A server state monitoring method, electronic device

Abstract

The application discloses a server state monitoring method and electronic equipment, and relates to the technical field of computers, which comprises the following steps: collecting original hardware data through a first preset data interface and collecting baseboard management controller data through a second preset data interface according to a unified first preset data format and a preset sampling frequency, so that the data can be efficiently and normatively transmitted and synchronous / asynchronous data acquisition is supported; determining the baseboard management controller state and the hardware state according to standard baseboard management controller data and standard hardware data, and then determining the server state, so that the function failure caused by the overload of the baseboard management controller resource can be identified, and the reliability and operation and maintenance efficiency of the system are improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a server status monitoring method and electronic device. Background Technology

[0002] Traditional baseboard management controllers are gradually transitioning to open-source baseboard management controller firmware projects to adapt to a wider range of application scenarios and more flexible needs. Running large language models through artificial intelligence modules presents the following problems in current open-source baseboard management controller firmware projects: First, the module architecture is loose: functional modules such as monitoring algorithms, data acquisition, and artificial intelligence models are mostly developed independently, lacking a unified system interaction standard. Data flow relies on temporary interfaces, easily leading to data inconsistencies and poor module compatibility. For example, hardware data needs to undergo multiple format conversions before being transmitted to the artificial intelligence model, increasing system latency. Second, resource scheduling is lacking: baseboard management controllers need to simultaneously support basic services (such as bus communication and power management), monitoring functions, and artificial intelligence models, but existing systems lack a targeted resource allocation mechanism. When multiple modules compete for processor and / or memory resources, core functions are often delayed due to resource preemption, even causing system lag. Third, there is insufficient functional synergy: the monitoring algorithm and the artificial intelligence model mostly transmit data in a one-way manner. For example, the monitoring algorithm only outputs early warning information to the artificial intelligence model, without forming a closed-loop synergy of "early warning → analysis → feedback → optimization". The diagnostic results of the artificial intelligence model cannot effectively feed back into the optimization of the monitoring algorithm, thus limiting the overall intelligence level of the system. Fourth, there is a lack of local resource monitoring for the baseboard management controller: the existing system mainly focuses on server hardware resources, such as processors and memory, and has not designed a monitoring module for the baseboard management controller's own resources (such as processor utilization and memory usage). It cannot identify "functional failures caused by baseboard management controller resource overload". For example, when the basic management controller is short of memory, the data acquisition process crashes, affecting the overall monitoring process. Excessive memory usage of advanced functions can also easily affect the implementation of basic functions. Summary of the Invention

[0003] This application provides a server status monitoring method and electronic device to at least solve at least one of the following problems in related technologies: loose module architecture, lack of resource scheduling, insufficient functional coordination, and lack of local resource monitoring in the baseboard management controller.

[0004] This application provides a server status monitoring method, which includes: collecting raw hardware data through a first preset data interface at a preset sampling frequency, and collecting raw baseboard management controller data through a second preset data interface at a preset sampling frequency, wherein the data formats of the raw hardware data and the raw baseboard management controller data are both the first preset data format; preprocessing the raw hardware data to obtain standard hardware data, and preprocessing the raw baseboard management controller data to obtain standard baseboard management controller data; obtaining a preset baseboard management controller data threshold and a preset hardware data threshold; determining the baseboard management controller status based on the standard baseboard management controller data and the preset baseboard management controller data threshold, and generating basic management controller early warning information based on the baseboard management controller status; determining the hardware status based on the standard hardware data and the preset hardware data threshold, and generating hardware early warning information based on the hardware status; obtaining server early warning information based on the basic management controller early warning information and the hardware early warning information, and determining the server status based on the server early warning information.

[0005] This application also provides an electronic device, including: a memory for storing a computer program; and a processor for executing the computer program to implement at least the following steps of a server status monitoring method: acquiring raw hardware data through a first preset data interface at a preset sampling frequency, and acquiring raw baseboard management controller data through a second preset data interface at a preset sampling frequency, wherein the data formats of the raw hardware data and the raw baseboard management controller data are both the first preset data format; preprocessing the raw hardware data to obtain standard hardware data, and preprocessing the raw baseboard management controller data to obtain standard baseboard management controller data; obtaining a preset baseboard management controller data threshold and a preset hardware data threshold; determining the baseboard management controller status based on the standard baseboard management controller data and the preset baseboard management controller data threshold, and generating basic management controller warning information based on the baseboard management controller status; determining the hardware status based on the standard hardware data and the preset hardware data threshold, and generating hardware warning information based on the hardware status; obtaining server warning information based on the basic management controller warning information and the hardware warning information, and determining the server status based on the server warning information.

[0006] This application enables the acquisition of raw hardware data through a first preset data interface and a second preset data interface, in accordance with a unified first preset data format and preset sampling frequency. This ensures efficient and standardized data transmission and supports synchronous / asynchronous data acquisition. Based on standard baseboard management controller data and standard hardware data, the status of the baseboard management controller and hardware is determined, thereby determining the server status. This allows for the identification of "functional failures caused by baseboard management controller resource overload," thereby improving system reliability and operational efficiency. Attached Figure Description

[0007] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0008] Figure 1 This is a flowchart illustrating the server status monitoring method in the first embodiment;

[0009] Figure 2 This is a flowchart illustrating the steps of waking up the AI ​​module from the front end in the first embodiment;

[0010] Figure 3 This is a flowchart illustrating the timed scheduling steps of the monitoring algorithm module in the first embodiment;

[0011] Figure 4 This is a partial module-level block diagram of the server status monitoring system in the second embodiment;

[0012] Figure 5 This is a hierarchical block diagram of the server status monitoring system in the second embodiment;

[0013] Figure 6 This is a diagram of the internal structure of the electronic device in the third embodiment. Detailed Implementation

