Routing Optimization Method, Physical Network Device, and Computer-Readable Storage Medium

Abstract

The present invention discloses a routing optimization method, a physical network device, and a computer-readable storage medium, which are applied to a first physical network device and include: obtaining probe messages from at least one second physical network device; the probe messages include the host names and interface information of the second physical network devices; generating an underlay routing table corresponding to the underlay network according to the probe messages, where the underlay routing table contains the host names and interface information; synchronizing the underlay routing table to the corresponding overlay network locally, so that the overlay network generates an overlay routing table according to the host names and interface information; obtaining service messages through the overlay network and determining the target physical network device, and determining the target path corresponding to the target physical network device according to the overlay routing table; sending the service messages to the target overlay network corresponding to the target physical network device through the target path. The overlay network can obtain the topology and interface connection conditions of the underlay network according to the overlay routing table, select a suitable path to forward the service messages, thereby optimizing the utilization of network resources.

Description

Technical Field

[0001] Embodiments of the present invention relate to, but are not limited to, the field of communication technologies, and in particular, to a routing optimization method, a physical network device, and a computer-readable storage medium. Background Art

[0002] With the explosive growth of 5G users, it is necessary to provide greater device connectivity and network capacity than the previous generation of technologies. Therefore, for 5G, virtualization may take over most of the edge elements of the 5G network, especially the access RAN (radio access network) and UE (User Equipment). Since 5G needs to handle different services and devices at the edge, the 5G network uses network slicing technology to divide a physical infrastructure into multiple virtual networks so that each slice can provide different and unique connections under the same infrastructure.

[0003] To achieve this flexibility, each slice must be able to access different types of resources, whether physical or virtual. Therefore, 5G revolutionizes the network architecture through SDN (Software Defined Network) with programmable network control, virtualizing the actual physical network. In terms of implementation, most virtual networks use the overlay technology to quickly provide logical networks with different requirements and isolation. However, the overlay network and the underlay physical network are at different network levels and have independent routing and addressing. Therefore, packets from different nodes will largely choose the same path or the same GW (Gateway), resulting in the inability to utilize network resources faster and more optimally and the inability to provide fast and reliable network services for various applications. Summary of the Invention

[0004] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of protection of the claims.

[0005] Embodiments of the present invention provide a routing optimization method, a physical network device, and a computer-readable storage medium, which can optimize the utilization of network resources.

[0006] In a first aspect, an embodiment of the present invention provides a routing optimization method, which is applied to a first physical network device and includes:

[0007] Obtaining probe packets from at least one second physical network device; the probe packets include the host name and interface information of the second physical network device;

[0008] Generate an underlay routing table corresponding to the underlay network according to the detection message, where the underlay routing table includes the host name and interface information of the second physical network device;

[0009] Synchronize the underlay routing table to the corresponding overlay network locally, so that the overlay network generates an overlay routing table according to the host name and interface information in the underlay routing table;

[0010] Obtain a service message through the overlay network and determine a target physical network device, and determine a target path corresponding to the target physical network device according to the overlay routing table;

[0011] Send the service message to the target overlay network corresponding to the target physical network device through the target path.

[0012] In a second aspect, an embodiment of the present invention further provides a physical network device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the routing optimization method described above is implemented.

[0013] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium storing computer-executable instructions for executing the routing optimization method described above.

[0014] Embodiments of the present invention include: A first physical network device obtains probe messages from at least one second physical network device, where the probe messages include the host names and interface information of the second physical network devices; then generates an underlay routing table corresponding to the underlay network according to the probe messages, and the underlay routing table contains the host names and the interface information of the second physical network devices; and synchronizes the underlay routing table to the corresponding overlay network locally, so that the overlay network generates an overlay routing table according to the host names and the interface information in the underlay routing table; the first physical network device obtains service messages through the overlay network and determines a target physical network device, and determines a target path corresponding to the target physical network device according to the overlay routing table; finally, sends the service messages to the target overlay network corresponding to the target physical network device through the target path. According to the solution provided by the embodiments of the present invention, the overlay network of the first physical network device can obtain the topology and interface connection conditions of the underlay network according to the overlay routing table, and can select a suitable path according to the target physical network device to guide the forwarding of service messages. Therefore, the embodiments of the present invention can optimize the utilization of network resources and meet the requirements of reliable and fast network forwarding.

