Load system scheduling method and device, electronic equipment and storage medium

Abstract

The invention provides a load system scheduling method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining service demand data corresponding to a target application service, the service demand data comprising resource demand data corresponding to a plurality of network resources; determining a plurality of first load systems capable of running the target application service at present; for each first load system, obtaining a maximum load feature of the first load system, the maximum load feature comprising maximum load data corresponding to the plurality of network resources; determining an initial performance score corresponding to the first load system according to the resource demand data and the maximum load data corresponding to the plurality of network resources; and determining the first load system with the highest corresponding initial performance score as the initial load system for running the target application service. Therefore, multi-dimensional and globally optimal load scheduling of the network resources is realized.

Description

Technical Field

[0001] The present application relates to the technical field of network resource scheduling, and in particular to a load system scheduling method, device, electronic device and storage medium. Background Art

[0002] With the development of Internet technology, the load problem in network systems has become increasingly prominent. How to effectively schedule and manage network resources to achieve load balancing and optimization has become a technical problem that needs to be solved urgently.

[0003] Currently, when implementing network system scheduling, most of them only consider a single load feature, for example, the load feature is CPU usage. If the CPU usage of a load system meets the requirements of the target application service, the load system is used to run the target application service.

[0004] However, this approach, which only considers a single load characteristic, cannot meet the multi-dimensional demands of complex application services for network resources, and there is a problem of unreasonable resource allocation. Summary of the invention

[0005] The present application provides a load system scheduling method, device, electronic device and storage medium to solve the problem that the existing technology only considers a single load feature, cannot meet the multi-dimensional requirements of complex application services for network resources, and has unreasonable resource allocation.

[0006] In a first aspect, the present application provides a load system scheduling method, comprising:

[0007] Acquire service demand data corresponding to the target application service, wherein the service demand data includes resource demand data corresponding to a plurality of network resources;

[0008] Determining a plurality of first load systems that can currently run the target application service;

[0009] For each first load system, obtaining a maximum load characteristic of the first load system, wherein the maximum load characteristic includes maximum load data corresponding to a plurality of the network resources;

[0010] Determining an initial performance score corresponding to the first load system according to the resource demand data and the maximum load data corresponding to the plurality of network resources;

[0011] The first load system corresponding to the highest initial performance score is determined as the initial load system for running the target application service.

[0012] In a possible implementation manner, determining the initial performance score corresponding to the first load system according to the resource demand data and the maximum load data corresponding to the plurality of network resources includes:

[0013] For each network resource, calculating a ratio of maximum load data and resource demand data corresponding to the network resource;

[0014] Substituting the ratio into a preset function to obtain resource performance data corresponding to the network resource, wherein the preset function is a monotonically increasing function;

[0015] An initial performance score corresponding to the first load system is determined based on resource performance data corresponding to the plurality of network resources.

[0016] In a possible implementation manner, determining the initial performance score corresponding to the first load system according to the resource performance data corresponding to the plurality of network resources includes:

[0017] Get the weight corresponding to each network resource;

[0018] According to the weight corresponding to each network resource, a weighted sum operation is performed on the resource performance data corresponding to the plurality of network resources to obtain an initial performance score corresponding to the first load system.

[0019] In a possible implementation, the method further includes:

[0020] In the process of running the target application service using the initial load system, obtaining a first real-time load feature of the initial load system at every preset time interval, wherein the first real-time load feature includes first real-time load data corresponding to a plurality of the network resources;

[0021] Obtaining a preset first threshold and a second threshold;

[0022] It is determined whether it is necessary to redeploy the load system running the target application service according to the first real-time load characteristic, the first threshold, and the second threshold.

[0023] In a possible implementation manner, determining whether it is necessary to redeploy the load system running the target application service according to the first real-time load characteristic, the first threshold, and the second threshold includes:

[0024] Substituting the first real-time load characteristic, the first threshold, and the second threshold into a preset formula, a first real-time performance score of the initial load system is obtained, wherein the preset formula is specifically as follows:

[0025] Q i (t) = [r ij (t)-θ 2j ][θ 1j -r ij (t)](Formula 1);

[0026] Among them, Q i (t) represents the first real-time performance score of the initial load system at time t, r ij (t) represents the first real-time load data of the jth network resource in the initial load system at time t, θ 1j represents the first threshold of the jth network resource, θ 2j represents a second threshold value of the j-th network resource;

[0027] When the first real-time performance score is greater than zero, it is determined that the initial load system is operating normally and there is no need to redeploy the load system running the target application service;

[0028] When the first real-time performance score is less than or equal to zero, it is determined that the initial load system is operating abnormally, and the load system operating the target application service needs to be redeployed.

