Methods and devices for cross-technology stack interconnection of cloud networks

Abstract

This invention discloses a method and apparatus for cross-technology stack interconnection in cloud networks, applicable to the fintech field. The method includes: receiving data packets and identifying the packet type; for business data packets of type VPC to IDC, decapsulating successfully matched VPC to IDC business data packets and forwarding the decapsulated packets; for business data packets of type IDC to VPC, tunneling successfully matched IDC to VPC business data packets based on the destination address in the IDC to VPC business data packets, and forwarding the tunneled packets; when the packet type is a control packet, marking the metadata in the control packet and sending the marked metadata to the CPU. This invention can meet stable low-latency requirements and reduce the overall system complexity.

Description

Technical Field

[0001] This invention relates to the field of financial technology, and in particular to a method and apparatus for interconnection and interoperability of cloud networks across technology stacks. Background Technology

[0002] This section is intended to provide background or context for embodiments of the present invention. The description herein is not intended to imply that it is prior art simply because it is included in this section.

[0003] Currently, enterprises are deploying and migrating various business systems to cloud environments. During this deployment and migration process, several situations arise, including the coexistence of newly built public cloud environments and existing private cloud environments, the coexistence of cloud environments with different technology stacks, and the coexistence of cloud environments with the same technology stack but different versions of management and control systems. Furthermore, due to regulatory requirements or requirements for high availability and business isolation, these situations will persist for a long time. Given the independence of various cloud management systems, the interconnectivity of cloud networks across different technology stacks becomes a bottleneck during the deployment and migration process.

[0004] In the traditional model, to achieve interconnection of cloud networks for different technology stacks, it is necessary to rely on dedicated lines for each technology stack to access cloud products, connect the cloud network with the enterprise's local area network and core network, and perform corresponding configurations to ensure that the cloud networks of the two technology stacks are routable. There is no solution to this problem in the existing technology. Summary of the Invention

[0005] This invention provides a method for cross-technology stack interconnection in cloud networks to meet stable low-latency requirements and reduce overall system complexity. The method includes:

[0006] Receive data packets and identify the message type of the data packets, wherein the message type includes control messages, business data packets sent from a Virtual Private Network (VPC) to an Internet Data Center (IDC), or business data packets sent from an IDC to a VPC.

[0007] For service data packets of type VPC to IDC, based on the tunnel ID and session information in the service data packets of VPC to IDC, the first route information is queried from the preset routing table, the first route information is compared with the preset route information, the service data packets of VPC to IDC that have a successful comparison are decapsulated, and the decapsulated packets are forwarded.

[0008] For service data packets of type IDC to VPC, based on the destination address in the service data packet sent from IDC to VPC, the second route information is queried from the preset routing table, the second route information is compared with the preset route information, the service data packets sent from IDC to VPC that match successfully are tunnel-encapsulated, and the tunnel-encapsulated packets are forwarded.

[0009] When the message type is a control message, the metadata in the control message is marked, and the marked metadata is sent to the CPU.

[0010] This invention also provides a cloud network cross-technology stack interconnection device to meet stable low latency requirements and reduce overall system complexity. The device includes:

[0011] The data receiving module is used to receive data packets and identify the message type of the data packets. The message type includes control messages, business data packets sent from a Virtual Private Network (VPC) to an Internet Data Center (IDC), or business data packets sent from an IDC to a VPC.

[0012] The decapsulation module is used to decapsulate service data packets of type VPC to IDC. Based on the tunnel ID and session information in the service data packets of VPC to IDC, it queries the first route information from the preset routing table, compares the first route information with the preset route information, decapsulates the service data packets of VPC to IDC that match the information, and forwards the decapsulated packets.

[0013] The encapsulation module is used to encapsulate the service data packets of type IDC to VPC by querying the second route information from the preset routing table based on the destination address in the service data packets of IDC to VPC, comparing the second route information with the preset route information, encapsulating the service data packets of IDC to VPC that match the information, and forwarding the encapsulated packets.

[0014] The tagging module is used to tag the metadata in a control message when the message type is a control message, and then send the tagged metadata to the CPU.

[0015] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for cross-technology stack interconnection of cloud networks.

[0016] This invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the aforementioned method for cross-technology stack interconnection of cloud networks.

[0017] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the aforementioned method for cross-technology stack interconnection of cloud networks.