[0015] Other features and advantages of the present invention will be described in the following specification, and in part will become apparent from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in the specification, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings are used to provide a further understanding of the technical solutions of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solutions of the present invention and do not constitute a limitation to the technical solutions of the present invention.

[0017] Figure 1 It is a schematic diagram of a system architecture platform for executing a routing optimization method provided by an embodiment of the present invention;

[0018] Figure 2 It is a flowchart of a routing optimization method provided by an embodiment of the present invention;

[0019] Figure 3 It is a topology diagram provided by an embodiment of the present invention;

[0020] Figure 4 It is a schematic diagram of the sending of probe messages in a routing optimization method provided by an embodiment of the present invention;

[0021] Figure 5 It is a schematic diagram of the underlay global routing table generated in the routing optimization method according to an embodiment of the present invention;

[0022] Figure 6 It is a schematic diagram of the overlay global routing table generated in the routing optimization method according to an embodiment of the present invention;

[0023] Figure 7 It is a flowchart of the routing optimization method provided by another embodiment of the present invention;

[0024] Figure 8 It is a flowchart of the routing optimization method provided by another embodiment of the present invention;

[0025] Figure 9 It is a flowchart of the routing optimization method provided by another embodiment of the present invention;

[0026] Figure 10 It is a schematic diagram of the transmission extension header provided by an embodiment of the present invention;

[0027] Figure 11 It is a flowchart of the routing optimization method provided by another embodiment of the present invention;

[0028] Figure 12 It is a schematic diagram of the multicast mode in the routing optimization method provided by an embodiment of the present invention;

[0029] Figure 13 It is a routing flowchart of the service message of the existing overlay network;

[0030] Figure 14 It is a routing flowchart of the service message of the overlay network provided by an embodiment of the present invention. Detailed implementation manners

[0031] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

[0032] It should be noted that although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from the module division in the device or the order in the flowchart. Terms such as "first" and "second" in the description, claims or the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence.

[0033] The present invention provides a routing optimization method, a physical network device, and a computer-readable storage medium, including: a first physical network device obtains detection packets from at least one second physical network device, where the detection packets include the host name and interface information of the second physical network device; and generates an underlay routing table corresponding to the underlay network according to the detection packets, where the underlay routing table contains the host name and interface information of the second physical network device; then the first physical network device synchronizes the underlay routing table to the corresponding overlay network locally, so that the overlay network generates an overlay routing table according to the host name and interface information in the underlay routing table; when the overlay network obtains a service packet and determines the target physical network device, the first physical network device determines the target path corresponding to the target physical network device according to the overlay routing table, and sends the service packet to the target overlay network corresponding to the target physical network device through the target path. For this technical solution, the overlay network of the first physical network device can obtain the topology and interface connection conditions of the underlay network according to the overlay routing table, and can select a suitable path according to the target physical network device to guide the forwarding of the service packet. Therefore, the embodiments of the present invention can optimize the utilization of network resources and meet the requirements of reliable and fast network forwarding.

[0034] The following further elaborates on the embodiments of the present invention in conjunction with the accompanying drawings.

[0035] As Figure 1 shown, Figure 1 is a schematic diagram of a system architecture platform for executing the routing optimization method provided by an embodiment of the present invention.

[0036] In Figure 1 the example of, the system architecture platform includes a first physical network device 100 and at least one second physical network device 200, where the above-mentioned first physical network device 100 is provided with a memory 120 and a processor 110, where the memory 120 and the processor 110 can be connected by a bus or other means, Figure 1 taking connection by bus as an example.

[0037] The memory 120, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory 120 may include high-speed random access memory and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory 120 optionally includes a memory remotely disposed relative to the processor 110, and these remote memories can be connected to the system architecture platform through a network. Examples of the above networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0038] In the related art, with the explosive growth of 5G users, it is necessary to provide a larger device connection and network capacity than the previous generation technology. Therefore, for 5G, virtualization may take over most of the edge elements of the 5G network, especially the access RAN and UE. Since 5G needs to handle different services and devices at the edge, the 5G network will use network slicing technology to divide a physical infrastructure into multiple virtual networks so that each slice can provide different and unique connections under the same infrastructure.

