Communication method and apparatus, device, system, and readable storage medium

By clustering instances in computing nodes in the SDN cloud platform and determining the configuration table entry forwarding relationship based on traffic interaction information, the problem of low efficiency of configuration table entry distribution in the cloud platform is solved, and efficient communication between instances is achieved , reduces network latency.

WO2024235272A1PCT designated stage expired Publication Date: 2024-11-21HUAWEI CLOUD COMPUTING TECHNOLOGIES CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2024/093508
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-08-04
Filing Date
2024-05-15
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

In a cloud platform built by software-defined network (SDN), the traditional configuration issuance method has the problem of low efficiency in configuration table entries, especially in scenarios where the scale of virtual private clouds is large, resulting in communication between instances Longer delay.

Method used

By clustering multiple instances in the computing node, determining the configuration table entry forwarding relationship based on the traffic interaction information between class clusters, and issuing the required configuration table entry to the corresponding computing nodes, thereby achieving efficient communication between instances.

Benefits of technology

It reduces the time-consuming issuance of configuration table items, improves overall communication efficiency, and avoids the long effective time and delay of first packets in traditional full-volume issuance and on-demand issuance methods.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024093508_21112024_PF_FP_ABST
    Figure CN2024093508_21112024_PF_FP_ABST
Patent Text Reader

Abstract

The present application relates to the field of communications, and provides a communication method and apparatus, a device, a system, and a readable storage medium. The method comprises: when issuing configuration table entries to computing nodes, clustering a plurality of instances comprised in the at least two computing nodes to obtain at least two class clusters; determining a configuration table entry forwarding relationship according to traffic interaction information between the at least two class clusters, wherein the configuration table entry forwarding relationship is used for instructing to issue to a first computing node a configuration table entry of another class cluster having traffic interaction with the class cluster of the first computing node; and sending the configuration table entries to the at least two computing nodes according to the configuration table entry forwarding relationship. Thus, when issuing configuration table entries, there is no need to issue configuration table entries of all the instances or indirectly issue the configuration table entries by means of a forwarding node, thereby reducing the communication time delay and improving the overall communication efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Communication method, device, equipment, system and readable storage medium

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on May 16, 2023, with application number 202310551806.9 and application name “Communication method, device, equipment, system and readable storage medium”, and the Chinese patent application filed with the State Intellectual Property Office on August 4, 2023, with application number 202310980555.6 and application name “Communication method, device, equipment, system and readable storage medium”, all contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communications, and in particular to a communication method, apparatus, device, system, and readable storage medium. Background Art

[0003] In cloud platforms built on software-defined networking (SDN), network creation, resource application, and network changes all require configurations to be distributed to data plane devices via the control plane. Traditional configuration distribution methods include global distribution and on-demand distribution. Global distribution involves the controller distributing configuration entries for all instances in the cloud platform to a virtual switch on a compute node for forwarding. On-demand distribution involves forwarding nodes recording configuration entries for all instances in the cloud platform and then matching and distributing the configuration entries to the instances.

[0004] However, when the number of configuration items is large, the first instance access of the items in the full delivery method takes a long time to take effect. The on-demand delivery method requires forwarding nodes to forward the configuration items, resulting in a long first packet delay. Therefore, traditional configuration delivery methods all suffer from low communication efficiency.

[0005] Summary of the Invention

[0006] The embodiments of the present application provide a communication method, apparatus, device, system and readable storage medium, which can solve the problem of low efficiency in configuration table item delivery during configuration delivery.

[0007] In a first aspect, a communication method is provided. The communication method includes: first, clustering multiple instances contained in at least two computing nodes to obtain at least two clusters. Then, determining a configuration table item forwarding relationship based on traffic interaction information between the at least two clusters, namely, issuing configuration table items for other clusters that have traffic interaction with the cluster of the first computing node to a first computing node, where the first computing node is one of the at least two computing nodes. Next, sending the configuration table items to the at least two computing nodes based on the configuration table item forwarding relationship.

[0008] In a possible implementation of the present application, each of the at least two clusters includes at least one instance. A configuration entry forwarding relationship indicates to which compute node the configuration entry for each instance is to be delivered. Delivering the configuration entry refers to delivering the instance's configuration entry to a data plane device (e.g., a virtual switch) of the compute node corresponding to the instance.

[0009] Optionally, the instance is a container (docker), and the cluster is an application to which multiple containers belong.

[0010] Based on this communication method, through the traffic interaction between the clusters to which each instance belongs, the clusters that need to access each other are determined, and for each cluster, the configuration table items are sent to the computing node to which the cluster that needs to communicate with the cluster belongs, so that the instances contained in each cluster can access each other. In this way, compared with the full delivery of configuration items, in the scenario of a large-scale virtual private cloud, a large number of configuration table items need to be sent to a certain computing node for configuration. In this application, there is no need to send the configuration table items of all instances when a certain computing node is cold started. Compared with the on-demand delivery of configuration items, the instance learning configuration table items need to pass through the forwarding node that records all the configuration table items. In this application, there is no need to indirectly send the configuration table items through the forwarding node. Therefore, compared with the full delivery and on-demand delivery of configuration items, the communication method of the present application reduces the network communication delay caused by the long time spent on forwarding configuration table items or sending all configuration table items between instances, thereby improving the overall communication efficiency.

[0011] As a possible implementation method, the configuration table item forwarding relationship includes: sending the configuration table item of the instance contained in the cluster corresponding to the first computing node to the first computing node, and the corresponding cluster includes a cluster that has traffic interaction with the cluster to which the instance contained in the first computing node belongs.

[0012] As a possible implementation manner, the configuration table item forwarding relationship further includes: sending the configuration table item of the instance included in the first computing node to the first computing node.

[0013] In this way, the cluster-based traffic interaction information reflects which clusters the computing node to which the cluster belongs needs to communicate with, thereby determining which clusters each computing node needs to support access between instances, and thus sending to the computing node the configuration table entries of the instances contained in the clusters that the instance of the computing node may subsequently access.

[0014] As a possible implementation, before determining the configuration table entry forwarding relationship based on the traffic interaction information between clusters, it is also necessary to determine the traffic interaction information between at least two clusters based on the traffic interaction information between multiple instances.

[0015] Optionally, traffic interaction information between multiple instances is first obtained, and then it is determined that clusters to which every two instances with traffic interaction belong have traffic interaction, thereby obtaining traffic interaction information between at least two clusters.

[0016] For example, traffic interaction information between multiple instances may be obtained based on a flow table of a data plane device of a computing node.

[0017] For another example, traffic interaction information between multiple instances may be obtained based on connection tracking (CT) entries of computing nodes.

