A server fault determination method, device, equipment and readable storage medium

Abstract

The present application discloses a method, device, equipment and readable storage medium for determining server faults, the method comprising: obtaining the inspection cycle of the server to be inspected and the parameters of each server in the cluster; establishing an optimization model with constraints, the constraints comprising the migration constraints of the load of the server to be inspected and the inspection constraints of the server to be inspected, so as to minimize the cluster load fluctuation and / or shorten the overall inspection time of the server to be inspected; determining the inspection parameters of the server to be inspected according to the inspection cycle of the server to be inspected, the parameters of each server in the cluster and the optimization model, the inspection parameters comprising the inspection sequence of the server to be inspected and the migration sequence of the load on the server to be inspected and the server to be entered by the migration; performing fault detection on the server to be inspected according to the inspection parameters. By implementing the present application, the automatic setting of the inspection parameters can be realized, and when inspecting according to the inspection parameters, it will not cause too much fluctuation in the cluster load.

Description

Technical Field

[0001] The present application relates to the technical field of fault detection, and in particular to a server fault determination method, apparatus, device and readable storage medium. Background Art

[0002] Damage to server memory can lead to problems such as server operating system crashes, business interruptions, and data loss. In particular, damage to cloud computing host servers will affect the virtual machines running on them. Therefore, it is necessary to regularly perform memory detection on cloud computing host servers. At present, when performing memory detection on host servers in cloud computing clusters, inspection parameters are usually determined based on user experience, and then memory inspection is performed on the inspected servers according to the inspection parameters. However, this server fault detection method is set based on user experience, and the memory detection environment of the host servers in the cloud computing cluster will change. Therefore, it is easy to cause the server memory detection to fail to be completed in time within the set detection time period, and the range of servers shut down for detection in the same time period is too large, resulting in excessive load fluctuations in the cluster, affecting user experience. Summary of the invention

[0003] In view of this, the embodiments of the present application provide a server fault determination method, device, equipment and readable storage medium to solve the problem in the prior art that when inspection parameters are set based on user experience, it is easy to cause excessive load fluctuations in the cluster, affecting the user experience.

[0004] In order to solve the above problems, on the first aspect, an embodiment of the present application provides a server fault determination method, including: obtaining the inspection cycle of the server to be inspected and the parameters of each server in the cluster; establishing an optimization model with constraints, the constraints including the migration constraints of the load of the server to be inspected and the inspection constraints of the server to be inspected, so as to minimize the cluster load fluctuation and / or shorten the overall inspection time of the server to be inspected; determining the inspection parameters of the server to be inspected according to the inspection cycle of the server to be inspected, the parameters of each server in the cluster and the optimization model, the inspection parameters including the inspection order of the server to be inspected and the migration order of the load on the server to be inspected and the server to which the migration enters; and performing fault detection on the server to be inspected according to the inspection parameters.

[0005] Optionally, obtaining the inspection cycle of the server to be inspected includes: obtaining the inspection batch of the server to be inspected; and searching the inspection cycle of the server to be inspected in a mapping table between batches and inspection cycles according to the inspection batch.

[0006] Optionally, the inspection batch division step includes: obtaining application data, device data and monitoring data of each server in the cluster; dividing the servers into batches according to the application data, device data and monitoring data to obtain multiple inspection batches.

[0007] Optionally, the parameters of each server in the cluster include at least: application data, equipment data and monitoring data; the inspection parameters of the server to be inspected are determined according to the inspection cycle of the server to be inspected, the parameters of each server in the cluster and the optimization model, including: solving the optimization model according to the inspection cycle, application data, equipment data and monitoring data of the server to be inspected to obtain the inspection parameters of the server to be inspected.

[0008] Optionally, the server fault determination method further includes: obtaining the type of anomaly generated during fault detection of the server to be inspected within a preset time period and the frequency of occurrence of the anomaly; and updating the inspection cycle of the server to be inspected according to the type of anomaly and the frequency of occurrence of the anomaly.