[0018] In this embodiment of the invention, data packets are received, and the message type of the data packets is identified. The message type includes control messages, service data packets from a Virtual Private Network (VPC) to an Internet Data Center (IDC), or service data packets from an IDC to a VPC. For service data packets from a VPC to an IDC, based on the tunnel ID and session information in the service data packets from the VPC to the IDC, first routing information is queried from a preset routing table. The first routing information is compared with the preset routing information. Service data packets from the VPC to the IDC that match successfully are decapsulated, and the decapsulated packets are forwarded. For service data packets from an IDC to a VPC, based on the destination address in the service data packets from the IDC to the VPC, second routing information is queried from a preset routing table. The second routing information is compared with the preset routing information. Service data packets from the IDC to the VPC that match successfully are tunnel-encapsulated, and the tunnel-encapsulated packets are forwarded. When the message type is a control message, the metadata in the control message is marked, and the marked metadata is sent to the CPU. In this way, the high throughput capability of the dedicated programmable switching chip allows for Tbps-level network throughput with only a small number of devices equipped with the chip. Simultaneously, the dedicated network chip can meet stable low-latency requirements under any load conditions. On the control plane, the agent components originally located on the gateway server are reused by utilizing the programmable switching chip's accompanying CPU and operating system, reducing the overall system complexity. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0020] Figure 1 This is a flowchart of a method for cross-technology stack interconnection and interoperability of cloud networks provided in an embodiment of the present invention;

[0021] Figure 2 This is an example diagram of the data plane physical network architecture provided in an embodiment of the present invention;

[0022] Figure 3 This is a schematic diagram of the cluster and network scheme provided in the embodiments of the present invention;

[0023] Figure 4 This is a schematic diagram of a cloud network cross-technology stack interconnection device provided in an embodiment of the present invention;

[0024] Figure 5This is a structural block diagram of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0026] In this document, the term "and / or" merely describes a relationship, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0027] In the description of this specification, the terms "comprising," "including," "having," and "containing" are open-ended terms, meaning that they include but are not limited to. The terms "an embodiment," "a specific embodiment," "some embodiments," and "for example," etc., refer to specific features, structures, or characteristics described in connection with that embodiment or example that are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. The order of steps involved in the various embodiments is used to illustrate the implementation of this application, and the order of steps is not limited and can be adjusted appropriately as needed.

[0028] First, the technical terms used in the embodiments of this application will be explained:

[0029] VPC: Virtual Private Cloud, an isolated network space in the cloud.

[0030] DC: Direct Connect is a cloud service that provides fast and reliable connection between a user's data center and cloud resources.

[0031] IDC: Internet Data Center, a type of data center with complete equipment (high-speed Internet access, high-performance local area network, secure and reliable data center environment), professional management, and a comprehensive application service platform.

[0032] Overlay network: Cloud logical network: refers to one or more logical networks built on a physical network in the cloud using network virtualization technology.

[0033] Underlay network: The physical network that carries the overlay logical network refers to the physical network that is actually composed of physical devices such as switches, routers, and physical servers.

[0034] NFV: Network Function Virtualization, which uses network virtualization technology to implement the functions of each network node in software.

[0035] API: Application Program Interface, the interface through which an application's functions, definitions, or protocols interact.

[0036] PoP (Point of Presence): The point of entry for accessing a company's network.

[0037] PE: Provider Edge, a backbone network edge device.

[0038] VRF: Virtual Routing Forwarding is a technology that uses multiple routing tables on a single routing and switching device to achieve service isolation.

[0039] SDN: Software Defined Network, a network management approach that supports dynamically programmable network configuration.

[0040] P4 (Programming Protocol-Independent Packet Processors) is a high-level programming language specifically designed for configuring the data plane forwarding and processing logic of switches.

[0041] In recent years, an increasing number of enterprises have chosen to build their own enterprise-grade cloud environments as their IT infrastructure for application deployment. As application services gradually migrate to the cloud, a situation inevitably arises where existing data center infrastructure, private clouds, and newly built enterprise-grade public clouds coexist. Furthermore, due to regulatory and data security needs, enterprises may continue, or even maintain, this hybrid cloud configuration for an extended period. Meeting the high throughput, low latency, and financial-grade high availability requirements of local area networks across different technology stacks presents significant challenges to existing cloud network gateway architectures based on server NFV technology.