[0018] This application does not limit the clustering criteria of multiple instances. The clustering criteria can be used to classify instances that implement the same function into the same cluster. For example, multiple instances belonging to the same application are classified into the same cluster (or called application).

[0019] As a first possible implementation, instances of the same application or similar applications are usually grouped into the same security group. The clustering criteria include grouping instances in the same security group into a cluster.

[0020] As a second possible implementation method, in a cloud-native scenario, applications are deployed in only one subnet and applications do not access each other across subnets. In this case, the clustering criteria include grouping instances in the same subnet into a cluster.

[0021] As a third possible implementation method, instances in the same auto scaling (AC) group or load balancing cluster are usually the same or similar applications. The clustering criteria include: grouping the instances in the same auto scaling group or load balancing cluster into a cluster.

[0022] As a fourth possible implementation, multiple instances may be preset with application identifiers or network prefixes for distinguishing the applications to which the instances belong. The clustering criteria include: grouping instances with the same application identifier or network prefix into a cluster.

[0023] Among them, the application identifier includes the identifier used to represent the application attributes in the network card, the identifier used by the container orchestration engine to divide the application to which the container belongs, etc.

[0024] In a second aspect, a communication device is provided. The communication device includes a clustering module, a matching module, and a transceiver module. The clustering module is used to cluster multiple instances contained in at least two computing nodes to obtain at least two clusters, each of the at least two clusters including at least one instance. The matching module is used to determine a configuration table item forwarding relationship based on traffic interaction information between the at least two clusters, the configuration table item forwarding relationship being used to indicate that configuration table items of other clusters that have traffic interaction with the cluster of the first computing node are sent to a first computing node, where the first computing node is one of the at least two computing nodes. The transceiver module is used to send configuration table items to the at least two computing nodes based on the configuration table item forwarding relationship.

[0025] As a possible implementation method, the configuration table item forwarding relationship includes: sending the configuration table item of the instance contained in the cluster corresponding to the first computing node to the first computing node, and the corresponding cluster includes a cluster that has traffic interaction with the cluster to which the instance contained in the first computing node belongs.

[0026] As a possible implementation manner, the corresponding cluster also includes the cluster to which the instance included in the first computing node belongs.

[0027] As a possible implementation manner, the communication device further includes a traffic processing module, configured to determine traffic interaction information between at least two clusters based on traffic interaction information between a plurality of instances.

[0028] Optionally, the traffic processing module is specifically used to: obtain traffic interaction information between multiple instances; determine that there is traffic interaction between the clusters to which every two instances with traffic interaction belong, and obtain traffic interaction information between at least two clusters.

[0029] As a possible implementation manner, the clustering module is specifically configured to: cluster the multiple instances according to the network configurations of the multiple instances included in at least two computing nodes to obtain at least two clusters.

[0030] Optionally, the clustering module is specifically configured to cluster instances belonging to the same security group, subnet, elastic scaling group, or load balancing cluster among the multiple instances to obtain at least two clusters.

[0031] Optionally, the clustering module is specifically used to: cluster instances carrying the same network prefix or application identifier in multiple instances to obtain at least two clusters, where the application identifier includes an identifier in the network card used to represent application attributes and an identifier used by the container orchestration engine to divide the application to which the container belongs.

[0032] It should be noted that the communication device described in the second aspect can be a communication device, such as a terminal device or a network device, or a chip (system) or other parts or components that can be set in a terminal device or a network device, or a device that includes a terminal device or a network device. This application does not limit this.

[0033] In a third aspect, a communication device is provided, comprising a memory and a processor, wherein the memory is used to store a set of computer instructions, and when the processor executes the set of computer instructions, it is used to execute the operating steps of the communication method in any possible design in the first aspect.

[0034] In a fourth aspect, a communication system is provided. The communication system includes a controller and at least two computing nodes, wherein the at least two computing nodes have multiple instances deployed. The controller is configured to execute the operation steps of the communication method in any possible design of the first aspect, and the at least two computing nodes are configured to receive configuration entries sent by the controller.

[0035] In addition, the technical effects of the communication device described in the second aspect, the technical effects of the communication equipment described in the third aspect, and the technical effects of the communication system described in the fourth aspect can refer to the technical effects of the communication method described in the first aspect and will not be repeated here.

[0036] In a fifth aspect, a readable storage medium is provided, which includes a computer program or instructions that, when executed on a computer, causes the computer to execute the communication method described in any possible implementation of the first aspect.

[0037] In a sixth aspect, a computer program product is provided, which includes a computer program or instructions, and when the computer program or instructions are executed on a computer, causes the computer to execute the communication method described in any possible implementation of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 is a schematic diagram of the process of issuing configuration items on a traditional cloud platform;

[0039] FIG2 is a flow chart of a method for sending all configuration items;

[0040] FIG3 is a flow chart of an on-demand delivery method for configuration items;

[0041] FIG4 is a schematic diagram of the architecture of a communication system provided by the present application;

[0042] FIG5 is a schematic diagram of a layered structure of a cloud platform provided by this application;

[0043] FIG6 is a flow chart of a communication method provided by the present application;

[0044] FIG7 is a schematic diagram of a clustering result provided by this application;

[0045] FIG8 is a schematic diagram of traffic interaction information between clusters provided by the present application;

[0046] FIG9 is a schematic diagram of the structure of a communication system in a cloud-native application scenario provided by this application;

[0047] FIG10 is a schematic structural diagram of a communication system in a traditional application scenario provided by the present application;

[0048] FIG11 is a schematic structural diagram of a communication device provided by the present application;

[0049] FIG12 is a schematic structural diagram of a communication device provided in this application. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. In the present application, "at least one" refers to one or more, and "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can represent: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b and c can be single or multiple.

[0051] It should be noted that, in this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0052] The data transmission method provided in the embodiment of the present application can be applied to cloud platform management scenarios in the field of cloud computing. The following is a brief introduction to the technologies that may be involved in this application.

[0053] (1) Software-Defined Networking

[0054] Software-defined networking (SDN) separates the network's control plane from its data forwarding plane. This allows for programmable control of the underlying hardware through a centralized controller's software platform, enabling flexible, on-demand allocation of network resources. In an SDN network, network devices are solely responsible for data forwarding, utilizing general-purpose hardware. The original control operating system is refined into an independent network operating system, responsible for adapting to diverse service characteristics. Furthermore, communication between the network operating system, service characteristics, and hardware devices can all be achieved programmatically.

[0055] (2) Cloud Platform

[0056] A cloud computing platform, also known as a cloud computing platform, refers to a service based on hardware and software resources that provides computing, networking, and storage capabilities. That is, the platform provider combines the cloud (remote hardware resources) and computing (remote software resources) to form a platform that provides various services to users.

