Network interconnection method and related equipment

Abstract

The invention discloses a network interconnection method and related equipment. According to the embodiment of the invention, port states of member ports in a preset link aggregation group of a server can be traversed; when detecting that the port state of the member port is an open state, synchronously sending an address resolution protocol message to each access switch connected with each member port based on each member port in the preset link aggregation group; each access switch obtains the mac address of the server according to the address resolution protocol message, and forwards the mac address of the server to a preset core switch; the core switch determines a routing path according to member ports connected with the access switch, the access switch and the mac address of the server; and the core switch forwards the data packet based on the routing path. According to the invention, the reliability and universality of network interconnection can be improved, and the cost of network interconnection is reduced.

Description

Technical Field

[0001] This application relates to the technical field of network architectures, and specifically relates to a network interconnection method and related devices. Background Art

[0002] A switch is a computer network device used to implement data transmission and communication between network devices. With the continuous expansion of the network scale and the increasing business requirements, in large-scale network architectures (such as Internet Data Centers, abbreviated as IDCs), traditional single switches can no longer meet the port requirements of large networks.

[0003] Traditional network architectures use device and link redundancy to meet network interconnection requirements, but their link utilization rate is low and the network maintenance cost is high. To improve the reliability, flexibility, and scalability of the network, stacking technology has emerged and is used as a common access method in large Internet data center architectures.

[0004] Stacking refers to connecting multiple switches supporting stacking characteristics together through dedicated stacking cables, virtually forming a single switching device logically and participating in data forwarding as a whole. Through dedicated connection lines, the "UP" stacking port of one switch can be directly connected to the "DOWN" stacking port of another switch to expand the switch ports. After connection, the two stacked switches can be regarded as one switch logically.

[0005] However, the current switch stacking technology has the following several disadvantages.

[0006] 1. Non-standardization: Each manufacturer has its own stacking standard and is not compatible with each other. The usage scenarios are limited, and it is impossible to mix-stack devices from different manufacturers.

[0007] 2. Poor reliability: It depends on stacking connections to connect switches, and there is a hidden danger of line failures.

[0008] 3. It is necessary to consume switch service ports for stacking connections, increasing the cost of network interconnection. Summary of the Invention

[0009] Embodiments of this application provide a network interconnection method and related devices. The related devices may include a network interconnection device, an electronic device, a computer-readable storage medium, and a computer program product, which can improve the reliability and versatility of network interconnection and reduce the cost of network interconnection.

[0010] Embodiments of this application provide a network interconnection method, including:

[0011] Traverse the port states of each member port in the preset link aggregation group of the server;

[0012] When it is detected that the port state of a member port is the open state, based on each of the member ports in the preset link aggregation group, send Address Resolution Protocol packets synchronously to each access switch connected to each of the member ports;

[0013] Each of the access switches obtains the MAC address of the server according to the Address Resolution Protocol packets, and forwards the MAC address of the server to a preset core switch;

[0014] The core switch determines a routing path according to the member port to which the access switch is connected, the access switch, and the MAC address of the server;

[0015] The core switch forwards data packets based on the routing path.

[0016] Further, before traversing the port states of each member port in the preset link aggregation group of the server, it further includes:

[0017] Configure the network card working mode of the server to the IEEE802.3ad dynamic link aggregation mode, create a link aggregation group, and configure the link aggregation group to the LACP mode;

[0018] Determine the member ports to be aggregated in the server, and add the member ports to be aggregated to the link aggregation group;

[0019] Create a link aggregation group on the access switch, and configure the link aggregation group to the LACP mode;

[0020] Add the interface of the access switch to the link aggregation group, and the member port is connected to the interface of the access switch;

[0021] Perform LACP function verification on the link aggregation group. When the LACP function verification passes, the member ports in the aggregation link group are connected to the access switch.

[0022] Further, before traversing the port states of each member port in the preset link aggregation group of the server, it further includes:

[0023] When it is detected that the port state of a member port is the open state, the server sends a first LACP negotiation packet to the access switch based on the member port. The first LACP negotiation packet includes the identity identifier of the member port and negotiation parameters for negotiating link aggregation;

[0024] The access switch receives the first LACP negotiation message and negotiates with the member port based on the identity identifier of the member port and the negotiation parameters;

[0025] When the negotiation is successful, the access switch generates a second LACP negotiation message and returns the second LACP negotiation message to the member port;

[0026] When receiving the second LACP negotiation message, determine the member link for implementing communication between the member port and the access switch interface.

[0027] Further, the step of synchronously sending Address Resolution Protocol (ARP) messages to each access switch connected to each member port based on each member port in the preset link aggregation group includes:

[0028] Add a synchronous sending flag to each member port in the preset link aggregation group;

[0029] When the synchronous sending flag is detected, synchronously send ARP messages to each access switch based on the member link.

[0030] Further, the step of each access switch obtaining the MAC address of the server according to the ARP message includes:

[0031] If the ARP message is an ARP message based on IPv4, the access switch parses the ARP message to obtain the IP address of the server;

[0032] Query the MAC address of the server corresponding to the IP address based on the routing table on the access switch;

[0033] If the ARP message is a Neighbor Discovery Protocol (NDP) message based on IPv6, extract the message header of the NDP message;

[0034] Parse the message header to obtain the MAC address of the server.

[0035] Further, the core switch performs data packet forwarding based on the routing path, including:

[0036] The core switch obtains the data packets uploaded by each server based on the routing path and distributes the data packets to each server based on the routing path.

[0037] Further, it further includes:

[0038] Determine the transmission time nodes corresponding to each of the member ports based on a preset time period, the preset link aggregation group, and the transmission timestamps corresponding to each member port;

[0039] When the member port reaches the transmission time node, add a synchronous transmission mark to the member port that reaches the time node;

[0040] When the synchronous transmission mark is detected, synchronously send Address Resolution Protocol (ARP) packets to each of the access switches based on the member links.

[0041] Furthermore, it further includes:

[0042] When it is detected that the member port triggers the sending of an Address Resolution Protocol packet, a preset hook function triggers the binding of the broadcast sending mode;

[0043] Based on the bound broadcast sending mode, synchronously send the Address Resolution Protocol packet from all member ports in the preset aggregation link group.