[0042] Currently, the mainstream solution is to use the DC products on the cloud of various technology stacks as a means to connect the cloud environment's overlay network with the off-cloud underlay network. Cloud environments in different regions and with different technology stacks can access the enterprise-level core network through DC, and by configuring the corresponding routes on the core network, the interconnection of the cloud overlay network can be achieved. This approach distinguishes VPCs through cloud-based logical isolation and on-premises physical isolation.

[0043] In the data forwarding plane, the current mainstream solution involves deploying data forwarding gateway applications on physical servers using NFV technology, in conjunction with Layer 3 border switches and L2VPN technology. This enables outer tunnel encapsulation, decapsulation, and protocol conversion for cloud leased line traffic. Simultaneously, based on virtual routing protocol applications and equal-cost routing policies deployed on the servers, multiple physical servers are grouped into a gateway cluster, achieving horizontal scaling while ensuring high availability. However, current mainstream server network cards are 10G, 25G, and 100G specifications, making it difficult to simultaneously meet the throughput and packet transmission / reception volume requirements for line-speed forwarding, even with technologies like DPDK. Furthermore, the packet forwarding process involves data interaction between the network card, memory, and CPU, resulting in high and unstable packet processing and forwarding latency under high network load.

[0044] In the control plane, the netconf interfaces and SDN controller API interfaces provided by various manufacturers are not entirely consistent. When using multiple devices, it is often necessary to develop and deploy a separate component to adapt to the system interfaces of each manufacturer, which increases the development workload and the complexity of the cloud network control system.

[0045] Currently, network interconnection between multiple cloud technology stacks still relies on dedicated line access or similar cloud network products that use server gateway clusters based on NFV technology to carry data plane traffic. Internally, these products use components such as gateway clusters, border switches, and switch controllers to automatically orchestrate and distribute data plane multi-stack interconnection traffic and control plane multi-stack interconnection configurations.

[0046] From a data perspective, the traffic carrying the interconnection between multiple stacks is handled by data forwarding applications deployed in physical server clusters and Layer 3 leased access switches deployed at the physical network boundaries of each technology stack. The data forwarding applications in the physical servers, through technologies such as DPDK, achieve high network packet forwarding efficiency. Functionally, they perform network protocol conversion and logical isolation between multiple VPCs in the cloud, while their forwarding efficiency meets the line-speed level of typical 10G / 100G network cards on servers. From a control perspective, the gateway servers in the cluster automatically obtain cloud VPC routes and external IDC routes from the platform's centralized configuration management center by deploying agents. The boundary leased access switches, through controllers deployed in the cloud, generate switch configuration commands using methods such as netconf, and complete the configuration distribution.

[0047] Through the above analysis of the data plane and control plane logic, it is clear that in the data plane, the network capacity provided by the gateway cluster is determined by the number of gateway servers and the specifications of their network interface cards (NICs). In hybrid cloud application scenarios, to meet the high network bandwidth requirements within the local area network, a large number of physical servers are often needed to horizontally scale the gateway cluster. On the other hand, the data forwarding applications deployed on physical servers involve a large amount of data interaction between the CPU, memory, and NICs, and their forwarding latency increases and becomes unstable as the data forwarding volume increases. In the control plane, the agent component in the gateway server is a cloud-native component that automatically obtains updates by listening to the cloud infrastructure's public configuration library. Border switches, on the other hand, require additional controller components to distribute configurations via control protocols such as netconf. Furthermore, because the netconf commands of different switch vendors are inconsistent, the controller needs to adapt the syntax and semantics of configurations from different vendors, increasing the system complexity.

[0048] Based on this, embodiments of the present invention provide a method for cross-technology stack interconnection and interoperability of cloud networks, such as... Figure 1 As shown, it includes:

[0049] Step 101: Receive data packets and identify the message type of the data packets. The message type includes control messages, service data packets sent from a Virtual Private Network (VPC) to an Internet Data Center (IDC), or service data packets sent from an IDC to a VPC.

[0050] Step 102: For service data packets of type VPC to IDC, query the first route information from the preset routing table according to the tunnel ID and session information in the service data packets of VPC to IDC, compare the first route information with the preset route information, decapsulate the service data packets of VPC to IDC that have successfully matched, and forward the decapsulated packets.