[0057] Services provided by cloud platforms can include software as a service (SaaS), platform as a service (PaaS), and infrastructure as a service (IaaS). SaaS involves a service provider deploying application software on the cloud platform's servers, and users subscribe to the application software services from the service provider over the internet based on their needs. PaaS offers a development environment as a service, meaning the service provider provides users with services such as a development environment, server platforms, and hardware resources. Users develop applications within the cloud platform's development environment and share them with other users via the cloud platform and the internet. IaaS involves a service provider providing a cloud infrastructure consisting of multiple servers as a service to users. This integrates memory, input / output devices, storage, and computing resources into a virtual resource pool, providing users with storage resources and virtualized servers.

[0058] In a cloud platform built on SDN technology, the control plane is like the human brain, responsible for the control and scheduling of the entire branch network. This enables full lifecycle management of the entire branch network, including device online, configuration distribution, operations monitoring, and network optimization. This unified management and operations enable intelligent analysis and diagnosis based on the overall network operation status, shortening service impacts and improving service stability.

[0059] (3) Configuration table entries

[0060] In a cloud platform, when tenants create networks, apply for resources, or change networks, they must send configurations to the data plane devices through the control plane. For example, as shown in Figure 1, when a tenant chooses to use the cloud platform to migrate their business to the cloud, they first need to operate in the user interface and use the application program interface (API) to create a virtual private cloud (VPC), create multiple subnets, and then purchase or rent one or more virtual machines (VMs) or containers and configure them in the subnets. The control plane controller 110 needs to be on different computing nodes (such as computing nodes 120 and computing nodes 130 shown in Figure 1), and the instances purchased or rented by the user will be assigned to different computing nodes. Multiple instances are configured in the same virtual private cloud through virtualization technology, and the controller stores configuration entries for each instance in the virtual private cloud. The controller needs to send configuration entries for the network cards corresponding to each instance in the virtual private cloud to the virtual switches of different computing nodes, so that instances on different computing nodes can communicate with each other based on the configuration entries.

[0061] Among them, configuration table items include location tables, access control lists (ACLs), security groups, etc. After the configuration table items are sent to the data plane, the data plane devices can communicate with one or more instances to perform the functions expected by the tenants.

[0062] In cloud-native scenarios, to meet the needs of a large number of customers, each virtual private cloud typically deploys a large number of containers. As customer business volume grows, the number of containers can reach tens of millions or even hundreds of millions. To meet such large-scale virtual private cloud requirements, a massive number of configuration items must be issued. Furthermore, these containers elastically scale with changes in business volume, and the speed with which these configuration items take effect directly impacts customer business.

[0063] Currently, there are some solutions for delivering configuration items, such as full delivery and on-demand delivery. These solutions have problems such as long configuration validity time and extended first-packet network time, resulting in low efficiency in delivering configuration items.

[0064] The following describes the method of sending all configuration items in conjunction with FIG2 .

[0065] As shown in Figure 2, controller 210 maintains all the configuration entries required by the cloud network data plane. When a user creates or changes the configuration of a virtual private cloud network, the controller sends the configuration entries to the data plane (Figure 2 shows compute nodes 220, 230, and n), that is, all related virtual switches. Compute node 220 is configured with virtual switch 1 and runs instance 1. Compute node 230 is configured with virtual switch 2 and runs instances 2 and 3. Compute node n is configured with virtual switch n and runs instances n-1 and n.

[0066] User-created instance 1 is the first instance deployed on compute node 220 within the corresponding virtual private cloud. Controller 210 must deliver all configuration entries to compute node 220 so that virtual switch 1 can forward traffic from instance 1 to the destination instance, such as instance 2. Controller 210 must also deliver the configuration entries corresponding to instance 1 to virtual switch 2 within compute node 230 so that virtual switch 2 can forward packets from instance 2 to instance 1 within compute node 220.

[0067] The steps of sending all configuration items in FIG. 2 may include the following steps 201 to 204 .

[0068] Step 201: The user creates instance 1 through the user interface. The controller 210 creates a network card in the virtual private cloud and binds the network card to instance 1.

[0069] Step 202: The controller 210 calculates the configuration table items that need to be sent to the virtual switches of different computing nodes in the data plane for this request.

[0070] Step 203 : The controller 210 sends all configuration entries in the virtual private cloud to the virtual switch of the computing node 220 , and sends the configuration entries of instance 1 to the virtual switches of other related computing nodes.

[0071] Step 204: After the configuration entries in the virtual switches of other related computing nodes take effect, traffic interaction is implemented between instance 1 and other instances (such as instance 2, instance n, etc.).

[0072] In the above step 203, all configuration items are sent to the virtual switch of the computing node 220. When the number of configuration items is large, the effective time may reach tens of seconds or even minutes. Therefore, the items corresponding to the instance to be accessed by instance 1 take effect later. It takes a long time for instance 1 to successfully access the instance, which affects the user experience.

[0073] In cloud platforms built on SDN technology, the main reason why configuration items take a long time to take effect is that high-level services for orchestrating virtual private clouds cannot distinguish whether it is a cold start scenario, that is, whether the configuration items are being sent to the computing nodes for the first time. Therefore, all virtual private cloud configuration items will be sent to the computing nodes. In addition, the orchestration requires a clear waiting time for the items to take effect, resulting in low overall communication efficiency.

[0074] Next, the on-demand delivery method of the configuration table items will be described with reference to FIG3 .

[0075] As shown in Figure 3, the controller 310 maintains all the configuration items required by the cloud network data plane (Figure 3 shows computing nodes 320 and computing nodes 330). When the user creates and changes the configuration of the virtual private cloud network through the user interface, the controller 310 sends the configuration items to the forwarding node 340, which records all the configuration items. The function of forwarding node 340 to send configuration items on demand may be implemented through the control plane or data plane. Among them, computing node 320 is provided with virtual switch 1 and runs instance 1. Computing node 330 is provided with virtual switch 2 and runs instance 2.

[0076] When inter-instance traffic is accessed, the virtual switch matches the default entry and sends it to forwarding node 340. Forwarding node 340 then forwards the traffic to the destination instance and sends the corresponding configuration entry to the virtual switch. Subsequent inter-instance traffic is forwarded directly by the compute node's virtual switch, without passing through forwarding node 340.

[0077] The on-demand delivery step of the configuration table items in FIG3 may include the following steps 301 to 305 .

[0078] Step 301: The user creates instance 1 through the user interface. The controller 310 creates a network card in the virtual private cloud and binds the network card to instance 1.

[0079] Step 302: The controller 310 sends the configuration table entries of instance 1 to the forwarding node 340, and the forwarding node 340 records all the configuration table entries.

[0080] Step 303 : When instance 1 accesses instance 2 for the first time, the virtual switch of computing node 320 matches the default entry and sends the traffic to forwarding node 340 .