[0009] Optionally, the server failure determination method further includes: marking a target server that cannot be inspected within the inspection cycle; and setting the target server as a server to be inspected first in the next inspection cycle.

[0010] Optionally, the server fault determination method further includes: recording execution conditions in the process of detecting faults of the server to be inspected; and updating inspection constraint conditions of the server to be inspected according to the execution conditions.

[0011] In the second aspect, an embodiment of the present application also provides a server fault determination device, including: a first acquisition unit, used to obtain the inspection cycle of the server to be inspected and the parameters of each server in the cluster; an establishment unit, used to establish an optimization model with constraints, the constraints including the migration constraints of the load of the server to be inspected and the inspection constraints of the server to be inspected, so as to minimize the cluster load fluctuation and / or shorten the overall inspection time of the server to be inspected; a determination unit, used to determine the inspection parameters of the server to be inspected according to the inspection cycle of the server to be inspected, the parameters of each server in the cluster and the optimization model, the inspection parameters including the inspection order of the server to be inspected and the migration order of the load on the server to be inspected and the server to which the migration enters; a detection unit, used to perform fault detection on the server to be inspected according to the inspection parameters.

[0012] In a third aspect, an embodiment of the present application provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor executes a server fault determination method as in the first aspect or any embodiment of the first aspect.

[0013] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute a server fault determination method as in the first aspect or any implementation scheme of the first aspect.

[0014] The server fault determination method, apparatus, equipment and readable storage medium provided in the embodiments of the present application calculate the inspection parameters of the server to be inspected by establishing an optimization model with constraints. When calculating the inspection parameters, it is necessary to consider the parameters of each server in the cluster, including the parameters of the server to be inspected, in real time. Thus, when calculating the inspection parameters, the memory detection environment of the server to be inspected is considered in real time, and the migration constraints of the load of the server to be inspected and the inspection constraints of the server to be inspected can be met. The load fluctuation in the cluster can be minimized when the server to be inspected is inspected, and / or the overall inspection time of the server to be inspected can be shortened. Compared with setting the inspection parameters based on user experience, the automatic setting of the inspection parameters is realized. Moreover, the calculated inspection parameters can minimize the cluster load fluctuation when the server to be inspected is inspected. Therefore, when the server to be inspected is inspected according to the inspection parameters, the cluster load will not fluctuate too much, thereby improving the user experience.

[0015] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of a method for determining a server failure in an embodiment of the present application;

[0017] Figure 2 This is a structural diagram of a server failure determination device in an embodiment of the present application;

[0018] Figure 3 This is a schematic diagram of the hardware structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0020] When detecting a server memory fault, the server needs to be restarted, and the detection cannot be performed while the server is running. The host server (hereinafter referred to as the server) in the cloud computing cluster has a load, such as a cloud computing virtual machine. In order not to affect the load on the server, when performing fault detection on the server, the load on the server needs to be migrated to other servers, and then the fault detection is performed. When inspecting the servers to be inspected in the same inspection batch, the load migration will cause cluster load fluctuations. In order to reduce the load fluctuation in the cluster, the inspection time of the servers to be inspected needs to be staggered, and the migration time of the load of the servers to be inspected needs to be staggered. Therefore, it is necessary to set the inspection order of the servers to be inspected, the migration order of the load on the servers to be inspected, and the servers to be migrated. At present, the detection time period of the server to be inspected, the migration time period of the load on the server to be inspected, and the server to be migrated are set according to user experience, and then the method of performing fault detection on the server is easy to cause the server memory detection to fail to be completed in time within the set detection time period, and the range of servers shut down for detection in the same time period is too large, resulting in too large load fluctuations in the cluster. For this reason, the embodiment of the present application provides a server fault determination method, which can be applied to the memory fault detection of the server in the cluster, such as Figure 1 As shown, the server failure determination method includes:

[0021] S101. Obtain the inspection cycle of the server to be inspected and the parameters of each server in the cluster.