[0044] Furthermore, before the preset hook function triggers the binding of the broadcast sending mode when it is detected that the member port sends an Address Resolution Protocol packet, it further includes:

[0045] Configure the network card working mode of the server to the IEEE802.3ad dynamic link aggregation mode, and create a link aggregation group;

[0046] Determine the member ports to be aggregated in the server, and add the member ports to be aggregated to the link aggregation group;

[0047] Create a link aggregation group on the access switch, and add the interfaces of the access switch to the link aggregation group;

[0048] Based on the Link Aggregation Control Protocol (LACP), determine each member link for realizing communication between each member port and each access switch interface;

[0049] Add hook points to each of the member links corresponding to each member port.

[0050] Furthermore, the synchronously sending the Address Resolution Protocol packet from all member ports in the preset aggregation link group includes:

[0051] If the Address Resolution Protocol packet is an Address Resolution Protocol packet based on IPv4, synchronously send the Address Resolution Protocol packet from all member ports in the preset aggregation link group;

[0052] If the Address Resolution Protocol packet is a Neighbor Discovery Protocol packet based on IPv6, extract the packet header of the Neighbor Discovery Protocol packet;

[0053] Parse the neighbor discovery protocol packet based on the packet header. If the parsed packet is a neighbor solicitation packet or a neighbor advertisement packet, synchronously send the neighbor discovery protocol packet from all member ports in the preset aggregated link group.

[0054] Further, it further includes:

[0055] Parse the neighbor discovery protocol packet based on the packet header;

[0056] If the parsed packet is neither a neighbor solicitation packet nor a neighbor advertisement packet, send the neighbor discovery protocol packet from the member port that triggered the address translation protocol packet to the access switch.

[0057] Correspondingly, an embodiment of the present application provides a network interconnection device, including:

[0058] A traversal unit, configured to traverse the port status of each member port in the preset link aggregation group of the server;

[0059] An access unit, configured to, when it is detected that there is a member port with an open port status, synchronously send an address resolution protocol packet to each access switch connected to each member port based on each member port in the preset link aggregation group;

[0060] An acquisition unit, configured to each access switch obtain the MAC address of the server according to the address resolution protocol packet, and forward the MAC address of the server to a preset core switch;

[0061] A routing unit, configured to the core switch determine a routing path according to the member port connected to the access switch, the access switch, and the MAC address of the server;

[0062] A forwarding unit, configured to the core switch perform data packet forwarding based on the routing path.

[0063] Optionally, in some embodiments of the present application, the access unit includes an adding subunit and a sending subunit, as follows:

[0064] An adding subunit, configured to add a synchronous sending mark to each member port in the preset link aggregation group;

[0065] A sending subunit, configured to, when the synchronous sending mark is detected, synchronously send an address resolution protocol packet to each access switch based on the member links respectively.

[0066] Optionally, in some embodiments of the present application, the network interconnection device further includes a second detection unit, an adding unit, and a third synchronization unit, as follows:

[0067] The second detection unit is configured to determine the transmission time nodes corresponding to the respective member ports based on a preset time period, the preset link aggregation group, and the transmission timestamps corresponding to the respective member ports;

[0068] The adding unit is configured to add a synchronous transmission mark to the member ports that reach the transmission time node when the member ports reach the transmission time node;

[0069] The third synchronization unit is configured to, when detecting the synchronous transmission mark, synchronously send Address Resolution Protocol (ARP) packets to each of the access switches based on the member links.

[0070] Optionally, in some embodiments of the present application, the network interconnection device may further include a third detection unit and a third synchronization unit, as follows:

[0071] The third detection unit is configured to, when detecting that a member port triggers the sending of an Address Resolution Protocol packet, if a preset synchronization trigger condition is met, a preset hook function triggers the binding of a broadcast sending mode;

[0072] The third synchronization unit is configured to synchronously send the Address Resolution Protocol packet from all member ports in a preset aggregation link group based on the bound broadcast sending mode.

[0073] Optionally, in some embodiments of the present application, the third synchronization unit further includes an IPv4 protocol parsing subunit, an IPv6 protocol parsing subunit, a first packet header parsing subunit, and a second packet header parsing subunit, as follows:

[0074] The IPv4 protocol parsing subunit is configured to, if the Address Resolution Protocol packet is an Address Resolution Protocol packet based on IPv4, synchronously send the Address Resolution Protocol packet from all member ports in a preset aggregation link group;

[0075] The IPv6 protocol parsing subunit is configured to, if the Address Resolution Protocol packet is a Neighbor Discovery Protocol packet based on IPv6, extract the packet header of the Neighbor Discovery Protocol packet;

[0076] The first packet header parsing subunit is configured to parse the Neighbor Discovery Protocol packet based on the packet header, and if the parsed packet is a Neighbor Solicitation packet or a Neighbor Advertisement packet, synchronously send the Neighbor Discovery Protocol packet from all member ports in a preset aggregation link group;

[0077] The second packet header parsing subunit is configured to send the neighbor discovery protocol packet from the member port that triggered the address conversion protocol packet to the access switch if the parsed packet is neither a neighbor solicitation request packet nor a neighbor advertisement packet.

[0078] An electronic device provided by an embodiment of the present application includes a processor and a memory. The memory stores multiple instructions, and the processor loads the instructions to execute the steps in the network interconnection method provided by the embodiment of the present application.

[0079] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the network interconnection method provided by the embodiment of the present application are implemented.

[0080] In addition, an embodiment of the present application further provides a computer program product, including a computer program or instruction. When the computer program or instruction is executed by a processor, the steps in the network interconnection method provided by the embodiment of the present application are implemented.

[0081] An embodiment of the present application provides a network interconnection method and related devices, which can traverse the port states of each member port in a preset link aggregation group of a server; when it is detected that there is a member port with an open port state, based on each member port in the preset link aggregation group, send an address resolution protocol packet to each access switch connected to each member port synchronously; each access switch obtains the MAC address of the server according to the address resolution protocol packet and forwards the MAC address of the server to a preset core switch; the core switch determines a routing path according to the member port connected to the access switch, the access switch, and the MAC address of the server; the core switch performs packet forwarding based on the routing path. Through the scheme of synchronous sending through multiple member ports, the present application converges multiple access switches connected to the server to the core switch, so that multiple access switches can convert the address resolution protocol into a host route and upload it to the core switch. There is no need to set up physical connections between two access switches, which improves the stability of the cloud network compared with the stacking technology, does not require additional occupation of the service ports of the switch, and saves the network interconnection cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative efforts.