[0051] Step 103: For service data packets of type IDC to VPC, according to the destination address in the service data packets of IDC to VPC, query the second route information from the preset routing table, compare the second route information with the preset route information, encapsulate the service data packets of IDC to VPC that match successfully, and forward the encapsulated packets.

[0052] Step 104: When the message type is a control message, mark the metadata in the control message and send the marked metadata to the CPU.

[0053] The cloud network cross-technology stack interconnection method proposed in this invention utilizes the high throughput capability of a dedicated programmable switching chip. Only a small number of devices equipped with this chip are needed to meet Tbps-level network throughput requirements. Simultaneously, the dedicated network chip can meet stable low-latency requirements under any load conditions. On the control plane, the programmable switching chip's accompanying CPU and operating system reuse the agent components originally on the gateway server, reducing the overall system complexity.

[0054] In specific implementation, the overall data plane network scheme proposed in the embodiments of this application is as follows: Figure 2 As shown. The programmable switch system (hereinafter referred to as the programmable switch), serving as the core switch at the boundary between the Overlay and Underlay networks in this region, primarily functions to decapsulate isolated tunnel packets from the cloud and pass them through to the Underlay network, while simultaneously publishing cloud VPC addresses externally using dynamic routing. In the other direction, it identifies and encapsulates non-tunnel packets destined for cloud VPCs into the corresponding tunnel. Because inner-layer packets are used for transmission between the external IDC and the enterprise core network, the VPC addresses used for multi-stack interconnection with this solution need to be planned in advance by the enterprise IT department.

[0055] The routing scheme proposed in this application embodiment is as follows: Figure 3 As shown, multiple programmable switches provide services externally in a multi-active cluster configuration. Physically, they are connected to the regional core switch via a full mesh network. For routing, for cloud VPCs, each programmable switch in the cluster advertises the same virtual address via EBGP. Cloud computing resources use this address as the outer next-hop address for accessing other technology stacks. For other technology stacks, when each programmable switch in the cluster learns that a new VPC has added routes to access other technology stacks, it automatically obtains the address range of that VPC and advertises it to the regional core switch through the same BGP AS. Traffic from other technology stacks accessing that VPC is automatically routed to the cluster.

[0056] In one embodiment, the programmable switch chip data packet processing logic proposed in this application mainly divides the packets processed by the programmable switch chip into three categories:

[0057] a) Business data packets sent from cloud VPCs across technology stacks to IDCs. To distinguish VPCs, these packets are tunnel-encapsulated. The programmable switching chip needs to look up the table based on the tunnel ID and inner session information. Only business data packets from VPCs with added routes and that match the ACL whitelist can be forwarded. During the forwarding process, the tunnel packets will be decapsulated and the inner packets will be sent.

[0058] b) Business data packets sent from IDC across technology stacks to VPCs in the cloud. These packets are not tunnel-encapsulated. They are routed from the VPC network segment published by the cluster to the programmable switch. The programmable switch chip looks up the table according to the destination address of the data packet to obtain the tunnel ID of the VPC to which it belongs. Only business packets of VPCs with added routes and that match the ACL whitelist can be forwarded. The forwarding process will tunnel-encapsulate the packets. The outer source address is the gateway cluster VIP, and the destination address is the VIP address of the host machine or other gateway cluster corresponding to the destination in the routing table.

[0059] c) Control messages generally include network protocol messages, such as Layer 2 ARP messages, ICMP messages for port address and VIP address probing, and control messages related to routing protocols such as BGP, OSPF, and BFD. These messages need to be processed by the CPU. Therefore, after receiving the message, the message metadata will be marked and finally sent to the CPU.

[0060] In one embodiment, the service data packets sent from the successfully matched VPC to the IDC are decapsulated, and the decapsulated packets are forwarded, including:

[0061] Decapsulate the business data packets sent from the VPC to the IDC that have been successfully matched, and then transparently transmit the decapsulated business data packets of type VPC to IDC.

[0062] By using dynamic routing, the VPC address in the decapsulated business data packets sent from VPC to IDC is published externally.

[0063] In one embodiment, the service data packets sent from the successfully matched IDC to the VPC are tunnel-encapsulated. Before forwarding the tunnel-encapsulated packets, the method further includes:

[0064] Unified planning of VPC addresses for multi-stack interconnection.