[0022] In the embodiment of the present application, since the cluster includes many servers, when detecting server faults, inspections are usually performed according to inspection batches. The servers in each inspection batch also need to set an inspection cycle and perform inspections according to the inspection cycle. For example, the insured servers are inspected once a quarter, and the out-of-warranty servers are inspected once every two weeks or every week according to the situation. The servers to be inspected are servers in the same inspection batch, including at least one server.

[0023] The inspection of the servers in each inspection batch can be triggered by setting a timer. The timer duration is the duration of the inspection cycle of the servers in the inspection batch. When the inspection of the servers in a certain inspection batch is triggered, the inspection cycle of the servers to be inspected can be obtained by obtaining the timer duration or querying the list of servers in the inspection batch.

[0024] The server to be inspected is also a server in the cluster. The parameters of each server in the cluster include the parameters of the server to be inspected, and also include the parameters of other servers except the server to be inspected. The parameters of each server include but are not limited to application data, device data and monitoring data. Application data includes system information, data of virtual machines running on the server, information of applications running on the virtual machines, etc. Device data includes purchase time, manufacturer, model, maintenance scope, maintenance time, etc. Monitoring data includes the capacity of the virtual machine, CPU utilization, CPU capacity, memory capacity, the data center to which the server belongs, availability zone (AZ), application type, etc. The virtual machine is the load of the server.

[0025] S102. Establish an optimization model with constraints, including load migration constraints of the servers to be inspected and inspection constraints of the servers to be inspected, so as to minimize cluster load fluctuations and / or shorten the overall inspection time of the servers to be inspected.

[0026] In the embodiment of the present application, since load migration during inspection will cause cluster load fluctuation, in order to reduce the load fluctuation in the cluster, it is necessary to stagger the inspection time of the servers to be inspected and stagger the migration time of the load of the servers to be inspected. This problem belongs to an optimization problem with constraints, and the following optimization model can be established, as shown in Table 1:

[0027] Table 1

[0028]

[0029] Among them, constraints 1, 2, 3, 4, and 5 are migration constraints of the load of the server to be inspected, and constraints 6, 7, 8, 9, and 10 are inspection constraints of the server to be inspected.

[0030] S103. Determine inspection parameters of the servers to be inspected according to the inspection cycle of the servers to be inspected, the parameters of each server in the cluster and the optimization model. The inspection parameters include the inspection order of the servers to be inspected and the migration order of the load on the servers to be inspected and the servers to be migrated.

[0031] In the embodiment of the present application, all the servers to be inspected are inspected, and the overall time taken should be within the duration corresponding to an inspection cycle of the servers to be inspected. When the load of the servers to be inspected is migrated to other servers, it is necessary to determine which loads the servers to be inspected have, the capacity of each load, etc., it is necessary to determine the CPU, memory and other capacities of other servers, it is necessary to determine the CPU load rate of other servers, etc. When the servers to be inspected are inspected, it is necessary to determine the model and memory capacity configuration information of the servers to be inspected. Therefore, according to the inspection cycle of the servers to be inspected, the parameters of each server in the cluster, and the optimization goals, i.e., the constraints, the inspection order of the servers to be inspected, the load migration order on the servers to be inspected, and the servers to be migrated can be determined.

[0032] S104: Perform fault detection on the server to be inspected according to the inspection parameters.

[0033] In the embodiment of the present application, once the inspection order of the servers to be inspected and the migration order of the load on the servers to be inspected and the servers to be migrated to are determined, the servers to be inspected can be inspected according to the inspection order of the servers to be inspected.

[0034] The following is a detailed description of the steps for fault detection of the inspection server, which mainly includes:

[0035] 1. Migrate the virtual machines in the server to be inspected according to the migration order of the virtual machines and the server they migrated into. After the virtual machines are migrated out, remove the server to be inspected from the cluster, create a snapshot of the test node, and stop monitoring the server to be inspected if necessary.