[0081] Step 304 : The forwarding node 340 sends the traffic to instance 2 according to the traffic matching configuration entry, and sends the instance 2 configuration entry to the virtual switch of the computing node 320 .

[0082] Step 305 : When instance 1 accesses instance 2 again, computing node 320 matches the configuration entry of instance 2 on the virtual switch and directly sends the traffic to instance 2 of computing node 330 .

[0083] In the above steps 303 and 304, the traffic from instance 1 to instance 2 does not go directly from computing node 1 to computing node 2, but needs to go through the forwarding node, which will cause a large first packet delay and affect the overall communication efficiency.

[0084] The present application provides a communication method, in particular, a communication method for "issuing configuration table items of instances that require traffic interaction with instances deployed by the computing node itself." First, the controller clusters multiple instances contained in at least two computing nodes to obtain at least two clusters, so that at least one instance contained in each cluster belongs to the same or similar application. Secondly, the controller determines the configuration table item forwarding relationship based on the traffic interaction information between at least two clusters. The configuration table item forwarding relationship is used to indicate that configuration table items of other clusters that have traffic interaction with the cluster of the first computing node are sent to the first computing node, thereby associating the configuration table item forwarding relationship with the traffic interaction between instances. Then, the controller sends the configuration table items to at least two computing nodes based on the configuration table item forwarding relationship.

[0085] Based on this communication method, through the traffic interaction between the clusters to which each instance belongs, the clusters that need to access each other are determined, and for each cluster, the configuration table items are sent to the computing node to which the cluster that needs to communicate with the cluster belongs, so that the instances contained in each cluster can access each other. In this way, compared with the full delivery of configuration items, in the scenario of a large-scale virtual private cloud, a large number of configuration table items need to be sent to a certain computing node for configuration. In this application, there is no need to send the configuration table items of all instances when a certain computing node is cold started. Compared with the on-demand delivery of configuration items, the instance learning configuration table items need to pass through the forwarding node that records all the configuration table items. In this application, there is no need to indirectly send the configuration table items through the forwarding node. Therefore, compared with the full delivery and on-demand delivery of configuration items, the communication method of the present application reduces the network communication delay caused by the long time spent on forwarding configuration table items or sending all configuration table items between instances, thereby improving the overall communication efficiency.

[0086] The implementation of the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0087] Figure 4 is a schematic diagram of the architecture of a communication system provided by this application. Communication system 400 can be a cloud platform based on the SDN technology architecture, and communication system 400 includes a controller 410 and a computing node cluster. The computing node cluster communicates with controller 410 via a network.

[0088] The controller 410 may be an SDN controller such as an OpenDaylight controller or an open network operating system (ONOS) controller.

[0089] Controller 410 is used to allocate resources and issue configurations to tenants based on their needs, thereby building a cloud platform. For example, controller 410 manages the entire lifecycle of devices within a computing node cluster within the network, including device online, configuration delivery, operations and maintenance monitoring, and network optimization, achieving unified management and operations. User needs can be input into controller 410 through a user interface.

[0090] As a possible implementation method, the controller 410 clusters multiple instances contained in at least two computing nodes to obtain at least two clusters, and then determines the configuration table item forwarding relationship based on the traffic interaction information between the at least two clusters. The configuration table item forwarding relationship is used to indicate that the configuration table items of other clusters that have traffic interaction with the cluster of the first computing node are sent to the first computing node, and then the configuration table items are sent to at least two computing nodes based on the configuration table item forwarding relationship.

[0091] The computing node cluster includes one or more computing nodes (four computing nodes, namely computing node 420 , computing node 430 , computing node 440 , and computing node 450 , are shown in FIG. 4 ).

[0092] Each compute node contains one or more instances, which are used to implement the functions required by cloud platform tenants. These instances can be executable units of applications such as containers.

[0093] As a possible implementation, each computing node includes one or more virtual machines and a virtual switch for implementing instance communication between the computing nodes. The virtual switches of each computing node are connected to each other (the connecting lines are not shown in Figure 4) and are respectively connected to the controller 410.

[0094] Optionally, each virtual machine runs one or more containers to implement the functionality of the instance. Each container communicates with the virtual switch via a network card (represented by a circle in Figure 4).

[0095] The computing nodes in the computing node cluster are used to receive the configuration items sent by the controller 410 and deploy the configuration items on the virtual switch.

[0096] It is worth noting that FIG4 is only a schematic diagram and should not be understood as limiting the present application. The communication system 400 may also include other devices that are not shown in FIG4 .

[0097] The computing nodes in the communication system 400 provided herein may be nodes in a cloud platform. The communication system 400 implements the functions of computing nodes based on infrastructure as a service (IaaS), platform as a service (PaaS), and software as a service (SaaS), and provides services (such as computing services, etc.) to tenants through computing nodes. The computing nodes may be cloud-based service nodes virtualized using the resources (such as computing resources and storage resources, etc.) of the communication system 400.

[0098] Next, the layered structure of the communication system 400 as a cloud platform will be described with reference to FIG5 .

[0099] As shown in FIG5 , the IaaS platform 510 is used to virtualize all infrastructure resources in the communication system 400 and provide users with virtual resources (eg, computing resources, network resources, and storage resources) in a software-defined manner.

[0100] PaaS platform 520 implements the runtime environment and application support functions of communication system 400. Users can apply for computing units within quotas rather than virtual resources to run their own services. Alternatively, computing units can be instances, such as containers, and communication system 400 deploys and runs user code by scheduling containers. It should be noted that the number of containers in PaaS platform 520 can be one or more; Figure 5 shows only two containers as an example.

[0101] As a possible implementation, the communication system 400 may inject one or more components into a container to implement code deployment and execution.

[0102] The SaaS application 530 is used to provide services to users by composing user-deployed applications in the form of application program interface responses based on the IaaS platform 510 and the PaaS platform 520. The applications and containers of the SaaS application 530 can communicate through a web server.

[0103] It is worth noting that FIG5 is only a schematic diagram and should not be understood as a limitation on the present application. The cloud platform layered structure of the communication system 400 may also include other modules that are not drawn in FIG5.

[0104] Next, the communication method provided by this application is described in detail with reference to the accompanying drawings.

[0105] The steps of the communication method provided in this application are executed by the controller 410 and the computing node in the communication system 400. Next, steps 610 to 630 of the communication method provided in this application are described in conjunction with Figure 6.

[0106] Step 610: The controller 410 clusters multiple instances included in at least two computing nodes to obtain at least two clusters.

[0107] In some possible embodiments, the controller 410 clusters the multiple instances according to the network configurations of the multiple instances included in at least two computing nodes to obtain at least two clusters.