[0029] In a possible implementation, the method further includes:

[0030] In the case where it is determined that the load system running the target application service needs to be redeployed, determining a plurality of second load systems that can currently run the target application service;

[0031] For each second load system, obtaining a second real-time load feature of the second load system, where the second real-time load feature includes second real-time load data corresponding to a plurality of the network resources;

[0032] Determine a second real-time performance score corresponding to the second load system according to the resource demand data corresponding to the plurality of network resources and the second real-time load data;

[0033] Determine the second load system with the highest second real-time performance score as the target load system for running the target application service;

[0034] Migrate the target application service to the target load system.

[0035] In a possible implementation, the method further includes:

[0036] Determine the first load system whose corresponding initial performance score is greater than a preset score threshold as a candidate load system;

[0037] Obtain the system priority of each candidate load system;

[0038] The candidate load system with the highest corresponding system priority is determined as the initial load system for running the target application service.

[0039] In a second aspect, the present application provides a load system scheduling device, comprising:

[0040] A data acquisition module, used to acquire service demand data corresponding to a target application service, wherein the service demand data includes resource demand data corresponding to a plurality of network resources;

[0041] A first determining module, used to determine a plurality of first load systems that can currently run the target application service;

[0042] A first feature acquisition module, configured to acquire, for each first load system, a maximum load feature of the first load system, wherein the maximum load feature includes maximum load data corresponding to a plurality of the network resources;

[0043] A second determination module is used to determine an initial performance score corresponding to the first load system according to resource demand data and maximum load data corresponding to the plurality of network resources;

[0044] The third determination module is used to determine the first load system corresponding to the highest initial performance score as the initial load system for running the target application service.

[0045] In a possible implementation manner, the second determining module includes:

[0046] A calculation unit, used to calculate, for each network resource, a ratio of maximum load data and resource demand data corresponding to the network resource;

[0047] A substitution unit, used for substituting the ratio into a preset function to obtain resource performance data corresponding to the network resource, wherein the preset function is a monotonically increasing function;

[0048] A determination unit is used to determine an initial performance score corresponding to the first load system based on resource performance data corresponding to the plurality of network resources.

[0049] In a possible implementation, the determining unit includes:

[0050] An acquisition subunit is used to obtain the weight corresponding to each network resource;

[0051] The operation subunit is used to perform a weighted sum operation on the resource performance data corresponding to the plurality of network resources according to the weight corresponding to each network resource, so as to obtain an initial performance score corresponding to the first load system.

[0052] In a possible implementation, the device further includes:

[0053] A second feature acquisition module is used to acquire a first real-time load feature of the initial load system at a preset time interval during the process of running the target application service using the initial load system, wherein the first real-time load feature includes first real-time load data corresponding to a plurality of the network resources;

[0054] A threshold acquisition module, used to acquire a preset first threshold and a second threshold;

[0055] The fourth determination module is used to determine whether it is necessary to redeploy the load system running the target application service according to the first real-time load characteristic, the first threshold and the second threshold.

[0056] In a possible implementation, the fourth determining module includes:

[0057] A score calculation unit is used to substitute the first real-time load characteristic, the first threshold value, and the second threshold value into a preset formula to obtain a first real-time performance score of the initial load system, wherein the preset formula is specifically as follows:

[0058] Q i (t) = [r ij (t)-θ 2j ][θ 1j -r ij (t)](Formula 1);

[0059] Among them, Q i (t) represents the first real-time performance score of the initial load system at time t, r ij (t) represents the first real-time load data of the jth network resource in the initial load system at time t, θ 1j represents the first threshold of the jth network resource, θ 2j represents a second threshold value of the j-th network resource;

[0060] A first determining subunit is used to determine that the initial load system is operating normally and there is no need to redeploy the load system running the target application service when the first real-time performance score is greater than zero;

[0061] The second determining subunit is used to determine that the initial load system is running abnormally and needs to redeploy the load system running the target application service when the first real-time performance score is less than or equal to zero.

[0062] In a possible implementation, the device further includes:

[0063] A fifth determining module, configured to determine a plurality of second load systems that can currently run the target application service if it is determined that the load system running the target application service needs to be redeployed;

[0064] A third feature acquisition module is used to acquire, for each second load system, a second real-time load feature of the second load system, where the second real-time load feature includes second real-time load data corresponding to a plurality of the network resources;

[0065] A sixth determination module, configured to determine a second real-time performance score corresponding to the second load system according to the resource demand data corresponding to the plurality of network resources and the second real-time load data;

[0066] A seventh determination module, configured to determine the second load system having the highest second real-time performance score as the target load system for running the target application service;

[0067] A migration module is used to migrate the target application service to the target load system.

