (i.e., the first original CPU occupancy rate of each process in the BMC system to be monitored). Step 3 is performed for the system-level CPU occupancy rate, and step 4 is performed for the process-level CPU occupancy rate.

[0123] Step 3: Use the system-level CPU occupancy rate as the second original CPU occupancy rate of the BMC system to be monitored.

[0124] Step 4: Use the process-level CPU occupancy rate as the first original CPU occupancy rate of each process in the BMC system to be monitored.

[0125] Step 5: Collect CPU usage using polling and return to step 2.

[0126] Step 6: Save the collected raw CPU usage.

[0127] Based on the above embodiments, Figure 5 The flowchart of the data processing and analysis module for abnormal analysis of CPU usage is shown, including the following steps:

[0128] Step 1: The data collection module inputs the original CPU occupancy rate collected by in-band collection and / or out-of-band collection within a first preset time into the data processing and analysis module.

[0129] Step 2: The data processing and analysis module cleans and extracts the first original CPU occupancy rate and the second original CPU occupancy rate in the original CPU occupancy rate to obtain the first CPU occupancy rate of each process in the BMC system to be monitored and the second CPU occupancy rate of the BMC system to be monitored.

[0130] Step 3: for the second CPU occupancy of the BMC system to be monitored, determine the BMC-ZIP index value corresponding to the second CPU occupancy at each preset time in the BMC system to be monitored, or determine the second CPU occupancy average value corresponding to the second CPU occupancy at each preset time in the BMC system to be monitored.

[0131] For the first CPU occupancy rate of each process in the BMC system to be monitored, according to the first CPU occupancy rate of each process in the BMC system to be monitored at each preset moment, determine the top N candidate processes with the highest CPU occupancy rate at each preset moment, determine the number of occurrences of each candidate process in the top N, and determine the top N candidate processes with the largest number of occurrences as target processes.

[0132] Step 4: Determine whether the BMC-ZIP indicator value corresponding to the BMC system to be monitored exceeds the initial baseline through the initial baseline output by the policy model. If so, execute step 5; if not, execute step 6.

[0133] The first N target processes and the first N historical target normal processes are input into the process strategy model. Based on the process strategy model, it is determined whether there is a target process different from the first N historical target normal processes among the first N target processes. If so, the target process is determined to be an abnormal process, and step five is executed; if not, it is determined that there is no abnormal process among the first N target processes, and step six is ​​executed.

[0134] Step 5: Issue an abnormal alarm and execute step 6.

[0135] Step 6: Generate a final analysis report, wherein the final analysis report includes information on whether the BMC system to be monitored is abnormal and / or whether there is an abnormal process in the BMC system to be monitored.

[0136] Embodiment 7:

[0137] In order to accurately determine the BMC-ZIP indicator value corresponding to the BMC system to be monitored, based on the above embodiments, in the embodiment of the present application, according to the number of preset occupancy rates in each second CPU occupancy rate, the BMC-ZIP indicator value corresponding to the BMC system to be monitored is determined, including:

[0138] The BMC-ZIP indicator value corresponding to the BMC system to be monitored is determined according to the ratio of the number of preset occupancy rates in each second CPU occupancy rate to the number of all second CPU occupancy rates within the first preset time.

[0139] In an embodiment of the present application, the number of second CPU occupancy rates with a preset occupancy rate is counted, and according to the ratio of the number of second CPU occupancy rates with the preset occupancy rate in each second CPU occupancy rate to the number of all second CPU occupancies within the first preset time, the ratio result is determined as the BMC-ZIP indicator value corresponding to the BMC system to be monitored.

[0140] For example, the number of second CPU occupancy rates with a preset occupancy rate is 60, and the number of all second CPU occupancy rates within the first preset time is 100. The ratio of the number of preset occupancy rates in each second CPU occupancy rate to the number of all second CPU occupancy rates within the first preset time is 60%. The ratio result 60% is determined as the BMC-ZIP indicator value corresponding to the BMC system to be monitored.