[0108] The clusters can be regarded as applications, that is, multiple instances belonging to the same cluster are a group of instances included in an application. The result of clustering is to divide the multiple instances included in at least two computing nodes into different applications.

[0109] For example, as shown in Figure 7, compute node 420 includes instances 2 and 3, compute node 430 includes instances 1, 4, and 7, compute node 440 includes instances 8 and 9, and compute node 450 includes instances 5 and 6. Application 1 consists of instances 2 and 3 of compute node 420, application 2 consists of instances 1, 4, and 7 of compute node 430, and instance 8 of compute node 440, and application 3 consists of instances 5 and 6 of compute node 450, and instance 9 of compute node 440.

[0110] Optionally, the controller 410 clusters the multiple instances according to the security group, subnet, elastic scaling group, or load balancing cluster to which the multiple instances belong.

[0111] For example, instances belonging to the same security group, subnet, elastic scaling group, or load balancing cluster are typically the same or similar applications. Controller 410 groups instances belonging to the same security group, subnet, elastic scaling group, or load balancing cluster into the same cluster. The specific steps for this are described in FIG10 and are not repeated here.

[0112] The load balancing cluster may be an application load balancing (ALB) cluster, a classic load balancing (CLB) cluster, a network load balancing (NLB) cluster, or the like.

[0113] Optionally, the controller 410 clusters the multiple instances according to network prefixes or application identifiers carried by the multiple instances.

[0114] For example, in a tag-based access control scenario, different tags are typically used to distinguish different access permissions, and instances with the same access permissions are typically the same or similar applications. The controller 410 groups instances carrying the same access control tag into the same cluster.

[0115] For example, when classless inter-domain routing (CIDR) is used for address allocation and classification using Internet Protocol version 6 (IPv6), instances belonging to the same CIDR address block generally belong to the same or similar applications. Controller 410 groups instances carrying the same CIDR network prefix into the same cluster.

[0116] For another example, in a scenario where an application identifier is recorded in the attributes of a network card, the application identifier in the network card is used to represent the application attributes of the application to which the instance belongs. Instances with the same application identifier are generally the same or similar applications. The controller 410 classifies the instances carrying the application identifier representing the same application attributes into the same cluster.

[0117] For example, when using a container orchestration engine such as Kubernetes to host instances, Kubernetes uses application identifiers to indicate which pods constitute an application. Instances with the same application identifier typically represent the same or similar application. Controller 410 groups multiple instances that carry the same Kubernetes application identifier into the same cluster. The specific steps for this are described in FIG9 and are not repeated here.

[0118] This application does not limit the specific method by which controller 410 clusters instances. The above clustering methods are merely examples of possible clustering methods listed in this application. Other possible embodiments may employ other clustering methods. For example, controller 410 may also collect traffic information and use machine learning to group instances with similar traffic into clusters. Exhaustive examples of clustering methods are not provided here.

[0119] In step 610, clustering operations are used to determine which instances each application contains. Each application is a collection of network card information corresponding to the instance (such as Internet Protocol (IP), Media Access Control Address (MAC), virtual private cloud, etc.). Next, in step 620, the controller 410 parses the business traffic information between each instance to determine which network cards have traffic, that is, traffic interaction information between multiple instances, and thus determine which two applications have business interaction, that is, traffic interaction information between at least two clusters, based on the traffic interaction information between multiple instances, to determine the configuration table forwarding relationship.

[0120] Step 620: The controller 410 determines a configuration table entry forwarding relationship based on traffic interaction information between at least two clusters.

[0121] In some possible embodiments, the controller 410 determines traffic interaction information between at least two clusters based on traffic interaction information between multiple instances, and determines a configuration table entry forwarding relationship based on the traffic interaction information between the at least two clusters.

[0122] The configuration table item forwarding relationship is used to instruct the computing node to deliver the configuration table item to the instance contained in the corresponding cluster. The corresponding cluster is a cluster that has traffic interaction with the cluster to which the instance contained in the computing node belongs.

[0123] Taking the clustering results shown in Figure 7 as an example, please refer to Figure 8. The controller 410 determines that there is business traffic between instance 2 and instance 3 in application 1 and instance 1 in application 2 (indicated by a double-arrow connecting line), and there is business traffic between instance 4 in application 2 and instances 5 and instance 6 in application 3. Then it is determined that there is traffic interaction between application 1 and application 2 (indicated by a double-arrow connecting line), and there is traffic interaction between application 2 and application 3.

[0124] As a possible implementation method, the controller 410 first obtains traffic interaction information between multiple instances, determines that there is traffic interaction between the clusters to which each two instances with traffic interaction belong, and thus obtains traffic interaction information between at least two clusters.

[0125] Optionally, the controller 410 may determine the traffic interaction information between multiple instances through a flow table (eg, a br-int flow table, a br-tun flow table, etc.) of a virtual switch of each computing node.

[0126] Optionally, the controller 410 can obtain business traffic information (such as triples, quintuples, etc.) through the connection tracking table entries of each computing node, thereby determining the traffic information between the network cards of multiple instances, that is, the traffic interaction information between multiple instances.

[0127] This application does not limit the method in which the controller 410 collects traffic interaction information between multiple instances. The above method of determining the traffic interaction information of an instance based on the flow table and connection tracking table entries is only an example given in this application. The controller 410 can also determine the traffic interaction information of an instance based on traffic-related data such as flow logs.

[0128] As a possible implementation method, the controller 410 determines the configuration table item forwarding relationship based on the traffic interaction information between at least two clusters, so as to send the configuration table items of the instance that each computing node itself needs to access to at least two computing nodes in the computing node cluster according to the configuration table item forwarding relationship.

[0129] Optionally, the configuration table item forwarding relationship is used to indicate that configuration table items of other clusters that have traffic interaction with the cluster of the first computing node are sent to the first computing node. The first computing node is one of at least two computing nodes in the computing node cluster (e.g., computing node 420, computing node 430, computing node 440, or computing node 450).

[0130] Optionally, the configuration table item forwarding relationship includes: sending the configuration table item of the instance included in the cluster corresponding to the first computing node to the first computing node, and the corresponding cluster includes a cluster that has traffic interaction with the cluster to which the instance included in the first computing node belongs.

[0131] Optionally, the corresponding cluster further includes the cluster to which the instance included in the first computing node belongs.

[0132] Continuing with the traffic interaction between applications in Figure 8 as an example, based on the traffic interaction information of Application 1, Application 2, and Application 3, as well as the applications and compute nodes to which instances 1 through 9 belong, the resulting division of the configuration table forwarding relationship can be as follows:

[0133] For example, computing node 420 includes instance 2 and instance 3. Application 1, to which instances 2 and 3 belong, interacts with application 2. Therefore, the cluster corresponding to computing node 420 is application 2. The configuration entry forwarding relationship includes: controller 410 sends configuration entries for the instances included in application 2, namely, configuration entries for instance 1, instance 4, instance 7, and instance 8, to computing node 420.

