Elastic load balancing method, transmission system, storage medium and program product

Abstract

The embodiment of the application provides a kind of elastic load balancing method, transmission system, storage medium and program product, elastic load balancing method includes: real-time acquisition application type load balancing instance corresponding four-layer load balancing instance's traffic index and seven-layer load balancing instance's traffic index;According to whether four-layer load balancing instance's traffic index and seven-layer load balancing instance's traffic index is associated index, a series of processing is carried out, to carry out elastic load balancing to four-layer load balancing instance and / or seven-layer load balancing instance.The application is based on network function virtualization, carries out the elastic load balancing of network, when there is associated index in four-layer load balancing instance and seven-layer load balancing instance, simultaneously carries out elastic load balancing to four-layer load balancing instance and seven-layer load balancing instance, improves the resource use ratio of system, simultaneously improves processing speed.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of network, and in particular, to an elastic load balancing method, a transmission system, a storage medium and a program product. BACKGROUND

[0002] Load balancing instance is a cluster technology which distributes specific services (such as network services, network traffic, etc.) to multiple servers, thereby improving service processing capacity and ensuring high reliability of services.

[0003] According to different levels of identification information, load balancing instances are divided into the following two kinds: (1) four-layer load balancing instance: can identify network layer and transport layer information, is flow-based load balancing, and distributes messages of the same flow to the same server through flow-by-flow distribution; (2) seven-layer load balancing instance: in addition to being able to identify network layer and transport layer information, it can also identify application layer information, is content-based load balancing, and distributes packets according to the content thereof through deep analysis of the content carried by the message, and directs the connection to the specified server according to the established strategy, thereby realizing application load balancing with a wider range of services. Generally, in network system architecture, four-layer load balancing instances and seven-layer load balancing instances are usually deployed at the same time.

[0004] However, when performing elasticity on four-layer load balancing instances and seven-layer load balancing instances based on the above architecture, there is a waste of resources. SUMMARY

[0005] Therefore, embodiments of the present application provide an elastic load balancing scheme to at least partially solve the above problems.

[0006] According to a first aspect of embodiments of the present application, an elastic load balancing method is provided, comprising: collecting traffic indicators of a four-layer load balancing instance and traffic indicators of a seven-layer load balancing instance corresponding to an application-type load balancing instance in real time, wherein the four-layer load balancing instance and the seven-layer load balancing instance are two load balancing instances which are decoupled by network function virtualization and independent of each other; and performing elastic load balancing on the four-layer load balancing instance and / or the seven-layer load balancing instance according to comparison results of the traffic indicators with a first elastic threshold of the four-layer load balancing instance and a second elastic threshold of the seven-layer load balancing instance, respectively.

[0007] According to a second aspect of the embodiments of the present application, a network data transmission system is provided, comprising: an elasticity control module, a four-layer load balancing instance and a seven-layer load balancing instance for transmitting data, wherein the four-layer load balancing instance and the seven-layer load balancing instance are two load balancing instances that are decoupled by network function virtualization and independent of each other; the elasticity control module is configured to collect traffic indexes of the four-layer load balancing instance and traffic indexes of the seven-layer load balancing instance in real time; if the traffic indexes of the four-layer load balancing instance and the traffic indexes of the seven-layer load balancing instance are associated indexes, then performing associated elasticity load balancing on the four-layer load balancing instance and the seven-layer load balancing instance according to a comparison result of the traffic indexes of the four-layer load balancing instance and a first elasticity threshold of the four-layer load balancing instance; if the traffic indexes of the four-layer load balancing instance and the traffic indexes of the seven-layer load balancing instance are not associated indexes, then performing elasticity load balancing on the four-layer load balancing instance according to a comparison result of the traffic indexes and the first elasticity threshold of the four-layer load balancing instance, and / or performing elasticity load balancing on the seven-layer load balancing instance according to a comparison result of the traffic indexes and a second elasticity threshold of the seven-layer load balancing instance.

[0008] According to a third aspect of the embodiments of the present application, a computer storage medium is provided, and the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method according to the first aspect.

[0009] According to a fourth aspect of the embodiments of the present application, a computer program product is provided, comprising computer instructions, and the computer instructions instruct a computing device to perform operations corresponding to the method according to the first aspect.

[0010] According to the scheme provided in the embodiment of the present application, in the network data transmission system based on the four-layer load balancing instance and the seven-layer load balancing instance architecture, the elastic load balancing of the four-layer load balancing instance and the seven-layer load balancing instance is decoupled through network function virtualization. In this case, when the elastic load balancing of the network is needed, whether the traffic index of the four-layer load balancing instance and the traffic index of the seven-layer load balancing instance are associated indexes is judged. If the result of the judgment is yes, since the traffic index of the four-layer load balancing instance and the traffic index of the seven-layer load balancing instance are associated indexes, the elastic load balancing of the four-layer load balancing instance and the seven-layer load balancing instance can be realized only according to the comparison result of the traffic index of the four-layer load balancing instance and the first elastic threshold of the four-layer load balancing instance. Since the traffic collection and comparison of the seven-layer load balancing instance are not needed, the multiple resource consumption of the seven-layer load balancing instance itself is avoided, the resource utilization of the system is improved, and the processing speed is improved. If the result of the judgment is no, whether the elastic load balancing of the four-layer load balancing instance, the elastic load balancing of the seven-layer load balancing instance, or the elastic load balancing of the four-layer load balancing instance and the seven-layer load balancing instance is performed is determined according to the comparison result of the traffic index of the four-layer load balancing instance and the first elastic threshold corresponding to the four-layer load balancing instance, and the comparison result of the traffic index of the seven-layer load balancing instance and the second elastic threshold corresponding to the seven-layer load balancing instance. In this way, unnecessary elastic load balancing of the load balancing instance is avoided, and the resource waste caused by the fact that the elastic load balancing of the four-layer load balancing instance and the seven-layer load balancing instance can only be performed simultaneously in the traditional way is also avoided. BRIEF DESCRIPTION OF DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments described in the embodiments of the present application, and other drawings can also be obtained by those skilled in the art according to these drawings.

[0012] Figure 1 A schematic diagram of an exemplary system suitable for the elastic load balancing method according to the embodiment of the present application;

[0013] Figure 2A A step flowchart of an elastic load balancing method according to the first embodiment of the present application;

[0014] Figure 2B A schematic diagram of an elastic load balancing system suitable for the first embodiment;

[0015] Figure 3 A step flowchart of a virtualization decoupling method according to the second embodiment of the present application;

[0016] Figure 4 FIG. 3 is a flowchart illustrating steps of another elastic load balancing method according to an embodiment of the present application;

[0017] Figure 5 FIG. 4 is a schematic diagram of an electronic device according to an embodiment of the present application;

[0018] Figure 6 FIG. 5 is a schematic diagram of a network data transmission system according to an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to enable persons skilled in the art to better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the embodiments of the present application, all other embodiments obtained by persons skilled in the art should belong to the scope of protection of the embodiments of the present application.