[0141] In an embodiment of the present application, the number of second CPU occupancy rates with a preset occupancy rate is counted, and the BMC-ZIP indicator value is determined based on the ratio of the number to the number of all second CPU occupancy rates within the first preset time, thereby accurately determining the BMC-ZIP indicator value corresponding to the BMC system to be monitored.

[0142] Embodiment 8:

[0143] Based on the above embodiments, the present application embodiment provides a schematic diagram of an abnormality location process, such as Figure 6 As shown, the process includes:

[0144] Step 1: perform stress testing on the BMC system to be monitored and collect the original CPU occupancy of the BMC system to be monitored, wherein the original CPU occupancy includes the first original CPU occupancy of each process in the BMC system to be monitored and the second original CPU occupancy corresponding to the BMC system to be monitored.

[0145] Step 2: Process the raw CPU usage of the BMC system to be monitored:

[0146] The incomplete and erroneous data in the original CPU occupancy rate is cleaned, and the idle CPU occupancy rate is extracted from the cleaned original CPU occupancy rate to obtain the CPU occupancy rate of the BMC system to be monitored. The CPU occupancy rate of the BMC system to be monitored includes the first CPU occupancy rate of each process in the BMC system to be monitored and the second CPU occupancy rate corresponding to the BMC system to be monitored.

[0147] Analyze the CPU usage of the BMC system to be monitored:

[0148] For the first CPU occupancy rate of each process in the BMC system to be monitored, identify the top N target processes with the highest first CPU occupancy rate in the BMC system to be monitored, obtain the top N historical target normal processes with the highest CPU occupancy rate corresponding to the BMC system to be monitored, and determine whether there is a target process different from the top N historical target normal processes among the top N target processes.

[0149] For the second CPU occupancy corresponding to the BMC system to be monitored, determine the BMC-ZIP indicator value corresponding to the BMC system to be monitored according to the number of preset occupancy rates in each second CPU occupancy; and determine whether the BMC-ZIP indicator value exceeds the saved initial baseline.

[0150] Step 3: Determine whether the BMC system and / or process to be monitored is abnormal according to the CPU occupancy of the BMC system to be monitored. If so, issue an abnormal alarm, generate a data analysis report, and execute step 5; if not, execute step 6.

[0151] Specifically, for each process in the BMC system to be monitored, if there is a target process among the first N target processes that is different from the first N historical target normal processes, the target process is determined to be an abnormal process, and an abnormal alarm is issued, a first data analysis report is generated, and step four is executed; if there is no target process among the first N target processes that is different from the first N historical target normal processes, it is determined that each process in the BMC system to be monitored is a normal process, and step five is executed.

[0152] For the BMC system to be monitored, if the BMC-ZIP indicator value corresponding to the BMC system to be monitored exceeds the saved initial baseline, it is determined that there is an abnormality in the BMC system to be monitored, and an abnormal alarm is issued, a third data analysis report is generated, and step four is executed; if the BMC-ZIP indicator value corresponding to the BMC system to be monitored does not exceed the saved initial baseline, it is determined that the BMC system to be monitored is normal, and step five is executed.

[0153] Step 4: If an abnormal alarm is identified, the data analysis report is parsed to determine the abnormal BMC system or process and the recorded model configuration information to determine a candidate BMC system with the same model as the BMC system to be monitored, and a secondary verification is performed on the candidate BMC system within a second preset time on the abnormal BMC system or abnormal process; determine whether the result of whether the BMC system or the process in the BMC system is abnormal contained in the secondary verification result is the same as the abnormal BMC system or process contained in the data analysis report; if they are the same, locate the abnormal process in the BMC system and execute step 5; if they are different, output the information that the secondary verification failed and execute step 5.

[0154] The secondary verification process is the same as the anomaly detection process and will not be described in detail here.

[0155] Step 5: If no abnormal BMC system or abnormal process is detected during abnormality detection, a final analysis report indicating that the BMC system is normal or the process in the BMC system is normal is generated; if an abnormal BMC system or abnormal process is identified, a final analysis report including the abnormal BMC system or abnormal process is generated; if the information identified by the secondary verification is output, a final analysis report indicating that the secondary verification failed is generated.

