Computing power routing method and apparatus, routing node, node, and client device

Abstract

The present disclosure relates to the technical field of communications, and provides a computing power routing method and apparatus, a routing node, a node, and a client device. The computing power routing method is applied to a first routing node, and comprises: receiving a first packet sent by a second routing node; performing decapsulation processing on the first packet to obtain a second packet and a first segment routing identifier SID; on the basis of the first SID, determining a local first target node connected to the first routing node; and sending the second packet to the first target node, wherein the first routing node is a first-hop provider edge (PE) routing node of a network accessed by the first target node, and the first target node is a first edge computing MEC device or a first computing power service node. The solution of the present disclosure can avoid the problem of routing confusion in distributed scenarios, thereby avoiding the problems of multi-point decision-making and inconsistent routing states.

Description

Computing power routing method and device, routing node, node and client device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This disclosure is based on and claims the priority of Chinese patent application with application number 202310964007.4 and application date August 2, 2023. The entire content of the Chinese patent application is hereby incorporated into this disclosure as a reference. Technical Field

[0003] The present disclosure relates to the field of communication technology, and in particular to a computing power routing method and apparatus, routing nodes, nodes, and client devices. Background Art

[0004] In the existing computing power routing mechanism, computing power information is notified through the Border Gateway Protocol (BGP). The purpose of the computing power network is to jointly schedule the computing network to find a suitable service node (the suitable service node is a service node that is close to the user and has sufficient computing resources). On the one hand, it meets the user's business needs, and on the other hand, it optimizes the use of network and computing power resources.

[0005] In the existing distributed computing power routing mechanism, multiple routing nodes in the network can support serviceID1, and the serviceID1 (an anycast IP address) route is spread in the network (currently there are many means and they have not yet converged). The ingress node integrates the network and computing power conditions (monitors the computing power and latency of several alternative nodes) to generate a forwarding table entry for serviceID1, for example, selecting one from the alternative tunnels reaching R6 and R14. Ingress1 (for example, R1) receives a message with a destination address (DA) of serviceID1 and enters the tunnel according to the aforementioned table entry. However, the above-mentioned distributed computing power routing mechanism has the problem of inconsistent routing status caused by inconsistent multi-point decision-making, which in turn causes traffic to jump continuously in the network and routing confusion.

[0006] Summary of the Invention

[0007] The purpose of the technical solution disclosed in the present invention is to provide a computing power routing method and device, routing nodes, servers and client devices to solve the routing confusion problem existing in the existing distributed computing power routing mechanism.

[0008] In order to solve the above technical problems, the embodiments of the present disclosure provide the following technical solutions.

[0009] In a first aspect, an embodiment of the present disclosure provides a computing power routing method, which is applied to a first routing node, and the method includes: receiving a first message sent by a second routing node; decapsulating the first message to obtain a second message and a first segment routing identifier SID; determining a local first target node connected to the first routing node based on the first SID; and sending the second message to the first target node; wherein the first routing node is a first-hop provider edge PE routing node for the first target node to access a network; and the first target node is a first mobile edge computing MEC device or a first computing power service node.

[0010] Optionally, the first SID is a SID associated with target information, wherein the target information is used to instruct the first routing node to send the second message to a local MEC device or a local computing power service node.

[0011] Optionally, determining the local first target node to which the first routing node is connected based on the first SID includes: determining the local node to which the first routing node is connected based on the target information corresponding to the first SID, wherein the local node is a local MEC device or a local computing power service node; and determining the first target node from the local node.

[0012] Optionally, the receiving the first message sent by the second routing node includes: sending the first SID to the second routing node; and receiving the first message after the second routing node encapsulates the second message according to the first SID.

[0013] Optionally, sending the first SID to the second routing node includes: sending routing attribute information of Border Gateway Protocol (BGP) to the second routing node, wherein the routing attribute information of BGP carries the first SID.

[0014] Optionally, the first SID is carried in a computing power information sub-TLV, and the computing power information sub-TLV is a sub-TLV added to the extended community attribute information of the BGP routing attribute information or a sub-TLV added to the BGP routing attribute information.

[0015] In a second aspect, an embodiment of the present disclosure also provides a computing power routing method, which is applied to a second routing node. The method includes: sending a first message to a first routing node, wherein the first message carries a first segment routing header SID, and the first SID is used to indicate the first routing node to determine the first target node of the local connection; wherein the first routing node is the first hop provider edge PE routing node of the first target node access network; the first target node is the local first mobile edge computing MEC device or the first computing power service node connected to the first routing node.

[0016] Optionally, sending a first message to a first routing node includes: receiving the first SID sent by the first routing node; receiving a second message sent by a first client device; encapsulating the second message according to the first SID to obtain the first message; and sending the first message to the first routing node.

[0017] Optionally, receiving the first SID sent by the first routing node includes: receiving routing attribute information of a Border Gateway Protocol (BGP) sent by the first routing node, wherein the BGP routing attribute information carries the first SID.

[0018] Optionally, the first SID is carried in a computing power information sub-TLV, and the computing power information sub-TLV is a sub-TLV added to the extended community attribute information of the BGP routing attribute information or a sub-TLV added to the BGP routing attribute information.

[0019] In a third aspect, an embodiment of the present disclosure also provides a computing power routing method, which is applied to a first target node, and the method includes: receiving a second message sent by a first routing node, wherein the first routing node is the first-hop provider edge PE routing node of the first target node access network, and the first target node is a local node determined by the first routing node according to the first segment routing header SID carried by the first message; determining a first client device according to the second message; establishing a first connection with the first client device, wherein the first connection is a connection between a server in the first target node and the first client device; through the first connection, and sending a third message to the first client device, wherein the third message is used to instruct the first client device to establish a second connection, and the second connection is a connection between the first client device and the server in the first target node; wherein the first target node is a local first mobile edge computing MEC device or a first computing power service node connected to the first routing node.

[0020] Optionally, the third message carries a unicast address corresponding to the server in the first target node.

[0021] In a fourth aspect, an embodiment of the present disclosure also provides a computing power routing method, which is applied to a first client device, and the method includes: receiving a third message sent by a server in a first target node through a first connection, wherein the first connection is a connection between the server in the first target node and the first client device, and the first target node is a local node determined by the first routing node based on the first segment routing header SID carried by the first message; and establishing a second connection with the server in the first target node based on the third message; wherein the first target node is a first mobile edge computing MEC device or a first computing power service node.

[0022] Optionally, the third message carries a unicast address corresponding to the server in the first target node.

[0023] Optionally, before receiving the third message sent by the server in the first target node through the first connection, the method further includes: sending a second message to the second routing node.