[0134] For example, computing node 430 includes instance 1, instance 4, and instance 7. Application 2, to which instances 1, 4, and 7 belong, interacts with application 1 and application 3, respectively. Therefore, the clusters corresponding to computing node 430 are application 1 and application 3. The configuration entry forwarding relationship includes: controller 410 sends configuration entries for the instances included in application 1 and application 2, namely, configuration entries for instance 2, instance 3, instance 5, instance 6, and instance 9, to computing node 430.

[0135] For example, compute node 440 includes instances 8 and 9. Application 2, to which instance 8 belongs, interacts with both applications 1 and 3. Application 3, to which instance 9 belongs, interacts with application 2. The clusters corresponding to compute node 440 are application 1, application 2, and application 3. The configuration entry forwarding relationship includes: controller 410 sends configuration entries for the instances included in application 1, application 2, and application 3, namely, configuration entries for instances 1 through 9, to compute node 440.

[0136] For example, compute node 450 includes instances 5 and 6. Application 3, to which instances 5 and 6 belong, interacts with application 2, and the cluster corresponding to compute node 450 is application 2. The configuration entry forwarding relationship includes controller 410 sending configuration entries for the instances included in application 2, namely, configuration entries for instances 1, 4, 7, and 8, to compute node 450.

[0137] Exemplarily, the configuration item forwarding relationship may further include: controller 410 sends configuration items of instances included in the first computing node to the first computing node. For example, controller 410 sends configuration items of instances 2 and 3 to computing node 420, and controller 410 sends configuration items of instances 1, 4, 7, and 8 to computing node 430.

[0138] In the above step 620, the controller 410 determines the configuration table items to be delivered according to the actual traffic between the instances. The configuration table items of each instance are determined by the controller 410 according to the configuration information of the network card corresponding to each instance stored in the controller 410.

[0139] Step 630: The controller 410 sends the configuration entry to at least two computing nodes according to the configuration entry forwarding relationship.

[0140] In some possible embodiments, the controller 410 sends the configuration table items of the instances included in the class clusters corresponding to at least two computing nodes in the computing node cluster to the at least two computing nodes respectively according to the configuration table item forwarding relationship.

[0141] Optionally, the controller 410 sends the configuration table entry to the computing node, which means that the controller 410 sends the configuration table entry to the virtual switch of the computing node, so that the computing node can communicate with the instance corresponding to the configuration table entry through the virtual switch based on the configuration table entry.

[0142] Based on steps 610-630 of the above communication method, the controller 410 determines the configuration items for the instances that need to be sent to each computing node based on the traffic interaction information between different clusters. In this way, the controller 410 only needs to send the configuration items for the instances that the computing node needs to communicate to each computing node. Compared to the full configuration item sending method, the total number of configuration items sent is reduced. There is no need to wait for the configuration items in the virtual switch of the computing node that receives the configuration items of all instances in the cloud platform to take effect before the traffic between instances is interconnected, thereby reducing the network latency of inter-instance communication in the cloud platform. At the same time, the configuration items sent by the controller 410 to the computing node include the configuration items of all instances contained in other clusters that the cluster to which the instance of the computing node belongs needs to communicate. This allows some instances of the computing node to complete the deployment of configuration items before they interact with some instances of other clusters. Compared to the on-demand configuration item sending method, the access traffic between instances does not need to be forwarded by the forwarding node, avoiding the first packet delay, thereby reducing the network latency of inter-instance communication in the cloud platform and improving the overall communication efficiency between instances.

[0143] The above text combines Figures 6-8 to provide an overall description of the communication method of the present application. Below, combined with Figure 9, the specific clustering steps and specific configuration table item issuance method of the communication method in the cloud native application scenario are explained.

[0144] As shown in Figure 9, taking the cloud-native application scenario and cluster-hosted container products as an example, cloud vendors provide highly scalable, high-performance enterprise-level Kubernetes clusters that support running containers (also called instances) and easily deploy, manage, and scale containerized applications.

[0145] The communication system for the cloud-native application scenario includes a VPC controller 910, a Kubernetes controller 920, and a compute node cluster. The compute node cluster includes one or more compute nodes (compute nodes 930, 940, 950, and 960 are shown in FIG9 ). The VPC controller 910 is connected to the Kubernetes controller 920, and the Kubernetes controller 920 is connected to the compute node cluster, including one or more compute nodes (indicated by unarrowed connecting lines in FIG9 ).

[0146] The Kubernetes controller 920 is used to release instances through the API provided by the cloud platform, create application containers within the instances, call the VPC controller 910 to create network resources, and mount the network card or auxiliary network card into the container.

[0147] Applications are implemented using containers (also called pods), as shown in Figure 9 , which are deployed in virtual machines on compute nodes. For example, as shown in Figure 9 , compute node 930 includes virtual machines 1 and 2, compute node 940 includes virtual machines 3 and 4, compute node 950 includes virtual machine 5, and compute node 960 includes virtual machine 6. Virtual machine 1 is deployed with containers 1 and 2, virtual machine 2 is deployed with container 3, virtual machine 3 is deployed with containers 4 and 5, virtual machine 4 is deployed with container 6, virtual machine 5 is deployed with containers 7 and 8, and virtual machine 6 is deployed with containers 9 and 10.

[0148] An application consists of a group of containers with the same service. In Figure 9, containers 1, 6, and 8 belong to application 1, containers 2 and 4 belong to application 2, containers 3, 5, and 7 belong to application 3, container 9 belongs to application 4, and container 10 belongs to application 5.

[0149] The following is an example of how to cluster containers.

[0150] As a first possible implementation, the Kubernetes controller 920 can add the application ID to the NIC properties when creating a network interface card (NIC) or auxiliary NIC. For example, if application 1, consisting of containers 1, 6, and 8, is considered a blue application, the blue application ID, application_id, can be added to the binding:profile property. The VPC controller 910 determines the application 1 to which the container belongs by querying the NIC properties of the NIC corresponding to the container.

[0151] As a second possible implementation, the Kubernetes controller 920 stores the mapping information between applications and network interfaces (NICs) or auxiliary NICs, for example, in a remote dictionary server (Redis) or an Etcd layer medium. The VPC controller 910 determines the application to which a container belongs by querying the mapping information for the NIC corresponding to the container.

[0152] As a third possible implementation, the Kubernetes controller 920 manages the containers on each compute node through a Kubernetes agent on each compute node. The Kubernetes agent configures the application identifier on the network interface card (NIC) or auxiliary NIC connected to the virtual switch. The VPC controller 910 determines the application to which the container belongs by querying the application identifier on the NIC connected to the virtual switch corresponding to the container.