[0065] In one embodiment, it further includes:

[0066] Install the preset chip driver in the operating system and load the data processing program in the chip driver into the programmable switch chip;

[0067] Add routing configuration information through the interface of the programmable switching chip;

[0068] The preset routing table is dynamically updated based on the routing configuration information.

[0069] In one embodiment, it further includes:

[0070] The monitoring information is read from the interface of the programmable switch chip, and the monitoring information is the operating data of the corresponding interface of the programmable switch chip.

[0071] When the monitoring information reaches the warning standard, the monitoring information of the corresponding interface is reported.

[0072] In practical implementation, the control plane scheme proposed in this application mainly includes the following processes:

[0073] The "chip control process" has the following functions: when the program starts, it installs the chip driver in the operating system kernel and loads the data plane forwarding logic program into the programmable switch chip; it adds routing configuration and reads custom information such as monitoring through the driver API; and it starts services in the operating system for other processes to call.

[0074] The "routing agent" process obtains the cluster's routing, ACL, and other configuration information by listening to the unified configuration management platform provided by the cloud platform. It then dynamically updates the entries in the programmable switching chip by calling the chip control program's interface.

[0075] The "monitor" process obtains current port usage, latency, packet loss statistics, and other business monitoring statistics by calling the interface of the chip control program, and reports them to the unified business monitoring and alarm platform provided by the cloud platform.

[0076] The "routing protocol program" is mainly a series of processes that control the routing protocols of the Underlay network. These processes handle BFD session persistence, BGP neighbor maintenance, and route advertising. All protocol control messages are sent and received through the kernel protocol stack in conjunction with the chip driver.

[0077] The "monitoring agent" process is mainly responsible for collecting operation and maintenance monitoring information related to the operating system and hardware, and reporting it to the unified operation and maintenance monitoring and alarm platform provided by the cloud platform.

[0078] The "daemon process" mainly performs real-time monitoring of the above key processes, and restarts the processes in a timely manner when the program exits abnormally or freezes, thereby improving the high availability of the system.

[0079] In practical implementation, the high availability design of the cloud network cross-technology stack interconnection method proposed in this application embodiment is as follows:

[0080] a) Port-level high availability design: Each programmable switch is connected to the regional core switch via a full mesh network. Ports are connected directly without aggregation, and routing protocols are published via BGP. Each port forms an equal-cost route at the routing layer. When a single port or a line between ports fails, port isolation can be achieved through the BGP protocol. At the same time, the BFD protocol is used to accelerate BGP monitoring time, so that the fault recovery time can reach the millisecond level.

[0081] b) Device-level high availability design: Each gateway cluster consists of multiple programmable switches, with each switch maintaining consistent BGPAS, and equal-cost routes formed between devices at the routing layer. A unified management platform ensures rule consistency across all devices. Based on port-level fault recovery time, the overall device fault automatic recovery time reaches the millisecond level.

[0082] c) Cluster-level high availability design: Each cloud network technology stack has the capability of multiple gateway clusters, which allows different VPCs to use the capabilities of different gateway clusters and supports the migration of VPCs between different gateways. For faulty clusters, the faulty clusters can be isolated through the batch migration function of VPC instances on the cluster, and cloud services can be quickly restored; alternatively, the original leased line access can be retained, and the cross-stack interconnection method can be restored to the leased line access gateway cluster by modifying the VPC subnet routing table, thus realizing fault recovery of heterogeneous methods.

[0083] The programmable switching chip involved in the embodiments of this application does not specifically refer to a particular model of chip, nor does the designed switching device specify a particular manufacturer. Therefore, in order to be compatible with devices using different chips, or devices using the same chip but from different manufacturers, some components need to be adapted. Regarding the routing agent, monitoring monitor, and routing protocol program, these mainly use the operating system kernel protocol stack and the virtual and physical network interface cards (NICs) of the CPU; therefore, only the operating system needs to be adapted. In the chip control process, on the one hand, a standard and unified RPC interface is provided for the routing agent and monitoring monitor; on the other hand, it is necessary to adapt to the chip and the specific design definitions of different manufacturers for the same chip.

[0084] Furthermore, the data forwarding program inside the chip is generally developed, designed, and compiled using the P4 language. For different chips, P4 language compilation tools are usually provided. Therefore, this part of the program does not present any adaptation difficulties; it only requires recompiling using the same code and the corresponding compilation tools to complete the adaptation.