[0024] In the fifth aspect, an embodiment of the present disclosure also provides a computing power routing device, which includes: a first receiving module for receiving a first message sent by a second routing node; a first processing module for decapsulating the first message to obtain a second message and a first segment routing identifier SID; a first determination module for determining, based on the first SID, a local first target node connected to the first routing node; and a first sending module for sending the second message to the first target node; wherein, the first routing node is the first-hop provider edge PE routing node of the first target node access network; the first target node is a first mobile edge computing MEC device or a first computing power service node.

[0025] In the sixth aspect, an embodiment of the present disclosure also provides a computing power routing device, which includes: a second sending module, used to send a first message to a first routing node, wherein the first message carries a first segment routing header SID, and the first SID is used to indicate the first routing node to determine the first target node of the local connection; wherein, the first routing node is the first hop provider edge PE routing node of the first target node access network; the first target node is the local first mobile edge computing MEC device or the first computing power service node connected to the first routing node.

[0026] In the seventh aspect, an embodiment of the present disclosure also provides a computing power routing device, which includes: a second receiving module for receiving a second message sent by a first routing node, wherein the first routing node is the first-hop provider edge PE routing node of the first target node access network, and the first target node is a local node determined by the first routing node according to the first segment routing header SID carried by the first message; a second determination module for determining a first client device based on the second message; a second processing module for establishing a first connection with the first client device, wherein the first connection is a connection between a server in the first target node and the first client device; and a third sending module for sending a third message to the first client device through the first connection, wherein the third message is used to instruct the first client device to establish a second connection, and the second connection is a connection between the first client device and the server in the first target node; wherein the first target node is a local first mobile edge computing MEC device or a first computing power service node connected to the first routing node.

[0027] In the eighth aspect, an embodiment of the present disclosure also provides a computing power routing device, which includes: a third receiving module for receiving a third message sent by a server in a first target node through a first connection, wherein the first connection is a connection between the server in the first target node and a first client device, and the first target node is a local node determined by the first routing node based on the first segment routing header SID carried by the first message; and a third processing module for establishing a second connection with the server in the first target node based on the third message; wherein the first target node is a first mobile edge computing MEC device or a first computing power service node.

[0028] In the ninth aspect, an embodiment of the present disclosure further provides a routing node, comprising: a processor, a memory, and a program stored on the memory and executable on the processor, wherein when the program is executed by the processor, the computing power routing method as described in any one of the first aspects is implemented, or the computing power routing method as described in any one of the second aspects is implemented.

[0029] In the tenth aspect, an embodiment of the present disclosure further provides a node, comprising: a processor, a memory, and a program stored on the memory and executable on the processor, wherein when the program is executed by the processor, the computing power routing method as described in any one of the third aspects is implemented.

[0030] In the eleventh aspect, an embodiment of the present disclosure further provides a client device, comprising: a processor, a memory, and a program stored on the memory and executable on the processor, wherein when the program is executed by the processor, the computing power routing method as described in any one of the fourth aspects is implemented.

[0031] In the twelfth aspect, an embodiment of the present disclosure further provides a readable storage medium, on which a program is stored. When the program is executed by a processor, it implements the computing power routing method as described in any one of the first aspects, or implements the computing power routing method as described in any one of the second aspects, or implements the steps in the computing power routing method as described in any one of the third aspects, or implements the computing power routing method as described in any one of the fourth aspects.

[0032] In the thirteenth aspect, an embodiment of the present disclosure further provides a computer program product comprising instructions, which, when executed by a processor, causes the processor to execute the computing power routing method as described in any one of the first aspects, or implement the computing power routing method as described in any one of the second aspects, or implement the steps in the computing power routing method as described in any one of the third aspects, or implement the computing power routing method as described in any one of the fourth aspects.

[0033] At least one of the above technical solutions of the present disclosure has the following beneficial effects:

[0034] In the computing power routing method provided by the present disclosure, a first routing node receives a first message sent by a second routing node, decapsulates the first routing node, obtains a second message and a first SID, and determines the local first target node connected to the first routing node based on the first SID, thereby sending the second message to the local first target node. The first routing node is the first hop PE routing node for the first target node to access the network. The present disclosure determines the local first target node based on the first SID by the first routing node, and forwards the message, thereby avoiding the problem of inconsistent multi-point decisions and inconsistent routing states caused by the first routing node performing a global search for other routing nodes after receiving the first message in a distributed scenario, forwarding the first message to the other routing nodes found, and then globally forwarding by other routing nodes, thereby solving the problem of routing confusion in distributed scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] FIG1 is a schematic diagram of one of the distributed computing power routing scenarios provided by the present disclosure.

[0036] FIG2 is a second schematic diagram of the distributed computing power routing scenario provided by the present disclosure.

[0037] FIG3 is a flowchart of a computing power routing method applied to a first routing node according to an embodiment of the present disclosure.

[0038] FIG4 is a schematic diagram of function information corresponding to Router1 provided in an embodiment of the present disclosure.

[0039] FIG5 is a schematic diagram of function information corresponding to Router3 provided in an embodiment of the present disclosure.

[0040] FIG6 is a schematic diagram of function information corresponding to Router5 provided in an embodiment of the present disclosure.

[0041] FIG7 is a schematic diagram of function information corresponding to Egress2 provided in an embodiment of the present disclosure.

[0042] FIG8 is a flowchart of a computing power routing method applied to a second routing node according to an embodiment of the present disclosure.

[0043] FIG9 is a flowchart of a computing power routing method applied to a first target node according to an embodiment of the present disclosure.

[0044] FIG10 is a flowchart of a computing power routing method applied to a client device provided in an embodiment of the present disclosure.

[0045] FIG11 is a schematic diagram of the structure of the computing power routing system provided in an embodiment of the present disclosure.

[0046] FIG12 is a schematic structural diagram of a computing power routing device applied to a first routing node according to an embodiment of the present disclosure.

[0047] FIG13 is a schematic structural diagram of a computing power routing device applied to a second routing node according to an embodiment of the present disclosure.

[0048] FIG14 is a schematic structural diagram of a computing power routing device applied to a first target node according to an embodiment of the present disclosure.

[0049] FIG15 is a schematic diagram of the structure of a computing power routing device applied to a client device provided in an embodiment of the present disclosure.

[0050] FIG16 is a schematic structural diagram of a first routing node provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0051] In order to make the technical problems, technical solutions and advantages to be solved by the present disclosure clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0052] Before describing the specific implementation method, the following description is first given:

[0053] The core of the computing power routing mechanism is to extend L3 load balancing (LB) at the ingress node, supporting LB or anycast that considers computing power information, rather than just traditional LB or anycast that considers network distance.