[0014] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0015] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. The terms "first," "second," etc., in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0016] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0017] In the first embodiment, such as Figure 1 As shown, a server status monitoring method is provided. The server status monitoring method includes: collecting raw hardware data through a first preset data interface at a preset sampling frequency, and collecting raw baseboard management controller data through a second preset data interface at a preset sampling frequency, wherein the data formats of the raw hardware data and the raw baseboard management controller data are both the first preset data format; preprocessing the raw hardware data to obtain standard hardware data, and preprocessing the raw baseboard management controller data to obtain standard baseboard management controller data; obtaining preset baseboard management controller data thresholds and preset hardware data thresholds; determining the baseboard management controller status based on the standard baseboard management controller data and the preset baseboard management controller data thresholds, and generating basic management controller early warning information based on the baseboard management controller status; determining the hardware status based on the standard hardware data and the preset hardware data thresholds, and generating hardware early warning information based on the hardware status; obtaining server early warning information based on the basic management controller early warning information and the hardware early warning information, and determining the server status based on the server early warning information.

[0018] Specifically, raw hardware data is collected through the first preset data interface and the second preset data interface, in accordance with a unified first preset data format and preset sampling frequency, to ensure efficient and standardized data transmission and support synchronous / asynchronous data acquisition. Based on the standard baseboard management controller data and standard hardware data, the status of the baseboard management controller and the hardware are determined, thereby determining the server status. This enables the identification of "functional failure caused by baseboard management controller resource overload", thereby improving the reliability and operational efficiency of the system.

[0019] In a specific embodiment, hardware data acquisition: Through the first preset data interface, namely the standard data bus interface of the open-source baseboard management controller firmware project, such as the org.openbmc.Sensors series of interfaces, subscribe to server hardware sensor data, including processor temperature, processor voltage, fan speed, hard disk data, and memory error rate, etc. The sampling frequency can be configured in the form of a configuration file, for example, setting 1 second / time as the preset sampling frequency to ensure real-time performance. The first preset data format is .json.

[0020] In specific implementation, the baseboard management controller collects data through a second preset data interface, namely a custom data bus interface, such as org.openbmc.BMCResources, which collects local core resource data of the baseboard management controller, including processor utilization, memory usage, remaining memory capacity, and storage resource (such as cache database and log) usage by core.

[0021] In practice, data preprocessing involves "null value removal, range verification, and format standardization" of the collected raw data to prevent abnormal data from affecting upper-layer functions. The preprocessed data is stored in a local shared cache, such as a lightweight cache, which supports concurrent reading by multiple modules and notifies the upper-layer modules through a "data ready signal".

[0022] Further, the original hardware data is preprocessed to obtain standard hardware data, including: performing null value removal processing on the original hardware data to obtain intermediate hardware data; determining the hardware data range corresponding to the intermediate hardware data and comparing the value of the intermediate hardware data with the hardware data range; in response to the value of the intermediate hardware data being within the hardware data range, converting the intermediate hardware data into standard hardware data according to the second preset data format.

[0023] Specifically, by performing "null value removal, range verification, and format standardization" on the raw hardware data, the reliability of subsequent data analysis and data application is ensured.

[0024] In a specific embodiment, the second preset data format is a data format that conforms to the transmission conditions of the data acquisition module's interactive interface. Preprocessing the original baseboard management controller data is the same as or similar to preprocessing the original hardware data. Here, data range indicates the data range of the corresponding hardware data.

[0025] Furthermore, the standard baseboard management controller data includes at least the standard processor utilization rate and the standard remaining memory capacity. The preset baseboard management controller data thresholds include at least a first processor utilization rate threshold, a second processor utilization rate threshold, a first remaining memory capacity threshold, and a second remaining memory capacity threshold. Based on the standard baseboard management controller data and the preset baseboard management controller data thresholds, the baseboard management controller state is determined, including: comparing the standard processor utilization rate with the first and second processor utilization rate thresholds, and simultaneously comparing the standard remaining memory capacity with the first and second remaining memory capacity thresholds; responding to a standard processor utilization rate greater than or equal to... If the first processor utilization threshold and / or the standard memory remaining capacity is less than the second memory remaining capacity threshold, the baseboard management controller is determined to be in an overload state; if the standard processor utilization is greater than the second processor utilization threshold and the standard processor utilization is less than the first processor utilization threshold, and / or the standard memory remaining capacity is greater than or equal to the second memory remaining capacity threshold and the standard memory remaining capacity is less than the first memory remaining capacity threshold, the baseboard management controller is determined to be in a warning state; if the standard processor utilization is less than or equal to the second processor utilization threshold and the standard memory remaining capacity is greater than or equal to the first memory remaining capacity threshold, the baseboard management controller is determined to be in a normal state.

[0026] Specifically, the status of the baseboard management controller is determined based on the first processor utilization threshold, the second processor utilization threshold, the first memory remaining capacity threshold, and the second memory remaining capacity threshold, so as to ensure that the core business operates stably under the current baseboard management controller status.

[0027] In a specific embodiment, the baseboard management controller resource status is monitored by reading the baseboard management controller data output from the data acquisition layer in real time. A "real-time baseboard management controller resource dashboard" can be built on the front end, including processor utilization trends, changes in remaining memory capacity, and storage usage curves, displayed in detail by core / process dimension (with a focus on monitoring the resource usage of core functional layer processes, such as how much processor and memory the artificial intelligence module process is currently using). Baseboard management controller resource management is implemented by designing a baseboard management controller resource monitoring module to monitor processor, memory, and other resources in real time and provide tiered warnings. In case of overload, resources are dynamically allocated according to process priority, non-core processes are paused, and the artificial intelligence module is forced to hibernate to ensure the stability of core functions.