[0020] The specific implementation of the embodiments of the present application will be further described below in conjunction with the drawings in the embodiments of the present application.

[0021] Figure 1 An exemplary system suitable for the elastic load balancing method according to the embodiments of the present application is shown. As shown in FIG. 1, the system 100 can include a traffic collection end 102, a communication network 104, an application type load 106, and an elastic end 108. Figure 1

[0022] The traffic collection end 102 can be any appropriate device for collecting information, data, programs, and / or any other suitable type of content, including but not limited to an integrated device for collecting and analyzing network traffic, a network traffic collector, a traffic detector, etc. In some embodiments, the traffic collection end 102 can perform any appropriate function. For example, in some embodiments, the traffic collection end 102 can be used to collect real-time traffic. As an optional example, in some embodiments, the traffic collection end 102 can be used to clean the collected traffic data. As another example, in some embodiments, the traffic collection end 102 can be used to send the traffic data to the elastic end 108.

[0023] ​In some embodiments, the communication network 104 can be any suitable combination of one or more wired and / or wireless networks. For example, the communication network 104 can include any one or more of the following: the Internet, an intranet, a local area network (LAN), a wide area network (WAN), a wireless network, a digital subscriber line (DSL) network, a frame relay network, an asynchronous transfer mode (ATM) network, a virtual private network (VPN), and / or any other suitable communication network. The application workload 106 can be connected to the communication network 104 through one or more communication links (e.g., communication link 112), which can be linked via one or more communication links (e.g., communication link 114) to the traffic collection end 102. The communication links can be any communication links suitable for communicating data among the application workload 106 and the traffic collection end 102, such as network links, dial-up links, wireless links, hard-wired links, any other suitable communication links, or any suitable combination of such links.

[0024] The application workload 106 can include any one or more load balancing instances suitable for advanced content-based routing features, such as forwarding, redirection, and rewriting based on HTTP headers, cookies, and query strings, etc. In some embodiments, the application workload 106 can include any suitable type of device. For example, in some embodiments, the application workload 106 can include a layer 4 load balancing instance 1061 and a layer 7 load balancing instance 1062, with the layer 7 load balancing instance 1062 piggybacked on the layer 4 load balancing instance 1061. The resilient end 108 can perform resilient load balancing of the layer 4 load balancing instance 1061 and the layer 7 load balancing instance 1062.

[0025] In general, in a network system architecture, four-layer load balancing instances and seven-layer load balancing instances are usually deployed at the same time, and therefore, when performing elastic load balancing, the difference in the requirements for four-layer load balancing instances and seven-layer load balancing instances is not distinguished, and the ability to simultaneously shrink four-layer load balancing instances and seven-layer load balancing instances without distinction is performed. The inventor found that due to the difference in the traffic model of the client instance, the processing capacity (such as the number of new connections per second, the number of concurrent connections, etc.) of the four-layer load balancing instance and the processing capacity (such as QPS (Queries-per-second)) of the seven-layer load balancing instance are different, and the traffic model of the same instance may change at different time periods. The above-mentioned traditional solution will cause a large waste of resources. For example, if the user has a high demand for four-layer load balancing instances and a low demand for seven-layer load balancing instances, when performing elasticity, the resources of the four-layer load balancing instances need to be increased, but the resources of the seven-layer load balancing instances also need to be increased at the same time, but the resources of the seven-layer load balancing instances before the increase can already meet the user demand, so that the resources of the seven-layer load balancing instances that are increased this time are idle, resulting in a waste of resources; if the user has the opposite demand, the resources of the four-layer load balancing instances will be idle, resulting in a waste of resources.

[0026] In order to solve the problem of resource waste caused by the simultaneous elasticity of four-layer load balancing instances and seven-layer load balancing instances, the inventor decouples the four-layer load balancing instances and the seven-layer load balancing instances, but after decoupling, it is found that if the parameters of the four-layer load balancing instances and the seven-layer load balancing instances are collected and controlled respectively according to the collected parameters, the connection between the four-layer load balancing instances and the seven-layer load balancing instances is not considered in the elastic control process, resulting in low control efficiency.

[0027] Therefore, the inventor adds a correlation index in the process of elastic load balancing. Through the correlation index, the elastic load balancing of the four-layer ALB load balancing instance and the seven-layer ALB load balancing instance can be realized only by comparing the traffic index of the four-layer ALB load balancing instance with the first elastic threshold of the four-layer ALB load balancing instance. Since the traffic of the seven-layer ALB load balancing instance does not need to be collected and compared, the multiple resource consumption of the seven-layer ALB load balancing instance itself is avoided, the resource utilization of the system is improved, and the processing speed is also improved. The related content of the correlation index is specifically described in the following embodiments.

[0028] Based on the above-mentioned system, the embodiments of the present application provide an elastic load balancing method, which is described below through a plurality of embodiments.

[0029] Embodiment one

[0030] Reference Figure 2A, shows a flow chart of steps of an elastic load balancing method according to Embodiment One of the present application.

[0031] As shown in Figure 2A , the elastic load balancing method comprises the following steps:

[0032] Step 202, real-time collection of traffic indicators of the four-layer load balancing instance and traffic indicators of the seven-layer load balancing instance corresponding to the application-type load balancing instance.

[0033] The four-layer load balancing instance and the seven-layer load balancing instance are decoupled through network function virtualization. Network function virtualization (NFV) uses general-purpose hardware such as x86 and virtualization technology to carry software processing of many functions, thereby reducing the cost of expensive network equipment. Through software and hardware decoupling and function abstraction, network device functions are no longer dependent on special hardware, resources can be fully and flexibly shared, new network element products can be quickly developed and deployed, and automatic deployment, elastic scaling, fault isolation, and self-healing can be performed based on actual needs. The decoupled four-layer load balancing instance and the seven-layer load balancing instance are two independent load balancing instances. When performing elastic load balancing on the four-layer load balancing instance and / or the seven-layer load balancing instance, both can be performed simultaneously, or only one of them can be performed independently. The four-layer load balancing instance and the seven-layer load balancing instance do not affect each other when performing elastic load balancing.

[0034] The traffic indicators of the four-layer load balancing instance can be data creation volume, data concurrency volume, and traffic bandwidth, and the traffic indicators of the seven-layer load balancing instance can be QPS (Queries Per Second) and the like.

[0035] When performing elastic load balancing, the traffic indicators of the four-layer load balancing instance and the traffic indicators of the seven-layer load balancing instance corresponding to the application-type load balancing instance can be real-time collected.

[0036] Step 204, judgment of whether the traffic indicators of the four-layer load balancing instance and the traffic indicators of the seven-layer load balancing instance are associated indicators. If yes, step 206 is performed, and if no, step 208 is performed.