[0083] Figure 1It is a schematic diagram of the scenario of the network interconnection method provided by the embodiments of the present application;

[0084] Figure 2a It is a flowchart of the first synchronous transmission trigger scenario provided by the embodiments of the present application;

[0085] Figure 2b It is another schematic diagram of the process of the first synchronous transmission trigger scenario provided by the embodiments of the present application;

[0086] Figure 2c It is a schematic diagram of the process of the second synchronous transmission trigger scenario provided by the embodiments of the present application;

[0087] Figure 2d It is a schematic diagram of the third synchronous transmission trigger scenario provided by the embodiments of the present application;

[0088] Figure 3 It is a timing schematic diagram of the first synchronous transmission trigger scenario and the second synchronous transmission trigger scenario provided by the embodiments of the present application;

[0089] Figure 4 It is a schematic diagram of the structure of the network interconnection device provided by the embodiments of the present application;

[0090] Figure 5 It is a schematic diagram of the structure of the electronic device provided by the embodiments of the present application. Detailed implementation manners

[0091] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present application.

[0092] The cloud technology involved in the embodiments of the present application refers to a hosting technology that unifies a series of resources such as hardware, software, and networks within a wide area network or a local area network to achieve data calculation, storage, processing, and sharing.

[0093] Cloud technology is the general term for network technology, information technology, integration technology, management platform technology, application technology, etc. based on the cloud computing business model. It can form a resource pool, be used as needed, and is flexible and convenient. Cloud computing technology will become an important support. The back-end services of the technical network system require a large amount of computing and storage resources, such as video websites, picture websites, and more portal websites. With the high development and application of the Internet industry, in the future, each item may have its own identification mark and needs to be transmitted to the back-end system for logical processing. Data at different levels will be processed separately, and various industry data requires a powerful system back-end support, which can only be achieved through cloud computing.

[0094] Embodiments of this application provide a network interconnection method and related devices. The related devices may include a network interconnection device, an electronic device, a computer-readable storage medium, and a computer program product. The network interconnection device may be specifically integrated in the electronic device, and the electronic device may be a device such as a terminal or a server.

[0095] It can be understood that the network interconnection method of this embodiment may be jointly executed by a server, an access switch, and a core switch in a network architecture.

[0096] An access switch is generally used to directly connect to a computer. Usually, the part of the network that directly faces users for connection or access to the network is called the access layer. The purpose of the access layer is to allow end users to connect to the network. Therefore, the access switch has the characteristics of low cost and high port density.

[0097] Usually, the backbone part of the network is called the core layer. The main purpose of the core layer is to provide an optimized and reliable backbone transmission structure through high-speed communication forwarding. Therefore, the core switch should have higher reliability, performance, and throughput.

[0098] In the network architecture of the prior art, there is also an aggregation layer. The aggregation layer switch layer is the convergence point of multiple access switches and must be able to handle all traffic from the access layer devices and provide an uplink to the core layer. Therefore, compared with the access layer switch, the aggregation layer switch requires higher performance, fewer interfaces, and higher switching rates. And in this application, through a synchronous transmission scheme, multiple access switches are aggregated to the core switch. There is no need to set up a physical connection between two access switches, and the aggregation function can be achieved without setting up a separate aggregation layer.

[0099] Such as Figure 1As shown in the figure, take the example where the core switch, access switch, and server jointly execute the network interconnection method. The network interconnection system provided by the embodiments of the present application includes a server 10, an access switch 11, a core switch 12, etc.; the access switch 11 is connected to the core switch 12 through a network, for example, through a wired or wireless network connection, etc. Among them, the network interconnection device can be integrated in the server 10.

[0100] Among them, the server 10 can be used to: detect the port status of each member port in the preset link aggregation group of the server; when it is detected that there is a member port with an open port status, traverse the other member ports in the preset link aggregation group and update the port status of the other member ports to the open state; based on each of the ports in the open state, synchronously send Address Resolution Protocol (ARP) packets to each access switch connected to each member port. Among them, the server 11 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. For the network interconnection method or device disclosed in the present application, multiple servers can form a blockchain, and the server is a node on the blockchain.

[0101] Among them, the access switch 11 can be used to: receive the ARP packet, obtain the MAC address of the server according to the ARP packet, and forward the MAC address of the server to the preset core switch.

[0102] Among them, the core switch 12 can be used to: determine the routing path according to the member port connected by the access switch, the access switch, and the MAC address of the server; the core switch forwards data packets based on the routing path.

[0103] Through the solution of synchronously sending through multiple member ports, the present application converges multiple access switches connected to the server to the core switch, so that multiple access switches can convert the ARP into a host route and upload it to the core switch. There is no need to set up physical connections between two access switches, which improves the stability of the cloud network compared with the stacking technology, does not require additional occupation of the service ports of the switch, and saves the network interconnection cost.

[0104] The embodiments of the present invention use the ARP and NDP protocols to obtain the MAC address of the server.

[0105] Among them, ARP: Address Resolution Protocol, an IPv4 address resolution protocol. It is a protocol for obtaining the MAC address based on the IP address. It is divided into ARP requests and responses. The server broadcasts an ARP request containing the target IP address to the network. After receiving the ARP request, the target server replies with an ARP response containing its own MAC address. In this way, the requesting side establishes the correspondence between the target IP address and the MAC address after receiving the response message.

[0106] Among them, Gratuitous ARP: a special ARP request message. The general ARP request is to obtain the MAC address corresponding to a certain IP. The Gratuitous ARP request is to request the MAC address corresponding to its own IP address, and is used to announce its own MAC address to other devices in the network. In this application, the ARP protocol message sent by the server is a Gratuitous ARP message.

[0107] Among them, NDP: Neighbor Discovery Protocol, an IPv6 neighbor discovery protocol based on ICMPv6. IPv6 does not have the ARP protocol, and the NDP protocol is used instead. Through NS (Neighbor Solicitation) neighbor requests and NA (Neighbor Advertisement) neighbor advertisements, the mapping between IPv6 addresses and MAC addresses is achieved.

[0108] Among them, synchronous transmission means that the aggregated link group contains two or more member ports. When sending an ARP / NDP message from one of the member ports to the access switch, it is also sent simultaneously from other member ports in the aggregated link group.

[0109] To achieve synchronous transmission of multiple member ports for ARP / NDP, the present invention provides 4 configuration interfaces for users. The following is a usage example:

[0110] Switch for dual transmission of ipv4 ARP:

[0111] echo 1> / sys / class / net / bond1 / bonding / broadcast_arp enables dual transmission of IPv4 ARP

[0112] Switch for dual transmission of ipv6 NDP:

[0113] echo 1> / sys / class / net / bond1 / bonding / broadcast_nd enables dual transmission of IPv6 NDP

[0114] Enable periodic sending of arp / ndp messages:

[0115] echo 1> / sys / class / net / bond1 / bonding / periodic_na

[0116] Enable sending period: 90s

[0117] echo 90> / sys / class / net / bond1 / bonding / periodic_na_interval

[0118] Among them, the echo command is the most basic command in Linux. The path where the instruction to be triggered is located is followed after the echo command.