[0028] In a specific embodiment, the first processor utilization threshold is 90%, the second processor utilization threshold is 70%, the first memory remaining capacity threshold is 400MB, and the second memory remaining capacity threshold is 100MB. The preset baseboard management controller data thresholds can be set according to actual conditions. Overload determination and warning: Based on the preset baseboard management controller data thresholds (which can be dynamically adjusted via the web configuration interface), the baseboard management controller status is determined as follows: Normal state: processor utilization ≤ 70% and remaining memory ≥ 400MB; Warning state: 70% < processor utilization < 90%, and / or 100MB ≤ remaining memory < 400MB; Overload state: processor utilization ≥ 90%, and / or remaining memory < 100MB. When entering a warning state / overload state, a "baseboard management controller warning message" is generated, including the warning level, trigger indicators, and current baseboard management controller data. The baseboard management controller warning message is then synchronously pushed to the collaborative scheduling layer and the output interaction layer.

[0029] Furthermore, based on the status of the baseboard management controller, basic management controller warning information is generated, including: in response to the baseboard management controller being in an overload state, determining the warning level of the baseboard management controller as a first warning level, and generating first basic management controller warning information based on the first warning level and standard baseboard management controller data; in response to the baseboard management controller being in a warning state, determining the warning level of the baseboard management controller as a second warning level, and generating second basic management controller warning information based on the second warning level and standard baseboard management controller data; wherein, the urgency level of the first warning level is higher than that of the second warning level.

[0030] Furthermore, the preset hardware data threshold includes at least a preset hardware anomaly score threshold. Determining the hardware status based on standard hardware data and the preset hardware data threshold includes: acquiring first historical standard hardware data within a first preset time period, inputting the first historical standard hardware data into a preset long short-term memory network to obtain the predicted value of the standard hardware data at the current moment; determining the actual value of the standard hardware data at the current moment, and obtaining the standard hardware data residual value at the current moment based on the actual value and the predicted value; inputting the standard hardware data residual value into a preset isolated forest model to obtain a hardware anomaly score; and determining the hardware status based on the hardware anomaly score and the preset hardware anomaly score threshold.

[0031] Specifically, based on a preset long short-term memory network and a preset isolated forest model, a hardware anomaly score is determined, and then the hardware status is determined based on the hardware anomaly score, thereby improving the system's hardware fault identification and processing speed.

[0032] In a specific embodiment, the first preset time period is 10 minutes. Based on the set frequency, the collaborative scheduling layer sends a signal to invoke the monitoring algorithm module. The monitoring algorithm module determines whether an alert is needed based on set standards. For example, it might invoke a common statistical algorithm every 5 minutes to calculate the data characteristics within those 5 minutes, compare them with previously calculated feature sequences, and output the degree of anomaly in the most recent 5 minutes. If the degree of anomaly exceeds a preset standard, an alert is issued. Alternatively, it might invoke a Long Short-Term Memory network every 10 minutes to predict the processor temperature at the next moment, compare it with the collected actual value (or the actual value after noise reduction and preprocessing, or the average or median), calculate the residual, and then invoke the Isolation Forest algorithm to identify whether the residual is abnormal. Simultaneously, the calculated data indicators, such as the data characteristics or residuals mentioned above, are stored in a database to avoid recalculation during subsequent use. Alert grading: Alerts can be graded with different thresholds. If the first hardware anomaly score threshold is exceeded, a level 1 alert message is pushed, and so on. In addition, the warning level for key hardware can be appropriately upgraded. For example, if the processor is in the second warning state, the first hardware warning information can also be generated. Warning information packaging: Generate standardized hardware warning information, including warning level, fault type, associated sensor ID, triggering reason and real-time data / predicted data. Store the hardware warning information in a lightweight cache or shared memory and send it to the collaborative scheduling layer.

[0033] In a specific embodiment, the artificial intelligence module includes: Fault Diagnosis: Receiving hardware warning information pushed by the collaborative scheduling layer, combining it with historical hardware data (last 24 hours) from the data acquisition layer, and analyzing the root cause of the fault through a fault diagnosis model (e.g., "high temperature caused by fan jamming"). The model type is selected according to business needs, including Long Short-Term Memory Networks and Convolutional Neural Networks, etc., and outputting diagnostic results (including cause description, fault probability, and scope of impact); Natural Language Interaction: Receiving user natural language queries (e.g., "How to solve the fan warning") through a "user interaction interface", and generating structured answers (including operation steps and precautions) by combining real-time warning information and diagnostic results; Result Feedback: Feeding back the diagnostic results and optimization suggestions (e.g., "adjust the monitoring algorithm threshold") to the collaborative scheduling layer, forming a functional closed loop.

[0034] In a specific embodiment, the resource scheduling module takes "absolute priority of basic functions and minimum adaptation of artificial intelligence modules" as its core principle to ensure that the artificial intelligence model does not occupy basic function resources. The specific design is as follows: (1) Process priority division: P0 (highest, core of basic functions): hardware data acquisition process and baseboard management controller data acquisition process of data acquisition layer; baseboard management controller resource status monitoring process of resource monitoring layer; first-level early warning direct push process of output interaction layer, to ensure that "data source is not interrupted, baseboard management controller status can be monitored, and emergency early warning can be pushed", and resources are allocated first in any case. P1 (second highest, auxiliary of basic functions): overload judgment and early warning process of resource monitoring layer; web page core service process of output interaction layer (only retaining early warning display and configuration modification functions), to assist the operation of basic functions, to ensure that baseboard management controller resource overload can be identified in time and users can view core early warning in real time. P2 (medium, core business): monitoring algorithm process of core function layer (first-level / second-level / third-level early warning logic calculation); log storage process of output interaction layer (only retaining early warning log and baseboard management controller resource log storage), to realize the core business logic of hardware fault early warning, and resource allocation should be carried out without affecting P0 / P1. P3 (Lower, Auxiliary Functions): Non-core web page function processes in the output interaction layer (e.g., historical data report generation and non-core configuration interface loading); timed synchronization processes of the data synchronization module (synchronizing historical logs to external platforms), providing non-essential auxiliary operation and maintenance functions. Resource consumption can be dynamically compressed, and priority is lower than core business. P4 (Lowest, Dedicated to the Artificial Intelligence Module): The artificial intelligence module process in the core function layer. As an intelligent auxiliary function, it only runs when P0-P3 process resources are fully sufficient. Under any circumstances, it must avoid basic functions and core business, and is not allowed to affect the basic operation of the system.