[0054] Specifically, the core of the computing power routing mechanism includes: computing power registration, computing power nodes register in the network; computing power notification, computing power information is spread in the network; network status detection, entry nodes collect network status information; user request scheduling, entry nodes decide which service node to forward user data to based on the collected computing power information and network status information.

[0055] In the distributed computing power routing scenario, as shown in Figures 1 and 2, it is necessary to perceive computing power information and network information at the Ingress node (e.g., Ingress1), and then make an Egress selection for a specific anycast address (e.g., service ID) (e.g., a comprehensive decision is made to select Mobile Edge Computing (MEC, or Multi-Access Edge Computing (MEC)) MEC2). Afterwards, the Client (i.e., client device) accesses service1 in MEC2. As shown in Figure 1, the latency monitoring of Ingress1 is usually to regularly measure the latency corresponding to the egress node (Egress) at the other end, i.e., RTT1, RTT2, and RTT3 in Figure 1. As shown in Figure 2, the service load monitoring of Ingress1 can be carried out by carrying computing power status information or server load information through the Border Gateway Protocol (BGP).

[0056] The purpose of the present disclosure is to provide a computing power routing method and apparatus, routing nodes, nodes and client devices to solve the routing confusion problem existing in the existing distributed computing power routing mechanism.

[0057] As shown in FIG3 , an embodiment of the present disclosure provides a computing power routing method, which is applied to a first routing node. The method includes steps 301 - 304 .

[0058] In step 301, a first message sent by a second routing node is received.

[0059] The computing power routing method provided by the embodiment of the present disclosure is applied to the computing power routing scenario shown in FIG2 , wherein the second routing node is Ingress1.

[0060] The servers in MEC1, MEC2, and MEC3 all support a specific service ID. Three computing node entries are established in Ingress1 (e.g., computing node entries corresponding to Egress1, Egress2, and Egress3), and related computing power status information and network status information (e.g., server load information) are collected. Service load monitoring for Ingress1 can be achieved by carrying computing power status information or server load information via BGP.

[0061] Specifically, a computing node table entry is established in Ingress1 to record the routing information of computing service nodes that use themselves as egress nodes. This routing information is sent from the external access network and carries computing power-related information (external computing power routing information notification). The Egress is the first hop provider edge (PE) router for these computing service nodes to access the network. Specifically, the computing service node can be an MEC, where servers or virtual servers can deploy related computing services.

[0062] In this step, the first client device (Client1) sends a second message to Ingress1, and the second message includes Client1's source address (Source Address, SA) clientIP and destination address (serviceID) serviceID1. Ingress1 uses the first segment routing identifier (Segment Routing ID, SID) to encapsulate the second message to obtain the first message. Specifically, the second message has an outer encapsulation, and the last SID is of type END.DTCL6, and the first SID is the SID published in advance by Egress. The newly defined END.DTCL6 indicates that after decapsulation, a local computing power service forwarding table is searched according to the destination address of the inner message, and the address also exists in the global routing table. Among them, D means decapsulation, T means table lookup, C represents the computing power service table, L represents Local, and 6 represents IPv6.

[0063] After Ingress1 receives the second message, it determines the SRv6 policy (Segment Routing based on IPv6 Policy, SRv6 Policy) to be forwarded to Egress2 based on serviceID1 and the three computing node entries established in Ingress1, and forwards the first message to Egress2, where Egress2 is the first routing node. Egress2 is the first hop PE routing node for the first target node to access the network. The first target node is the local first MEC device or the first computing service node connected to the first routing node. Egress2 receives the first message sent by the second routing node. The first message also includes the destination address (i.e., serviceID1).

[0064] For example, the forwarding path of the first message is<Router1,Router3,Router5,Egress2> .

[0065] Specifically, during the forwarding process, the function (FUNCT) information corresponding to Router1 is shown in FIG4 , the function (FUNCT) information corresponding to Router3 is shown in FIG5 , the function (FUNCT) information corresponding to Router5 is shown in FIG6 , and the function (FUNCT) information corresponding to Egress2 is shown in FIG7 .

[0066] The information shown in Figures 4 through 7 all includes the virtual network (overlay): source address SA (client IP) and destination address DA (service ID). The overlay information in Figures 4 through 7 is identical. The information shown in Figures 4 through 7 also includes the physical layer network (underlay): source address SA and destination address DA's Segment Routing Header (SRH). In the information shown in Figure 4, the SA in the underlay is Ingress1, and the DA in the underlay is Router1END. In the information shown in Figure 5, the SA in the underlay is Ingress1, and the DA in the underlay is Router3END. In the information shown in Figure 6, the SA in the underlay is Ingress1, and the DA in the underlay is Router5END. In the information shown in Figure 7, the SA in the underlay is Ingress1, and the DA in the underlay is Egress2END.DTCL6. The information shown in Figures 4 through 7 also includes several END functions: Egress2END.DTCL6, Router5END, Router3END, and Router1END.

[0067] In Figures 4 to 7, it is assumed that in the information of the local computing service table (LOC: FUNCT) of SRv6 based on IPv6, for example, E2, R1, R3, and R5 are LOC, and specific function values ​​are set, such as 0000 represents END FUNCT and D300 represents END.DTCL6 FUNCT.

[0068] In step 302, the first message is decapsulated to obtain a second message and a first segment routing identifier SID.

[0069] In this step, Egress2 decapsulates the first message sent by Ingress1 to obtain the second message and the first SID.

[0070] In step 303, a local first target node to which the first routing node is connected is determined according to the first SID, where the first target node is a first MEC device or a first computing power service node.

[0071] In this step, Egress2 determines that the decapsulated second message needs to be forwarded to the local first target node based on the decapsulated first SID. In this embodiment, taking the first target node as the first MEC device as an example, the first target node is MEC2, and it does not matter to whom the forwarding address corresponding to the destination address (serviceID1) in the global routing table is sent.

[0072] In step 304, the second message is sent to the first target node.

[0073] In this step, Egress2 forwards the second message to the first target node, namely MEC2.

[0074] Optionally, the first SID is a SID associated with target information, and the target information is used to instruct the first routing node to send the second message to a local MEC device or a local computing power service node.

[0075] In this embodiment, the target information is the newly defined function END.DTCL6, which is used to instruct the routing node to decapsulate the received message and look up the local computing service forwarding table. The local computing service forwarding table includes the local MEC device (or local computing service node) and the corresponding network status information, etc., where D means decapsulation, T means table lookup, C represents the computing service table, L represents Local, and 6 represents IPv6.

[0076] It should be noted that the END function is a common function in SRv6, mainly used for explicit paths. It has a series of extensions, such as END.DT4, which means to search the routing table of an IPv4 VPN instance for forwarding after decapsulation.