[0039] To achieve this flexibility, each slice should be able to access different types of resources, whether physical or virtual. Therefore, 5G revolutionizes the network architecture through network control programmability with SDN, virtualizing the actual physical network. In terms of implementation, most virtual networks use the overlay technology to quickly provide logical networks with different requirements and isolation from each other. However, the overlay network and the underlay network are at different network levels and route and address independently. Therefore, packets from different nodes will largely choose the same path or the same GW, resulting in the inability to utilize network resources faster and more optimally and the inability to provide fast and reliable network services for various applications.

[0040] Therefore, based on the above situation, in Figure 1In the system architecture platform provided by the example, the first physical network device 100 can obtain a detection message from the second physical network device 200 and generate an underlay routing table corresponding to the underlay network according to the detection message. The detection message and the underlay routing table both include the host name and interface information of the second physical network device 200. Then, the first physical network device 100 synchronizes the underlay routing table to the corresponding overlay network locally, so that the overlay network generates an overlay routing table according to the host name and interface information in the underlay routing table. When the overlay network of the first physical network device 100 needs to forward a service message to a target physical network device, the overlay network determines a target path corresponding to the target physical network device according to the overlay routing table. Finally, the service message is sent to the target overlay network corresponding to the target physical network device through the target path. According to the solution provided by the embodiment of the present invention, the overlay network of the first physical network device 100 can obtain the topology and interface connection conditions of the underlay network according to the overlay routing table, and can select a suitable path according to the target physical network device to guide the forwarding of the service message. Therefore, the embodiment of the present invention can optimize the utilization of network resources and meet the requirements of reliable and fast network forwarding.

[0041] Those skilled in the art can understand that the system architecture platform can be applied to 3G communication network systems, LTE communication network systems, 5G communication network systems, and subsequent evolved mobile communication network systems, etc. The present embodiment does not make specific limitations on this.

[0042] Those skilled in the art can understand that Figure 1 the system architecture platform shown in

[0043] In Figure 1 the shown system architecture platform, the processor 110 can call the routing optimization program stored in the memory 120, so as to execute the routing optimization method between the first physical network device 100 and the second physical network device 200.

[0044] Based on the above system architecture platform, the following presents various embodiments of the routing optimization method of the present invention.

[0045] As Figure 2 shown, Figure 2It is a flowchart of a routing optimization method provided by an embodiment of the present invention. This routing optimization method can be applied to a first physical network device and includes, but is not limited to, steps S100, S200, S300, S400, and S500.

[0046] Step S100: Obtain probe messages from at least one second physical network device; the probe messages include the host names and interface information of the second physical network devices.

[0047] In one embodiment, when the first physical network device and the second physical network devices are powered on, at least one second physical network device will integrate its own host name and the interface information of each interface into a probe message and send it to the first physical network device. Therefore, the first physical network device will obtain the probe messages of at least one second physical network device, enabling the first physical network device to know the host names and interface information of each second physical network device.

[0048] Alternatively, in another embodiment, the first second physical network device sends a probe message to the second second physical network device at the other end. Then, the second second physical network device will add the host name and interface information in the probe message corresponding to the first second physical network device to its own corresponding probe message. Next, the second second physical network device will send the probe message carrying the host names and interface information of the first and second second physical network devices to the third second physical network device, and so on, until the Nth (N is a positive integer) second physical network device sends the probe message carrying the host names and interface information of multiple second physical network devices to the first physical network device. Therefore, the first physical network device will obtain the probe messages of multiple second physical network devices, enabling the first physical network device to know the host names and interface information of each second physical network device.

[0049] Exemplarily, as Figures 3 to 4 shown, nodes 1 to 8 are all physical network devices. If node 1 is the first physical network device and nodes 2 to 8 are all second physical network devices, node 5 can directly send the probe message carrying its own host name and the interface information of each interface to node 1 at the other end. Secondly, node 6 can also directly send the probe message carrying its own host name and the interface information of each interface to node 2 at the other end. Then, node 2 will add the host name and interface information in the probe message corresponding to node 6 to its own corresponding probe message and forward the probe message carrying the host names and interface information of node 6 and node 2 to node 1, enabling node 1 to obtain the host names and interface information of node 5, node 6, and node 2. And so on, node 1 can obtain all the host names and interface information of nodes 2 to 8.

[0050] It should be noted that, in the embodiments of the present invention, the forwarding hop count of the detection message can be configured according to the actual situation of the planned network deployment, so that each node can obtain the topology and interface connection situation of the underlay network. For Figures 3 to 4 the network architecture in

[0051] In the embodiments of the present invention, it should be noted that the above interface information may include, but is not limited to, at least one of the interface maximum rate information, the current packet receiving and sending rate information, the delay information, the jitter information, and the packet loss information.