[0035] In a specific embodiment, such as Figure 2As shown, the functional collaboration module and the artificial intelligence module are in a delayed collaboration and do not interfere with the basic process. (1) Artificial intelligence module process wake-up strategy: The artificial intelligence model process is in a dormant state by default. It can be woken up by the functional collaboration module when all of the following prerequisites are met: a. The P0-P3 level process resource occupancy meets the "idle threshold"; b. There is no first-level warning push task in the system (the first-level warning task has the highest priority and must be completed first); c. The local resource monitoring module of the baseboard management controller has no overload warning output (the basic function must be guaranteed first under overload conditions); After the artificial intelligence model process is woken up, the "single task triggering" mechanism is adopted, that is, after completing a single fault diagnosis or a single natural language interaction task, the resources are released immediately and the process returns to the dormant state. Continuous operation is not supported. (2) Early Warning-Diagnosis Collaborative Logic (Basic Early Warning Priority): For the early warning information output by the monitoring algorithm module, the functional collaboration module formulates differentiated collaboration strategies according to the early warning level to ensure that the basic early warning process does not rely on the artificial intelligence model: First hardware early warning information: directly triggers the P0 level first-level early warning direct push process, completes the output operations such as web front-end display, baseboard management controller local indicator alarm, etc., without triggering the artificial intelligence model wake-up, and ensures that the early warning response delay is ≤100ms. For example Figure 3 As shown, fault diagnosis: When a user needs to diagnose a problem (and the resource detection layer finds that the current system resources are sufficient), the function collaboration module will schedule the data analysis results of the monitoring algorithm module and the artificial intelligence module in sequence, and input the merged complete background data and the problem to be analyzed into the model. If the resources are insufficient, the front-end page will prompt the user that the current system is under high load and does not support the operation of the artificial intelligence module.

[0036] In a specific embodiment, the anomaly isolation module is: anomaly isolation of the artificial intelligence module / monitoring algorithm module. (1) Anomaly monitoring and isolation of the artificial intelligence module: the artificial intelligence module process status is monitored in real time by subscribing to the artificial intelligence module status change event through the data bus. When the signal of the module status change is received, the parameters are parsed and the anomaly judgment is performed. The parameters may include the model running status, process number, timestamp, etc. When the following abnormal scenarios occur, the anomaly isolation operation is performed immediately: a. abnormal running status: if the running status is "ERROR", it is judged as an internal error of the artificial intelligence module, such as model loading failure, inference logic abnormality, etc.; b. resource occupation limit: if the processor utilization rate is >70% or the memory occupation is >70% (pre-set resource limit), and it lasts for 2 signal cycles (1 second), it is judged as a resource occupation abnormality; c. task dead: if the running status is "RUNNING", the task status does not change for 3 consecutive signal cycles (1.5 seconds), and the processor utilization rate is <1% (no actual calculation), it is judged as a task dead anomaly. The abnormal isolation operation includes: forcibly terminating the artificial intelligence module process, releasing associated processor and memory resources, marking the artificial intelligence function module as "abnormal state", and pushing abnormal information through the front-end page of the baseboard management controller, without affecting the normal operation of other modules. (2) Artificial intelligence module fault recovery strategy: The recovery process after the artificial intelligence module process is abnormal follows the principle of "basic functions first" to avoid the recovery operation occupying basic resources. Recovery priority: The system prioritizes the fault recovery of P0-P3 level processes. After the basic functions are restored to normal and the resources enter the "idle threshold", the recovery process of the artificial intelligence model process is started. Retry mechanism: After the first recovery fails, the system performs a second recovery after a 5-minute interval. If the second recovery still fails, the artificial intelligence function module is marked as "fault state" and the recovery operation is suspended. Users need to manually trigger the recovery through the "fault reset interface" on the web page front end to avoid repeated retries occupying system resources.

[0037] Furthermore, the preset hardware anomaly score threshold includes at least a first hardware anomaly score threshold and a second hardware anomaly score threshold. Determining the hardware state based on the hardware anomaly score and the preset hardware anomaly score threshold includes: comparing the hardware anomaly score with the first hardware anomaly score threshold; determining the hardware state as a first warning state in response to the hardware anomaly score being greater than or equal to the first hardware anomaly score threshold; comparing the hardware anomaly score with the second hardware anomaly score threshold in response to the hardware anomaly score being less than the first hardware anomaly score threshold; determining the hardware state as another warning state in response to the hardware anomaly score being greater than or equal to the second hardware anomaly score threshold, wherein the other warning states include at least the second warning state, and the urgency of the first warning state is higher than the urgency of the second warning state; and determining the hardware state as a normal state in response to the hardware anomaly score being less than the second hardware anomaly score threshold.

[0038] In a specific embodiment, a first hardware anomaly score threshold and a second hardware anomaly score threshold are set according to the actual situation and hardware type. The second hardware anomaly score threshold can also be divided to obtain more warning states and warning levels.