[0068] In a possible implementation, the device further includes:

[0069] An eighth determination module, configured to determine a first load system whose corresponding initial performance score is greater than a preset score threshold as a candidate load system;

[0070] A priority acquisition module, used to obtain the system priority of each candidate load system;

[0071] The ninth determination module is used to determine the candidate load system with the highest corresponding system priority as the initial load system for running the target application service.

[0072] In a third aspect, the present application provides a device comprising: a processor and a memory, wherein the processor is used to execute a load system scheduling program stored in the memory to implement the load system scheduling method described in any one of the first aspects.

[0073] In a fourth aspect, the present application provides a storage medium storing one or more programs, wherein the one or more programs can be executed by one or more processors to implement the load system scheduling method described in any one of the first aspects.

[0074] The above technical solution provided by the embodiment of the present application has the following advantages over the prior art: the method provided by the embodiment of the present application, by obtaining the service demand data corresponding to the target application service, wherein the service demand data includes the resource demand data corresponding to multiple network resources, determines multiple first load systems that can currently run the target application service, obtains the maximum load characteristics of the first load system for each first load system, wherein the maximum load characteristics include the maximum load data corresponding to multiple network resources, determines the initial performance score corresponding to the first load system according to the resource demand data and the maximum load data corresponding to the multiple network resources, and determines the first load system with the highest initial performance score as the initial load system for running the target application service. Through the present application, the load data of multiple network resources (such as CPU, memory, bandwidth, etc.) can be comprehensively considered to determine the initial load system for running the target application service, realizing multi-dimensional and globally optimal load scheduling of network resources, effectively avoiding the problem of unreasonable resource allocation caused by only considering a single load characteristic in the prior art, and improving the overall utilization efficiency of network resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0076] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0077] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0078] Figure 1 A flow chart of an embodiment of a load system scheduling method provided in an embodiment of the present application;

[0079] Figure 2 A flowchart of an embodiment of the present application for determining an initial performance score corresponding to the first load system according to resource demand data and maximum load data corresponding to a plurality of network resources;

[0080] Figure 3 A flowchart of another load system scheduling method provided in an embodiment of the present application;

[0081] Figure 4 A block diagram of an embodiment of a load system scheduling device provided in an embodiment of the present application;

[0082] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0083] 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 ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0084] The disclosure below provides many different embodiments or examples to realize the different structures of the present application. In order to simplify the disclosure of the present application, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present application. In addition, the present application can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0085] In order to solve the problem that the existing technology only considers a single load feature, cannot meet the multi-dimensional demands of complex application services for network resources, and has the problem of unreasonable resource allocation, the present application provides a load system scheduling method, which can realize multi-dimensional and globally optimal load scheduling of network resources, effectively avoids the problem of unreasonable resource allocation caused by only considering a single load feature in the existing technology, and improves the overall utilization efficiency of network resources.

[0086] Figure 1 The following is a flow chart of an embodiment of a load system scheduling method provided in an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0087] Step 101: Obtain service demand data corresponding to a target application service, wherein the service demand data includes resource demand data corresponding to a plurality of network resources.

[0088] Application service refers to a service that provides a specific function or solution through the network or mobile devices. In actual applications, the application service is run through a load system (for example, a server cluster, a cloud service instance, etc.) to provide users with the specific function or solution corresponding to the application service.

[0089] The target application service refers to the application service of the load system to be distributed. In actual applications, it can be specified by the user.

[0090] Resource demand data is used to characterize the demand of the target application service for corresponding network resources (such as CPU resources, memory resources, and bandwidth resources), and is generally input by the user.

[0091] For example, the service demand data is D=(80, 120, 30), where 80 represents the demand for CPU resources, 120 represents the demand for memory resources, and 30 represents the demand for bandwidth resources. That is, the resource demand data corresponding to CPU resources is 80, the resource demand data corresponding to memory resources is 120, and the resource demand data corresponding to bandwidth resources is 30.

[0092] Step 102: Determine a plurality of first load systems that can currently run the target application service.

[0093] The first load system refers to a load system that is in an operable state and can provide services normally within a given time interval.

[0094] In actual applications, the user may specify multiple first load systems, or use an automated tool or script to automatically scan the network or cloud platform to discover multiple first load systems that are currently available.

[0095] Step 103: For each first load system, obtain a maximum load characteristic of the first load system, wherein the maximum load characteristic includes maximum load data corresponding to a plurality of network resources.

[0096] The maximum load characteristic is used to characterize the maximum load of multiple network resources in the first load system, including the maximum load data corresponding to the multiple network resources. The maximum load data is used to characterize the maximum load of the corresponding network resources in the first load system.