[0077] In an optional embodiment of the present disclosure, the local first target node connected to the first routing node is determined according to the first SID, including: according to the target information corresponding to the first SID (i.e., END.DTCL6), searching the local computing power service forwarding table, determining the local node connected to Ingress1 (i.e., the local MEC device or the local computing power service node), and when the number of local nodes (i.e., the local MEC device or the local computing power service node) is greater than 1, determining the first MEC device or the first computing power service node with the best status from the local nodes according to the local computing power service forwarding table.

[0078] Among them, the network status information corresponding to MEC in the local computing power service forwarding table is announced by the local computing power routing information.

[0079] It should also be noted that, in the embodiment of the present disclosure, the first SID should be released in advance by the Egress to other routing nodes in the network, that is, the first SID is sent in advance by the Egress2 to the Ingress1 (that is, the first routing node sends the first SID to the second routing node), and the Ingress1 performs an outer layer encapsulation on the second message according to the first SID to obtain the first message, and the last SID of the outer layer encapsulated SRH is the first SID, and the Ingress1 sends the first message to the Egress2.

[0080] Optionally, the first routing node sends the first SID to the second routing node, including: sending BGP routing attribute information to the second routing node, the BGP routing attribute information carries the first SID, that is, Egress2 sends the first SID to Ingress1 in advance via BGP routing attribute information.

[0081] Furthermore, the first SID is carried in a computing power information sub-TLV (type-length-value), and the computing power information sub-TLV is a sub-TLV added in the extended community attribute information of the BGP routing attribute (Path Attribute) information or a sub-TLV in a new BGP routing attribute (Path Attribute) (that is, the computing power information sub-TLV is a sub-TLV added in the BGP routing attribute information).

[0082] Specifically, unlike the existing BGP Prefix-SID attribute [RFC9252] logic, in this embodiment, this SID is selected and placed in the computing power information TLV instead of the ordinary BGP Prefix-SID attribute. The BGP Prefix-SID attribute [RFC9252] is a TLV specifically used to store the Segment ID of Segment Routing.

[0083] In this embodiment, optionally, the above-mentioned computing power information TLV is carried in the extended community attribute information of the BGP Path Attribute or in a new BGP routing attribute, that is, in the scheme where Egress2 sends the first SID to Ingress1 through the BGP routing attribute information, a sub-TLV (sub-TLV, type=10) is added to the extended community attribute information in the routing attribute information or a new BGP Path Attribute, and the sub-TLV carries the first SID. The sub-TLV contains the SID information of the Egress, and the specific content is the same as the ordinary BGP Prefix-SID, for example, including Information sub-sub-TLV, etc. However, this computing power information sub-TLV does not affect the first SID when the next hop (that is, the next hop of BGP) is changed or when it is transmitted across management domains, that is, it will not be deleted.

[0084] After Ingress1 receives the first SID corresponding to END.DTCL6, when forwarding the computing service message with the destination address as the anycast address (ServiceID), the first SID corresponding to END.DTCL6 is used as the last SID in the SID list in the matching SRv6 Policy.

[0085] One implementation of the present disclosure is as follows:

[0086] The egress advertises serviceID1 information through BGP messages. In this case, the relevant routing information is the anycast address serviceID1, and the relevant computing power information is placed in the extended community attribute or a new BGP routing attribute.

[0087] The Path Attributes field in a BGP UPDATE message can contain several different attributes, each of which is organized in TLV format.

[0088] Select the extended community attribute (RFC4360) in the BGP routing attribute information as the bearer attribute of the computing power information (Attr.Type Code is 16: Extended Communities);

[0089] The subtype field is set to 0x0314, and the length and flag fields and computing power information sub-TLV are added. The computing power information sub-TLVs carried are all optional, such as computing power busy and idle information, accumulated delay information, etc. A new computing power information sub-TLV is defined here, type = 10, that is, a new computing power information sub-TLV is defined to carry the information of the function END.DTCL6.

[0090] or,

[0091] Select a new BGP routing attribute as the bearer attribute of the computing power information (Attr.Type Code is 50: Metadata Path Attribute Type metadata routing attribute type);

[0092] This attribute includes the Length field, the Flag field, and the computing power information sub-TLV. The computing power information sub-TLVs carried are optional, and can include information such as computing power busy / idle information and accumulated latency. A new computing power information sub-TLV, type = 10, is defined here to carry information about the END.DTCL6 function.

[0093] It should be noted that for a computing service, there is only one Ingress and one Egress. However, for a PE node, even if it is the same computing service, it may be both the Ingress of one computing service and the Egress of another computing service.

[0094] As shown in FIG8 , an embodiment of the present disclosure further provides a computing power routing method, which is applied to a second routing node. The method includes step 801 .

[0095] In step 801, a first message is sent to a first routing node, wherein the first message carries a first segment routing header (SID). The first SID is used to instruct the first routing node to determine a first target node for a local connection. The first routing node is a first-hop provider edge (PE) routing node for the first target node to access a network. The first target node is a local first mobile edge computing (MEC) device or a first computing service node connected to the first routing node.

[0096] The computing power routing method provided by the embodiment of the present disclosure is applied to the computing power routing scenario shown in Figure 2, wherein the second routing node is Ingress 1. The first target node is the first MEC device, namely MEC 2.

[0097] In this step, Ingress1 determines the SRv6 Policy that forwards the message to Egress2 based on the DA serviceID1 in the first message and the computing node table entry established in Ingress1. Egress2 is the first routing node.

[0098] The first message is obtained by encapsulating the second message through a first segment routing header SID, and the first SID is used to instruct the first routing node to determine a first target node for a local connection.

[0099] The first SID should be published in advance by Egress to other routing nodes in the network, that is, the first SID is sent in advance by Egress2 to Ingress1. In an optional embodiment of the present disclosure, sending a first message to the first routing node includes: Ingress1 receiving the first SID sent by Egress2, and Ingress1 receiving a second message sent by a first client device (Client1), encapsulating the second message using the first SID to obtain the first message, and Ingress1 sending the first message to Egress2. Specifically, the last SID of the outer encapsulation of the second message is the first SID, and the first SID is a SID of the END.DTCL6 type.

[0100] Optionally, Ingress1 receives the first SID sent by Egress2, including: receiving routing attribute information of Border Gateway Protocol (BGP) sent by the first routing node, wherein the BGP routing attribute information carries the first SID. That is, Egress2 sends the first SID to Ingress1 in advance via the BGP routing attribute information.

[0101] Furthermore, the first SID is carried in a computing power information sub-TLV, which is a sub-TLV added in the extended community attribute information of the BGP routing attribute information or a sub-TLV in a new BGP routing attribute (Path Attribute) (i.e., the computing power information sub-TLV is a sub-TLV added in the BGP routing attribute information).