[0039] Furthermore, based on the hardware status, hardware early warning information is generated, including: in response to the hardware status being a first early warning state, determining the hardware early warning level as a first early warning level, and generating first hardware early warning information based on the first early warning level, the predicted value of standard hardware data, and the actual value of standard hardware data; in response to the hardware status being another early warning state, determining the hardware early warning level as another early warning level, and generating second hardware early warning information based on the other early warning level, the predicted value of standard hardware data, and the actual value of standard hardware data; wherein, other early warning levels include at least the second early warning level, and the second early warning level corresponds to the second early warning state, and the urgency of the first early warning level is higher than that of the second early warning level.

[0040] Specifically, generating hardware warning signals based on hardware status to achieve real-time warning and classification of hardware faults is the core of rapid response to hardware problems.

[0041] Furthermore, the server status monitoring method also includes: constructing an initial long short-term memory network; acquiring second historical standard hardware data within a second preset time period, wherein the second preset time period is longer than the first preset time period; training the initial long short-term memory network based on the second historical standard hardware data to obtain a preset long short-term memory network, wherein the server status corresponding to the second historical standard hardware data is a normal state.

[0042] Specifically, the initial long short-term memory network is trained based on the second historical standard hardware data to obtain a long short-term memory network that can accurately predict the standard hardware data in normal mode.

[0043] In a specific embodiment, the second preset time period is longer than the first preset time period, and can be set to the most recent 3 months, or adjusted according to the actual situation.

[0044] Furthermore, the server status monitoring method also includes: constructing an initial isolated forest model; inputting the second historical standard hardware data into a preset long short-term memory network to obtain the predicted value of the historical standard hardware data; obtaining the actual value of the historical standard hardware data, and obtaining the residual value of the historical standard hardware data based on the actual value and the predicted value of the historical standard hardware data; and training the initial isolated forest model based on the residual value of the historical standard hardware data to obtain the preset isolated forest model.

[0045] Specifically, the initial isolated forest model is trained based on the residual values ​​of historical standard hardware data to obtain an anomaly detector that can determine whether the new input residuals after training deviate from the historical normal pattern.

[0046] In addition, determining the hardware status based on the hardware anomaly score and a preset hardware anomaly score threshold also includes: determining the key hardware types in the server based on the relevance of the hardware to the business and the frequency of hardware usage; determining the hardware type of the current hardware in response to the current hardware status being a second warning state, where the second warning state has the highest urgency among the other warning states; comparing the current hardware type with the key hardware types; determining the current hardware type as a first warning state in response to the current hardware type belonging to a preset key hardware type; and determining the current hardware type as a second warning state in response to the current hardware type not belonging to a preset key hardware type.

[0047] Specifically, by appropriately adjusting the warning status of key hardware according to the hardware type, the probability of major global accidents is effectively reduced, the reliability of core components is improved, and thus the stability and business continuity of the system are enhanced with the highest efficiency.

[0048] In a specific embodiment, the web interface provides a visual web interface, including a "Real-time Baseboard Management Controller Resource Monitoring Dashboard" (including hardware status, baseboard management controller status, and processor usage and remaining memory capacity of the AI ​​module and monitoring algorithm module), an "Advanced Early Warning Management Center" (including an early warning list and processing records, mainly recording early warnings from the monitoring algorithm module and AI module), a "System Configuration Interface" (including sampling frequency, various thresholds, and resource quotas), and a "Natural Language Query Entry." Early warning push notifications support multiple channels: Direct push: Receiving first-level early warning information from the monitoring algorithm module and pushing it in real-time via web interface pop-ups, local indicator lights on the baseboard management controller (solid red), and a buzzer (intermittent beeping), with a push latency ≤100ms; Auxiliary push: Receiving second- / third-level early warnings and AI diagnostic results forwarded by the collaborative scheduling layer and pushing them via SMS, email, and the operation and maintenance platform interface, supporting user-defined push channels and rules. Data Synchronization: Alarm records, diagnostic results, and baseboard management controller resource logs can be synchronized to an external operation and maintenance platform. It supports "real-time synchronization" (alarm information) and "scheduled synchronization" (historical logs, default 1 hour / time). The synchronization interface uses a standardized application interface to ensure compatibility. Forced Termination Function: A detailed interface for the current baseboard management controller resource usage is added to the page, displaying the specific tasks, running status, and resource usage of the artificial intelligence module and monitoring algorithm module. It also displays the resource usage of basic functions (details can be omitted). For the artificial intelligence module and monitoring algorithm module, an interface or front-end interactive button is provided to allow users to manually force termination / restart the process.

[0049] It should be understood that, although Figure 1 , Figure 2 , Figure 3 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 , Figure 2 , Figure 3 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0050] In the second embodiment, as Figure 4As shown, a server status monitoring system is provided, including: a data acquisition module, which is used to acquire raw hardware data through a first preset data interface at a preset sampling frequency, and acquire raw baseboard management controller data through a second preset data interface at a preset sampling frequency, wherein the data format of the raw hardware data and the raw baseboard management controller data is the first preset data format; the data acquisition module is also used to preprocess the raw hardware data to obtain standard hardware data, and preprocess the raw baseboard management controller data to obtain standard baseboard management controller data; and a baseboard management controller resource status monitoring module, which is used to acquire... The system includes: a preset baseboard management controller data threshold and a preset hardware data threshold; an overload judgment and early warning module, which determines the baseboard management controller status based on the standard baseboard management controller data and the preset baseboard management controller data threshold, and generates basic management controller early warning information based on the baseboard management controller status; a monitoring algorithm module, which determines the hardware status based on the standard hardware data and the preset hardware data threshold, and generates hardware early warning information based on the hardware status; and an early warning push module, which obtains server early warning information based on the basic management controller early warning information and the hardware early warning information, and determines the server status based on the server early warning information.