[0097] For example, the maximum load characteristic of load system A is LA=(100, 200, 50), where 100 represents the maximum CPU resource of load system A, 200 represents the maximum memory resource of load system A, and 50 represents the maximum bandwidth resource of load system A. That is, the maximum load data corresponding to the CPU resource is 100, the maximum load data corresponding to the memory resource is 200, and the maximum load data corresponding to the bandwidth resource is 50.

[0098] In the embodiment of the present application, the maximum load characteristics of each first load system are determined by collecting basic information of each first load system, such as configuration, location, network bandwidth, etc.

[0099] Step 104: Determine an initial performance score corresponding to the first load system according to the resource demand data and maximum load data corresponding to the plurality of network resources.

[0100] Step 105: Determine the first load system corresponding to the highest initial performance score as the initial load system for running the target application service.

[0101] For ease of understanding, step 104 and step 105 are described uniformly below:

[0102] The initial performance score is used to characterize the performance of the target application service running on the corresponding first load system. A higher initial performance score means a better performance of the target application service running on the corresponding first load system.

[0103] In the embodiment of the present application, by setting and calculating the resource demand data and maximum load data corresponding to multiple network resources, the initial performance score corresponding to the first load system is obtained. In this way, the performance evaluation of each first load system can be achieved through the load characteristics of multi-dimensional network resources. Furthermore, by determining the first load system with the highest initial performance score as the initial load system for running the target application service, the global optimal load scheduling is achieved, and the overall utilization efficiency of network resources is improved.

[0104] In another embodiment of the present application, the following steps may also be included after step 104: determining the first load system whose corresponding initial performance score is greater than a preset score threshold as a candidate load system, obtaining the system priority of each candidate load system, and determining the candidate load system with the highest corresponding system priority as the initial load system for running the target application service.

[0105] The preset scoring threshold is used to screen the first load system that can guarantee the operating effect of the target application service. That is, when the initial performance score of the first load system is greater than the preset scoring threshold, it means that when the target application service is run through the first load system, the operating effect of the target application service can be guaranteed.

[0106] System priority is used to characterize the usage priority of the corresponding first load system and is generally set by the user according to actual needs.

[0107] Based on this, in the embodiment of the present application, after the candidate load systems are screened out by the preset scoring threshold, the candidate load system with the highest corresponding system priority can be determined as the initial load system for running the target application service. In this way, the determined initial load system can be made more in line with user needs while ensuring the running effect of the target application service.

[0108] The technical solution provided by the embodiment of the present application obtains the service demand data corresponding to the target application service, wherein the service demand data includes the resource demand data corresponding to multiple network resources, determines multiple first load systems that can currently run the target application service, obtains the maximum load characteristics of the first load system for each first load system, wherein the maximum load characteristics include the maximum load data corresponding to multiple network resources, determines the initial performance score corresponding to the first load system according to the resource demand data and the maximum load data corresponding to the multiple network resources, and determines the first load system with the highest initial performance score as the initial load system for running the target application service. Through the present application, the load data of multiple network resources (such as CPU, memory, bandwidth, etc.) can be comprehensively considered to determine the initial load system for running the target application service, thereby realizing multi-dimensional and globally optimal load scheduling of network resources, effectively avoiding the problem of unreasonable resource allocation caused by only considering a single load characteristic in the prior art, and improving the overall utilization efficiency of network resources.

[0109] Figure 2 A flowchart of an embodiment of the present application is provided for determining an initial performance score corresponding to a first load system based on resource demand data and maximum load data corresponding to multiple network resources. Figure 2 The process shown in Figure 1 Based on the process shown, the following steps are included:

[0110] Step 201: For each network resource, calculate the ratio of the maximum load data and the resource demand data corresponding to the network resource.

[0111] Step 202: Substitute the ratio into a preset function to obtain resource performance data corresponding to the network resource, wherein the preset function is a monotonically increasing function.

[0112] Step 203: Determine an initial performance score corresponding to the first load system according to resource performance data corresponding to the plurality of network resources.

[0113] For ease of understanding, steps 201 to 203 are described in a unified manner as follows:

[0114] In the embodiment of the present application, first, the ratio of the maximum load data and the resource demand data corresponding to each network resource is calculated, and the ratio is used to characterize the load characteristics of the corresponding network resource in the first load system for the target application service.

[0115] Then, by substituting the ratio into a preset function (monotonically increasing function), the corresponding resource performance data is obtained. Thus, the load characteristic (i.e., the ratio of maximum load data to resource demand data) is converted into a performance index (i.e., resource performance data). It can be understood that the larger the load characteristic, the higher the performance index and the larger the resource performance data.

[0116] In the application, the preset function can be f(x)=log(1+x). This function satisfies the monotonically increasing condition, and when x increases, the growth rate of f(x) will gradually slow down. In this way, the growth trend of resource utilization in actual applications can be simulated, making the obtained data more accurate.