[0156] The final analysis report is displayed via email or on the tool page.

[0157] Embodiment 9:

[0158] Based on the same technical concept, on the basis of the above embodiments, the present application provides an abnormality locating device, Figure 7 A schematic diagram of the structure of an abnormality locating device provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the device comprises:

[0159] The acquisition module 701 is used to acquire a first CPU occupancy rate of each process in a baseboard management controller BMC system to be monitored within a first preset time;

[0160] The positioning module 702 is used to identify the top N target processes with the highest first CPU occupancy rate in the BMC system to be monitored, obtain the top N historical target normal processes with the highest CPU occupancy rate corresponding to the BMC system to be monitored, and determine the target processes among the top N target processes that are different from the top N historical target normal processes as abnormal processes.

[0161] In a possible implementation, the positioning module 702 is specifically used to determine, for each preset moment within the first preset time, the top N candidate processes with the highest CPU occupancy at the preset moment according to the first CPU occupancy of each process in the BMC system to be monitored at the preset moment; count the number of times the top N candidate processes appear at each preset moment, and determine the top N candidate processes with the largest number of appearances as target processes.

[0162] In a possible implementation, the acquisition module 701 is further configured to acquire a second CPU occupancy rate of the BMC system to be monitored at each preset time within the first preset time;

[0163] In a possible implementation, the positioning module 702 is further used to determine the BMC-ZIP indicator value corresponding to the BMC system to be monitored based on the number of preset occupancy rates in each second CPU occupancy rate; and determine whether the BMC-ZIP indicator value exceeds the saved initial baseline. If so, it is determined that there is an abnormality in the BMC system to be monitored.

[0164] In a possible implementation, the positioning module 702 is specifically used to obtain the environment adjustment parameter value corresponding to the configuration environment of the BMC system to be monitored in the previous cycle and the change law adjustment parameter value corresponding to the previous cycle; input the first preset number of historical BMC-ZIP indicator values ​​in the previous cycle, the environment adjustment parameter value and the change law adjustment parameter value corresponding to the previous cycle into the strategy model, and determine the initial baseline based on the strategy model.

[0165] In one possible implementation, the positioning module 702 is specifically used for the strategy model to determine the expected value corresponding to the first preset number of historical BMC-ZIP indicator values ​​in the previous cycle based on the first preset number of historical BMC-ZIP indicator values ​​in the previous cycle; and to determine the initial baseline corresponding to the BMC system to be monitored in the previous cycle based on the expected value, the environment adjustment parameter value and the change law adjustment parameter value corresponding to the previous cycle.

[0166] In a possible implementation, the acquisition module 701 is specifically used to collect the original CPU occupancy rate corresponding to the BMC system to be monitored within the first preset time; wherein the original CPU occupancy rate includes the first original CPU occupancy rate of each process in the BMC system to be monitored and the second original CPU occupancy rate of the BMC system to be monitored; the original CPU occupancy rate is cleaned to determine the first CPU occupancy rate and the second CPU occupancy rate corresponding to the BMC system to be monitored.

[0167] In a possible implementation, the positioning module 702 is specifically configured to determine the BMC-ZIP indicator value corresponding to the BMC system to be monitored according to the ratio of the number of preset occupancy rates in each second CPU occupancy rate to the number of all second CPU occupancies within the first preset time.

[0168] Embodiment 10:

[0169] Based on the same technical concept, the present application also provides an electronic device, Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 8 As shown, it includes: a processor 801, a communication interface 802, a memory 803 and a communication bus 804, wherein the processor 801, the communication interface 802, and the memory 803 communicate with each other through the communication bus 804;

[0170] The memory 803 stores a computer program. When the program is executed by the processor 801, the processor 801 performs the following steps:

[0171] Obtaining a first CPU occupancy rate of each process in the baseboard management controller BMC system to be monitored within a first preset time;

[0172] Identify the top N target processes with the highest first CPU occupancy rate in the BMC system to be monitored, obtain the top N historical target normal processes with the highest CPU occupancy rate corresponding to the BMC system to be monitored, and determine the target processes among the top N target processes that are different from the top N historical target normal processes as abnormal processes.