[0102] Specifically, in a scheme where Egress2 sends the first SID to Ingress1 via BGP routing attribute information, a computing power information sub-TLV (sub-TLV, type=10) is added to the extended community attribute information in the routing attribute information, and the target sub-TLV carries the first SID. Alternatively, a computing power information sub-TLV (sub-TLV, type=10) is added to a new routing attribute information, and the computing power information sub-TLV carries the first SID.

[0103] As shown in FIG9 , an embodiment of the present disclosure further provides a computing power routing method, which is applied to a first target node. The method includes steps 901 - 904 .

[0104] In step 901, a second message is received from a first routing node. The first routing node is a first-hop provider edge (PE) routing node for accessing a network of the first target node. The first target node is a local node determined by the first routing node based on the first segment routing header (SID) carried in the first message. The first target node is a local first mobile edge computing (MEC) device or a first computing service node connected to the first routing node.

[0105] The computing power routing method provided by the embodiment of the present disclosure is applied to the computing power routing scenario as shown in Figure 2, wherein the second routing node is Ingress1, the first routing node is Egress2, and the first target node is the first MEC device, namely MEC2.

[0106] The process of the first routing node generating the second message is described in the computing power routing method on the first routing node side shown in FIG3 , and will not be repeated here.

[0107] The process of the first routing node determining the first target node in the local node according to the first SID carried in the first message is also described in the computing power routing method on the first routing node side, and will not be repeated here. In this step, the server in MEC2 receives the second message sent by Egress2.

[0108] In step 902, a first client device is determined according to the second message.

[0109] In this step, server2 in MEC2 receives the second message, which carries the source address corresponding to the first client device (Client1). MEC2 determines Client1 based on the source address.

[0110] In step 903 , a first connection is established with the first client device, wherein the first connection is a connection between a server in a first target node and the first client device.

[0111] That is, in this step, server2 in MEC2 establishes a first connection with Client1.

[0112] In step 904, a third message is sent to the first client device through the first connection, wherein the third message is used to instruct the first client device to establish a second connection, where the second connection is a server connection between the first client device and the first target node.

[0113] After the first connection is established, in this step, the server in MEC2 sends a third message to Client1 through the first connection. Client1 establishes a second connection with the server in MEC2 according to the third message and continues subsequent services.

[0114] Optionally, the third message carries a unicast address corresponding to the server in the first MEC device.

[0115] That is, the third message carries the unicast address of server2 in MEC2 (i.e., serverIP2), for example, carried in the Server's Preferred Address of the Quick User Datagram Protocol (UDP) network connection (Quick UDP Internet Connection, QUIC), for specific reference RFC9000.

[0116] Client1 initiates a second connection according to serverIP2 and continues subsequent services.

[0117] As shown in FIG10 , an embodiment of the present disclosure further provides a computing power routing method, which is applied to a first client device. The method includes steps 1001 - 1002 .

[0118] In step 1001, a third message sent by a first target node through a first connection is received, wherein the first connection is a connection between a server in the first target node and the first client device; the first target node is a local node determined by the first routing node based on the first segment routing header SID carried in the first message.

[0119] The computing power routing method provided by the embodiment of the present disclosure is applied to the computing power routing scenario shown in FIG2 , wherein the first target node is the first MEC device, namely MEC2.

[0120] It should be noted that the process of establishing the first connection is as described in the computing power routing method on the first target node side, and will not be repeated here.

[0121] The process of the first routing node determining the first target node in the local node according to the first segment routing header SID carried by the first message is also described in the computing power routing method on the first routing node side, and will not be repeated here.

[0122] In this step, the server in MEC2 sends a third message to the first client device (Client1) through the first connection, and the third message is used to instruct the first client device to establish a second connection.

[0123] In step 1002, a second connection is established with a server in the first target node according to the third message, wherein the second connection is a connection between the first client device and the server of the target node.

[0124] In this step, Client1 establishes a second connection with MEC2 based on the third message and continues subsequent services.

[0125] Optionally, the third message carries a unicast address corresponding to the server in the first MEC device.

[0126] That is, the third message carries the unicast address (serverIP2) of server2 in MEC2, for example, carried in the Server's Preferred Address of the Quick User Datagram Protocol (UDP) network connection (Quick UDP Internet Connection) QUIC, for specific reference RFC9000.

[0127] Optionally, before receiving the third message sent by the server in the first mobile edge computing MEC device through the first connection, the method also includes: sending a second message to the second routing node.

[0128] In an embodiment of the present disclosure, Ingress1 receives a second message sent by a first client device (Client1), encapsulates the second message using the first SID to obtain a first message, Ingress1 sends the first message to Egress2, Egress2 decapsulates the first message to obtain a second message and a first segment routing identifier SID, Egress2 determines the first MEC device to which Egress2 is connected based on the first SID, Egress2 sends the second message to the first MEC device, the server in the first MEC device determines the first client device based on the second message, establishes a first connection with the first client device, and the server in the first MEC device sends a third message to Client1 through the first connection.

[0129] In the disclosed embodiment, after the message arrives at the Egress, the local computing power service forwarding table is queried through SRv6 network programming, thereby avoiding the routing inconsistency problem caused by inconsistent multi-point decision-making in distributed scenarios. In addition, the deployment of the computing power network can improve the efficiency of network transmission and service provision.

[0130] The computing power routing method provided by the embodiments of the present disclosure can enable the computing power network to avoid some routing confusion problems.

[0131] 11 , which is a schematic diagram of the structure of a computing power routing system provided by an embodiment of the present disclosure, illustrates the overall process of the computing power routing method provided by an embodiment of the present disclosure.

[0132] The computing power routing system includes a first routing node, a second routing node, a first target node and a first client device.

[0133] The second routing node sends a first message to the first routing node. The first message carries a first SID, wherein the first SID is sent in advance by the first routing node to the second routing node. The first message is obtained by the second routing node encapsulating the second message after receiving the first SID, and the destination address of the first message is the serviceID corresponding to the first routing node. After receiving the first message, the first routing node decapsulates the first message to obtain the second message and the first SID. Based on the first SID, the first routing node searches a local table to determine the local node to which the first routing node is connected, and determines the first destination node among the local nodes. The first routing node then sends the second message to the first destination node. The first target node receives the second message sent by the first routing node, and the first target node determines the first client device based on the second message, wherein the first client device is the client device that sends the second message to the second routing node, the first target node establishes a connection with the first client device, and the server of the first target node sends a third message to the first client device through the first connection. The first client device receives the third message sent by the server in the first target node through the first connection and establishes a second connection with the server in the first target node based on the third message, and continues subsequent business.