[0153] The following describes in detail how to send configuration items.

[0154] The application to which containers 1, 6, and 8 belong is elastically expanded to generate container a. According to the communication relationship between containers shown in FIG9 , there is business traffic between application 1 to which containers 1, 6, and 8 belong and application 3 to which containers 3, 5, and 7 belong (the business traffic between containers is shown by the dotted line connected by double arrows in FIG9 ). Therefore, the VPC controller 910 needs to send the configuration table items of containers 3, 5, and 7 to computing node 950, and send the configuration table items of container 8 to computing node 930 and computing node 940.

[0155] After describing the communication method in the cloud-native application scenario in conjunction with Figure 9 above, the specific clustering steps and specific configuration table item delivery method of the communication method in the traditional application scenario are described in conjunction with Figure 10.

[0156] As shown in FIG10 , customers purchase or rent VPC, virtual machines, load balancing (LB) loads, etc. through the cloud vendor's website and deploy their own applications in the virtual machines.

[0157] The communication system in a traditional application scenario includes a VPC controller 1010 and a computing node cluster. The computing node cluster includes one or more computing nodes (compute node 1020, computing node 1030, computing node 1040, and computing node 1050 are shown in FIG10 ). The VPC controller 1010 is connected to each computing node in the computing node cluster (indicated by unarrowed connecting lines in FIG10 ).

[0158] For example, as shown in Figure 10, computing node 1020 includes virtual machine 1, virtual machine 2 and virtual machine 3, computing node 1030 includes virtual machine 4, virtual machine 5 and virtual machine 6, computing node 1040 includes virtual machine 7 and virtual machine 8, and computing node 1050 includes virtual machine 9.

[0159] The following is an example of how to cluster containers.

[0160] After purchasing or renting virtual machines, customers typically place the same or similar applications in the same security group. This means that the security access policies for the same applications are the same, or the IP addresses of the same application are placed in the same address group, and security group rules are configured between the two address groups. For example, VMs 1, 6, and 8 share the same security group configuration 1; VMs 2 and 4 share the same security group configuration 2; VMs 3, 5, and 7 share the same security group configuration 3; and VM 9 shares the same security group configuration 4.

[0161] The VPC controller 1010 performs clustering based on the security group configuration. For example, the VPC controller 1010 determines that virtual machine 1, virtual machine 6, and virtual machine 8 have the same security group configuration 1, virtual machine 2 and virtual machine 4 have the same security group configuration 2, virtual machine 3, virtual machine 5, and virtual machine 7 have the same security group configuration 3, and virtual machine 9 has a security group configuration 4. Then, based on different security group configurations, virtual machine 1, virtual machine 6, and virtual machine 8 are clustered into application 1, virtual machine 2 and virtual machine 4 are clustered into application 2, virtual machine 3, virtual machine 5, and virtual machine 7 are clustered into application 3, and virtual machine 9 is clustered into application 4.

[0162] The following describes in detail how to send configuration items.

[0163] When application 1 needs to add a new VM a, according to the communication relationship between containers shown in Figure 10 (indicated by the double-arrow dashed lines in Figure 10), application 1 interacts with application 3, application 2 interacts with application 4, and application 2 interacts with application 3. Therefore, VPC controller 1010 needs to send configuration entries for VMs 4, 6, 7, and 8 to compute node 1020, VMs 2, 3, 8, and 9 to compute node 1030, VMs 2, 3, and 6 to compute node 1040, and VM 4 to compute node 1050.

[0164] The communication method provided by the present application is described in detail above with reference to Figures 6 to 10. The communication device for executing the communication method provided by the present application is described in detail below with reference to Figure 11.

[0165] For example, Figure 11 is a schematic diagram of the structure of a communication device provided by this application. This communication device can be used to implement the functions of the corresponding communication device in the above method embodiment, and thus also has the beneficial effects of the above method embodiment. In this embodiment, the communication device can be the controller 410 shown in Figure 4, or it can be a module (such as a chip) applied to a server.

[0166] As shown in FIG. 11 , the communication device 1100 includes a clustering module 1110 , a matching module 1120 , and a transceiver module 1130 .

[0167] In some possible embodiments, the communication device 1100 may be used to implement the functions of the controller 410 in the method embodiment shown in FIG. 6 , and the modules included in the communication device 1100 are specifically used to implement the following functions.

[0168] The clustering module 1110 is configured to cluster multiple instances included in at least two computing nodes to obtain at least two clusters, each of which includes at least one instance. For example, the clustering module 1110 is configured to execute step 610 as shown in FIG6 .

[0169] Matching module 1120 is configured to determine a configuration table item forwarding relationship based on traffic interaction information between at least two clusters, where the configuration table item forwarding relationship indicates that configuration table items for other clusters that have traffic interaction with the cluster of the first computing node are distributed to a first computing node, where the first computing node is one of the at least two computing nodes. For example, matching module 1120 is configured to execute step 620 as shown in FIG6 .

[0170] The transceiver module 1130 is configured to send the configuration entry to at least two computing nodes according to the configuration entry forwarding relationship. For example, the transceiver module 1130 is configured to execute step 630 as shown in FIG6 .

[0171] As a possible implementation method, the configuration table item forwarding relationship includes: sending the configuration table item of the instance contained in the cluster corresponding to the first computing node to the first computing node, and the corresponding cluster includes a cluster that has traffic interaction with the cluster to which the instance contained in the first computing node belongs.

[0172] As a possible implementation manner, the corresponding cluster also includes the cluster to which the instance included in the first computing node belongs.

[0173] As a possible implementation manner, the communication device further includes a traffic processing module, configured to determine traffic interaction information between at least two clusters based on traffic interaction information between a plurality of instances.

[0174] Optionally, the traffic processing module is specifically used to: obtain traffic interaction information between multiple instances; determine that there is traffic interaction between the clusters to which every two instances with traffic interaction belong, and obtain traffic interaction information between at least two clusters.

[0175] As a possible implementation manner, the clustering module 1110 is specifically configured to cluster multiple instances according to network configurations of the multiple instances included in at least two computing nodes to obtain at least two clusters.

[0176] Optionally, the clustering module 1110 is specifically configured to cluster instances belonging to the same security group, subnet, elastic scaling group, or load balancing cluster among the multiple instances to obtain at least two clusters.

[0177] Optionally, the clustering module 1110 is specifically used to: cluster instances carrying the same network prefix or application identifier in multiple instances to obtain at least two clusters, where the application identifier includes an identifier in the network card used to represent application attributes and an identifier used by the container orchestration engine to divide the application to which the container belongs.