[0117] Finally, a set operation is performed on the resource performance data corresponding to the plurality of network resources to obtain an initial performance score corresponding to the first load system.

[0118] Wherein, determining the initial performance score corresponding to the first load system according to the resource performance data corresponding to the plurality of network resources may include the following steps:

[0119] Step A1, obtaining the weight corresponding to each network resource;

[0120] Step A2: performing a weighted sum operation on resource performance data corresponding to a plurality of network resources according to the weight corresponding to each network resource, so as to obtain an initial performance score corresponding to the first load system.

[0121] The above weights are used to characterize the influence of the corresponding network resources on the performance of the application service. In actual applications, users can flexibly set them according to the actual application service requirements to adapt to different application scenarios and service requirements.

[0122] It can be seen from the description of the above steps A1 and A2 that in the technical solution of the embodiment of the present application, the resource performance data corresponding to multiple network resources can be weighted summed according to the weight corresponding to each network resource, so that the calculated initial performance score is more accurate.

[0123] Specifically, assume that Li = (li1, li2, ..., lin) is the maximum load characteristic of the i-th load system, where lij represents the maximum load data of the j-th resource of the i-th load system (such as maximum CPU resources, maximum memory resources, maximum bandwidth resources, etc.); D = (d1, d2, ..., dn) is the indicator vector of application service requirements (i.e., service demand data), where dj represents the resource demand data of the target application service for the j-th resource; wj represents the weight of the j-th resource in the target application service; the preset function is f(x), and f(x) is a monotonically increasing function.

[0124] The initial performance score That is to say, the initial performance score is obtained by comparing the maximum load data lij of each network resource with the service demand data dj of the target application service for the network resource, converting the comparison result into a performance indicator through the function f(x), and then multiplying it by the weight wj of the network resource. Finally, the performance indicators of all network resources are added together.

[0125] Taking the preset function f(x)=log(1+x) as an example, suppose there are two load systems A and B, whose maximum load characteristics include maximum CPU resources, maximum memory resources and maximum bandwidth resources, which are LA=(100, 200, 50) and LB=(150, 100, 100), respectively. The application service demand of the target application service is D=(80, 120, 30). Assume that the weights of the three network resources are equal, that is, w1=w2=w3=1 / 3.

[0126] Then the initial performance score of load system A is:

[0127] PA=1 / 3[log(1+80 / 100)+log(1+120 / 200)+log(1+30 / 50)];

[0128] Then the initial performance score of load system A is:

[0129] PB=1 / 3[log(1+80 / 150)+log(1+120 / 100)+log(1+30 / 100)];

[0130] After calculating the values ​​of PA and PB, by comparing the sizes of PA and PB, the load system with a higher initial performance score can be selected as the initial load system.

[0131] Figure 2 The process shown in Figure 1 On the basis of the shown process, by calculating the ratio of the maximum load data and the resource demand data corresponding to each network resource, the ratio is substituted into a monotonically increasing function to obtain the corresponding resource performance data, and the initial performance score corresponding to the first load system is determined according to the resource performance data corresponding to multiple network resources. This enables the performance of each first load system to be evaluated through the load characteristics of multi-dimensional network resources. Furthermore, in this solution, by converting load characteristics into performance indicators, a quantitative evaluation of the processing capacity of the load system is achieved, which helps to more accurately select a load system that meets application service requirements.

[0132] Figure 3 This is a flow chart of another embodiment of a load system scheduling method provided in an embodiment of the present application. Figure 3 As shown, the process includes the following steps:

[0133] Step 301, in the process of using the initial load system to run the target application service, obtaining a first real-time load feature of the initial load system at every preset time interval, the first real-time load feature including first real-time load data corresponding to a plurality of network resources;

[0134] Step 302, obtaining a preset first threshold and a second threshold;

[0135] Step 303: Determine whether it is necessary to redeploy the load system running the target application service according to the first real-time load characteristic, the first threshold and the second threshold.

[0136] For ease of understanding, steps 301 to 303 are described in a unified manner as follows:

[0137] The first real-time load feature is used to characterize the real-time load of multiple network resources in the initial load system, including first real-time load data corresponding to the multiple network resources. The first real-time load data is used to characterize the real-time load of the corresponding network resources in the initial load system.

[0138] The first threshold and the second threshold are set by the user based on experience. When the first real-time load characteristic is greater than the first threshold, it is considered that the current load system cannot be maintained and the target load system needs to be deployed and configured; when the first real-time load characteristic is less than the second threshold, it is considered that the current load system performance is wasted and the target load system also needs to be deployed and configured.