[0037] After obtaining the traffic indicators, it is first judged whether the traffic indicators of the four-layer load balancing instance and the traffic indicators of the seven-layer load balancing instance are associated indicators. Then, according to the judgment result, it is determined whether to perform associated elastic load balancing on the four-layer load balancing instance and the seven-layer load balancing instance.

[0038] Step 206, associated elastic load balancing is performed on the four-layer load balancing instance and the seven-layer load balancing instance according to the comparison result of the traffic indicators of the four-layer load balancing instance and the first elastic threshold of the four-layer load balancing instance. And the current flow is ended.

[0039] After judging that the traffic index of the four-layer load balancing instance and the traffic index of the seven-layer load balancing instance are the correlation index, only need to compare the traffic index of the four-layer load balancing instance with the first elastic threshold of the four-layer load balancing instance, and then the four-layer load balancing instance and the seven-layer load balancing instance can be associated with the elastic load balancing.

[0040] It should be noted that in this case, the four-layer load balancing instance and the seven-layer load balancing instance are simultaneously subjected to elastic load balancing.

[0041] Step 208, according to the comparison result of the traffic index and the first elastic threshold of the four-layer load balancing instance, the four-layer load balancing instance is subjected to elastic load balancing; and / or, according to the comparison result of the traffic index and the second elastic threshold of the seven-layer load balancing instance, the seven-layer load balancing instance is subjected to elastic load balancing.

[0042] After determining that the traffic index of the four-layer load balancing instance and the traffic index of the seven-layer load balancing instance are not the correlation index, the first elastic threshold of the four-layer load balancing instance and the second elastic threshold of the seven-layer load balancing instance corresponding to the collected traffic index are determined, and according to the comparison result of the first elastic threshold and the traffic index, it is determined whether to perform elastic load balancing on the four-layer load balancing instance; according to the comparison result of the second elastic threshold and the traffic index, it is determined whether to perform elastic load balancing on the seven-layer load balancing instance, the four-layer load balancing instance and the seven-layer load balancing instance can be simultaneously subjected to elastic load balancing, or only one of them can be subjected to elastic load balancing.

[0043] It should be noted that the elastic threshold can be a percentage or a numerical value, when the elastic threshold is a percentage, the ratio of the collected traffic number to the total traffic number is calculated, and the ratio is taken as the traffic index, when the elastic threshold is a numerical value, the collected traffic index is a specific traffic value. Elastic load balancing can include elastic load expansion or elastic load shrinkage. Elastic load expansion can be performed when the elastic threshold reaches the traffic index, and elastic load shrinkage can be performed when the elastic threshold does not reach the traffic index.

[0044] For example, the process of elastic load expansion of the four-layer load balancing instance can be that the traffic index of the four-layer load balancing instance corresponding to the application type load balancing instance is first collected in real time, then the first elastic threshold of the four-layer load balancing instance is determined to reach the traffic index, and finally the four-layer load balancing instance is subjected to elastic load expansion.

[0045] In the embodiments of the present application, in a network system based on four-layer load balancing instances and seven-layer load balancing instances, the elastic load balancing of the four-layer load balancing instances and the seven-layer load balancing instances is decoupled through network function virtualization. In this case, when elastic load balancing of the network is needed, by judging whether the traffic indicators of the four-layer load balancing instances and the traffic indicators of the seven-layer load balancing instances are associated indicators, and in the case of a positive judgment result, since the traffic indicators of the four-layer load balancing instances and the traffic indicators of the seven-layer load balancing instances are associated indicators, elastic load balancing of the four-layer load balancing instances and the seven-layer load balancing instances can be realized only according to the comparison result of the traffic indicators of the four-layer load balancing instances and the first elastic threshold of the four-layer load balancing instances, since traffic collection and comparison of the seven-layer load balancing instances are not needed, the multiple resource consumption of the seven-layer load balancing instances itself is avoided, the resource utilization of the system is improved, and the processing speed is also improved. In the case of a negative judgment result, whether to perform elastic load balancing on the four-layer load balancing instances, the seven-layer load balancing instances, or both the four-layer load balancing instances and the seven-layer load balancing instances can be determined according to the comparison result of the real-time collected traffic indicators of the four-layer load balancing instances and the corresponding first elastic threshold, and the comparison result of the traffic indicators of the seven-layer load balancing instances and the corresponding second elastic threshold. Thus, unnecessary elastic load balancing of the load balancing instances is avoided, and the resource waste caused by the traditional method of simultaneously performing elastic load balancing on the four-layer load balancing instances and the seven-layer load balancing instances is also avoided.

[0046] In a possible implementation manner, the process of performing associated elastic load balancing on the four-layer load balancing instances and the seven-layer load balancing instances according to the comparison result of the traffic indicators of the four-layer load balancing instances and the first elastic threshold of the four-layer load balancing instances can include: determining an elastic target according to the comparison result of the traffic indicators of the four-layer load balancing instances and the first elastic threshold of the four-layer load balancing instances. At the same time of performing elastic load balancing on the four-layer load balancing instances according to the elastic target, the elastic target of the seven-layer load balancing instances is determined according to a preset proportional relationship, and elastic load balancing is performed on the seven-layer load balancing instances based on the elastic target of the seven-layer load balancing instances.

[0047] First, the traffic index of the four-layer load balancing instance is compared with the first elasticity threshold of the four-layer load balancing instance to obtain a comparison result, and then an elasticity target is determined according to the comparison result. After obtaining the elasticity target, the four-layer load balancing instance is elastically load balanced according to the elasticity target. Meanwhile, since the traffic index of the four-layer load balancing instance and the traffic index of the seven-layer load balancing instance are associated indexes, the elasticity target of the seven-layer load balancing instance is determined according to a preset proportional relationship, and then the seven-layer load balancing instance is elastically load balanced based on the elasticity target of the seven-layer load balancing instance.

[0048] In the embodiment of the present application, by determining the elasticity target of the four-layer load balancing instance, the elasticity target of the seven-layer load balancing instance corresponding to the traffic index of the seven-layer load balancing instance which is an associated index of the traffic index of the four-layer load balancing instance can be determined according to the preset proportional relationship, without separately determining the elasticity target of the seven-layer load balancing instance, thereby improving the efficiency of elastic load balancing.

[0049] In a possible implementation manner, if the traffic index of the four-layer load balancing instance is the number of new connections per second CPS, and the traffic index of the seven-layer load balancing instance is the number of requests per second QPS, it is determined that the traffic index of the four-layer load balancing instance and the traffic index of the seven-layer load balancing instance are associated indexes.

[0050] When the traffic index of the four-layer load balancing instance is the number of new connections per second CPS, and the traffic index of the seven-layer load balancing instance is the number of requests per second QPS, since the four-layer load balancing instance is hung behind the seven-layer load balancing instance, the four-layer load balancing instance actually also monitors the seven-layer load balancing instance, and therefore it can be determined that the traffic index of the four-layer load balancing instance and the traffic index of the seven-layer load balancing instance are associated indexes.