[0052] It can be understood that the above first physical network device and second physical network device can be physical servers or other physical devices with software control systems.

[0053] Step S200: Generate an underlay routing table corresponding to the underlay network according to the detection message. The underlay routing table includes the host names and interface information of the second physical network devices.

[0054] In one embodiment, since the first physical network device will obtain the host names and interface information of each second physical network device, the link and interface information of the global underlay network will converge on the first physical network device, thereby generating an underlay routing table corresponding to the underlay network. Among them, the underlay routing table includes the host names and interface information of the first physical network device and each second physical network device.

[0055] Exemplarily, as Figures 3 to 5 shown, if node 1 obtains all the host names and interface information of nodes 2 to 8, then the link and interface information of the global underlay network will converge on node 1, and an underlay routing table as Figure 6 shown will be generated.

[0056] Step S300: Synchronize the underlay routing table to the corresponding overlay network locally, so that the overlay network generates an overlay routing table according to the host names and interface information in the underlay routing table.

[0057] In one embodiment, after the first physical network device generates the underlay routing table corresponding to the underlay network, it synchronizes the information of the underlay routing table to the overlay network corresponding to the local of the first physical network device. Then, the overlay network corresponding to the local of the first physical network device generates an overlay routing table based on the host names and interface information in the obtained underlay routing table.

[0058] It should be noted that for the above overlay routing table, it includes the cost values of each path between the first physical network device and each second physical network device; among them, the cost values of each path are determined by the interface information in the underlay routing table. Specifically, the calculation of the cost value can be obtained by adding weights to various interface information in the underlay routing table according to the actual situation of the network. The cost value calculation formula is as follows:

[0059]

[0060] Among them, D in the above formula is the cost benchmark value of the outgoing interface of the first physical network device, rx is the packet reception rate information in the underlay routing table, tx is the packet transmission rate information in the underlay routing table, maxspeed is the maximum interface rate information in the underlay routing table, k1 is the weight of the bandwidth occupation ratio of sending and receiving, delay is the delay information in the underlay routing table, jitter is the jitter information in the underlay routing table, k2 is the weight of delay jitter, drop is the packet loss information in the underlay routing table, and k3 is the weight of the number of packet losses within a period.

[0061] Exemplarily, as Figures 5 to 6 shown, if the value of D is 1, the value of k1 is 3, the value of k2 is 3, and the value of k3 is 1, then from Figure 5 the underlay routing table and the above cost value calculation formula, the cost value of directly routing from node 1 to node 5 can be obtained, and the cumulative cost value of passing through node 2 and node 6 from node 1 to node 5 can also be calculated, and the cumulative cost value of passing through node 2, node 4, node 7, and node 6 from node 1 to node 5 can also be calculated. Thus, the cost values of all paths between node 1 and node 5 can be calculated. And so on, the cost values of all paths between node 1 and any node among nodes 2 to 8 can be calculated, as Figure 6 shown.

[0062] It should be noted that the above synchronization method for synchronizing the underlay routing table to the corresponding overlay network locally may include, but is not limited to, periodic synchronization and / or change synchronization. Among them, periodic synchronization may refer to synchronizing the information of the underlay routing table to the corresponding overlay network locally when a preset time period is reached, and change synchronization may refer to synchronizing the information of the changed underlay routing table to the corresponding overlay network locally when the information of the underlay routing table changes.

[0063] Step S400, obtaining a service packet through the overlay network and determining a target physical network device, and determining a target path corresponding to the target physical network device according to the overlay routing table.

[0064] In an embodiment, after the overlay routing table is generated for the overlay network corresponding to the first physical network device, if the overlay network corresponding to the first physical network device needs to send a service packet to the target physical network device, since the overlay routing table contains the path information from the first physical network device to the target physical network device, therefore, the overlay network corresponding to the first physical network device can select a suitable target path according to the overlay routing table and the target physical network device.

[0065] Specifically, the overlay routing table includes the cost values of each path from the first physical network device to each second physical network device. Since the target physical network device is one of the multiple second physical network devices, the overlay routing table also includes the cost values of each path from the first physical network device to the target physical network device; among them, the cost values of each path are determined by the interface information in the underlay routing table.