[0139] In an embodiment of the present application, in order to promptly discover and process overloaded or idle resources, the first real-time load characteristics of the initial load system are obtained at every preset time interval, and by comparing the first real-time load characteristics, the first threshold and the second threshold, it is determined whether the current initial load system is overloaded or idle, and then, based on the judgment result, it is determined whether it is necessary to redeploy the load system running the target application service.

[0140] Specifically, the implementation of determining whether it is necessary to redeploy the load system running the target application service according to the first real-time load characteristic, the first threshold and the second threshold may include the following steps:

[0141] Step B1, substituting the first real-time load characteristic, the first threshold value and the second threshold value into a preset formula to obtain a first real-time performance score of the initial load system, wherein the preset formula is specifically as follows:

[0142] Q i (t) = [r ij (t)-θ 2j ][θ 1j -r ij (t)] (Formula 1);

[0143] Among them, Qi (t) represents the first real-time performance score of the initial load system at time t, r ij (t) represents the first real-time load data of the jth network resource in the initial load system at time t, θ 1j represents the first threshold of the jth network resource, θ 2j represents a second threshold value of the j-th network resource;

[0144] Step B2, when the first real-time performance score is greater than zero, it is determined that the initial load system is operating normally and there is no need to redeploy the load system running the target application service;

[0145] Step B3: when the first real-time performance score is less than or equal to zero, it is determined that the initial load system is operating abnormally and it is necessary to redeploy the load system running the target application service.

[0146] From the description of step B1 to step B3, it can be seen that according to formula 1, when the first real-time load characteristic is between the first threshold and the second threshold, the first real-time performance score Q i (t) is a positive number, otherwise, Q i (t) is less than or equal to 0, that is, in Q i If (t) is greater than zero, it is determined that the initial load system is operating normally and there is no need to redeploy the load system running the target application service. i When (t) is less than or equal to zero, it is determined that the initial load system is operating abnormally (i.e., there is an overload or idle situation), and the load system running the target application service needs to be redeployed.

[0147] In this solution, Formula 1 can be used to calculate whether the first real-time performance score exceeds the threshold interval or is within the threshold interval, so that the calculated value can be used to assist in further judgment of the initial load system.

[0148] In addition, in another embodiment of the present application, after step 303, the following steps may be further included:

[0149] Step C1, in the case where it is determined that the load system running the target application service needs to be redeployed, determining a plurality of second load systems that can currently run the target application service;

[0150] Step C2: for each second load system, obtaining a second real-time load characteristic of the second load system, where the second real-time load characteristic includes second real-time load data corresponding to a plurality of network resources;

[0151] Step C3, determining a second real-time performance score corresponding to the second load system according to the resource demand data corresponding to the plurality of network resources and the second real-time load data;

[0152] Step C4, determining the second load system corresponding to the highest second real-time performance score as the target load system running the target application service;

[0153] Step C5: Migrate the target application service to the target load system.

[0154] For ease of understanding, steps C1 to C5 are described in a unified manner as follows:

[0155] The second load system refers to a load system that is in a working state and can provide services normally within a given time interval.

[0156] The second real-time load feature is used to characterize the real-time load of multiple network resources in the corresponding second load system, including the second real-time load data corresponding to the multiple network resources. The second real-time load data is used to characterize the real-time load of the corresponding network resources in the corresponding second load system.

[0157] In an embodiment of the present application, when it is determined that the load system running the target application service needs to be redeployed, first, based on the resource demand data corresponding to the multiple network resources and the second real-time load data of each second load system, the second real-time performance score corresponding to the second load system is determined, wherein the process of determining the second real-time performance score is the same as the process of determining the initial performance score in step 104, and will not be repeated here.

[0158] Then, the second load system with the highest second real-time performance score is determined as the target load system for running the target application service, and finally, the target application service is migrated to the target load system, and the target application service is continued to run using the target load system, thereby ensuring the stable operation of the target application service and improving system stability.

[0159] Figure 3 In the process shown, the first real-time load feature of the initial load system is obtained at every preset time interval, and the first real-time load feature, the first threshold and the second threshold are compared to determine whether the current initial load system is overloaded or idle, and then, the load system running the target application service needs to be redeployed based on the judgment result. In this way, the operating status of the initial load system can be detected in real time, so that overloaded or idle resources can be discovered and processed in time, effectively avoiding the risks of system performance degradation and crash, and enhancing the stability and reliability of the network system.

[0160] Figure 4 This is a block diagram of an embodiment of a load system scheduling device provided in an embodiment of the present application. Figure 4 As shown, the device comprises:

[0161] The data acquisition module 41 is used to acquire service demand data corresponding to the target application service, wherein the service demand data includes resource demand data corresponding to a plurality of network resources;

[0162] A first determining module 42, configured to determine a plurality of first load systems that can currently run the target application service;

[0163] A first feature acquisition module 43 is used to acquire, for each first load system, a maximum load feature of the first load system, wherein the maximum load feature includes maximum load data corresponding to a plurality of the network resources;

[0164] A second determination module 44 is used to determine an initial performance score corresponding to the first load system according to resource demand data and maximum load data corresponding to the plurality of network resources;

[0165] The third determination module 45 is configured to determine the first load system corresponding to the highest initial performance score as the initial load system for running the target application service.