[0051] In the embodiment of the present application, whether the traffic index of the four-layer load balancing instance and the traffic index of the seven-layer load balancing instance are associated indexes is determined by the traffic index content of the four-layer load balancing instance and the traffic index content of the seven-layer load balancing instance, thereby improving the efficiency of associated index determination.

[0052] In a possible implementation manner, when the associated indexes are the CPS of the four-layer load balancing instance and the QPS of the seven-layer load balancing instance, the preset proportional relationship is an equal ratio relationship.

[0053] The equal ratio relationship refers to that the ratio of two numbers is equal to a constant, or in other words, there is a fixed proportional relationship between the two numbers. The preset proportional relationship is an equal ratio relationship, specifically, the ratio of the CPS of the four-layer load balancing instance and the QPS of the seven-layer load balancing instance is equal to a constant, for example, the proportional relationship between the CPS and the QPS can be 1:40000.

[0054] In the embodiments of the present application, by setting the preset proportional relationship as an equal ratio, the complexity of operation can be reduced.

[0055] Figure 2B For the schematic diagram of the elastic load balancing system suitable for embodiment one, as shown in Figure 2B , the elastic load balancing system comprises: a proxy server 210, a data cleaning module 212, a load balancing instance database 214, a load balancing instance management and control module 216, a cloud service security management system authentication (C-star) management and control module 218, and a resource management module 220. The proxy server 210 further comprises a client 2102 and a life cycle management component 2104, and the resource management module 220 further comprises a resource management database 2202, a load resource 2204, a life cycle permission management component 2206, and an elastic scaling component 2208.

[0056] The autonomous entity 2102 in the proxy server 210 reports dimension data to the data cleaning module 212, and then the data cleaning module 212 performs data cleaning on the dimension data and sends the cleaned data to the resource management database 2202 in the resource management module 220. The elastic scaling component 2208 can call the load balancing instance database 214, the load balancing instance management and control module 216, and the cloud service security management system authentication (C-star) management and control module 218 according to the traffic index, the first elastic threshold, and the second elastic threshold stored in the resource management database 2202 to perform the above-mentioned elastic load balancing processing. The load resource 2204, the life cycle permission management component 2206, and the elastic scaling component 2208 communicate with each other, manage the load resource 2204 according to the device life cycle management information through the life cycle permission management component 2206, and send the device life cycle management information to the life cycle management component 2104 in the proxy server 210.

[0057] Embodiment two

[0058] Referring to Figure 3 , a step flowchart of a virtualization decoupling method according to the embodiment two of the present application is shown.

[0059] As shown in Figure 3 , the virtualization decoupling method comprises the following steps:

[0060] Step 302, deploy the four-layer load balancing instance and the seven-layer load balancing instance as mutually independent virtual network elements on the network function virtualization platform.

[0061] The process of virtualization decoupling can be divided into physical decoupling and communication decoupling.

[0062] In the physical decoupling process, the four-layer load balancing instance and the seven-layer load balancing instance are deployed based on a network function virtualization (NFV) platform and deployed as independent virtual network elements to achieve physical decoupling of the four-layer load balancing instance and the seven-layer load balancing instance.

[0063] In step 304, a data encapsulation package for defining the number of sessions is added to the message transmitted between the four-layer load balancing instance and the seven-layer load balancing instance.

[0064] In the communication decoupling process, a data encapsulation package for defining the number of sessions is added to the message transmitted between the four-layer load balancing instance and the seven-layer load balancing instance. The data encapsulation package can be obtained through inner vxlan encapsulation. After the inner vxlan encapsulation, only the encapsulated message and the field of the vxlan in the message need to be agreed. For example, a double-layer vxlan encapsulation can be used in communication to place the data message in the innermost side. The four-layer load balancing instance or the seven-layer load balancing instance removes the outermost vxlan encapsulation and considers the traffic as a UDP message (inner vxlan), and agrees on the five-tuple encapsulation rule of inner_ip and udp in the inner vxlan, so that the number of sessions between the four-layer and the seven-layer can be limited to a certain number of sessions through the five-tuple, thereby decoupling the communication between the four-layer load balancing instance and the seven-layer load balancing instance.

[0065] In the embodiments of the present application, the four-layer load balancing instance and the seven-layer load balancing instance are physically decoupled and communication decoupled, which improves the management efficiency and reduces the cost, and fully releases the forwarding performance of the cloud server.

[0066] Embodiment Three

[0067] Referring to Figure 4 , a step flowchart of an elastic load balancing method according to Embodiment Three of the present application is shown.

[0068] As Figure 4 shown, the elastic load balancing method includes:

[0069] In step 402, the four-layer load balancing instance and the seven-layer load balancing instance are deployed as independent virtual network elements on the NFV, and a data encapsulation package for defining the number of sessions is added to the message transmitted between the four-layer load balancing instance and the seven-layer load balancing instance.

[0070] By deploying the four-layer load balancing instance and the seven-layer load balancing instance based on the NFV platform and deploying them as independent virtual network elements, physical decoupling of the four-layer load balancing instance and the seven-layer load balancing instance is realized, and by adding a data encapsulation package for defining the number of sessions in the message transmitted between the four-layer load balancing instance and the seven-layer load balancing instance, the data encapsulation package is encapsulated through an inner vxlan, and after the encapsulation of the vxlan, only the encapsulated vxlan needs to be maintained, thereby realizing the communication decoupling of the four-layer load balancing instance and the seven-layer load balancing instance.

[0071] Step 404, real-time collection of traffic indexes of the four-layer load balancing instance and the seven-layer load balancing instance corresponding to the application-type load balancing instance.

[0072] The four-layer load balancing instance and the seven-layer load balancing instance are two load balancing instances that are decoupled through network function virtualization and independent of each other. When performing elastic load balancing, first, the traffic indexes of the four-layer load balancing instance and the seven-layer load balancing instance corresponding to the application-type load balancing instance are collected in real time.

[0073] Step 406, judgment of whether the traffic indexes of the four-layer load balancing instance and the seven-layer load balancing instance are associated indexes, if yes, step 408 is performed, and if no, step 410 is performed.

[0074] After obtaining the traffic indexes, first, it is judged whether the traffic indexes of the four-layer load balancing instance and the seven-layer load balancing instance are associated indexes, and then, according to the judgment result, it is determined whether to perform associated elastic load balancing on the four-layer load balancing instance and the seven-layer load balancing instance.

[0075] Step 408, associated elastic load balancing of the four-layer load balancing instance and the seven-layer load balancing instance according to the comparison result of the traffic index of the four-layer load balancing instance and the first elastic threshold of the four-layer load balancing instance, and the current process is ended.