[0119] Among them, the / sys / class directory contains all device types registered in the kernel. This is a device model classified by device functions. Each device type represents a device with a single function. Under each device type subdirectory are symbolic links to various specific devices of this device type. These links point to the specific devices under / sys / devices / . There is no one-to-one correspondence between device types and devices. A physical device may have multiple device types; a device type only represents a device with a single function. For example, all network devices in the system will appear under / sys / class / net, regardless of the bus through which they are connected to the system.

[0120] The implementation principle of these configuration interfaces is: Enable the switch in the Linux kernel struct

[0121] bond_params data structure through the echo1 command, and disable the switch in the Linux kernel struct

[0122] bond_params data structure through the echo0 command. Specifically, it includes:

[0123] broadcast_arp: IPv4 ARP transmission switch.

[0124] broadcast_nd: IPv6 NDP transmission switch.

[0125] last_na: Timestamp of the last gratuitous ARP and NDP sent.

[0126] periodic_na: Switch for whether to periodically send gratuitous ARP and NDP.

[0127] Add the time interval for sending duplicate packets through the echo command. For example, echo 90 means the time interval is 90s.

[0128] periodic_na_interval: The time interval for the dual - sender free ARP and NDP.

[0129] The following will be described in detail respectively. It should be noted that the description order of the following embodiments does not limit the preferred order of the embodiments.

[0130] The embodiments of this application will be described from the perspective of a network interconnection device, which can be specifically integrated in an electronic device. The electronic device includes devices such as servers, access switches, and core switches.

[0131] The scheme of multiple member ports synchronously sending Address Resolution Protocol packets has multiple trigger scenarios. In the first scenario, when there are member ports in the preset link aggregation group in the open state, the synchronous sending scheme is triggered. As Figure 2a , Figure 2b and Figure 3 shown, the specific process of this network interconnection method can be as follows:

[0132] 201. Traverse the port states of each member port in the preset link aggregation group of the server.

[0133] Linux has built - in driver programs for network card bonding, which can bundle multiple physical network cards into multiple different logical network cards respectively.

[0134] Among them, IEEE 802.3ad dynamic link aggregation is a network card bonding method that binds multiple physical network cards to a logical network card, that is, by creating a link aggregation group and adding the Ethernet ports of two physical network cards on the server side to the 802.3ad bonding of a logical network card (that is, the link aggregation group of this application).

[0135] A link aggregation group (Link Aggregation Group) refers to bundling several Ethernet links together to form a logical link. Each aggregation group corresponds to a link aggregation interface, and each physical interface that makes up the link aggregation interface is called a member interface, and the link corresponding to the member interface is called a member link.

[0136] In some embodiments, before detecting the port states of each port in the preset link aggregation group of the server, it further includes:

[0137] Configure the network card working mode of the server to the IEEE802.3ad dynamic link aggregation mode, create a link aggregation group, and configure the link aggregation group to the LACP mode;

[0138] Determine the member ports to be aggregated in the server, and add the member ports to be aggregated to the link aggregation group;

[0139] Create a link aggregation group on the access switch and configure the link aggregation group to the LACP mode;

[0140] Add the interfaces of the access switch to the link aggregation group, and the member ports are connected to the interfaces of the access switch;

[0141] Verify the LACP function for the link aggregation group. When the LACP function verification is passed, the member ports within the aggregated link group are connected to the access switch.

[0142] The advantage of using IEEE 802.3ad "link aggregation" is that it can automatically create link aggregation in the server. In IEEE 802.3ad, enabling the "Link Aggregation Control Protocol" (LACP) automatically notifies the server which ports should be aggregated. After the IEEE 802.3ad aggregation configuration, the member ports of the server interact by sending LACPDU packets, and the server and the access switch reach an agreement on which member ports can send and receive packets, and determine the member links responsible for the service traffic from the link aggregation group.

[0143] Among them, the link aggregation technology is also known as the trunking technology or the bonding technology. LACP (Link Aggregation Control Protocol) is a link aggregation control protocol. One end of the link aggregation will inform the other end of its link aggregation information (port priority, system ID, key, etc.) through LACP protocol packets. The aggregated access switch and the server exchange aggregation information through protocol interaction, and automatically aggregate the matching links together to send and receive data according to the parameters and status of both parties. After the aggregation is formed, the access switch and the server maintain the status of the aggregated link, and when the configurations of both parties change, the aggregated link is automatically adjusted or disbanded.

[0144] In some embodiments, the access switch and the server interact through LACPDU packets and determine the member links responsible for the service traffic, which specifically includes the following steps:

[0145] When it is detected that the port status of a member port is in the open state, the server sends a first LACP negotiation packet to the access switch based on the member port. The first LACP negotiation packet includes the identity identifier of the member port and the negotiation parameters for negotiating link aggregation;

[0146] The access switch receives the first LACP negotiation packet and negotiates with the member port based on the identity identifier and the negotiation parameters of the member port;

[0147] When the negotiation is successful, the access switch generates a second LACP negotiation message and returns the second LACP negotiation message to the member port;

[0148] When receiving the second LACP negotiation message, determine the member link for implementing communication between the member port and the interface of the access switch.

[0149] After adding member ports to a link aggregation group in LACP mode, these member ports will advertise their system priority, MAC address, interface priority, interface number, operation Key, etc. to the access switch by sending LACPDUs. After receiving this information, the access switch compares this information with the information saved by its own interface to select the member ports that can be aggregated, and both sides reach an agreement on which interfaces can send and receive packets, and determine the member links for carrying traffic.

[0150] 202. When it is detected that the port state of a member port is in the open state, based on each of the member ports in the preset link aggregation group, synchronously send Address Resolution Protocol (ARP) packets to each access switch connected to each member port.

[0151] Reference Figure 2b , in this application, the up state of the member port is referred to as the open state, and the down state is referred to as the closed state.

[0152] After creating a link aggregation group using IEEE 802.3ad "Link Aggregation", the access switch and the server interact through LACPDU packets and determine the member links for carrying traffic. Different member ports in the server are connected to the interfaces of different access switches through different member links. When it is detected that there is a member port with its port state in the up state, ARP packets are synchronously sent to each access switch through the member links corresponding to all the member ports in the preset link aggregation group.