[0134] As shown in FIG12 , the embodiment of the present disclosure further provides a computing power routing device, which is applied to a first routing node. The device includes: a first receiving module 1201, which is used to receive a first message sent by a second routing node; a first processing module 1202, which is used to decapsulate the first message to obtain a second message and a first segment routing identifier SID; a first determining module 1203, which is used to determine the local first target node connected to the first routing node based on the first SID; and a first sending module 1204, which is used to send the second message to the first target node. The first routing node is the first hop provider edge PE routing node of the first target node's access network; the first target node is a first mobile edge computing MEC device or a first computing power service node.

[0135] Optionally, the first SID is a SID associated with target information, and the target information is used to instruct the first routing node to send the second message to a local MEC device or a local computing power service node.

[0136] Optionally, the first determination module 1203 includes: a first determination unit, used to determine the local node to which the first routing node is connected based on the target information corresponding to the first SID, wherein the local node is the local MEC device or the local computing power service node; a second determination unit, used to determine the first target node from the local node.

[0137] Optionally, the first receiving module 1201 includes: a first sending unit, configured to send the first SID to the second routing node; and a first receiving unit, configured to receive the first message after the second routing node encapsulates the second message according to the first SID.

[0138] Optionally, the first sending unit is specifically configured to send routing attribute information of Border Gateway Protocol (BGP) to the second routing node, wherein the routing attribute information of BGP carries the first SID.

[0139] Optionally, the first SID is carried in a computing power information sub-TLV, and the computing power information sub-TLV is a sub-TLV added to the extended community attribute information of the BGP routing attribute information or a sub-TLV added to the BGP routing attribute information.

[0140] It should be noted that the computing power routing device applied to the first routing node provided in the embodiment of the present disclosure is a device capable of executing the above-mentioned computing power routing method applied to the first routing node. All embodiments of the above-mentioned computing power routing method applied to the first routing node are applicable to the device and can achieve the same or similar technical effects.

[0141] As shown in FIG13 , an embodiment of the present disclosure further provides a computing power routing device, which is applied to a second routing node. The device includes: a second sending module 1301, which is used to send a first message to a first routing node, wherein the first message carries a first segment routing header SID, and the first SID is used to instruct the first routing node to determine a first target node for a local connection. The first routing node is a first-hop provider edge (PE) routing node for the first target node to access a network. The first target node is a local first mobile edge computing (MEC) device or a first computing power service node connected to the first routing node.

[0142] Optionally, the second sending module 1301 includes: a second receiving unit, used to receive the first SID sent by the first routing node; a third receiving unit, used to receive a second message sent by the first client device; a first processing unit, used to encapsulate the second message according to the first SID to obtain the first message; and a second sending unit, used to send the first message to the first routing node.

[0143] Optionally, the second receiving unit is specifically configured to receive routing attribute information of a Border Gateway Protocol (BGP) sent by the first routing node, wherein the routing attribute information of the BGP carries the first SID.

[0144] Optionally, the first SID is carried in a computing power information sub-TLV, and the computing power information sub-TLV is a sub-TLV added to the extended community attribute information of the BGP routing attribute information or a sub-TLV added to the BGP routing attribute information.

[0145] It should be noted that the computing power routing device applied to the second routing node provided in the embodiment of the present disclosure is a device capable of executing the above-mentioned computing power routing method applied to the second routing node. All embodiments of the above-mentioned computing power routing method applied to the second routing node are applicable to the device and can achieve the same or similar technical effects.

[0146] As shown in FIG14 , an embodiment of the present disclosure further provides a computing power routing device, applied to a first target node, the device comprising: a second receiving module 1401, configured to receive a second message sent by a first routing node, wherein the first routing node is a first-hop provider edge (PE) routing node for the first target node to access a network, and the first target node is a local node determined by the first routing node based on a first segment routing header (SID) carried by the first message; a second determining module 1402, configured to determine a first client device based on the second message; a second processing module 1403, configured to establish a first connection with the first client device, wherein the first connection is a connection between a server in the first target node and the first client device; and a third sending module 1404, configured to send a third message to the first client device via the first connection, wherein the third message is configured to instruct the first client device to establish a second connection, wherein the second connection is a connection between the first client device and a server in the first target node. The first target node is a local first mobile edge computing (MEC) device or a first computing power service node connected to the first routing node.

[0147] Optionally, the third message carries a unicast address corresponding to the server in the first target node.

[0148] It should be noted that the computing power routing device applied to the first mobile edge computing MEC device provided in the embodiment of the present disclosure is a device capable of executing the above-mentioned computing power routing method applied to the first mobile edge computing MEC device. All embodiments of the above-mentioned computing power routing method applied to the first mobile edge computing MEC device are applicable to the device and can achieve the same or similar technical effects.

[0149] As shown in FIG15 , an embodiment of the present disclosure further provides a computing power routing device, which is applied to a first client device. The device includes: a third receiving module 1501, which is used to receive a third message sent by a server in a first target node through a first connection, wherein the first connection is a connection between the server in the first target node and the first client device, and the first target node is a local node determined by the first routing node based on the first segment routing header SID carried by the first message; a third processing module 1502, which is used to establish a second connection with the server in the first target node based on the third message. The first target node is a first mobile edge computing MEC device or a first computing power service node.

[0150] Optionally, the third message carries a unicast address corresponding to the server in the first target node.

[0151] Optionally, the device further includes: a fourth sending module, configured to send a second message to the second routing node.

[0152] It should be noted that the computing power routing device applied to the first client device provided in the embodiment of the present disclosure is a device capable of executing the above-mentioned computing power routing method applied to the first client device. All embodiments of the above-mentioned computing power routing method applied to the first client device are applicable to the device and can achieve the same or similar technical effects.

[0153] As shown in Figure 16, an embodiment of the present disclosure also provides a routing node, which is a first routing node, including: a processor 1601; and a memory 1603 connected to the processor 1601 through a bus interface 1602, wherein the memory 1603 is used to store programs and data used by the processor 1601 when performing operations, and the processor 1601 calls and executes the programs and data stored in the memory 1603.

[0154] Among them, the transceiver 1604 is connected to the bus interface 1602, and is used to receive and send data under the control of the processor 1601. Specifically, the processor 1601 is used to read the program in the memory 1603, and the transceiver 1604 performs the following process: receiving the first message sent by the second routing node. The processor 1601 performs the following process: decapsulating the first message to obtain the second message and the first segment routing identifier SID; and determining the local first target node connected to the first routing node based on the first SID. The transceiver 1604 also performs the following process: sending the second message to the first target node. The first routing node is the first hop provider edge PE routing node for the first target node to access the network; the first target node is the first mobile edge computing MEC device or the first computing power service node.