[0076] After judging that the traffic indexes of the four-layer load balancing instance and the seven-layer load balancing instance are associated indexes, only the comparison result of the traffic index of the four-layer load balancing instance and the first elastic threshold of the four-layer load balancing instance is needed to perform associated elastic load balancing of the four-layer load balancing instance and the seven-layer load balancing instance.

[0077] It should be noted that in this case, the four-layer load balancing instance and the seven-layer load balancing instance are simultaneously subjected to elastic load balancing.

[0078] Step 410, according to the comparison result of the traffic index and the first elasticity threshold of the four-layer load balancing instance, performing elasticity load balancing on the four-layer load balancing instance; and / or, according to the comparison result of the traffic index and the second elasticity threshold of the seven-layer load balancing instance, performing elasticity load balancing on the seven-layer load balancing instance.

[0079] After determining that the traffic index of the four-layer load balancing instance and the traffic index of the seven-layer load balancing instance are not the associated indexes, the first elasticity threshold of the four-layer load balancing instance and the second elasticity threshold of the seven-layer load balancing instance corresponding to the collected traffic index are determined, and according to the comparison result of the first elasticity threshold and the traffic index, it is determined whether to perform elasticity load balancing on the four-layer load balancing instance; according to the comparison result of the second elasticity threshold and the traffic index, it is determined whether to perform elasticity load balancing on the seven-layer load balancing instance, which can simultaneously perform elasticity load balancing on the four-layer load balancing instance and the seven-layer load balancing instance, or only perform elasticity load balancing on one of them.

[0080] It should be noted that the elasticity threshold can be a percentage or a numerical value. When the elasticity threshold is a percentage, the ratio of the collected traffic number to the total traffic number is calculated as the traffic index, and when the elasticity threshold is a numerical value, the collected traffic index is a specific traffic value. Elastic load balancing can include elastic load expansion or elastic load reduction. Elastic load expansion can be performed when the elasticity threshold reaches the traffic index, and elastic load reduction can be performed when the elasticity threshold does not reach the traffic index.

[0081] For example, the process of elasticity load expansion of the four-layer load balancing instance can be to first collect the traffic index of the four-layer load balancing instance corresponding to the application load balancing instance in real time, then determine that the first elasticity threshold of the four-layer load balancing instance reaches the traffic index, and finally perform elasticity load expansion on the four-layer load balancing instance.

[0082] In the embodiments of the present application, the elastic load balancing of the four-layer load balancing instance and the seven-layer load balancing instance is decoupled through network function virtualization in a network system based on four-layer load balancing instance and seven-layer load balancing instance architecture. In this case, when elastic load balancing of the network is needed, whether the traffic index of the four-layer load balancing instance and the traffic index of the seven-layer load balancing instance are associated indexes is judged. If the result is yes, since the traffic index of the four-layer load balancing instance and the traffic index of the seven-layer load balancing instance are associated indexes, elastic load balancing of the four-layer load balancing instance and the seven-layer load balancing instance can be realized only according to the comparison result of the traffic index of the four-layer load balancing instance and the first elastic threshold of the four-layer load balancing instance. Since traffic collection and comparison of the seven-layer load balancing instance are not needed, the multiple resource consumption of the seven-layer load balancing instance itself is avoided, the resource utilization of the system is improved, and the processing speed is improved. If the result is no, whether elastic load balancing of the four-layer load balancing instance, elastic load balancing of the seven-layer load balancing instance, or elastic load balancing of the four-layer load balancing instance and the seven-layer load balancing instance is needed is determined according to the comparison result of the real-time collected traffic index of the four-layer load balancing instance and the corresponding first elastic threshold, and the comparison result of the traffic index of the seven-layer load balancing instance and the corresponding second elastic threshold. In this way, unnecessary elastic load balancing of the load balancing instance is avoided, and the resource waste caused by the traditional method of simultaneously performing elastic load balancing of the four-layer load balancing instance and the seven-layer load balancing instance is also avoided.

[0083] In a possible implementation manner, step 410 can include:

[0084] First, the traffic of the four-layer load balancing instance and / or the traffic of the seven-layer load balancing instance in the current period is predicted according to the obtained network traffic historical use data, and the corresponding first prediction result and / or second prediction result is obtained. Then, the four-layer load balancing instance is subjected to elastic load balancing according to the comparison result of the traffic index and the first elastic threshold of the four-layer load balancing instance, and the first prediction result, and / or the seven-layer load balancing instance is subjected to elastic load balancing according to the comparison result of the traffic index and the second elastic threshold of the seven-layer load balancing instance, and the second prediction result.

[0085] In order to perform elastic load balancing on the four-layer load balancing instance and / or the seven-layer load balancing instance, at least one of the traffic of the four-layer load balancing instance and the traffic of the seven-layer load balancing instance can be predicted by using the obtained network traffic historical usage data, for example, the traffic of the four-layer load balancing instance and the traffic of the seven-layer load balancing instance in the current period can be respectively predicted, the corresponding first and second prediction results are obtained, then the first elastic threshold of the four-layer load balancing instance and the second elastic threshold of the seven-layer load balancing instance are compared with the traffic index respectively, the four-layer load balancing instance is performed elastic load balancing according to the first prediction result and the comparison result of the four-layer load balancing instance, and the seven-layer load balancing instance is performed elastic load balancing according to the second prediction result and the comparison result of the seven-layer load balancing instance. For another example, only the traffic of the four-layer load balancing instance is predicted, and then the four-layer load balancing instance is performed elastic load balancing according to the comparison result of the traffic index and the first elastic threshold of the four-layer load balancing instance, and the first prediction result.

[0086] The historical usage data can be normally distributed, the traffic of the four-layer load balancing instance is predicted by using the historical usage data, and the corresponding first prediction result is obtained. The first prediction result indicates that the traffic of the four-layer load balancing instance will reach the first elastic threshold of the four-layer load balancing instance, and then the four-layer load balancing instance is performed elastic load expansion. For another example, the traffic of the four-layer load balancing instance and the traffic of the seven-layer load balancing instance can be predicted by using the historical usage data, and the corresponding first prediction result and second prediction result are obtained. The first prediction result indicates that the traffic of the four-layer load balancing instance will reach the first elastic threshold of the four-layer load balancing instance, and the second prediction result indicates that the traffic of the seven-layer load balancing instance is lower than the second elastic threshold of the seven-layer load balancing instance. Then the four-layer load balancing instance is performed elastic load expansion, and the seven-layer load balancing instance is performed elastic load contraction.

[0087] In the embodiment of the present application, by predicting the traffic of the four-layer load balancing instance and / or the traffic of the seven-layer load balancing instance in the current period by using the obtained network traffic historical usage data, the four-layer load balancing instance and the seven-layer load balancing instance can be simultaneously performed elastic load balancing, or at least one of them can be performed elastic load balancing at different times, thereby improving the utilization rate of system resources.