[0036] 2. Restart the server to be inspected.

[0037] a) Restart the server to be inspected, select the necessary memory detection tools and analysis methods, such as using the Preboot eXecution Environment (PXE) boot method to start, use an environment with a memory detection tool, such as Windows or a Linux environment with tools installed to check hardware errors, especially memory and CPU errors.

[0038] b) Use the bare metal management tool to generate the server image to be inspected and save it.

[0039] 3. Run the necessary operating system and perform memory detection.

[0040] Take the Windows Memory Diagnostic Tool as an example:

[0041] i. You can install the Windows operating system on the bare metal server and execute the memory check program built into the Windows operating system. Then use the program to identify the corresponding window handle and screen position, and click "Restart now and check for problems" through the program.

[0042] ii. Execute the memory check process, obtain the check results from the Windows Event Viewer after the check process is completed, and parse the results.

[0043] iii. If the result is normal, restart the server to be inspected and restore the server settings to be inspected. If it is abnormal, send a message and execute the pre-set execution job.

[0044] iv. If the detection process times out, it is forced to be interrupted, and the server is restarted and connected to the cloud computing environment.

[0045] The execution cost of the running process is recorded so that it can be used in the constraint conditions to evaluate the inspection time under different detection ranges.

[0046] The server fault determination method provided in the embodiment of the present application is to calculate the inspection parameters of the server to be inspected by establishing an optimization model with constraints. When calculating the inspection parameters, it is necessary to consider the parameters of each server in the cluster, including the parameters of the server to be inspected, in real time. Therefore, when calculating the inspection parameters, the memory detection environment of the server to be inspected is considered in real time, and the migration constraints of the load of the server to be inspected and the inspection constraints of the server to be inspected can be met. Moreover, the load fluctuation in the cluster can be minimized when the server to be inspected is inspected, and / or the overall inspection time of the server to be inspected can be shortened. Compared with setting the inspection parameters based on user experience, the automatic setting of the inspection parameters is realized. Moreover, since the calculated inspection parameters can minimize the cluster load fluctuation when the server to be inspected is inspected, when the server to be inspected is inspected according to the inspection parameters, it will not cause too large fluctuations in the cluster load, thereby improving the user experience.

[0047] In an optional embodiment, in step S101, obtaining the inspection cycle of the server to be inspected includes: obtaining the inspection batch of the server to be inspected; and searching the inspection cycle of the server to be inspected in a mapping table between batches and inspection cycles according to the inspection batch.

[0048] Specifically, since the inspection cycles of the servers to be inspected are divided according to inspection batches, and a mapping table between inspection batches and inspection cycles is formed during the division, when the inspection of the servers to be inspected is started, the inspection cycle of the servers to be inspected can be found by first obtaining the inspection batches of the servers to be inspected, and then searching the mapping table between batches and inspection cycles. By pre-establishing a mapping table between the inspection batches and inspection cycles of the servers to be inspected, the inspection cycles of servers under different conditions can be formed, and the inspections of the servers in the same inspection batch can be started at the same time, and regular inspections can be performed. When obtaining the inspection cycle of the servers to be inspected, the inspection cycle of the servers to be inspected can be quickly found by obtaining the inspection batches of the servers to be inspected.

[0049] In an optional implementation, since servers in different data centers belong to different clusters, servers purchased at different times are of different ages, servers of different models may use different inspection methods, and the inspection cycles of servers with different maintenance times should be differentiated, etc., they should be placed in different inspection batches for inspection, and data such as the server's data center, purchase time, model, maintenance time, etc. will be recorded in the parameters of the servers in the cluster, such as application data, device data, and monitoring data. Therefore, the steps for dividing the inspection batches include: obtaining the application data, device data, and monitoring data of each server in the cluster; batching the servers according to the application data, device data, and monitoring data to obtain multiple inspection batches.