[0153] Through the solution of synchronously sending by multiple member ports in this application, multiple access switches connected to the server are aggregated to the core switch, so that multiple access switches can convert the Address Resolution Protocol into a host route and upload it to the core switch. There is no need to set up physical connections between two access switches, which improves the stability of the cloud network compared with the stacking technology, does not require additional occupation of the service ports of the switch, and saves the network interconnection cost.

[0154] In some embodiments, the synchronously sending Address Resolution Protocol packets to each access switch connected to each member port based on each of the member ports in the preset link aggregation group includes:

[0155] Add a synchronization transmission flag to each of the member ports in the open state;

[0156] When the synchronization transmission flag is detected, send Address Resolution Protocol packets to each of the access switches synchronously based on the member links.

[0157] The Linux kernel Bonding state machine detects the port state. In the present invention, the ARP / NDP logic of both parties is embedded in the state machine. Once the port is detected as up, the ARP / NDP flag of both parties is set. After setting the ARP / NDP flag of both parties, it will trigger the Linux kernel to send ARP / NDP packets.

[0158] 203. Each of the access switches obtains the MAC address of the server according to the Address Resolution Protocol packet, and forwards the MAC address of the server to a preset core switch.

[0159] In some embodiments, each of the access switches obtains the MAC address of the server according to the Address Resolution Protocol packet, and forwards the MAC address of the server to a preset core switch, which may specifically include the following steps:

[0160] If the Address Resolution Protocol packet is an Address Resolution Protocol packet based on IPv4, the access switch parses the Address Resolution Protocol packet to obtain the IP address of the server;

[0161] Based on the routing table on the access switch, query the MAC address of the server corresponding to the IP address;

[0162] If the Address Resolution Protocol packet is a Neighbor Discovery Protocol packet based on IPv6, extract the packet header of the Neighbor Discovery Protocol packet;

[0163] Parse the packet header to obtain the MAC address of the server.

[0164] ARP (Address Resolution Protocol) is the address conversion protocol, which obtains the MAC address according to the IP address. In this application, the Address Resolution Protocol packet based on IPv4 sent by the server is a gratuitous ARP, which is used to request the MAC address corresponding to its own IP address and announce the server's own MAC address to the access switches in the network.

[0165] Different from ARP in IPv4, in order to complete the mapping between the MAC address and the IPv6 address, IPv6 uses the Neighbor Discovery Protocol, called NDP. In the embodiments of the present application, the neighbor discovery protocol packet based on IPv6 refers to the NDP neighbor discovery protocol, which is implemented based on ICMPv6. IPv6 does not have an ARP protocol. Instead, it has the NDP protocol. Through NS (Neighbor Solicitation) neighbor requests and NA (Neighbor Advertisement) neighbor advertisements, the mapping between the IPv6 address and the MAC address is achieved. The NDP neighbor discovery protocol is responsible for discovering other nodes and corresponding addresses on the link, and determining available routes and maintaining information reachability about available paths and other active nodes. NDP uses special ICMPv6 data packets to perform various functions. IPv6 uses neighbor request (NS) and neighbor advertisement (NA) messages to do what ARP requests and ARP replies do. There is no broadcast in IPv6. IPv6 uses multicast addresses to request and publish information. The multicast addresses used by IPv6 are mapped to Ethernet for propagating NDP data packets at the link layer.

[0166] 204. The core switch determines a routing path according to the member ports connected by the access switch, the access switch, and the MAC address of the server.

[0167] Wherein, the routing path refers to the path for the core switch to send data packets to the server. In the present application, the data packets can be sent from the core switch through the access switch, and then through the member link connected by the access switch and the member port to the member port of the server.

[0168] 205. The core switch forwards data packets based on the routing path.

[0169] In some embodiments, the core switch forwards data packets based on the routing path, including the following steps:

[0170] The core switch obtains the data packets uploaded by each server based on the routing path, and distributes the data packets to each server based on the routing path.

[0171] As described above, the embodiments of the present application provide a network interconnection method and related devices, which traverse the port states of each member port in a preset link aggregation group of a server; when it is detected that there is a member port with an open port state, based on each of the member ports in the preset link aggregation group, an Address Resolution Protocol (ARP) packet is synchronously sent to each access switch connected to each member port; each access switch obtains the MAC address of the server according to the ARP packet and forwards the MAC address of the server to a preset core switch; the core switch determines a routing path according to the member port to which the access switch is connected, the access switch, and the MAC address of the server; and the core switch performs data packet forwarding based on the routing path. Through the scheme of synchronously sending by multiple member ports, the present application converges multiple access switches connected to the server to the core switch, so that multiple access switches can convert the ARP into a host route and upload it to the core switch. There is no need to set up a physical connection between two access switches, which improves the stability of the cloud network compared with the stacking technology, does not require additional occupation of the service ports of the switch, and saves the network interconnection cost.

[0172] In the second scenario, when the sending time node of the periodic sending is reached, the synchronous sending scheme is triggered. The purpose of the periodic sending is to refresh the ARP / NDP information of the access switch to prevent it from being aged. For example, if the user sets the timeout period to 90 seconds, then when it exceeds 90 seconds, the present invention will set the dual-sending ARP / NDP flag. As Figure 2c and Figure 3 shown, the specific process of this network interconnection method can be as follows:

[0173] 301. Determine the sending time node corresponding to each member port based on a preset time period, the preset link aggregation group, and the sending timestamps corresponding to each member port.

[0174] 302. When the member port reaches the sending time node, add a synchronous sending flag to the member port that reaches the time node.

[0175] 303. When the synchronous sending flag is detected, synchronously send an Address Resolution Protocol packet to each access switch based on the member link and update the sending timestamp.

[0176] As described above, in the solution of the present application where multiple member ports send synchronously, multiple access switches connected to the server are aggregated to the core switch, so that multiple access switches can convert the Address Resolution Protocol into a host route and upload it to the core switch. There is no need to set physical connections between two access switches, which improves the stability of the cloud network compared with the stacking technology, does not require additional occupation of the service ports of the switches, and saves the network interconnection cost.

[0177] In the third scenario, during normal operation, when sending ARP / NDP packets, if the server sends an ARP / NDP request to the network or receives a request sent by other network devices, and the server makes a reply. Synchronous sending is required in both cases. The present invention will set a dual-send ARP / NDP flag. As Figure 2d shown, the specific process of this network interconnection method can be as follows:

[0178] 401. When it is detected that the member port triggers the sending of an Address Resolution Protocol packet, if the preset synchronization trigger condition is met, the preset hook function triggers the binding of the broadcast sending mode.