[0051] In a specific embodiment, such as Figure 5 As shown, the server status monitoring system comprises a basic support layer (data acquisition module), a resource assurance layer (resource monitoring layer), a core function layer (business implementation layer), a collaborative scheduling layer (system central layer), and an output interaction layer (user interaction layer). These five layers interact through standardized interfaces, resolving the issue of loose module architecture and improving the system's maintainability and scalability.

[0052] In a specific embodiment, the basic support layer is positioned as follows: it provides standardized real-time data input for the entire system, serving as the foundation for functional implementation; it includes modules: a hardware data acquisition module and a baseboard management controller data acquisition module; its core functions are: hardware data acquisition, baseboard management controller data acquisition, and data preprocessing; its interaction interface provides a standardized data interface that allows the core functional layer to obtain data by "data type" (hardware data / baseboard management controller data) and "time range" (real-time data / historical data). The interface supports both synchronous query and asynchronous subscription modes.

[0053] In a specific embodiment, the resource monitoring layer (resource assurance layer) is positioned to monitor the local resource status of the baseboard management controller in real time, prevent system risks caused by resource overload of the baseboard management controller, and ensure the stable operation of the system. It includes modules: a baseboard management controller resource status monitoring module and an overload judgment and early warning module. Its core functions are: baseboard management controller resource status monitoring and overload judgment and early warning. Its interaction interface provides a baseboard management controller data query interface (called by the collaborative scheduling layer) to the upper layer and a baseboard management controller early warning information interface (subscribed by the output interaction layer) to the lower layer.

[0054] In a specific embodiment, the core functional layer (business implementation layer) is positioned as follows: It implements the core business functions of the system, including hardware fault early warning and AI-assisted diagnosis, and is the core embodiment of the system's value; it includes the following modules: a monitoring algorithm module and an artificial intelligence module. Specifically, the monitoring algorithm module stores the implementations of various algorithms, including statistical methods for calculating data features, such as calculating data distribution, variance, and mean, as well as complex algorithms such as machine learning and deep learning, such as Long Short-Term Memory networks and Isolation Forest algorithms. The algorithms are uniformly encapsulated and presented in the form of interfaces for invocation; this module first receives hardware data output from the data acquisition module, or can obtain it through a lightweight cache, parses the hardware data, and generates the data format required by the corresponding algorithm; its functional positioning is: to realize real-time early warning and classification of hardware faults based on hardware data, which is the core of rapid response to hardware problems; its core logic is: early warning classification and generation of early warning information. The artificial intelligence module typically consumes significant resources. Its function is to diagnose faults, generate solutions, and facilitate natural language interaction with users, based on expert knowledge, early warning information, and historical data, thereby improving the intelligence level of operations and maintenance. Its core functional logic includes fault diagnosis, natural language interaction, and result feedback. It supports both "on-demand wake-up" and "continuous operation" modes, which can be dynamically configured or disabled through the collaborative scheduling layer (on-demand wake-up is the default to reduce resource consumption). However, if resource consumption affects basic functions, the collaborative scheduling layer will automatically stop the module. The monitoring algorithm module and the artificial intelligence module work in a closed loop: the monitoring algorithm generates standardized early warning information, and the artificial intelligence module diagnoses faults and provides interactive Q&A based on early warnings and historical data. Together, they form a closed loop of "early warning-diagnosis-feedback-optimization" through the collaborative scheduling layer, dynamically optimizing algorithm parameters.

[0055] In a specific embodiment, the collaborative scheduling layer (the system's central layer) is positioned as follows: coordinating the operating rhythm of modules at each layer, allocating system resources, managing functional collaboration logic, prioritizing the operation of core basic functions (data acquisition, baseboard management controller resource monitoring, and first-level early warning), and operating the artificial intelligence module as a non-core function with the principle of "lowest priority and resource avoidance" to avoid any impact on the basic functions; it includes the following modules: resource scheduling module, functional collaboration module, and exception handling module.

[0056] In a specific embodiment, the output interaction layer (user interaction layer) is positioned as follows: to realize the interaction between the system and the user / external platform, including the output of warning information, user operation entry, and data synchronization, etc., and is the layer that presents the value of the system; it includes modules: web page interaction module, warning push module, and data synchronization module; core functions: web page interaction, warning push (including direct push and auxiliary push), data synchronization, and forced termination function.

[0057] In a specific embodiment, signal-response interaction: modules interact based on the "signal-response" mechanism, clarifying core processes such as early warning push, artificial intelligence diagnosis, and resource overload emergency response, avoiding coupling, and ensuring rapid system response.

[0058] For specific limitations regarding the server status monitoring system, please refer to the limitations of the server status monitoring method described above, which will not be repeated here. Each module in the aforementioned server status monitoring system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in an electronic device, or stored in the memory of the electronic device as software, so that the processor can call and execute the corresponding operations of each module.

[0059] In a third embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it performs the following steps: acquiring raw hardware data through a first preset data interface at a preset sampling frequency, and acquiring raw substrate management controller data through a second preset data interface at a preset sampling frequency, wherein the data formats of the raw hardware data and the raw substrate management controller data are both the first preset data format; preprocessing the raw hardware data to obtain standard hardware data, and preprocessing the raw substrate management controller data to obtain standard substrate management controller data; obtaining a preset substrate management controller data threshold and a preset hardware data threshold; determining the substrate management controller status based on the standard substrate management controller data and the preset substrate management controller data threshold, and generating basic management controller warning information based on the substrate management controller status; determining the hardware status based on the standard hardware data and the preset hardware data threshold, and generating hardware warning information based on the hardware status; obtaining server warning information based on the basic management controller warning information and the hardware warning information, and determining the server status based on the server warning information.