[0050] Specifically, the servers can be divided into batches based on the same data center, availability zone, application type, purchase time, model, maintenance information, system information, load information and application information, to obtain multiple inspection batches. The purchase time and model of the server are the equipment data of the server. The division of the same data center and availability zone depends on the monitoring data of the server. The system information, load information and application information can be obtained from the application data. Therefore, the application data, equipment data and monitoring data of each server in the cluster can be obtained, and then the servers can be divided into batches based on the same data center, availability zone, application type, purchase time, model, maintenance information, system information, load information and application information, to obtain multiple inspection batches.

[0051] In an embodiment of the present application, servers are batched according to application data, device data and monitoring data to obtain multiple inspection batches, so that servers with the same data center, availability zone, application type, purchase time, model, maintenance information, system information, load information and application information can be inspected in the same batch, and the same inspection cycle can be used for servers with the same parameters.

[0052] In an optional embodiment, step S103 determines the inspection parameters of the server to be inspected based on the inspection cycle of the server to be inspected, the parameters of each server in the cluster and the optimization model, including: solving the optimization model according to the inspection cycle, application data, equipment data and monitoring data of the server to be inspected to obtain the inspection parameters of the server to be inspected.

[0053] Specifically, when solving the optimization model, some optimization objectives, such as shorter overall time consumption, can be converted into constraints, and then the inspection parameters of the server to be inspected can be calculated by an integer programming algorithm. The inspection parameters of the server to be inspected can also be calculated by a heuristic algorithm such as a simulated annealing combined with a taboo search algorithm. When calculating the inspection parameters of the server to be inspected by a cutting plane method or a heuristic algorithm, it is necessary to determine which loads are on the server to be inspected, the capacity of each load, etc., the CPU, memory and other capacities of other servers, and the CPU load rate of other servers. When the server to be inspected is inspected, it is necessary to determine the model and memory capacity configuration information of the server to be inspected. This information can be obtained by searching the application data, device data and monitoring data of each server in the cluster. Therefore, the optimization model can be solved according to the inspection cycle, application data, device data and monitoring data of the server to be inspected, and the inspection parameters of the server to be inspected can be quickly obtained.

[0054] In an optional embodiment, the server failure determination method further includes: obtaining the type of anomaly generated during the failure detection of the server to be inspected within a preset time period and the frequency of occurrence of the anomaly; and updating the inspection cycle of the server to be inspected according to the type of anomaly and the frequency of occurrence of the anomaly.

[0055] Specifically, in the server fault detection, an abnormal data record of the server to be inspected will be formed within a time window. In the embodiment of the present application, the frequency of occurrence of different types of abnormalities and the types of abnormalities of the server to be inspected within a time window are mainly analyzed. If the key indicators are abnormal, for example, there is damage and replacement of key components, the inspection frequency of the server to be inspected needs to be increased, the inspection cycle of the server to be inspected needs to be shortened, and the inspection cycle of the server to be inspected needs to be updated.

[0056] In this embodiment, by monitoring the types of abnormalities of the servers to be inspected and the frequency of their occurrence within a time window, the inspection cycle of the servers to be inspected is updated according to the types of abnormalities and the frequency of their occurrence. This allows the inspection frequency of servers to be inspected that are prone to damage to key parts to be higher, thereby preventing critical damage to such servers to be inspected and improving server reliability.

[0057] In an optional embodiment, the server failure determination method further includes: marking a target server that cannot be inspected within the inspection cycle; and setting the target server as a server to be inspected first in the next inspection cycle.

[0058] Specifically, due to the large detection range, some servers to be inspected may take a long time to detect, which may result in some servers to be inspected failing to complete the detection within the duration corresponding to the inspection cycle of the servers to be inspected. The target servers that failed to complete the detection can be marked. For target servers that failed to complete the detection, they will be prioritized for inspection during the inspection process of the next inspection cycle. The priority inspection conditions of the target servers can be added to the constraints of the optimization model, so that the target servers become the priority inspection servers in the next inspection cycle.