[0088] In a possible implementation manner, the step 410 can further include:

[0089] First, according to the obtained network traffic history usage data, the traffic of the four-layer load balancing instance and / or the traffic of the seven-layer load balancing instance in the current period is predicted to obtain corresponding first and / or second prediction results, then the real-time collected traffic index of the four-layer load balancing instance is corrected using the first prediction result, and according to the comparison result of the correction result and the first elastic threshold of the four-layer load balancing instance, the four-layer load balancing instance is elastically load balanced, and the real-time collected traffic index of the seven-layer load balancing instance can be corrected using the second prediction result, and according to the comparison result of the correction result and the second elastic threshold of the seven-layer load balancing instance, the seven-layer load balancing instance is elastically load balanced.

[0090] In the process of elastically load balancing the four-layer load balancing instance and / or the seven-layer load balancing instance, the traffic index of the four-layer load balancing instance can be corrected using the first prediction result, and / or the traffic index of the seven-layer load balancing instance can be corrected using the second prediction result. Then the elastically load balancing can be performed according to the corrected correction result.

[0091] For example, the traffic of the four-layer load balancing instance and the traffic of the seven-layer load balancing instance in the current period can be predicted respectively, for example, the traffic of the four-layer load balancing instance and the traffic of the seven-layer load balancing instance show a curve rising trend in a statistical graph, then the curvature of the curve in the statistical graph corresponding to the traffic of the four-layer load balancing instance and the traffic of the seven-layer load balancing instance is calculated respectively, and according to the curvature, the corresponding first and second prediction results are obtained. The first prediction result and the second prediction result can be specific numerical values, or can be ratios of the total traffic, and the units of the first prediction result and the second prediction result are the same as the traffic index. Then the real-time collected traffic index of the four-layer load balancing instance is corrected using the first prediction result, and the real-time collected traffic index of the seven-layer load balancing instance is corrected using the second prediction result. The correction result of the four-layer load balancing instance and the correction result of the seven-layer load balancing instance are compared with the traffic index respectively, and according to the comparison result of the correction result of the four-layer load balancing instance and the first elastic threshold of the four-layer load balancing instance, the four-layer load balancing instance is elastically load balanced, and according to the comparison result of the correction result of the seven-layer load balancing instance and the second elastic threshold of the seven-layer load balancing instance, the seven-layer load balancing instance is elastically load balanced.

[0092] In the embodiments of the present application, the real-time collected traffic index of the four-layer load balancing instance and / or the real-time collected traffic index of the seven-layer load balancing instance is corrected by the prediction result, which can make the comparison result more accurate and further improve the accuracy of the elastic load balancing.

[0093] In a possible implementation, the process of performing elastic load balancing on the four-layer load balancing instance and / or the seven-layer load balancing instance can include:

[0094] The historical traffic usage data of the client initiating the load balancing instance is acquired, and then the elastic capacity of the current period is determined for the client according to the historical traffic usage data, and the four-layer load balancing instance and / or the seven-layer load balancing instance are performed elastic load balancing according to the elastic capacity.

[0095] In order to perform elastic load balancing, the historical traffic usage data of the client initiating the load balancing instance is acquired, and after the data is acquired, the elastic capacity of the current period is determined for the client. The four-layer load balancing instance and / or the seven-layer load balancing instance can be performed elastic load balancing as needed.

[0096] For example, after the elastic capacity of the current period is determined for the client, the four-layer load balancing instance can be performed elastic load balancing according to the elastic capacity. For another example, the four-layer load balancing instance and the seven-layer load balancing instance can be performed elastic load balancing at the same time according to the elastic capacity.

[0097] In the embodiments of the present application, the elastic capacity of the current period is determined through the historical traffic usage data of the client, which can make the elastic decision more in line with the usage habits of the client, and improve the experience of the client.

[0098] Embodiment four

[0099] Referring to Figure 5 , a structural schematic diagram of an electronic device according to an embodiment of the present application is shown, and the specific implementation of the electronic device is not limited in the embodiments of the present application.

[0100] As shown in Figure 5 , the electronic device can include a processor 502, a communications interface 504, a memory 506, and a communications bus 508.

[0101] Among them:

[0102] The processor 502, the communications interface 504, and the memory 506 complete the communication among each other through the communications bus 508.

[0103] The communications interface 504 is configured to communicate with other electronic devices or servers.

[0104] The processor 502 is configured to execute the program 510, and specifically can execute the related steps in the above-mentioned elastic load balancing method embodiments.

[0105] Specifically, the program 510 can include program codes including computer operation instructions.

[0106] The processor 502 can be a CPU, or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present application. The one or more processors included in the smart device can be the same type of processor, such as one or more CPUs; or can be different types of processors, such as one or more CPUs and one or more ASICS.

[0107] The memory 506 is configured to store the program 510. The memory 506 can include a high-speed RAM memory, and can also include a non-volatile memory, such as at least one disk memory.

[0108] The program 510 can include a plurality of computer instructions, and the program 510 can specifically cause the processor 502 to perform operations corresponding to the elastic load balancing method described in any of the plurality of method embodiments by the plurality of computer instructions.

[0109] The specific implementation of each step in the program 510 can refer to the corresponding description in the corresponding steps and units in the above method embodiments, and has corresponding beneficial effects, which will not be described here. Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device and the module described above can refer to the corresponding process description in the above method embodiments, which will not be described here.

[0110] Embodiment five

[0111] Referring to Figure 6 , a structural schematic diagram of a network data transmission system according to an embodiment of the present application is shown, as Figure 6 shown, the network data transmission system 600 can include an elastic control module 606, a four-layer load balancing instance 602 and a seven-layer load balancing instance 604 for transmitting data, wherein the four-layer load balancing instance 602 and the seven-layer load balancing instance 604 are two load balancing instances decoupled by network function virtualization and independent of each other.

[0112] The elastic control module 606 is configured to collect the traffic indicators of the four-layer load balancing instance 602 and the traffic indicators of the seven-layer load balancing instance 604 in real time. If the traffic indicators of the four-layer load balancing instance 602 and the traffic indicators of the seven-layer load balancing instance 604 are associated indicators, the elastic control module 606 performs associated elastic load balancing on the four-layer load balancing instance 602 and the seven-layer load balancing instance 604 according to a comparison result of the traffic indicators of the four-layer load balancing instance 602 and a first elastic threshold of the four-layer load balancing instance 602. If the traffic indicators of the four-layer load balancing instance 602 and the traffic indicators of the seven-layer load balancing instance 604 are not associated indicators, the elastic control module 606 performs elastic load balancing on the four-layer load balancing instance 602 according to a comparison result of the traffic indicators and the first elastic threshold of the four-layer load balancing instance 602, and / or performs elastic load balancing on the seven-layer load balancing instance 604 according to a comparison result of the traffic indicators and a second elastic threshold of the seven-layer load balancing instance 604.