[0085] This invention also provides a cloud network cross-technology stack interconnection device, as described in the following embodiments. Since the principle by which this device solves the problem is similar to the method for cloud network cross-technology stack interconnection, the implementation of this device can be referred to the implementation of the method, and repeated details will not be elaborated further.

[0086] Figure 4 This is a schematic diagram of a cloud network cross-technology stack interconnection device provided in an embodiment of the present invention, such as... Figure 4 As shown, the device includes:

[0087] The data receiving module 401 is used to receive data packets and identify the message type of the data packets. The message type includes control messages, business data packets sent from a Virtual Private Network (VPC) to an Internet Data Center (IDC), or business data packets sent from an IDC to a VPC.

[0088] The decapsulation module 402 is used to decapsulate service data packets of type VPC to IDC, based on the tunnel ID and session information in the service data packets of type VPC to IDC, query the first route information from the preset routing table, compare the first route information with the preset route information, decapsulate the service data packets of VPC to IDC that have a successful comparison, and forward the decapsulated packets.

[0089] The encapsulation module 403 is used to encapsulate the service data packets of type IDC to VPC by querying the second route information from the preset routing table according to the destination address in the service data packets of IDC to VPC, comparing the second route information with the preset route information, encapsulating the service data packets of IDC to VPC that have a successful comparison, and forwarding the encapsulated packets.

[0090] The tagging module 404 is used to tag the metadata in the control message when the message type is a control message, and then send the tagged metadata to the CPU.

[0091] In one embodiment, the decapsulation module 402 is specifically used for:

[0092] Decapsulate the business data packets sent from the VPC to the IDC that have been successfully matched, and then transparently transmit the decapsulated business data packets of type VPC to IDC.

[0093] By using dynamic routing, the VPC address in the decapsulated business data packets sent from VPC to IDC is published externally.

[0094] In one embodiment, a planning module is further included, specifically used for:

[0095] Unified planning of VPC addresses for multi-stack interconnection.

[0096] In one embodiment, a configuration module is further included, specifically used for:

[0097] Install the preset chip driver in the operating system and load the data processing program in the chip driver into the programmable switch chip;

[0098] Add routing configuration information through the interface of the programmable switching chip;

[0099] The preset routing table is dynamically updated based on the routing configuration information.

[0100] In one embodiment, a monitoring module is further included, specifically for:

[0101] The monitoring information is read from the interface of the programmable switch chip, and the monitoring information is the operating data of the corresponding interface of the programmable switch chip.

[0102] When the monitoring information reaches the warning standard, the monitoring information of the corresponding interface is reported.

[0103] Based on the aforementioned inventive concept, such as Figure 5 As shown, the present invention also proposes a computer device 500, including a memory 510, a processor 520, and a computer program 530 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 530, it realizes the above-mentioned method for cross-technology stack interconnection of cloud networks.

[0104] This invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the aforementioned method for cross-technology stack interconnection of cloud networks.

[0105] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the aforementioned method for cross-technology stack interconnection of cloud networks.

[0106] In summary, in this embodiment of the invention, data packets are received, and the packet type is identified. The packet type includes control packets, service data packets from a Virtual Private Network (VPC) to an Internet Data Center (IDC), or service data packets from an IDC to a VPC. For service data packets from a VPC to an IDC, based on the tunnel ID and session information in the packet, first routing information is queried from a preset routing table. The first routing information is compared with the preset routing information. Successfully matched VPC-to-IDC service data packets are decapsulated, and the decapsulated packets are forwarded. For service data packets from an IDC to a VPC, based on the destination address in the packet, second routing information is queried from the preset routing table. The second routing information is compared with the preset routing information. Successfully matched IDC-to-VPC service data packets are tunnel-encapsulated, and the tunnel-encapsulated packets are forwarded. When the packet type is a control packet, the metadata in the control packet is marked, and the marked metadata is sent to the CPU. In this way, the high throughput capability of the dedicated programmable switching chip allows for Tbps-level network throughput with only a small number of devices equipped with the chip. Simultaneously, the dedicated network chip can meet stable low-latency requirements under any load conditions. On the control plane, the agent components originally located on the gateway server are reused by utilizing the programmable switching chip's accompanying CPU and operating system, reducing the overall system complexity.