[0173] In a possible implementation, the processor 801 is specifically used to determine, for each preset moment within the first preset time, the top N candidate processes with the highest CPU occupancy at the preset moment according to the first CPU occupancy of each process in the BMC system to be monitored at the preset moment; count the number of times the top N candidate processes appear at each preset moment, and determine the top N candidate processes with the largest number of appearances as target processes.

[0174] In a possible implementation, the processor 801 is further used to obtain the second CPU occupancy rate of the BMC system to be monitored at each preset time within the first preset time; determine the BMC-ZIP indicator value corresponding to the BMC system to be monitored according to the number of preset occupancy rates in each second CPU occupancy rate; and determine whether the BMC-ZIP indicator value exceeds the saved initial baseline, and if so, determine that there is an abnormality in the BMC system to be monitored.

[0175] In a possible implementation, the processor 801 is specifically used to obtain the environment adjustment parameter value corresponding to the configuration environment of the BMC system to be monitored in the previous cycle and the change law adjustment parameter value corresponding to the previous cycle; input the first preset number of historical BMC-ZIP indicator values ​​in the previous cycle, the environment adjustment parameter value and the change law adjustment parameter value corresponding to the previous cycle into the strategy model, and determine the initial baseline based on the strategy model.

[0176] In a possible implementation, the processor 801 is specifically used for the strategy model to determine the expected value corresponding to the first preset number of historical BMC-ZIP indicator values ​​in the previous cycle based on the first preset number of historical BMC-ZIP indicator values ​​in the previous cycle; and to determine the initial baseline corresponding to the BMC system to be monitored in the previous cycle based on the expected value, the environment adjustment parameter value and the change law adjustment parameter value corresponding to the previous cycle.

[0177] In a possible implementation, the processor 801 is specifically used to collect the original CPU occupancy rate corresponding to the BMC system to be monitored within the first preset time; wherein the original CPU occupancy rate includes the first original CPU occupancy rate of each process in the BMC system to be monitored and the second original CPU occupancy rate of the BMC system to be monitored; the original CPU occupancy rate is cleaned to determine the first CPU occupancy rate and the second CPU occupancy rate corresponding to the BMC system to be monitored.

[0178] In a possible implementation, the processor 801 is specifically configured to determine a BMC-ZIP indicator value corresponding to the BMC system to be monitored according to a ratio of the number of preset occupancy rates in each second CPU occupancy rate to the number of all second CPU occupancies within the first preset time.

[0179] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0180] The communication interface 802 is used for communication between the above electronic device and other devices.

[0181] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0182] The above-mentioned processor can be a general-purpose processor, including a central processing unit, a network processor (Network Processor, NP), etc.; it can also be a digital signal processing processor (Digital Signal Processing, DSP), an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc.

[0183] Embodiment 11:

[0184] Based on the same technical concept, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program that can be executed by an electronic device. When the program runs on the electronic device, the electronic device implements any of the above embodiments when executing.

[0185] The above-mentioned computer-readable storage medium can be any available medium or data storage device that can be accessed by the processor in the electronic device, including but not limited to magnetic storage such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc., optical storage such as CD, DVD, BD, HVD, etc., and semiconductor storage such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD), etc.

[0186] 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.

[0187] 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 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 produce 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.

[0188] 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.

[0189] 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 in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0190] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An abnormality location method, It is characterized in that The method comprises: Obtaining a first CPU occupancy rate of each process in the baseboard management controller BMC system to be monitored within a first preset time; Identify the top N target processes with the highest first CPU occupancy rate in the BMC system to be monitored, obtain the top N historical target normal processes with the highest CPU occupancy rate corresponding to the BMC system to be monitored, and determine the target processes among the top N target processes that are different from the top N historical target normal processes as abnormal processes.