[0059] In this embodiment, by marking the target server that cannot be inspected within the inspection cycle and setting the target server as the server to be inspected first in the next inspection cycle, the target server that cannot be inspected within the current inspection cycle can be inspected in the next inspection cycle in a timely manner to prevent the target server from being inspected in the next cycle, thereby preventing possible memory failures of the target server.

[0060] In an optional embodiment, the server fault determination method further includes: recording execution conditions in the process of detecting faults of the server to be inspected; and updating inspection constraint conditions of the server to be inspected according to the execution conditions.

[0061] Specifically, since the execution cost of the running process will be recorded so as to be used in constraint condition 7 to evaluate the inspection duration under different detection ranges, after each inspection, the inspection constraints of the inspection server are updated according to the execution conditions, so that the inspection constraints can be made consistent with the actual situation, thereby improving the accuracy and practicality of the inspection parameter calculation.

[0062] The present application also provides a server fault determination device, which can be used to detect faults in the memory of a server in a cluster, such as Figure 2 As shown, the server failure determination device includes:

[0063] The first acquisition unit 21 is used to acquire the inspection period of the server to be inspected and the parameters of each server in the cluster; the specific implementation method is detailed in the description of step S101 of the above method embodiment, which will not be repeated here.

[0064] Establish unit 22, which is used to establish an optimization model with constraints, wherein the constraints include migration constraints of the load of the server to be inspected and inspection constraints of the server to be inspected, so as to minimize the cluster load fluctuation and / or shorten the overall inspection time of the server to be inspected; the specific implementation method is detailed in the description of step S102 of the above method embodiment, which will not be repeated here.

[0065] The determination unit 23 is used to determine the inspection parameters of the server to be inspected according to the inspection cycle of the server to be inspected, the parameters of each server in the cluster and the optimization model. The inspection parameters include the inspection order of the server to be inspected and the migration order of the load on the server to be inspected and the server to which the migration enters; the specific implementation method is detailed in the description of step S103 of the above method embodiment, which will not be repeated here.

[0066] The detection unit 24 is used to perform fault detection on the server to be inspected according to the inspection parameters. The specific implementation method is described in step S104 of the above method embodiment, which will not be repeated here.

[0067] The server fault determination device provided in the embodiment of the present application calculates the inspection parameters of the server to be inspected by establishing an optimization model with constraints. When calculating the inspection parameters, it is necessary to consider the parameters of each server in the cluster, including the parameters of the server to be inspected, in real time. Therefore, when calculating the inspection parameters, the memory detection environment of the server to be inspected is considered in real time, and the migration constraints of the load of the server to be inspected and the inspection constraints of the server to be inspected can be met. The load fluctuation in the cluster can be minimized when the server to be inspected is inspected, and / or the overall inspection time of the server to be inspected can be shortened. Compared with setting the inspection parameters based on user experience, the automatic setting of the inspection parameters is realized. Moreover, since the calculated inspection parameters can minimize the cluster load fluctuation when the server to be inspected is inspected, when the server to be inspected is inspected according to the inspection parameters, it will not cause too large fluctuations in the cluster load, thereby improving the user experience.

[0068] Based on the same inventive concept as the server fault determination method in the aforementioned embodiment, the embodiment of the present application further provides an electronic device, such as Figure 3 As shown, it includes: a processor 31 and a memory 32, wherein the processor 31 and the memory 32 can be connected via a bus or other means. Figure 3 The bus connection is used as an example for explanation.

[0069] The processor 31 may be a central processing unit (CPU). The processor 31 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0070] The memory 32 is a non-transitory computer-readable storage medium that can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules corresponding to the server fault determination method in the embodiment of the present application. The processor 31 executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the memory 32, that is, the server fault determination method in the above method embodiment is implemented.