[0060] When the program instructions are read and executed by one or more processors, they can also perform operations corresponding to the steps in the above method embodiments, as described above, and will not be repeated here. Reference Figure 6This exemplifies the architecture of an electronic device, which may include a processor 610, a video display adapter 611, a disk drive 612, an input / output interface 613, a network interface 614, and a memory 620. The processor 610, video display adapter 611, disk drive 612, input / output interface 613, network interface 614, and memory 620 can communicate with each other via a communication bus 630.

[0061] The processor 610 can be implemented using a general-purpose central processing unit (CPU), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to achieve the technical solution provided in this application.

[0062] The memory 620 can be implemented as a read-only memory (ROM), random access memory (RAM), static storage device, dynamic storage device, etc. The memory 620 can store an operating system 621 for controlling the operation of the electronic device 600, and a basic input / output system (BIOS) 622 for controlling the low-level operations of the electronic device 600. Additionally, it can store a web browser 623, data storage management 624, and an icon / font processing system 625, etc. The aforementioned icon / font processing system 625 can be the application program that specifically implements the aforementioned steps in this embodiment. In summary, when implementing the technical solution provided in this application through software or firmware, the relevant program code is stored in the memory 620 and executed by the processor 610.

[0063] Input / output interface 613 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.

[0064] Network interface 614 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0065] Bus 630 includes a pathway for transmitting information between various components of the device, such as processor 610, video display adapter 611, disk drive 612, input / output interface 613, network interface 614, and memory 620.

[0066] In addition, the electronic device 600 can also obtain information on specific claim conditions from a virtual resource object claim condition information database (not shown in the figure) for use in condition judgment.

[0067] It should be noted that although the above-described electronic device 600 only shows a processor 610, a video display adapter 611, a disk drive 612, an input / output interface 613, a network interface 614, a memory 620, and a bus 630, in specific implementations, the electronic device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the solution of this application, and does not necessarily include all the components shown in the figures.

[0068] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause an electronic device (which may be a personal computer, cloud server, or network device, etc.) to execute the methods of various embodiments or some parts of the embodiments of this application.

[0069] In a fourth embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it performs the following steps: acquiring raw hardware data through a first preset data interface at a preset sampling frequency, and acquiring raw substrate management controller data through a second preset data interface at a preset sampling frequency, wherein the data formats of the raw hardware data and the raw substrate management controller data are both the first preset data format; preprocessing the raw hardware data to obtain standard hardware data, and preprocessing the raw substrate management controller data to obtain standard substrate management controller data; obtaining a preset substrate management controller data threshold and a preset hardware data threshold; determining the substrate management controller status based on the standard substrate management controller data and the preset substrate management controller data threshold, and generating basic management controller warning information based on the substrate management controller status; determining the hardware status based on the standard hardware data and the preset hardware data threshold, and generating hardware warning information based on the hardware status; obtaining server warning information based on the basic management controller warning information and the hardware warning information, and determining the server status based on the server warning information.

[0070] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0071] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0072] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application.

[0073] In the fifth embodiment, a computer program product is provided, on which a computer program is stored. When the computer program is executed by a processor, it performs the following steps: acquiring raw hardware data through a first preset data interface at a preset sampling frequency, and acquiring raw substrate management controller data through a second preset data interface at a preset sampling frequency, wherein the data formats of the raw hardware data and the raw substrate management controller data are both the first preset data format; preprocessing the raw hardware data to obtain standard hardware data, and preprocessing the raw substrate management controller data to obtain standard substrate management controller data; obtaining a preset substrate management controller data threshold and a preset hardware data threshold; determining the substrate management controller status based on the standard substrate management controller data and the preset substrate management controller data threshold, and generating basic management controller warning information based on the substrate management controller status; determining the hardware status based on the standard hardware data and the preset hardware data threshold, and generating hardware warning information based on the hardware status; obtaining server warning information based on the basic management controller warning information and the hardware warning information, and determining the server status based on the server warning information.

[0074] In a fifth embodiment, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it performs the following steps: acquiring raw hardware data through a first preset data interface at a preset sampling frequency, and acquiring raw baseboard management controller data through a second preset data interface at a preset sampling frequency, wherein the data formats of the raw hardware data and the raw baseboard management controller data are both the first preset data format; preprocessing the raw hardware data to obtain standard hardware data, and preprocessing the raw baseboard management controller data to obtain standard baseboard management controller data; obtaining a preset baseboard management controller data threshold and a preset hardware data threshold; determining the baseboard management controller status based on the standard baseboard management controller data and the preset baseboard management controller data threshold, and generating basic management controller warning information based on the baseboard management controller status; determining the hardware status based on the standard hardware data and the preset hardware data threshold, and generating hardware warning information based on the hardware status; obtaining server warning information based on the basic management controller warning information and the hardware warning information, and determining the server status based on the server warning information.

[0075] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer program product, and when the computer program is executed, it can include the processes of the embodiments of the methods described above.

[0076] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0077] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application.