2. The method according to claim 1, It is characterized in that The identifying the top N target processes with the highest first CPU occupancy in the BMC system to be monitored includes: For each preset moment within the first preset time, according to the first CPU occupancy rate of each process in the BMC system to be monitored at the preset moment, determine the top N candidate processes with the highest CPU occupancy rate at the preset moment; The number of times the top N candidate processes appear at each preset time is counted, and the top N candidate processes with the largest number of appearances are determined as target processes.

3. The method according to claim 1, It is characterized in that The method further comprises: Obtaining a second CPU occupancy rate of the BMC system to be monitored at each preset time within the first preset time; Determine the BMC-ZIP index value corresponding to the BMC system to be monitored according to the number of preset occupancy rates in each second CPU occupancy rate; It is determined whether the BMC-ZIP indicator value exceeds the saved initial baseline. If so, it is determined that the BMC system to be monitored is abnormal.

4. The method according to claim 3, It is characterized in that The process of determining the initial baseline includes: Obtaining an environment adjustment parameter value corresponding to the configuration environment of the BMC system to be monitored in the previous cycle and a change rule adjustment parameter value corresponding to the previous cycle; A first preset number of historical BMC-ZIP indicator values ​​in the previous period, the environment adjustment parameter value, and the change rule adjustment parameter value corresponding to the previous period are input into the strategy model, and the initial baseline is determined based on the strategy model.

5. The method according to claim 4, It is characterized in that The determining the initial baseline based on the policy model includes: The strategy model determines an expected value corresponding to a first preset number of historical BMC-ZIP indicator values ​​in a previous cycle according to the first preset number of historical BMC-ZIP indicator values ​​in a previous cycle; and determines an initial baseline corresponding to the BMC system to be monitored in the previous cycle according to the expected value, the environment adjustment parameter value and the change law adjustment parameter value corresponding to the previous cycle.

6. The method according to claim 3, It is characterized in that The process of obtaining any CPU occupancy rate includes: Collecting the original CPU occupancy rate corresponding to the BMC system to be monitored within the first preset time; wherein the original CPU occupancy rate includes the first original CPU occupancy rate of each process in the BMC system to be monitored and the second original CPU occupancy rate of the BMC system to be monitored; The original CPU occupancy rate is cleaned to determine a first CPU occupancy rate and a second CPU occupancy rate corresponding to the BMC system to be monitored.

7. The method according to claim 3, It is characterized in that The determining, according to the number of preset occupancy rates in each of the second CPU occupancy rates, the BMC-ZIP indicator value corresponding to the BMC system to be monitored includes: The BMC-ZIP indicator value corresponding to the BMC system to be monitored is determined according to the ratio of the number of preset occupancy rates in each second CPU occupancy rate to the number of all second CPU occupancy rates within the first preset time.

8. An abnormality locating device, It is characterized in that The device comprises: An acquisition module, used for acquiring a first CPU occupancy rate of each process in a baseboard management controller BMC system to be monitored within a first preset time; A positioning module is used to identify the top N target processes with the highest first CPU occupancy rate in the BMC system to be monitored, obtain the top N historical target normal processes with the highest CPU occupancy rate corresponding to the BMC system to be monitored, and determine the target processes among the top N target processes that are different from the top N historical target normal processes as abnormal processes.

9. An electronic device, It is characterized in that The electronic device comprises at least a processor and a memory, and the processor is used to implement the steps of the abnormality locating method according to any one of claims 1 to 7 when executing a computer program stored in the memory.

10. A computer storage medium, It is characterized in that It stores a computer program executable by an electronic device. When the program runs on the electronic device, the electronic device executes the steps of the abnormality locating method according to any one of claims 1 to 7.

Citation Information

Cited By

  • Process monitoring method, system and equipment of baseboard management controller and medium

    CN120386690A

  • Process monitoring method, system, device and medium for baseboard management controller

    CN120386690B