[0155] Optionally, the first SID is a SID associated with target information, and the target information is used to instruct the first routing node to send the second message to a local MEC device or a local computing power service node.

[0156] Optionally, the processor 1601 is used to: determine the local node to which the first routing node is connected based on the target information corresponding to the first SID, wherein the local node is a local MEC device or a local computing power service node; and determine the first MEC device from the local node.

[0157] Optionally, the transceiver 1604 is configured to: send the first SID to the second routing node; and receive the first message after the second routing node encapsulates the second message according to the first SID.

[0158] Optionally, the transceiver 1604 is specifically configured to send routing attribute information of Border Gateway Protocol (BGP) to the second routing node, where the routing attribute information of BGP carries the first SID.

[0159] Optionally, the first SID is carried in a computing power information sub-TLV, and the computing power information sub-TLV is a sub-TLV added to the extended community attribute information of the BGP routing attribute information or a sub-TLV added to the BGP routing attribute information.

[0160] In Figure 16, the bus architecture can include any number of interconnected buses and bridges, specifically linking together various circuits such as one or more processors represented by processor 1601 and memory represented by memory 1603. The bus architecture can also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are all well known in the art and, therefore, will not be further described herein. The bus interface provides a user interface 1605. The transceiver 1604 can be multiple components, including a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium. The processor 1601 is responsible for managing the bus architecture and general processing, and the memory 1603 can store data used by the processor 1601 when performing operations.

[0161] An embodiment of the present disclosure also provides a routing node, which is a second routing node, including: a processor; and a memory connected to the processor through a bus interface, the memory being used to store programs and data used by the processor when performing operations, and the processor calling and executing the programs and data stored in the memory.

[0162] The transceiver is connected to the bus interface and is used to receive and send data under the control of the processor.

[0163] It should be noted that the structure of the second routing node provided in the embodiment of the present disclosure is similar to that of the first routing node shown in FIG16 , and will not be described in detail here.

[0164] Specifically, the processor is configured to read a program in the memory, and the transceiver performs the following process: sending a first message to a first routing node, the first message carrying a first segment routing header SID, the first SID being used to instruct the first routing node to determine a first target node for a local connection. The first routing node is a first-hop provider edge (PE) routing node for the first target node to access a network; the first target node is a local first mobile edge computing (MEC) device or a first computing service node connected to the first routing node.

[0165] Optionally, the transceiver is configured to: receive the first SID sent by the first routing node; receive a second message sent by the first client device; the processor is configured to: encapsulate the second message according to the first SID to obtain the first message; and the transceiver is configured to: send the first message to the first routing node.

[0166] Optionally, the transceiver is specifically configured to receive routing attribute information of a Border Gateway Protocol (BGP) sent by the first routing node, where the routing attribute information of the BGP carries the first SID.

[0167] Optionally, the first SID is carried in a computing power information sub-TLV, and the computing power information sub-TLV is a sub-TLV added to the extended community attribute information of the BGP routing attribute information or a sub-TLV added to the BGP routing attribute information.

[0168] An embodiment of the present disclosure also provides a node, which is a first target node, including: a processor; and a memory connected to the processor through a bus interface, the memory being used to store programs and data used by the processor when performing operations, and the processor calling and executing the programs and data stored in the memory.

[0169] The transceiver is connected to the bus interface and is used for receiving and sending data under the control of the processor.

[0170] It should be noted that the node provided in the embodiment of the present disclosure has a similar structure to the first routing node shown in FIG16 , and will not be described in detail here.

[0171] Specifically, the processor is configured to read the program in the memory, and the transceiver performs the following process: receiving a second message sent by a first routing node, wherein the first routing node is a first-hop provider edge (PE) routing node for the first target node to access the network, and the first target node is a local node determined by the first routing node based on the first segment routing header (SID) carried by the first message. The processor performs the following process: determining a first client device based on the second message; and establishing a first connection with the first client device, wherein the first connection is a connection between a server in the first target node and the first client device. The transceiver also performs the following process: sending a third message to the first client device via the first connection, wherein the third message is used to instruct the first client device to establish a second connection, wherein the second connection is a connection between the first client device and a server in the first target node. The first target node is a local first mobile edge computing (MEC) device or a first computing power service node connected to the first routing node.

[0172] Optionally, the third message carries a unicast address corresponding to the server in the first target node.

[0173] An embodiment of the present disclosure also provides a client device, comprising: a processor; and a memory connected to the processor via a bus interface, the memory being used to store programs and data used by the processor when performing operations, and the processor calling and executing the programs and data stored in the memory.

[0174] The transceiver is connected to the bus interface and is used to receive and send data under the control of the processor.

[0175] It should be noted that the client device provided in the embodiment of the present disclosure has a similar structure to the first routing node shown in FIG16 , and will not be described in detail here.

[0176] Specifically, the processor is configured to read a program in the memory, and the transceiver performs the following process: receiving a third message sent by a server in a first target node via a first connection, wherein the first connection is a connection between the server in the first target node and the first client device, and the first target node is a local node determined by the first routing node based on the first segment routing header SID carried in the first message. The processor performs the following process: establishing a second connection with the server in the first target node based on the third message. The first target node is a first mobile edge computing MEC device or a first computing power service node.

[0177] Optionally, the third message carries a unicast address corresponding to the server in the first target node.

[0178] Optionally, the transceiver is further configured to: send a second message to a second routing node.

[0179] In addition, a specific embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the steps of the computing power routing method applied to the first routing node as described above are implemented, or the steps of the computing power routing method applied to the second routing node as described above are implemented, or the steps of the computing power routing method applied to the first mobile edge computing MEC device as described above are implemented, or the steps of the computing power routing method applied to the first client device as described above are implemented. In an embodiment of the present disclosure, the computer-readable storage medium may be a non-transitory computer-readable storage medium.

[0180] In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection of some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0181] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, each unit may be physically included separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional units.

[0182] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute some steps of the sending and receiving methods described in various embodiments of the present disclosure. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc., various media that can store program code.

[0183] The above is a preferred embodiment of the present disclosure. It should be pointed out that for ordinary personnel in this technical field, several improvements and modifications can be made without departing from the principles described in the present disclosure. These improvements and modifications should also be regarded as within the scope of protection of the present disclosure.

Claims

1. A computing power routing method, applied to a first routing node, the method comprising: Receiving a first message sent by a second routing node; Decapsulate the first message to obtain a second message and a first segment routing identifier SID; Determine, according to the first SID, a local first target node connected to the first routing node; as well as Sending the second message to the first target node; The first routing node is a first-hop provider edge PE routing node for accessing a network of the first target node; The first target node is a first mobile edge computing MEC device or a first computing power service node.