[0113] The elastic control module 606 first collects the traffic indicators of the four-layer load balancing instance 602 and the traffic indicators of the seven-layer load balancing instance 604 in real time. The traffic indicators of the four-layer load balancing instance 602 can be data new creation amount, data concurrency amount, traffic bandwidth, etc. The traffic indicators of the seven-layer load balancing instance 604 can be QPS (Queries Per Second), etc. After obtaining the traffic indicators, the elastic control module 606 first determines whether the traffic indicators of the four-layer load balancing instance 602 and the traffic indicators of the seven-layer load balancing instance 604 are associated indicators, and then determines whether to perform associated elastic load balancing on the four-layer load balancing instance 602 and the seven-layer load balancing instance 604 according to the determination result. After the elastic control module 606 determines that the traffic indicators of the four-layer load balancing instance 602 and the traffic indicators of the seven-layer load balancing instance 604 are associated indicators, the elastic control module 606 can perform associated elastic load balancing on the four-layer load balancing instance 602 and the seven-layer load balancing instance 604 according to a comparison result of the traffic indicators of the four-layer load balancing instance 602 and the first elastic threshold of the four-layer load balancing instance 602. After the elastic control module 606 determines that the traffic indicators of the four-layer load balancing instance 602 and the traffic indicators of the seven-layer load balancing instance 604 are not associated indicators, the elastic control module 606 determines the first elastic threshold of the four-layer load balancing instance 602 and the second elastic threshold of the seven-layer load balancing instance 604 corresponding to the collected traffic indicators, determines whether to perform elastic load balancing on the four-layer load balancing instance 602 according to a comparison result of the first elastic threshold and the traffic indicators, and / or determines whether to perform elastic load balancing on the seven-layer load balancing instance 604 according to a comparison result of the second elastic threshold and the traffic indicators. The four-layer load balancing instance 602 and the seven-layer load balancing instance 604 can be simultaneously subjected to elastic load balancing, or only one of them can be subjected to elastic load balancing.

[0114] It should be noted that the elasticity threshold can be a percentage or a numerical value. When the elasticity threshold is a percentage, the ratio of the collected traffic number to the total traffic number is calculated as the traffic index. When the elasticity threshold is a numerical value, the collected traffic index is a specific traffic value. Elastic load balancing can include elastic load expansion or elastic load contraction. Elastic load expansion can be performed when the elasticity threshold reaches the traffic index, and elastic load contraction can be performed when the elasticity threshold does not reach the traffic index.

[0115] For example, the process of elastic load expansion of the four-layer load balancing instance 602 can be to first collect the traffic index of the four-layer load balancing instance 602 corresponding to the application-type load balancing instance in real time, then determine that the first elasticity threshold of the four-layer load balancing instance 602 reaches the traffic index, and finally perform elastic load expansion on the four-layer load balancing instance 602.

[0116] In the embodiments of the present application, based on the network data transmission system 600, the elastic load balancing of the four-layer load balancing instance 602 and the seven-layer load balancing instance 604 is decoupled through network function virtualization. In this case, when elastic load balancing of the network is needed, by judging whether the traffic index of the four-layer load balancing instance 602 and the traffic index of the seven-layer load balancing instance 604 are associated indexes, and in the case of a positive result, since the traffic index of the four-layer load balancing instance 602 and the traffic index of the seven-layer load balancing instance 604 are associated indexes, elastic load balancing of the four-layer load balancing instance 602 and the seven-layer load balancing instance 604 can be achieved only by comparing the traffic index of the four-layer load balancing instance 602 with the first elasticity threshold of the four-layer load balancing instance 602. Since traffic collection and comparison of the seven-layer load balancing instance 604 are not needed, the multiple resource consumption of the seven-layer load balancing instance 604 itself is avoided, the resource utilization of the system is improved, and the processing speed is also improved. In the case of a negative result, whether to perform elastic load balancing on the four-layer load balancing instance 602, the seven-layer load balancing instance 604, or both the four-layer load balancing instance 602 and the seven-layer load balancing instance 604 can be determined according to the comparison results of the real-time collected traffic index of the four-layer load balancing instance 602 with its corresponding first elasticity threshold, and the comparison results of the traffic index of the seven-layer load balancing instance 604 with its corresponding second elasticity threshold. In this way, unnecessary elastic load balancing of load balancing instances is avoided, and the resource waste caused by the traditional method of simultaneously performing elastic load balancing on the four-layer load balancing instance 602 and the seven-layer load balancing instance 604 is also avoided.

[0117] The embodiments of the present application further provide a computer storage medium, which stores a computer program. The computer program is executed by a processor to implement the method described in any of the foregoing method embodiments. The computer storage medium includes, but is not limited to, a compact disc read-only memory (CD-ROM), a random access memory (RAM), a floppy disk, a hard disk, or an optical disk.

[0118] The embodiments of the present application further provide a computer program product, which includes computer instructions. The computer instructions instruct a computing device to perform operations corresponding to any of the elastic load balancing methods in the foregoing method embodiments.

[0119] In addition, it should be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) related to the user involved in the embodiments of the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of the related data need to comply with the relevant laws, regulations and standards of the country and region, and provide corresponding operation entrances for the user to choose authorization or refusal.

[0120] It should be noted that, according to the needs of implementation, each component / step described in the embodiments of the present application can be split into more components / steps, or two or more components / steps or part of the operations of the components / steps can be combined into a new component / step, to achieve the purpose of the embodiments of the present application.

[0121] The method according to the embodiments of the present application described above can be implemented in hardware, firmware, or software, or be implemented as software or computer code that can be stored in a recording medium such as a CD-ROM, a RAM, a floppy disk, a hard disk, or a magneto-optical disk, or be implemented by computer code originally stored in a remote recording medium or a non-transitory machine readable medium and downloaded into a local recording medium, so that the method described herein can be stored in a recording medium on a general computer, a special purpose processor, or a programmable or special purpose hardware such as an Application Specific Integrated Circuit (ASIC) or a Field Programmable Gate Array (FPGA) using such software processing. It can be understood that the computer, the processor, the microprocessor controller, or the programmable hardware includes a storage component (for example, a Random Access Memory (RAM), a Read-Only Memory (ROM), a flash memory, etc.) that can store or receive software or computer code, when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method described herein is implemented. Furthermore, when a general computer accesses the code for implementing the method shown herein, the execution of the code will convert the general computer into a special purpose computer for executing the method shown herein.

[0122] Those skilled in the art can realize that the units and method steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for a specific application, but such implementation should not be considered beyond the scope of the embodiments of the present application.

[0123] The above embodiments are only used to illustrate but not limit the embodiments of the present application. A person of ordinary skill in the art can make various changes and modifications without departing from the spirit and scope of the embodiments of the present application, therefore all equivalent technical solutions belong to the scope of the embodiments of the present application, the patent protection scope of the embodiments of the present application should be defined by the claims.