Claims

1. A method for monitoring server status, characterized in that, The method includes: According to the preset sampling frequency, raw hardware data is collected through the first preset data interface, and raw substrate management controller data is collected through the second preset data interface according to the preset sampling frequency, wherein the data format of the raw hardware data and the raw substrate management controller data is the first preset data format; The original hardware data is preprocessed to obtain standard hardware data, and the original baseboard management controller data is preprocessed to obtain standard baseboard management controller data. Obtain preset baseboard management controller data thresholds and preset hardware data thresholds; Based on the standard baseboard management controller data and the preset baseboard management controller data threshold, the baseboard management controller status is determined, and basic management controller early warning information is generated based on the baseboard management controller status. Based on the standard hardware data and the preset hardware data threshold, the hardware status is determined, and hardware warning information is generated based on the hardware status. Based on the basic management controller warning information and the hardware warning information, server warning information is obtained, and the server status is determined based on the server warning information. The standard substrate management controller data includes at least standard processor utilization and standard remaining memory capacity. The preset substrate management controller data thresholds include at least a first processor utilization threshold, a second processor utilization threshold, a first remaining memory capacity threshold, and a second remaining memory capacity threshold. Determining the substrate management controller status based on the standard substrate management controller data and the preset substrate management controller data thresholds includes: The standard processor utilization rate is compared with the first processor utilization rate threshold and the second processor utilization rate threshold, and the standard remaining memory capacity is compared with the first remaining memory capacity threshold and the second remaining memory capacity threshold. In response to the standard processor utilization rate being greater than or equal to the first processor utilization rate threshold, and / or the standard memory remaining capacity being less than the second memory remaining capacity threshold, the baseboard management controller is determined to be in an overload state. In response to the standard processor utilization rate being greater than the second processor utilization rate threshold and the standard processor utilization rate being less than the first processor utilization rate threshold, and / or the standard memory remaining capacity being greater than or equal to the second memory remaining capacity threshold and the standard memory remaining capacity being less than the first memory remaining capacity threshold, the baseboard management controller is determined to be in a warning state. In response to the standard processor utilization rate being less than or equal to the second processor utilization rate threshold, and the standard memory remaining capacity being greater than or equal to the first memory remaining capacity threshold, the baseboard management controller is determined to be in a normal state.

2. The method according to claim 1, characterized in that, The preprocessing of the raw hardware data to obtain standard hardware data includes: The original hardware data is processed to remove null values ​​to obtain intermediate hardware data; Determine the hardware data range corresponding to the intermediate hardware data, and compare the value of the intermediate hardware data with the hardware data range; In response to the value of the intermediate hardware data being within the hardware data range, the intermediate hardware data is converted into the standard hardware data according to the second preset data format.

3. The method according to claim 1, characterized in that, The step of generating basic management controller early warning information based on the status of the baseboard management controller includes: In response to the overload state of the baseboard management controller, the warning level of the baseboard management controller is determined to be the first warning level, and a first basic management controller warning message is generated based on the first warning level and the standard baseboard management controller data. In response to the baseboard management controller being in the warning state, the warning level of the baseboard management controller is determined to be the second warning level, and a second basic management controller warning information is generated based on the second warning level and the standard baseboard management controller data; The first warning level is more urgent than the second warning level.

4. The method according to claim 1, characterized in that, The preset hardware data threshold includes at least a preset hardware anomaly score threshold. The step of determining the hardware status based on the standard hardware data and the preset hardware data threshold includes: Obtain the first historical standard hardware data within the first preset time period in the past, and input the first historical standard hardware data into a preset long short-term memory network to obtain the predicted value of the standard hardware data at the current moment; Determine the actual value of the standard hardware data at the current moment, and obtain the standard hardware data residual value at the current moment based on the actual value of the standard hardware data and the predicted value of the standard hardware data; The standard hardware data residual values ​​are input into a preset isolated forest model to obtain hardware anomaly scores. The hardware status is determined based on the hardware anomaly score and the preset hardware anomaly score threshold.

5. The method according to claim 4, characterized in that, The preset hardware anomaly score threshold includes at least a first hardware anomaly score threshold and a second hardware anomaly score threshold. Determining the hardware state based on the hardware anomaly score and the preset hardware anomaly score threshold includes: Compare the hardware anomaly score with the first hardware anomaly score threshold. In response to the hardware anomaly score being greater than or equal to the first hardware anomaly score threshold, the hardware state is determined to be a first warning state. In response to the hardware anomaly score being less than the first hardware anomaly score threshold, the hardware anomaly score is compared with the second hardware anomaly score threshold; In response to the hardware anomaly score being greater than or equal to the second hardware anomaly score threshold, the hardware state is determined to be another warning state, wherein the other warning state includes at least the second warning state, and the urgency of the first warning state is higher than the urgency of the second warning state; In response to the hardware anomaly score being less than the second hardware anomaly score threshold, the hardware state is determined to be normal.

6. The method according to claim 5, characterized in that, The step of generating hardware warning information based on the hardware status includes: In response to the hardware state being the first warning state, the warning level of the hardware is determined to be the first warning level, and a first hardware warning message is generated based on the first warning level, the predicted value of the standard hardware data, and the actual value of the standard hardware data. In response to the hardware status being the other warning status, the warning level of the hardware is determined to be another warning level, and a second hardware warning information is generated based on the other warning level, the predicted value of the standard hardware data, and the actual value of the standard hardware data; Among them, the other warning levels include at least a second warning level, and the second warning level corresponds to the second warning state, and the urgency of the first warning level is higher than that of the second warning level.

7. The method according to claim 4, characterized in that, The method further includes: Construct an initial long short-term memory network; Obtain second historical standard hardware data within a second preset time period, wherein the second preset time period is longer than the first preset time period; The initial long short-term memory network is trained based on the second historical standard hardware data to obtain the preset long short-term memory network, wherein the server status corresponding to the second historical standard hardware data is in a normal state.

8. The method according to claim 7, characterized in that, The method further includes: Construct an initial isolated forest model; The second historical standard hardware data is input into the preset long short-term memory network to obtain the predicted value of the historical standard hardware data. Obtain the actual value of historical standard hardware data, and obtain the residual value of historical standard hardware data based on the actual value of historical standard hardware data and the predicted value of historical standard hardware data; The initial isolated forest model is trained based on the residual values ​​of the historical standard hardware data to obtain the preset isolated forest model.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the server status monitoring method as described in any one of claims 1 to 8 when executing the computer program.

Images