2. The computing power routing method according to claim 1, wherein: The first SID is a SID associated with target information, and the target information is used to instruct the first routing node to send the second message to a local MEC device or a local computing power service node.

3. The computing power routing method according to claim 2, wherein: Determining, according to the first SID, a local first target node to which the first routing node is connected, includes: Determine, according to the target information corresponding to the first SID, a local node to which the first routing node is connected, wherein the local node is the local MEC device or the local computing service node; and The first target node is determined from the local nodes.

4. The computing power routing method according to claim 1, wherein: The receiving a first message sent by the second routing node includes: sending the first SID to the second routing node; and Receive the first message after the second routing node encapsulates the second message according to the first SID.

5. The computing power routing method according to claim 4, wherein: Sending the first SID to the second routing node includes: Sending Border Gateway Protocol (BGP) routing attribute information to the second routing node, where the BGP routing attribute information carries the first SID.

6. The computing power routing method according to claim 5, wherein: The first SID is carried in a computing power information sub-TLV, and the computing power information sub-TLV is a sub-TLV added in the extended community attribute information of the BGP routing attribute information or a sub-TLV added in the BGP routing attribute information.

7. A computing power routing method, applied to a second routing node, the method comprising: Sending a first message to a first routing node, wherein the first message carries a first segment routing header SID, and the first SID is used to instruct the first routing node to determine a first target node of a local connection; The first routing node is a first-hop provider edge PE routing node for accessing a network of the first target node; The first target node is a local first mobile edge computing MEC device or a first computing power service node connected to the first routing node.

8. The computing power routing method according to claim 7, wherein: Sending a first message to a first routing node includes: receiving the first SID sent by the first routing node; receiving a second message sent by the first client device; encapsulate the second message according to the first SID to obtain the first message; and Send the first message to the first routing node.

9. The computing power routing method according to claim 8, wherein: Receiving the first SID sent by the first routing node includes: Receive routing attribute information of Border Gateway Protocol (BGP) sent by the first routing node, wherein the routing attribute information of BGP carries the first SID.

10. The computing power routing method according to claim 9, wherein: The first SID is carried in a computing power information sub-TLV, and the computing power information sub-TLV is a sub-TLV added in the extended community attribute information of the BGP routing attribute information or a sub-TLV added in the BGP routing attribute information.

11. A computing power routing method, applied to a first target node, the method comprising: Receiving a second message sent by a first routing node, wherein the first routing node is a first-hop provider edge PE routing node of the first target node access network, and the first target node is a local node determined by the first routing node according to a first segment routing header SID carried by the first message; Determine a first client device according to the second message; Establishing a first connection with the first client device, wherein the first connection is a connection between a server in the first target node and the first client device; Sending a third message to the first client device through the first connection, wherein the third message is used to instruct the first client device to establish a second connection, where the second connection is a connection between the first client device and a server in the first target node; Among them, the first target node is a local first mobile edge computing MEC device or a first computing power service node connected to the first routing node.

12. The computing power routing method according to claim 11, wherein: The third message carries the unicast address corresponding to the server in the first target node.

13. A computing power routing method, wherein: Applied to a first client device, the method comprises: receiving a third message sent by a server in a first target node through a first connection, wherein the first connection is a connection between the server in the first target node and the first client device, and the first target node is a local node determined by the first routing node according to a first segment routing header SID carried in the first message; and Establishing a second connection with the server in the first target node according to the third message; Among them, the first target node is the first mobile edge computing MEC device or the first computing power service node.

14. The computing power routing method according to claim 13, wherein: The third message carries the unicast address corresponding to the server in the first target node.

15. The computing power routing method according to claim 13, wherein: Before receiving the third message sent by the server in the first target node through the first connection, the method further includes: Send a second message to the second routing node.

16. A computing power routing device, the device comprising: A first receiving module, used to receive a first message sent by a second routing node; A first processing module, configured to decapsulate the first message to obtain a second message and a first segment routing identifier SID; A first determining module, configured to determine a local first target node to which the first routing node is connected according to the first SID; as well as A first sending module, used for sending the second message to the first target node; The first routing node is a first-hop provider edge PE routing node for accessing a network of the first target node; The first target node is a first mobile edge computing MEC device or a first computing power service node.

17. A computing power routing device, the device comprising: A second sending module, configured to send a first message to a first routing node, wherein the first message carries a first segment routing header SID, and the first SID is used to instruct the first routing node to determine a first target node of a local connection; The first routing node is a first-hop provider edge PE routing node for accessing a network of the first target node; The first target node is a local first mobile edge computing MEC device or a first computing power service node connected to the first routing node.

18. A computing power routing device, the device comprising: A second receiving module is used to receive a second message sent by a first routing node, wherein the first routing node is a first-hop provider edge PE routing node of a first target node access network, and the first target node is a local node determined by the first routing node according to a first segment routing header SID carried by the first message; A second determining module, configured to determine a first client device according to the second message; A second processing module, configured to establish a first connection with the first client device, wherein the first connection is a connection between a server in the first target node and the first client device; as well as A third sending module, configured to send a third message to the first client device through the first connection, wherein the third message is used to instruct the first client device to establish a second connection, where the second connection is a connection between the first client device and a server in the first target node; Among them, the first target node is a local first mobile edge computing MEC device or a first computing power service node connected to the first routing node.

19. A computing power routing device, the device comprising: A third receiving module is used to receive a third message sent by the server in the first target node through the first connection, wherein the first connection is a connection between the server in the first target node and the first client device, and the first target node is a local node determined by the first routing node according to the first segment routing header SID carried by the first message; as well as A third processing module, configured to establish a second connection with the server in the first target node according to the third message; Among them, the first target node is the first mobile edge computing MEC device or the first computing power service node.

20. A routing node, comprising: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the computing power routing method according to any one of claims 1 to 6 is implemented, or the computing power routing method according to any one of claims 7 to 10 is implemented.

21. A node, comprising: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the computing power routing method as claimed in claim 11 or 12.

22. A client device comprising: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the computing power routing method as described in any one of claims 13 to 15 is implemented.

23. A readable storage medium having a program stored thereon, wherein when the program is executed by a processor, the computing power routing method according to any one of claims 1 to 6 is implemented, or the computing power routing method according to any one of claims 7 to 10 is implemented, or the computing power routing method according to claim 11 or 12 is implemented, or the computing power routing method according to any one of claims 13 to 15 is implemented.

24. A computer program product comprising instructions, wherein when the instructions are executed by a processor, the processor performs the computing power routing method according to any one of claims 1 to 6, or implements the computing power routing method according to any one of claims 7 to 10, or implements the computing power routing method according to claims 11 or 12, or the computing power routing method according to any one of claims 13 to 15.

Images