[0071] The memory 32 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store data created by the processor 31, etc. In addition, the memory 32 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 32 may optionally include a memory remotely arranged relative to the processor 31, and these remote memories may be connected to the processor 31 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0072] The above one or more modules are stored in the memory 32, and when executed by the processor 31, the following is performed: Figure 1 The server failure determination method in the illustrated embodiment.

[0073] For details of the above electronic equipment, please refer to Figure 1 The corresponding related descriptions and effects in the illustrated embodiments can be understood and will not be repeated here.

[0074] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0075] 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.

[0076] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable information processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable information 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.

[0077] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable information processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including 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.

[0078] These computer program instructions can also be loaded onto a computer or other programmable information processing device so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0079] 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. A method for determining a server failure, comprising: Get the inspection cycle of the server to be inspected and the parameters of each server in the cluster; Establishing an optimization model with constraints, wherein the constraints include migration constraints of the load of the server to be inspected and inspection constraints of the server to be inspected, so as to minimize cluster load fluctuation and / or shorten the overall inspection time of the server to be inspected; Determine the inspection parameters of the server to be inspected according to the inspection cycle of the server to be inspected, the parameters of each server in the cluster and the optimization model, wherein the inspection parameters include the inspection order of the server to be inspected and the migration order of the load on the server to be inspected and the server to be migrated; Perform fault detection on the server to be inspected according to the inspection parameters.

2. The server fault determination method according to claim 1, obtaining the inspection cycle of the server to be inspected, comprising: Get the inspection batch of the servers to be inspected; The inspection cycle of the server to be inspected is found in a mapping table between batches and inspection cycles according to the inspection batch.

3. The server fault determination method according to claim 2, wherein the inspection batch division step comprises: Obtain application data, device data, and monitoring data for each server in the cluster; The servers are divided into batches according to the application data, device data and monitoring data to obtain multiple inspection batches.

4. According to the server failure determination method of claim 1, the parameters of each server in the cluster at least include: Application data, device data, and monitoring data; The step of determining the inspection parameters of the server to be inspected according to the inspection cycle of the server to be inspected, the parameters of each server in the cluster and the optimization model includes: The optimization model is solved according to the inspection cycle of the server to be inspected, the application data, the device data, and the monitoring data to obtain the inspection parameters of the server to be inspected.

5. The server failure determination method according to claim 2, further comprising: Obtain the types and frequencies of abnormalities generated during the fault detection of the server to be inspected within a preset time period; The inspection period of the server to be inspected is updated according to the type of the exception and the frequency of occurrence of the exception.

6. The server failure determination method according to claim 1, further comprising: Mark the target server that cannot be inspected within the inspection cycle; The target server is set as a server to be inspected first in the next inspection cycle.

7. The server failure determination method according to claim 6, further comprising: Record the execution conditions during the fault detection process of the server to be inspected; The inspection constraint conditions of the server to be inspected are updated according to the execution conditions.

8. A server failure determination device, comprising: A first acquisition unit is used to acquire the inspection cycle of the server to be inspected and the parameters of each server in the cluster; An establishing unit is used to establish an optimization model with constraints, wherein the constraints include migration constraints of the load of the server to be inspected and inspection constraints of the server to be inspected, so as to minimize cluster load fluctuation and / or shorten the overall inspection time of the server to be inspected; A determination unit, configured to determine inspection parameters of the server to be inspected according to the inspection cycle of the server to be inspected, the parameters of each server in the cluster and the optimization model, wherein the inspection parameters include the inspection order of the server to be inspected and the migration order of the load on the server to be inspected and the server to be migrated; A detection unit is used to perform fault detection on the server to be inspected according to the inspection parameters.

9. An electronic device, comprising: at least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor executes the server fault determination method as described in any one of claims 1-7.

10. A computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the server fault determination method according to any one of claims 1 to 7.

Images