[0107] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0108] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0109] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0110] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0111] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for cross-technology stack interconnection and interoperability of cloud networks, characterized in that, include: Receive data packets and identify the message type of the data packets, wherein the message type includes control messages, business data packets sent from a Virtual Private Network (VPC) to an Internet Data Center (IDC), or business data packets sent from an IDC to a VPC. For service data packets of type VPC to IDC, based on the tunnel ID and session information in the service data packets of VPC to IDC, the first route information is queried from the preset routing table, the first route information is compared with the preset route information, the service data packets of VPC to IDC that have a successful comparison are decapsulated, and the decapsulated packets are forwarded. For service data packets of type IDC to VPC, based on the destination address in the service data packet sent from IDC to VPC, the second route information is queried from the preset routing table, the second route information is compared with the preset route information, the service data packets sent from IDC to VPC that match successfully are tunnel-encapsulated, and the tunnel-encapsulated packets are forwarded. When the message type is a control message, the metadata in the control message is marked, and the marked metadata is sent to the CPU.

2. The method as described in claim 1, characterized in that, The business data packets sent from the successfully matched VPC to the IDC are decapsulated, and the decapsulated packets are forwarded, including: Decapsulate the business data packets sent from the VPC to the IDC that have been successfully matched, and then transparently transmit the decapsulated business data packets of type VPC to IDC. By using dynamic routing, the VPC address in the decapsulated business data packets sent from VPC to IDC is published externally.

3. The method as described in claim 1, characterized in that, Before forwarding the tunnel-encapsulated data packets from the successfully matched IDC to the VPC, the following steps are also included: Unified planning of VPC addresses for multi-stack interconnection.

4. The method as described in claim 1, characterized in that, Also includes: Install the preset chip driver in the operating system and load the data processing program in the chip driver into the programmable switch chip; Add routing configuration information through the interface of the programmable switching chip; The preset routing table is dynamically updated based on the routing configuration information.

5. The method as described in claim 4, characterized in that, Also includes: The monitoring information is read from the interface of the programmable switch chip, and the monitoring information is the operating data of the corresponding interface of the programmable switch chip. When the monitoring information reaches the warning standard, the monitoring information of the corresponding interface is reported.

6. A device for cross-technology stack interconnection and interoperability of cloud networks, characterized in that, include: The data receiving module is used to receive data packets and identify the message type of the data packets. The message type includes control messages, business data packets sent from a Virtual Private Network (VPC) to an Internet Data Center (IDC), or business data packets sent from an IDC to a VPC. The decapsulation module is used to decapsulate service data packets of type VPC to IDC. Based on the tunnel ID and session information in the service data packets of VPC to IDC, it queries the first route information from the preset routing table, compares the first route information with the preset route information, decapsulates the service data packets of VPC to IDC that match the information, and forwards the decapsulated packets. The encapsulation module is used to encapsulate the service data packets of type IDC to VPC by querying the second route information from the preset routing table based on the destination address in the service data packets of IDC to VPC, comparing the second route information with the preset route information, encapsulating the service data packets of IDC to VPC that match the information, and forwarding the encapsulated packets. The tagging module is used to tag the metadata in a control message when the message type is a control message, and then send the tagged metadata to the CPU.

7. The apparatus as claimed in claim 6, characterized in that, The decapsulation module is specifically used for: Decapsulate the business data packets sent from the VPC to the IDC that have been successfully matched, and then transparently transmit the decapsulated business data packets of type VPC to IDC. By using dynamic routing, the VPC address in the decapsulated business data packets sent from VPC to IDC is published externally.

8. The apparatus as claimed in claim 6, characterized in that, It also includes a planning module, specifically used for: Unified planning of VPC addresses for multi-stack interconnection.

9. The apparatus as claimed in claim 6, characterized in that, It also includes a configuration module, specifically used for: Install the preset chip driver in the operating system and load the data processing program in the chip driver into the programmable switch chip; Add routing configuration information through the interface of the programmable switching chip; The preset routing table is dynamically updated based on the routing configuration information.

10. The apparatus as claimed in claim 9, characterized in that, It also includes a monitoring module, specifically used for: The monitoring information is read from the interface of the programmable switch chip, and the monitoring information is the operating data of the corresponding interface of the programmable switch chip. When the monitoring information reaches the warning standard, the monitoring information of the corresponding interface is reported.

11. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 5.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 5.

13. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 5.

Images