[0066] Exemplarily, as Figure 6 shown, the cost value of directly routing from node 1 to node 5 is 3.1, the cumulative cost value of routing from node 1 through node 2 and node 6 to node 5 is 9.3, and the cumulative cost value of routing from node 1 through node 2, node 4, node 7, and node 6 to node 5 is 12.6, and so on. It can be known that the cost value of directly routing from node 1 to node 5 is the smallest. Since the cost accumulation of all interfaces on the full path of the overlay routing is the total cost value of this path, and the smaller the cost value, the higher the priority of this path being selected. Therefore, the service packet of the overlay network of the first physical network device will select the path with the smallest cost value as the target path, that is, select the path of directly routing from node 1 to node 5 as the target path.

[0067] It should be noted that regarding Figure 5 the down flag in, it means that the corresponding interface is unavailable. Therefore, the existence of the down flag indicates that the cost value of this interface is the maximum value. The path with the maximum value has the power of veto, that is, it indicates that this path will not participate in the selection. In addition, for Figure 5 the export flag in, it refers to the interface identifier output by the physical network device to the outside. For example, export51 refers to the interface identifier sent from node 5 to the router or switch.

[0068] Step S500: Send the service packet to the target overlay network corresponding to the target physical network device through the target path.

[0069] In an embodiment, when the overlay network corresponding to the first physical network device selects a suitable target path, it will send the service packet to the target overlay network corresponding to the target physical network device through the determined target path.

[0070] Since the embodiments of the present invention include the above-mentioned steps S100, step S200, step S300, step S400, and step S500, therefore, the overlay network of the first physical network device can obtain the topology and interface connection conditions of the underlay network according to the overlay routing table, and can select a suitable path according to the target physical network device to guide the forwarding of the service packet. Therefore, the embodiments of the present invention can optimize the utilization of network resources and meet the requirements of reliable and fast network forwarding.

[0071] In addition, referring to Figure 7 , in an embodiment, regarding the determination of the target path corresponding to the target physical network device according to the overlay routing table in the above-mentioned step S400, it includes but is not limited to step S600.

[0072] Step S600: Select the path with the smallest cost value from the paths corresponding to the target physical network device in the overlay routing table as the target path.

[0073] In an embodiment, the overlay routing table includes the cost values of each path from the first physical network device to the target physical network device. The smaller the cost value, the higher the priority of this path being selected. Therefore, the service packet of the overlay network of the first physical network device will select the path with the smallest cost value as the target path.

[0074] In addition, referring to Figure 8 , in an embodiment, the routing optimization method further includes but is not limited to steps S710, step S720, step S730, and step S740.

[0075] Step S710: When the underlay network updates the interface message, synchronize the new underlay routing table corresponding to the underlay network to the corresponding overlay network locally;

[0076] Step S720: Generate a new overlay routing table through the overlay network according to the host names and updated interface information in the new underlay routing table;

[0077] Step S730: When the cost value of the target path in the new overlay routing table reaches the preset upper limit value, determine a new target path corresponding to the target physical network device according to the new overlay routing table;

[0078] Step S740: Send the service packet to the target overlay network corresponding to the target physical network device through the new target path.

[0079] In an embodiment, in order to keep the target path of a service packet flow as the same as possible, unless the underlay network update message triggers the calculation that the cost value of an interface in the target path is updated to the maximum value, the service packet will use the new overlay routing table to re-select the route. Specifically, when the interface message in the underlay network is updated so that the cost value of the target path is the maximum value or the cost value of the target path reaches the preset upper limit value, that is, when the identifier of the interface is updated from up to down, the first physical network device will obtain the new underlay routing table after the underlay network is updated, and synchronize the information of the new underlay routing table to the corresponding overlay network locally. Then, the corresponding overlay network locally will generate a new overlay routing table according to the information of the new underlay routing table, and select a new target path corresponding to the target physical network device according to the new overlay routing table; finally, the overlay network of the first physical network device will continue to send the interrupted service packet to the target overlay network corresponding to the target physical network device through the new target path. Therefore, the embodiment of the present invention can re-select a new target path in the case of an unavailable interface, ensuring the normal transmission of service packets.

[0080] It should be noted that for the specific implementation manner and corresponding technical effects of re-selecting the new target path in the routing optimization method of the embodiment of the present invention, reference can be made to the embodiments of the above routing optimization method.