[0166] In a possible implementation manner, the second determining module 44 includes:

[0167] A calculation unit, used to calculate, for each network resource, a ratio of maximum load data and resource demand data corresponding to the network resource;

[0168] A substitution unit, used for substituting the ratio into a preset function to obtain resource performance data corresponding to the network resource, wherein the preset function is a monotonically increasing function;

[0169] A determination unit is used to determine an initial performance score corresponding to the first load system based on resource performance data corresponding to the plurality of network resources.

[0170] In a possible implementation, the determining unit includes:

[0171] An acquisition subunit is used to obtain the weight corresponding to each network resource;

[0172] The operation subunit is used to perform a weighted sum operation on the resource performance data corresponding to the plurality of network resources according to the weight corresponding to each network resource, so as to obtain an initial performance score corresponding to the first load system.

[0173] In a possible implementation, the device further includes:

[0174] A second feature acquisition module is used to acquire a first real-time load feature of the initial load system at a preset time interval during the process of running the target application service using the initial load system, wherein the first real-time load feature includes first real-time load data corresponding to a plurality of the network resources;

[0175] A threshold acquisition module, used to acquire a preset first threshold and a second threshold;

[0176] The fourth determination module is used to determine whether it is necessary to redeploy the load system running the target application service according to the first real-time load characteristic, the first threshold and the second threshold.

[0177] In a possible implementation, the fourth determining module includes:

[0178] A score calculation unit is used to substitute the first real-time load characteristic, the first threshold value, and the second threshold value into a preset formula to obtain a first real-time performance score of the initial load system, wherein the preset formula is specifically as follows:

[0179] Q i (t) = [r ij (t)-θ 2j ][θ 1j -r ij (t)](Formula 1);

[0180] Among them, Q i (t) represents the first real-time performance score of the initial load system at time t, r ij (t) represents the first real-time load data of the jth network resource in the initial load system at time t, θ 1j represents the first threshold of the jth network resource, θ 2j represents a second threshold value of the j-th network resource;

[0181] A first determining subunit is used to determine that the initial load system is operating normally and there is no need to redeploy the load system running the target application service when the first real-time performance score is greater than zero;

[0182] The second determining subunit is used to determine that the initial load system is running abnormally and needs to redeploy the load system running the target application service when the first real-time performance score is less than or equal to zero.

[0183] In a possible implementation, the device further includes:

[0184] A fifth determining module, configured to determine a plurality of second load systems that can currently run the target application service if it is determined that the load system running the target application service needs to be redeployed;

[0185] A third feature acquisition module is used to acquire, for each second load system, a second real-time load feature of the second load system, where the second real-time load feature includes second real-time load data corresponding to a plurality of the network resources;

[0186] A sixth determination module, configured to determine a second real-time performance score corresponding to the second load system according to the resource demand data corresponding to the plurality of network resources and the second real-time load data;

[0187] A seventh determination module, configured to determine the second load system having the highest second real-time performance score as the target load system for running the target application service;

[0188] A migration module is used to migrate the target application service to the target load system.

[0189] In a possible implementation, the device further includes:

[0190] An eighth determination module, configured to determine a first load system whose corresponding initial performance score is greater than a preset score threshold as a candidate load system;

[0191] A priority acquisition module, used to obtain the system priority of each candidate load system;

[0192] The ninth determination module is used to determine the candidate load system with the highest corresponding system priority as the initial load system for running the target application service.

[0193] like Figure 5 As shown, an embodiment of the present application provides a device, including a processor 111, a communication interface 112, a memory 113 and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114.

[0194] Memory 113, used for storing computer programs;

[0195] In one embodiment of the present application, the processor 111 is used to execute the program stored in the memory 113 to implement the load system scheduling method provided by any of the above method embodiments, including:

[0196] Acquire service demand data corresponding to the target application service, wherein the service demand data includes resource demand data corresponding to a plurality of network resources;

[0197] Determining a plurality of first load systems that can currently run the target application service;

[0198] For each first load system, obtaining a maximum load characteristic of the first load system, wherein the maximum load characteristic includes maximum load data corresponding to a plurality of the network resources;

[0199] Determining an initial performance score corresponding to the first load system according to the resource demand data and the maximum load data corresponding to the plurality of network resources;

[0200] The first load system corresponding to the highest initial performance score is determined as the initial load system for running the target application service.