[0179] Among them, the preset synchronization trigger condition includes that the server sends an ARP / NDP request to the network or receives a request sent by other network devices.

[0180] In some embodiments, before the preset hook function triggers the binding of the broadcast sending mode when it is detected that the member port sends an Address Resolution Protocol packet, the following steps are further included:

[0181] Configure the network card working mode of the server to the IEEE802.3ad dynamic link aggregation mode, and create a link aggregation group;

[0182] Determine the member ports to be aggregated in the server, and add the member ports to be aggregated to the link aggregation group;

[0183] Create a link aggregation group on the access switch, and add the interfaces of the access switch to the link aggregation group;

[0184] Based on the LACP protocol, determine the member links for realizing communication between each member port and each access switch interface;

[0185] Add hook points to the member links corresponding to each member port.

[0186] Among them, the hook function is also called a hook procedure. Before the system calls this function, the hook program captures this message first, and the hook function gains control first. At this time, the hook function can not only process (change) the execution behavior of this function, but also forcibly end the transmission of the message. Simply put, it is to pull out the system program and make it our own execution code segment. In this application, the hook function can forcibly end the sending of Address Resolution Protocol (ARP) packets on the member port and trigger the bound broadcast sending mode.

[0187] The present invention adds a hook point to the 802.3ad member link. When it senses that an ARP / NDP packet is sent, it enters the bound broadcast sending mode and sends the packet from all member ports under the aggregated link group.

[0188] 402. Based on the bound broadcast sending mode, synchronously send the Address Resolution Protocol packet from all member ports in a preset aggregated link group.

[0189] In some embodiments, the synchronously sending the Address Resolution Protocol packet from all member ports in a preset aggregated link group includes the following steps:

[0190] If the Address Resolution Protocol packet is an Address Resolution Protocol packet based on IPv4, then synchronously send the Address Resolution Protocol packet from all member ports in a preset aggregated link group;

[0191] If the Address Resolution Protocol packet is a Neighbor Discovery Protocol packet based on IPv6, then extract the packet header of the Neighbor Discovery Protocol packet;

[0192] Based on the packet header, parse the Neighbor Discovery Protocol packet. If the parsed packet is a Neighbor Solicitation packet or a Neighbor Advertisement packet, then synchronously send the Neighbor Discovery Protocol packet from all member ports in a preset aggregated link group;

[0193] If the parsed packet is neither a Neighbor Solicitation packet nor a Neighbor Advertisement packet, then send the Neighbor Discovery Protocol packet from the member port that triggered the Address Resolution Protocol packet to the access switch.

[0194] Since the IPv6 NDP protocol is implemented based on the ICMPv6 protocol, for IPv6, it is necessary to first parse the ICMP packet header and then obtain the NDP packet type.

[0195] As can be seen from the above, in the solution of the present application where multiple member ports send synchronously, multiple access switches connected to the server are aggregated to the core switch, so that multiple access switches can convert the Address Resolution Protocol into a host route and upload it to the core switch. There is no need to set up physical connections between two access switches, which improves the stability of the cloud network compared with the stacking technology, does not require additional occupation of the service ports of the switches, and saves the network interconnection cost.

[0196] To better implement the above method, an embodiment of the present application further provides a network interconnection device, as Figure 4 shown. The network interconnection device may include a traversing unit 501, an access unit 502, an obtaining unit 503, a routing unit 504, and a forwarding unit 505, as follows:

[0197] The traversing unit 501 is configured to traverse the port states of the member ports in a preset link aggregation group of the server;

[0198] The access unit 502 is configured to, when detecting that there is a member port with an open port state, synchronously send Address Resolution Protocol packets to each access switch connected to each of the member ports based on the member ports in the preset link aggregation group;

[0199] The obtaining unit 503 is configured to each access switch obtain the mac address of the server according to the Address Resolution Protocol packet and forward the mac address of the server to a preset core switch;

[0200] The routing unit 504 is configured to the core switch determine a routing path according to the member ports connected by the access switch, the access switch, and the mac address of the server;

[0201] The forwarding unit 505 is configured to the core switch perform data packet forwarding based on the routing path.

[0202] Optionally, in some embodiments of the present application, the access unit 502 includes an adding subunit and a sending subunit, as follows:

[0203] The adding subunit is configured to add a synchronous sending mark to each of the member ports in the preset link aggregation group;

[0204] The sending subunit is configured to, when detecting the synchronous sending mark, synchronously send Address Resolution Protocol packets to each access switch based on the member links respectively.

[0205] Optionally, in some embodiments of the present application, the network interconnection device further includes a second detection unit, an adding unit, and a third synchronous unit, as follows:

[0206] A second detection unit, configured to determine the transmission time nodes corresponding to the respective member ports based on a preset time period, the preset link aggregation group, and the transmission timestamps corresponding to the respective member ports;

[0207] An adding unit, configured to add a synchronous transmission mark to the member port that reaches the transmission time node when the member port reaches the transmission time node;

[0208] A third synchronization unit, configured to, when detecting the synchronous transmission mark, synchronously send Address Resolution Protocol (ARP) packets to each of the access switches based on the member links.

[0209] Optionally, in some embodiments of the present application, the network interconnection device may further include a third detection unit and a third synchronization unit, as follows:

[0210] A third detection unit, configured to, when detecting that the member port triggers the sending of an Address Resolution Protocol packet, if a preset synchronization trigger condition is met, a preset hook function triggers a bound broadcast sending mode;

[0211] A third synchronization unit, configured to synchronously send the Address Resolution Protocol packet from all member ports in a preset aggregation link group based on the bound broadcast sending mode.

[0212] Optionally, in some embodiments of the present application, the third synchronization unit further includes an IPv4 protocol parsing subunit, an IPv6 protocol parsing subunit, a first packet header parsing subunit, and a second packet header parsing subunit, as follows:

[0213] The IPv4 protocol parsing subunit is configured to, if the Address Resolution Protocol packet is an Address Resolution Protocol packet based on IPv4, synchronously send the Address Resolution Protocol packet from all member ports in a preset aggregation link group;

[0214] The IPv6 protocol parsing subunit is configured to, if the Address Resolution Protocol packet is a Neighbor Discovery Protocol packet based on IPv6, extract the packet header of the Neighbor Discovery Protocol packet;

[0215] The first packet header parsing subunit is configured to parse the Neighbor Discovery Protocol packet based on the packet header, and if the parsed packet is a Neighbor Solicitation packet or a Neighbor Advertisement packet, synchronously send the Neighbor Discovery Protocol packet from all member ports in a preset aggregation link group;

[0216] The second packet header parsing subunit is configured to, if the parsed packet is not a Neighbor Solicitation packet and not a Neighbor Advertisement packet, send the Neighbor Discovery Protocol packet from the member port that triggered the Address Resolution Protocol packet to the access switch.