[0178] It should be understood that the communication device 1100 of the embodiment of the present invention can be implemented by a central processing unit (CPU), an ASIC, or a programmable logic device (PLD). The PLD can be a complex programmable logical device (CPLD), an FPGA, a generic array logic (GAL), or any combination thereof. When the communication device 1100 implements the communication method shown in FIG. 6 via software, the communication device 1100 and its various modules can also be software modules.

[0179] It should be understood that the controller 410 in the embodiment of the present application may correspond to the communication device 1100 in the embodiment of the application, and may correspond to the corresponding subject in executing the method according to the embodiment of the present application, and the above-mentioned and other operations and / or functions of each module in the communication device 1100 are respectively for realizing the corresponding process of the method in Figure 6. For the sake of brevity, they will not be repeated here.

[0180] The present application also provides a communication device, each communication device 1200 including a memory 1201, a processor 1202, a communication interface 1203, and a bus 1204. The memory 1201, the processor 1202, and the communication interface 1203 are communicatively connected to each other via the bus 1204. The communication device 1200 may be the controller 410 in FIG. 6 , for example.

[0181] The memory 1201 may be a read-only memory, a static storage device, a dynamic storage device, or a random access memory. The memory 1201 may store computer instructions and a data set required to execute the computer instructions. When the computer instructions stored in the memory 1201 are executed by the processor 1202, the processor 1202 and the communication interface 1203 are used to perform any step of the communication method shown in FIG6 .

[0182] The processor 1202 may be a general-purpose central processing unit, an application specific integrated circuit (ASIC), a graphics processing unit (GPU) or any combination thereof. The processor 1202 may include one or more chips. The processor 1202 may include an AI accelerator, for example, a neural processing unit (NPU). In addition, FIG12 is illustrated by taking the example that each communication device 1200 includes one processor 1202. During specific implementation, the number and type of processors 1202 in each communication device 1200 may be set according to business requirements. The same communication device 1200 may include one or more processors. When the same communication device 1200 includes multiple processors, this application does not limit the type of processor.

[0183] The communication interface 1203 uses a transceiver module such as, but not limited to, a transceiver to implement communication between the communication device 1200 and other devices or a communication network. For example, management messages, isolation requests, etc. can be received or sent through the communication interface 1203.

[0184] The bus 1204 may include a path for transmitting information between various components of the communication device 1200 (eg, the memory 1201 , the processor 1202 , and the communication interface 1203 ).

[0185] Each of the communication devices 1200 can establish a communication path through the communication network as shown in Figure 12. Any communication device 1200 can be a computer (eg, a server) in a distributed storage system, a computer in an edge data center, or a terminal communication device.

[0186] The functions of the communication apparatus 1100 may be deployed on each communication device 1200 , for example, executing any step shown in FIG. 6 , or executing the functions of each module in the communication apparatus 1100 .

[0187] The method steps in this embodiment can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and storage medium can be located in an ASIC. In addition, the ASIC can be located in a terminal device. Of course, the processor and storage medium can also exist as discrete components in a network device or a terminal device.

[0188] In the above embodiments, they can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, they can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is executed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program or instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, a hard disk, or a tape; it can also be an optical medium, such as a digital video disc (DVD); it can also be a semiconductor medium, such as a solid state drive (SSD). The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A communication method, characterized in that: include: Clustering multiple instances included in at least two computing nodes to obtain at least two clusters, each of the at least two clusters including at least one instance; Determine a configuration table item forwarding relationship according to the traffic interaction information between the at least two clusters, the configuration table item forwarding relationship being used to indicate that configuration table items of other clusters having traffic interaction with the cluster of the first computing node are sent to the first computing node, the first computing node being one of the at least two computing nodes; The configuration table entry is sent to the at least two computing nodes according to the configuration table entry forwarding relationship.

2. The method according to claim 1, characterized in that The configuration table item forwarding relationship includes: sending the configuration table items of the instances included in the cluster corresponding to the first computing node to the first computing node, and the corresponding cluster includes a cluster that has traffic interaction with the cluster to which the instances included in the first computing node belong.

3. The method according to claim 2, characterized in that The corresponding cluster also includes the cluster to which the instance included in the first computing node belongs.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: The traffic interaction information between the at least two clusters is determined according to the traffic interaction information between the multiple instances.

5. The method according to claim 4, characterized in that The determining the traffic interaction information between the at least two clusters according to the traffic interaction information between the multiple instances includes: Obtaining traffic interaction information between the multiple instances; It is determined that there is traffic interaction between the clusters to which each two instances having traffic interaction belong, and traffic interaction information between the at least two clusters is obtained.

6. The method according to any one of claims 1 to 5, characterized in that The clustering of the multiple instances included in the at least two computing nodes to obtain at least two clusters includes: The multiple instances are clustered according to network configurations of the multiple instances included in the at least two computing nodes to obtain the at least two clusters.

7. The method according to claim 6, characterized in that The clustering of the multiple instances according to the network configurations of the multiple instances included in the at least two computing nodes to obtain the at least two clusters includes: The multiple instances are clustered according to the security groups, subnets, elastic scaling groups, or load balancing clusters to which the multiple instances belong, to obtain the at least two clusters.

8. The method according to claim 6, characterized in that The clustering of the multiple instances according to the network configurations of the multiple instances included in the at least two computing nodes to obtain the at least two clusters includes: The multiple instances are clustered according to network prefixes or application identifiers carried in the multiple instances to obtain the at least two clusters, where the application identifier includes an identifier in the network card for representing application attributes and an identifier used by the container orchestration engine to divide the application to which the container belongs.

9. A communication device, characterized in that: The communication device is used to execute the operation steps of the method according to any one of claims 1 to 8.

10. A communication device, characterized in that: The communication device comprises a memory and a processor, wherein the memory is used to store a set of computer instructions; when the processor executes the set of computer instructions, the operation steps of the method described in any one of claims 1 to 8 are performed.

11. A communication system, characterized in that: The communication system includes a controller and at least two computing nodes, wherein the at least two computing nodes are deployed with multiple instances, the controller is used to execute the operation steps of the method described in any one of claims 1 to 8, and the at least two computing nodes are used to receive configuration table items sent by the controller.

12. A readable storage medium, characterized in that: The readable storage medium includes a computer program or instructions. When the computer program or instructions are executed on a computer, the computer is caused to execute the operation steps of the method described in any one of claims 1 to 8.

Citation Information

Patent Citations

  • Forwarding method, equipment and system based on application group

    CN111163060A

  • Resource scheduling system and method, computer system and storage medium

    CN111638961A

  • Application deployment method and system and server

    CN113741924A

  • Communication method and device between virtual machine instances of cross-cloud server and processor

    CN114356493A

  • Virtualization infrastructure underlay network performance measurement and monitoring

    US20190386891A1