[0201] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the load system scheduling method provided in any of the aforementioned method embodiments are implemented.

[0202] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0203] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0204] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0205] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

Claims

1. A load system scheduling method, characterized in that: The method comprises: Acquire service demand data corresponding to the target application service, wherein the service demand data includes resource demand data corresponding to a plurality of network resources; Determining a plurality of first load systems that can currently run the target application service; For each first load system, obtaining a maximum load characteristic of the first load system, wherein the maximum load characteristic includes maximum load data corresponding to a plurality of the network resources; Determining an initial performance score corresponding to the first load system according to the resource demand data and the maximum load data corresponding to the plurality of network resources; The first load system corresponding to the highest initial performance score is determined as the initial load system for running the target application service.

2. The method according to claim 1, characterized in that Determining the initial performance score corresponding to the first load system according to the resource demand data and the maximum load data corresponding to the plurality of network resources includes: For each network resource, calculating a ratio of maximum load data and resource demand data corresponding to the network resource; Substituting the ratio into a preset function to obtain resource performance data corresponding to the network resource, wherein the preset function is a monotonically increasing function; An initial performance score corresponding to the first load system is determined based on resource performance data corresponding to the plurality of network resources.

3. The method according to claim 2, characterized in that The determining, according to the resource performance data corresponding to the plurality of network resources, an initial performance score corresponding to the first load system comprises: Get the weight corresponding to each network resource; According to the weight corresponding to each network resource, a weighted sum operation is performed on the resource performance data corresponding to the plurality of network resources to obtain an initial performance score corresponding to the first load system.

4. The method according to claim 1, characterized in that: The method further comprises: In the process of running the target application service using the initial load system, obtaining a first real-time load feature of the initial load system at every preset time interval, wherein the first real-time load feature includes first real-time load data corresponding to a plurality of the network resources; Obtaining a preset first threshold and a second threshold; It is determined whether it is necessary to redeploy the load system running the target application service according to the first real-time load characteristic, the first threshold, and the second threshold.

5. The method according to claim 4, characterized in that The determining whether it is necessary to redeploy the load system running the target application service according to the first real-time load characteristic, the first threshold, and the second threshold includes: Substituting the first real-time load characteristic, the first threshold, and the second threshold into a preset formula, a first real-time performance score of the initial load system is obtained, wherein the preset formula is specifically as follows: Q i (t) = [r ij (t)-θ 2j ][θ 1j -r ij (t)] (Formula 1); Among them, Q i (t) represents the first real-time performance score of the initial load system at time t, r ij (t) represents the first real-time load data of the jth network resource in the initial load system at time t, θ 1j represents the first threshold of the jth network resource, θ 2j represents a second threshold value of the j-th network resource; When the first real-time performance score is greater than zero, it is determined that the initial load system is operating normally and there is no need to redeploy the load system running the target application service; When the first real-time performance score is less than or equal to zero, it is determined that the initial load system is operating abnormally, and the load system operating the target application service needs to be redeployed.

6. The method according to claim 4, characterized in that The method further comprises: In the case where it is determined that the load system running the target application service needs to be redeployed, determining a plurality of second load systems that can currently run the target application service; For each second load system, obtaining a second real-time load feature of the second load system, where the second real-time load feature includes second real-time load data corresponding to a plurality of the network resources; Determine a second real-time performance score corresponding to the second load system according to the resource demand data corresponding to the plurality of network resources and the second real-time load data; Determine the second load system with the highest second real-time performance score as the target load system for running the target application service; Migrate the target application service to the target load system.

7. The method according to claim 1, characterized in that The method further comprises: Determine the first load system whose corresponding initial performance score is greater than a preset score threshold as a candidate load system; Obtain the system priority of each candidate load system; The candidate load system with the highest corresponding system priority is determined as the initial load system for running the target application service.

8. A load system scheduling device, characterized in that: The device comprises: A data acquisition module, used to acquire service demand data corresponding to a target application service, wherein the service demand data includes resource demand data corresponding to a plurality of network resources; A first determining module, used to determine a plurality of first load systems that can currently run the target application service; A feature acquisition module, configured to acquire, for each first load system, a maximum load feature of the first load system, wherein the maximum load feature includes maximum load data corresponding to a plurality of the network resources; A second determination module is used to determine an initial performance score corresponding to the first load system according to resource demand data and maximum load data corresponding to the plurality of network resources; The third determination module is used to determine the first load system corresponding to the highest initial performance score as the initial load system for running the target application service.

9. A device, characterized in that: include: A processor and a memory, wherein the processor is used to execute a load system scheduling program stored in the memory to implement the load system scheduling method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the load system scheduling method according to any one of claims 1 to 7.

Images