[0217] As described above, in this embodiment, the traversal unit 501 can be used to traverse the port states of the member ports in the preset link aggregation group of the server; when the access unit 502 detects that the port state of a member port is the open state, based on each of the member ports in the preset link aggregation group, an address resolution protocol packet is synchronously sent to each access switch connected to each of the member ports; through the acquisition unit 503, each access switch obtains the MAC address of the server according to the address resolution protocol packet, and forwards the MAC address of the server to a preset core switch; through the routing unit 504, the core switch determines a routing path according to the member port connected to the access switch, the access switch, and the MAC address of the server; the forwarding unit 505 is used for the core switch to forward data packets based on the routing path.

[0218] Through the solution of synchronously sending through multiple member ports, this application converges multiple access switches connected to the server to the core switch, so that multiple access switches can convert the address resolution protocol into a host route and upload it to the core switch. There is no need to set physical connections between two access switches, which improves the stability of the cloud network compared with the stacking technology, does not require additional occupation of the service ports of the switches, and saves the network interconnection cost.

[0219] This application embodiment also provides an electronic device, such as Figure 5 shown, which shows a schematic structural diagram of the electronic device involved in this application embodiment. The electronic device can be a terminal or a server, etc. Specifically:

[0220] The electronic device may include a processor 601 with one or more processing cores, a memory 602 with one or more computer-readable storage media, a power supply 603, an input unit 604 and other components. Those skilled in the art can understand that Figure 5 the structural diagram of the electronic device shown in does not constitute a limitation on the electronic device, and it may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements. Among them:

[0221] The processor 601 is the control center of the electronic device, connecting various parts of the entire electronic device through various interfaces and circuits. By running or executing software programs and / or modules stored in the memory 602, and by invoking the data stored in the memory 602, it executes various functions of the electronic device and processes data. Optionally, the processor 601 may include one or more processing cores; preferably, the processor 601 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface, application programs, etc., and the modem processor mainly processes wireless communications. It can be understood that the above-mentioned modem processor may not be integrated into the processor 601 either.

[0222] The memory 602 can be used to store software programs and modules. The processor 601 executes various functional applications and data processing by running the software programs and modules stored in the memory 602. The memory 602 may mainly include a program storage area and a data storage area. Among them, the program storage area can store the operating system, application programs required for at least one function (such as the sound playback function, image playback function, etc.); the data storage area can store the data created according to the use of the electronic device. In addition, the memory 602 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices. Correspondingly, the memory 602 may also include a memory controller to provide the processor 601 with access to the memory 602.

[0223] The electronic device further includes a power supply 603 that powers each component. Preferably, the power supply 603 can be logically connected to the processor 601 through a power management system, so as to implement functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 603 may also include any components such as one or more DC or AC power supplies, a recharge system, a power failure detection circuit, a power converter or inverter, and a power status indicator.

[0224] The electronic device may further include an input unit 604, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

[0225] Although not shown, the electronic device may further include a display unit, etc., which will not be elaborated here. Specifically, in this embodiment, the processor 601 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 602 according to the following instructions, and the processor 601 will run the application programs stored in the memory 602 to achieve various functions as follows:

[0226] Traverse the port status of each member port in the preset link aggregation group of the server;

[0227] When it is detected that there is a member port with an open port status, based on each of the member ports in the preset link aggregation group, synchronously send Address Resolution Protocol (ARP) packets to each access switch connected to each of the member ports;

[0228] Each of the access switches obtains the MAC address of the server according to the ARP packet, and forwards the MAC address of the server to a preset core switch;

[0229] The core switch determines a routing path according to the member port connected to the access switch, the access switch, and the MAC address of the server;

[0230] The core switch forwards data packets based on the routing path.

[0231] For the specific implementation of each of the above operations, reference may be made to the previous embodiments, and details will not be repeated here.

[0232] As can be seen from the above, the embodiments of the present application provide a network interconnection method and related devices, which traverse the port status of each member port in the preset link aggregation group of the server; when it is detected that there is a member port with an open port status, based on each of the member ports in the preset link aggregation group, synchronously send ARP packets to each access switch connected to each of the member ports; each of the access switches obtains the MAC address of the server according to the ARP packet, and forwards the MAC address of the server to a preset core switch; the core switch determines a routing path according to the member port connected to the access switch, the access switch, and the MAC address of the server; the core switch forwards data packets based on the routing path. Through the scheme of synchronously sending by multiple member ports, the present application converges multiple access switches connected to the server to the core switch, so that multiple access switches can convert the ARP to a host route and upload it to the core switch. There is no need to set physical connections between two access switches, which improves the stability of the cloud network compared with the stacking technology, does not require additional occupation of the service ports of the switch, and saves the network interconnection cost.

[0233] Those of ordinary skill in the art can understand that all or part of the steps in the above various methods can be completed by instructions, or by instructions controlling related hardware. The instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0234] To this end, an embodiment of the present application provides a computer-readable storage medium, which stores multiple instructions that can be loaded by a processor to execute the steps in any of the network interconnection methods provided by the embodiments of the present application. For example, the instructions can execute the following steps:

[0235] An embodiment of the present application provides a network interconnection method and related devices, which can traverse the port states of each member port in a preset link aggregation group of a server; when it is detected that there is a member port with an open port state, based on each of the member ports in the preset link aggregation group, send Address Resolution Protocol (ARP) packets synchronously to each access switch connected to the member ports; each access switch obtains the MAC address of the server according to the ARP packet, and forwards the MAC address of the server to a preset core switch; the core switch determines a routing path according to the member port to which the access switch is connected, the access switch, and the MAC address of the server; the core switch forwards data packets based on the routing path.

[0236] For the specific implementation of each of the above operations, reference can be made to the previous embodiments, which will not be elaborated here.

[0237] Among them, the computer-readable storage medium may include: Read Only Memory (ROM), Random Access Memory (RAM), a magnetic disk, an optical disc, etc.

[0238] Since the instructions stored in the computer-readable storage medium can execute the steps in any of the network interconnection methods provided by the embodiments of the present application, the beneficial effects that can be achieved by any of the network interconnection methods provided by the embodiments of the present application can be realized. For details, reference can be made to the previous embodiments, which will not be elaborated here.