[0081] In addition, referring to Figure 9 , in an embodiment, regarding the above step S500, it includes but is not limited to step S800.

[0082] Step S800: Encapsulate the service message into a tunnel format, and send the encapsulated service message to the target physical network device through the target path, so that the target physical network device can decrypt the service message and send the decrypted service message to the target overlay network corresponding to the target physical network device.

[0083] In an embodiment, after determining the target path, the first physical network device encapsulates the service message into a tunnel format, and then sends the encapsulated service message to one of the second physical network devices through the target path. When the second physical network device receives the service message encapsulated in the tunnel format, the second physical network device checks whether it is the destination of the service message locally. If it is verified that it is the destination of the service message locally, then the current second physical network device is the target physical network device. Then the target physical network device decrypts the service message in the tunnel format and forwards it to the destination service through the destination overlay network corresponding to the target physical network device.

[0084] It should be noted that in the embodiments of the present invention, the most widely used VXLAN (Virtual Extensible Local Area Network) GPE (Generic Protocol Encapsulation) extension of the current overlay application is used, and a list of all interfaces of the path is carried in the extension header. The application can also use other tunnel type extensions such as GENEVE (Generic Network Virtualization Encapsulation). The VXLAN extension header is as Figure 10 shown. The payload message inside VXLAN specified in RFC7348 must be an Ethernet message, which limits the usage scope of the VXLAN protocol. In order to enable VXLAN to more widely support the overlay transmission of other protocol messages, some reserved bits specified in the original FRC7348 are designated for GPE encapsulation in the RFC draft VXLAN GPE. Specifically, the reserved bits are as specified below:

[0085] Ver: Version, used to indicate the VXLAN GPE protocol version, with an initial value of 0.

[0086] P: Next Protocol Bit. If the P reserved bit is 1, the Next Protocol field is valid.

[0087] B: BUM Traffic Bit. If the B reservation bit is 1, it indicates that the encapsulated packet inside VXLAN is a BUM packet.

[0088] O: OAM Flag Bit. If the O reservation bit is 1, it indicates that the encapsulated packet inside VXLAN is an OAM packet.

[0089] Next Protocol: 8 bits, used to represent the protocol format of the encapsulated packet inside VXLAN.

[0090] In addition, it is defined in the protocol that:

[0091] |Next Protocol|Description|Reference|

[0092] |0x0|Reserved|This Document|

[0093] |0x1|IPv4|This Document|

[0094] |0x2|IPv6|This Document|

[0095] |0x3|Ethernet|This Document|

[0096] |0x4|NSH|This Document|

[0097] |0x05..0x7F|Unassigned||

[0098] |0x80..0xFF|Unassigned (shim headers)||

[0099] Specifically, the embodiments of the present invention can use a custom value of 0x10 to carry the path interface list. After determining the target path, the first physical network device will encapsulate the service packet in a tunnel format, that is, generate a tunnel packet. If the second physical network device in the target path receives the tunnel packet, it will parse the path interface list carried by the tunnel packet according to the next protocol as a custom protocol, pop the current interface from the list, and send it according to the next interface specified in the list. If there is no next interface, it will check whether it is the local destination. If it is verified that the local is the destination, then the current second physical network device is the target physical network device. Then the target physical network device will decrypt the tunnel packet and forward it to the destination overlay network corresponding to the target physical network device for the destination service.

[0100] In addition, referring toFigure 11 In one embodiment, the above-mentioned step S500 includes but is not limited to step S900.

[0101] Step S900: Send the service message to the intermediate physical network device, so that the intermediate physical network device forwards the service message to the target overlay network corresponding to the target physical network device according to the target path.

[0102] In one embodiment, after the target path is determined, the first physical network device will encapsulate the service message into a tunnel format, and then send the encapsulated service message to one of the second physical network devices through the target path. When the second physical network device receives the service message encapsulated into the tunnel format, the second physical network device will verify whether the local is the destination of the service message. If it is verified that the local is not the destination of the service message, the current second physical network device will forward the service message encapsulated into the tunnel format to the next second physical network device until it is forwarded to the target physical network device. Then the target physical network device will unpack the service message in the tunnel format and hand it over to the destination overlay network corresponding to the target physical network device to forward it to the destination service.