Claims

1. An elastic load balancing method, comprising: collecting, in real time, a traffic index of a four-layer load balancing instance and a traffic index of a seven-layer load balancing instance corresponding to an application-type load balancing instance, wherein the four-layer load balancing instance and the seven-layer load balancing instance are two load balancing instances that are decoupled by network function virtualization and independent of each other; if the traffic index of the four-layer load balancing instance and the traffic index of the seven-layer load balancing instance are associated indexes, performing associated elastic load balancing on the four-layer load balancing instance and the seven-layer load balancing instance according to a comparison result of the traffic index of the four-layer load balancing instance and a first elastic threshold of the four-layer load balancing instance; if the traffic index of the four-layer load balancing instance and the traffic index of the seven-layer load balancing instance are not associated indexes, performing elastic load balancing on the four-layer load balancing instance according to the comparison result of the traffic index of the four-layer load balancing instance and the first elastic threshold of the four-layer load balancing instance, and / or performing elastic load balancing on the seven-layer load balancing instance according to a comparison result of the traffic index of the seven-layer load balancing instance and a second elastic threshold of the seven-layer load balancing instance.

2. The method of claim 1, wherein, The four-layer load balancing instance and the seven-layer load balancing instance are decoupled in the following ways: deploying the four-layer load balancing instance and the seven-layer load balancing instance as virtual network elements independent of each other on a network function virtualization platform to realize physical decoupling of the four-layer load balancing instance and the seven-layer load balancing instance; and adding a data encapsulation package for defining a number of sessions in a message transmitted between the four-layer load balancing instance and the seven-layer load balancing instance to realize communication decoupling of the four-layer load balancing instance and the seven-layer load balancing instance.

3. The method of claim 1 or 2, wherein, The elastic load balancing on the four-layer load balancing instance according to the comparison result of the traffic index of the four-layer load balancing instance and the first elastic threshold of the four-layer load balancing instance, and / or the elastic load balancing on the seven-layer load balancing instance according to the comparison result of the traffic index of the seven-layer load balancing instance and the second elastic threshold of the seven-layer load balancing instance, comprises: predicting the traffic of the four-layer load balancing instance and / or the traffic of the seven-layer load balancing instance in a current period according to obtained historical network traffic usage data to obtain a corresponding first prediction result and / or a second prediction result; performing elastic load balancing on the four-layer load balancing instance according to the comparison result of the traffic index of the four-layer load balancing instance and the first elastic threshold of the four-layer load balancing instance, and the first prediction result; and / or performing elastic load balancing on the seven-layer load balancing instance according to the comparison result of the traffic index of the seven-layer load balancing instance and the second elastic threshold of the seven-layer load balancing instance, and the second prediction result. ​ 4. The method of claim 1 or 2, wherein, The comparison result of the traffic index of the four-layer load balancing instance and the first elasticity threshold of the four-layer load balancing instance is used to perform elasticity load balancing on the four-layer load balancing instance, and / or the comparison result of the traffic index of the seven-layer load balancing instance and the second elasticity threshold of the seven-layer load balancing instance is used to perform elasticity load balancing on the seven-layer load balancing instance, including: According to the obtained network traffic historical use data, the traffic of the four-layer load balancing instance and / or the traffic of the seven-layer load balancing instance in the current period is predicted to obtain a corresponding first prediction result and / or a second prediction result; The first prediction result is used to correct the real-time collected traffic index of the four-layer load balancing instance; and the comparison result of the correction result and the first elasticity threshold of the four-layer load balancing instance is used to perform elasticity load balancing on the four-layer load balancing instance; And / or, The second prediction result is used to correct the real-time collected traffic index of the seven-layer load balancing instance; and the comparison result of the correction result and the second elasticity threshold of the seven-layer load balancing instance is used to perform elasticity load balancing on the seven-layer load balancing instance.

5. The method of claim 1 or 2, wherein, The elasticity load balancing on the four-layer load balancing instance and / or the seven-layer load balancing instance includes: Obtaining historical traffic use data of a client initiating the load balancing instance; According to the historical traffic use data, an elasticity capacity of the client in the current period is determined; According to the elasticity capacity, the four-layer load balancing instance and / or the seven-layer load balancing instance is performed elasticity load balancing.

6. The method of claim 1, wherein, The comparison result of the traffic index of the four-layer load balancing instance and the first elasticity threshold of the four-layer load balancing instance is used to perform elasticity load balancing on the four-layer load balancing instance and the seven-layer load balancing instance, including: According to the comparison result of the traffic index of the four-layer load balancing instance and the first elasticity threshold of the four-layer load balancing instance, an elasticity target is determined; According to the elasticity target, the four-layer load balancing instance is performed elasticity load balancing, and at the same time, according to a preset proportional relationship, an elasticity target of the seven-layer load balancing instance is determined, and based on the elasticity target of the seven-layer load balancing instance, the seven-layer load balancing instance is performed elasticity load balancing.

7. The method of claim 6, wherein, If the traffic index of the four-layer load balancing instance is a new connection per second CPS, and the traffic index of the seven-layer load balancing instance is a request per second QPS, the traffic index of the four-layer load balancing instance and the traffic index of the seven-layer load balancing instance are determined as associated indexes.

8. The method of claim 7, wherein, When the associated indexes are the CPS of the four-layer load balancing instance and the GPS of the seven-layer load balancing instance, the preset proportional relationship is an equi-proportional relationship.

9. A network data transmission system comprising: An elasticity control module, a four-layer load balancing instance for transmitting data, and a seven-layer load balancing instance, wherein the four-layer load balancing instance and the seven-layer load balancing instance are two load balancing instances that are decoupled by network function virtualization and independent of each other; The elastic control module is configured to collect traffic indicators of the four-layer load balancing instance and traffic indicators of the seven-layer load balancing instance in real time; if the traffic indicators of the four-layer load balancing instance and the traffic indicators of the seven-layer load balancing instance are associated indicators, then according to a comparison result of the traffic indicators of the four-layer load balancing instance and a first elastic threshold of the four-layer load balancing instance, the four-layer load balancing instance and the seven-layer load balancing instance are subjected to associated elastic load balancing; if the traffic indicators of the four-layer load balancing instance and the traffic indicators of the seven-layer load balancing instance are not associated indicators, then according to the comparison result of the traffic indicators of the four-layer load balancing instance and the first elastic threshold of the four-layer load balancing instance, the four-layer load balancing instance is subjected to elastic load balancing, and / or according to a comparison result of the traffic indicators of the seven-layer load balancing instance and a second elastic threshold of the seven-layer load balancing instance, the seven-layer load balancing instance is subjected to elastic load balancing. 10.A computer storage medium having stored thereon a computer program, which, when executed by a processor, implements the method of any one of claims 1-8. 11.A computer program product comprising computer instructions instructing a computing device to perform operations corresponding to the method of any one of claims 1-8.

Images