[0239] According to one aspect of the present application, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in various optional implementation manners of the above network interconnection aspect.

[0240] The above has introduced in detail a network interconnection method and related devices provided by the embodiments of the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A network interconnection method, characterized in that, Including: Traverse the port states of each member port in the preset link aggregation group of the server; When it is detected that there is a member port with an open port state, based on each of the member ports in the preset link aggregation group, synchronously send Address Resolution Protocol (ARP) packets to each access switch connected to each member port; Each of the access switches obtains the MAC address of the server according to the ARP packet, and forwards the MAC address of the server to a preset core switch; The core switch determines a routing path according to the member port to which the access switch is connected, the access switch, and the MAC address of the server; The core switch forwards data packets based on the routing path.

2. The network interconnection method according to claim 1, wherein Before traversing the port states of each member port in the preset link aggregation group of the server, it further includes: Configure the network card working mode of the server to the IEEE802.3ad dynamic link aggregation mode, and create a link aggregation group; Determine the member ports to be aggregated in the server, and add the member ports to be aggregated to the link aggregation group; Create a link aggregation group on the access switch, and add the interface of the access switch to the link aggregation group; Perform LACP function verification on the link aggregation group. When the LACP function verification passes, the member ports within the aggregated link group are connected to the access switch.

3. The network interconnection method according to claim 2, characterized in that Before traversing the port states of each member port in the preset link aggregation group of the server, it further includes: When it is detected that there is a member port with an open port state, the server sends a first LACP negotiation packet to the access switch based on the member port. The first LACP negotiation packet includes the identity identifier of the member port and negotiation parameters for negotiating link aggregation; The access switch receives the first LACP negotiation packet, and negotiates with the member port based on the identity identifier of the member port and the negotiation parameters; When the negotiation passes, the access switch generates a second LACP negotiation packet and returns the second LACP negotiation packet to the member port; When receiving the second LACP negotiation packet, determine the member link for realizing communication between the member port and the access switch interface.

4. The network interconnection method according to claim 3, characterized in that The step of synchronously sending Address Resolution Protocol (ARP) packets to each access switch connected to each member port based on each of the member ports in the preset link aggregation group includes: Add a synchronous sending flag to each of the member ports in the preset link aggregation group; When the synchronous sending flag is detected, synchronously send Address Resolution Protocol (ARP) packets to each access switch based on the member link.

5. The network interconnection method according to claim 1, wherein The step that each of the access switches obtains the MAC address of the server according to the ARP packet includes: If the ARP packet is an ARP packet based on IPv4, the access switch parses the ARP packet to obtain the IP address of the server; Query the MAC address of the server corresponding to the IP address based on the routing table on the access switch; If the Address Resolution Protocol packet is a Neighbor Discovery Protocol packet based on IPv6, extract the packet header of the Neighbor Discovery Protocol packet; Parse the packet header to obtain the MAC address of the server.

6. The network interconnection method according to claim 1, wherein The core switch forwards data packets based on the routing path, including: The core switch obtains the data packets uploaded by each server based on the routing path, and distributes the data packets to each server based on the routing path.

7. The network interconnection method according to claim 1, characterized in that, It also includes: Determine the sending time nodes corresponding to each member port based on a preset time period, the preset link aggregation group, and the sending timestamps corresponding to each member port; When the member port reaches the sending time node, add a synchronous sending mark to the member port that reaches the time node; When the synchronous sending mark is detected, synchronously send Address Resolution Protocol packets to each access switch based on the member links, and update the sending timestamp.

8. The network interconnection method according to claim 1, characterized in that It also includes: When it is detected that the member port triggers the sending of an Address Resolution Protocol packet, if it meets the preset synchronous trigger condition, a preset hook function triggers the bound broadcast sending mode; Based on the bound broadcast sending mode, synchronously send the Address Resolution Protocol packet from all member ports in the preset aggregation link group.

9. The network interconnection method according to claim 8, wherein Before the preset hook function triggers the bound broadcast sending mode when it is detected that the member port sends an Address Resolution Protocol packet, it also includes: Configure the network card working mode of the server to the IEEE802.3ad dynamic link aggregation mode, and create a link aggregation group; Determine the member ports to be aggregated in the server, and add the member ports to be aggregated to the link aggregation group; Create a link aggregation group on the access switch, and add the interfaces of the access switch to the link aggregation group; Based on the LACP protocol, determine the member links for realizing communication between each member port and each access switch interface; Add hook points to the member links corresponding to each member port respectively.

10. The network interconnection method according to claim 8, wherein The synchronously sending the Address Resolution Protocol packet from all member ports in the preset aggregation link group includes: If the Address Resolution Protocol packet is an Address Resolution Protocol packet based on IPv4, synchronously send the Address Resolution Protocol packet from all member ports in the preset aggregation link group; If the Address Resolution Protocol packet is a Neighbor Discovery Protocol packet based on IPv6, extract the packet header of the Neighbor Discovery Protocol packet; Based on the packet header, parse the Neighbor Discovery Protocol packet. If the parsed packet is a neighbor solicitation request packet or a neighbor advertisement packet, synchronously send the Neighbor Discovery Protocol packet from all member ports in the preset aggregation link group.

11. The network interconnection method according to claim 10, wherein It also includes: Parse the Neighbor Discovery Protocol packet based on the packet header; If the parsed packet is neither a neighbor solicitation message nor a neighbor advertisement message, the neighbor discovery protocol packet is sent from the member port that triggered the address translation protocol packet to the access switch.

12. A network interconnection device, characterized in that, Comprising: A traversal unit, configured to traverse the port states of each member port in a preset link aggregation group of a server; An access unit, configured to, when detecting that there is a member port with an open port state, synchronously send an address resolution protocol packet to each access switch connected to each of the member ports based on each of the member ports in the preset link aggregation group; An acquisition unit, configured to each access switch obtain the MAC address of the server according to the address resolution protocol packet, and forward the MAC address of the server to a preset core switch; A routing unit, configured to the core switch determine a routing path according to the member port to which the access switch is connected, the access switch, and the MAC address of the server; A forwarding unit, configured to the core switch perform data packet forwarding based on the routing path.

13. An electronic device, characterized in that, Comprising a memory and a processor; the memory stores an application program, and the processor is configured to run the application program in the memory to perform the operations in the network interconnection method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores multiple instructions, and the instructions are suitable for being loaded by a processor to execute the steps in the network interconnection method according to any one of claims 1 to 11.

15. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instruction is executed by a processor, the steps in the network interconnection method according to any one of claims 1 to 11 are implemented.

Images