[0103] Specifically, after the target path is determined, the first physical network device will encapsulate the service message into a tunnel format, that is, generate a tunnel message. If the second physical network device in the target path receives the tunnel message, it will parse the path interface list carried by the tunnel message according to the custom protocol based on nextprotocol, and pop the current interface from the list, and send it to the next second physical network device according to the next interface specified in the list, and so on, until it is sent to the target physical network device. Then the target physical network device will unpack the tunnel message and hand it over to the destination overlay network corresponding to the target physical network device to forward it to the destination service.

[0104] In addition, refer to Figure 12 In one embodiment, when the service message is in unicast mode, each physical network device can obtain and maintain the information of the above-mentioned underlay routing table, and decide the forwarding path of the unicast respectively; when the service message is in multicast mode, at least two physical network devices can be selected as the master control node according to the cluster algorithm, and the overlay network on the master control node will collect information of all nodes and decide the forwarding path of the multicast.

[0105] In one embodiment, the present invention provides that when both GW1 and GW2 are L2 gateway functions, load sharing links are provided through cross-board aggregation. Multicast routing requires centralized determination of multicast port groups, and the topology is as follows Figure 12As shown in the figure. At all nodes, at least two devices are selected as master nodes through a clustering algorithm. In the embodiments of the present invention, three master nodes of HA (High Available) are selected. In addition to the functions of generating the underlay routing table and the overlay routing table, the above three nodes are also responsible for making decisions on multicast routing and optimizing the results of local routing.

[0106] It should be noted that L2 gateways generally set up aggregated links to support load sharing and fault tolerance. In a virtualized network, to support cross-board aggregation, a centralized control point is also required to uniformly distribute the information required for aggregated group negotiation. The decision-making module maintains the unified information distribution and issuance of the aggregated group.

[0107] Secondly, after the aggregated group negotiation is successful, if different nodes in the same network make decisions on multicast paths respectively, the multicast packets may be sent to two opposite ports simultaneously, and the multicast received from the opposite end may also be forwarded out from another port. Therefore, for multicast, it is also necessary to select a determined multicast outgoing interface for each virtual network according to the cost value, and all multicast packets in this network are sent from the same multicast outgoing interface.

[0108] In addition, the results of local routing of each node can be optimized or a guaranteed path can be provided for some important services. For example, important services specify their required bandwidth and delay requirements. After selecting a path that meets their requirements, through the interaction interface between the overlay and the underlay, the bandwidth and transceiver information of each interface are updated, and the bandwidth is reserved to prevent conflicts during local routing of nodes.

[0109] Based on the various embodiments of the above routing optimization method, the Figure 13 existing routing process of service packets can be optimized into the Figure 14 routing process in the embodiments of the present invention. Among them, Figure 13 and Figure 14 the hyper-1 and hyper-2 in Figure 3 and Figure 4 are one of the nodes 1 to 8 in Figure 13 VM1 and VMn are the corresponding virtual machines on the nodes. For the Figure 13 existing routing process of service packets in Figure 14The underlay information on the middle node includes not only the destinations gw1 and gw2, but also py1 and py2 corresponding to gw1 and gw2 respectively, where py refers to the physical interface between the gw and the hyper. Additionally, Figure 14 The overlay information on the middle node includes not only the destination dst service, but also the next-hop ports gw1 and gw2, and py1 and py2 corresponding to gw1 and gw2 respectively, and also includes the cost values of each path. Therefore, Figure 14 The service packets on the virtual machines VM1 and VMn in [] will select the path with the minimum cost value, so that the service packets of the virtual machine VM1 are sent from gw1, and the service packets of the virtual machine VMn are sent from gw2, so as to utilize network resources faster and more optimally and provide fast and reliable network services for various applications.

[0110] Based on the above routing optimization method, the following are the respective embodiments of the physical network device and the computer-readable storage medium of the present invention.

[0111] In addition, an embodiment of the present invention provides a physical network device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor.

[0112] The processor and the memory can be connected through a bus or other means.

[0113] It should be noted that the physical network device in this embodiment can be applied to the system architecture platform in the embodiment shown in Figure 1 The physical network device in this embodiment can form a part of the system architecture platform in the embodiment shown in Figure 1 The two belong to the same inventive concept, so they have the same implementation principle and beneficial effects, which will not be elaborated here.

[0114] The non-transitory software program and instructions required to implement the routing optimization method of the above embodiment are stored in the memory. When executed by the processor, the routing optimization method of the above embodiment is executed. For example, the method steps S100 to S500 described above are executed, Figure 2 the method steps S600 in [], Figure 7 the method steps S710 to S740 in [], Figure 8 the method S710 to S740 in [], Figure 9 the method steps S800 in [], Figure 11 the method steps S900 in [].

[0115] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0116] In addition, an embodiment of the present invention also provides a computer-readable storage medium, which stores computer-executable instructions for executing the above-mentioned routing optimization method. For example, when executed by a processor in the above physical network device embodiment, the above processor can execute the routing optimization method in the above embodiment. For example, execute the Figure 2 method steps S100 to S500 in Figure 7 method step S600 in Figure 8 method S710 to S740 in Figure 9 method step S800 in Figure 11 method step S900 in

[0117] Those of ordinary skill in the art can understand that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and their appropriate combinations. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory, or other memory technologies, CD-ROM, digital versatile disk (DVD), or other optical disk storage, magnetic cassette, tape, magnetic disk storage, or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, as is well known to those of ordinary skill in the art, communication media typically includes computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and can include any information delivery medium.

[0118] The above is a specific description of the preferred embodiment of the present invention. However, the present invention is not limited to the above-mentioned embodiments. Those skilled in the art can also make various equivalent deformations or substitutions without departing from the spirit of the present invention, and these equivalent deformations or substitutions are all included within the scope defined by the claims of the present invention.

Claims

1. A routing optimization method, applied to a first physical network device, comprising: Obtaining probe messages from at least one second physical network device; The probe messages include the host name and interface information of the second physical network device; Generating an underlay routing table corresponding to the underlying underlay network according to the probe messages, the underlay routing table including the host name and the interface information of the second physical network device; Synchronizing the underlay routing table to the corresponding local overlay network, so that the overlay network generates an overlay routing table according to the host name and the interface information in the underlay routing table; Obtaining service messages through the overlay network and determining a target physical network device, and determining a target path corresponding to the target physical network device according to the overlay routing table; Sending the service messages to the target overlay network corresponding to the target physical network device through the target path; Wherein, the overlay routing table includes the cost values of each path from the first physical network device to the target physical network device; the cost values of each path are determined by the interface information in the underlay routing table; In addition, the determining the target path corresponding to the target physical network device according to the overlay routing table includes: selecting the path with the smallest cost value among the paths corresponding to the target physical network device from the overlay routing table as the target path; In addition, the method further includes: When the underlay network updates the interface information, synchronizing the new underlay routing table corresponding to the underlay network to the corresponding local overlay network; Generating a new overlay routing table through the overlay network according to the host name in the new underlay routing table and the updated interface information; When the cost value of the target path in the new overlay routing table is less than a preset upper limit value, sending the service message to the target overlay network corresponding to the target physical network device through the old target path.

2. The routing optimization method according to claim 1, characterized in that Further includes: When the cost value of the target path in the new overlay routing table reaches the preset upper limit value, determining a new target path corresponding to the target physical network device according to the new overlay routing table; Sending the service message to the target overlay network corresponding to the target physical network device through the new target path.

3. The routing optimization method according to any one of claims 1 to 2, characterized in that The sending the service message to the target overlay network corresponding to the target physical network device through the target path includes: Encapsulate the service message into a tunnel format, and send the encapsulated service message to the target physical network device through the target path, so that the target physical network device can decrypt the service message and send the decrypted service message to the target overlay network corresponding to the target physical network device.

4. The routing optimization method according to any one of claims 1 to 2, characterized in that The step of sending the service message to the target overlay network corresponding to the target physical network device through the target path includes: Send the service message to an intermediate physical network device, so that the intermediate physical network device forwards the service message to the target overlay network corresponding to the target physical network device according to the target path.

5. The routing optimization method according to any one of claims 1 to 2, characterized in that The synchronization method of synchronizing the underlay routing table to the corresponding local overlay network includes periodic synchronization and / or change synchronization.

6. The routing optimization method according to any one of claims 1 to 2, characterized in that The interface information includes at least one of the following: interface maximum rate information, current packet receiving and sending rate information, delay information, jitter information, and packet loss information.

7. A physical network device, characterized in that, It includes: A memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the routing optimization method according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, Stored with computer-executable instructions for executing the routing optimization method according to any one of claims 1 to 6.

Images